{"items":[{"event":"verdict","at":"2026-09-28T10:19:47.811578+00:00","challenge_id":"chal-00721","repo":"r2://affine-private-models/models/registrations/8995857d0689af343c44608f9fe39fbab82c3a236dbe7a4ac772e5e8ed7d7fbe/","hotkey":"5D4fmtFaHEwBjbfvYdWWeky95xDTEAbMw6vnSNxYeBkesS7R","uid":49,"duration_s":2678.3,"revision":"feabefb021eab7bc6699b1d70b366312b0f17b9df39eaff891a7fdb7178c27e8","accepted":false,"error_code":null,"error_detail":"","z":-9.927856709915964,"margin":-0.6696704226401798,"se":0.06745367527024354,"n_paired_turns":978,"n_forfeit_turns":42,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":12295969866057418833,"n":1000,"digest":"a0e980705a748b7de90f04c58464e8c552f89e4adbddc370e0ad087c4092a157","n_paired_turns":978,"n_forfeit_turns":42,"margin":-0.6696704226401798,"se":0.06745367527024354,"z":-9.927856709915964,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":0.95,"n":20,"by_reason":{"no_think_close":1},"by_prompt":{"assistant_bash":{"ok":false,"reasons":["no_think_close"]},"assistant_code_block_only":{"ok":false,"reasons":["no_think_close"]},"assistant_code_only_he103":{"ok":false,"reasons":["no_think_close"]},"assistant_code_only_he134":{"ok":false,"reasons":["no_think_close"]},"assistant_code_only_he69":{"ok":true,"reasons":[]},"assistant_code_only_he70":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":17,"pass_rate":0.7083333333333334,"think_close_rate":0.7083333333333334,"by_reason":{"no_think_close":7}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.6696704226401798,"se":0.06745367527024354,"z":-9.927856709915964,"sd_diff":2.1094782162182355,"n_paired_turns":978,"n_forfeit_turns":42,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"bash":{"R":0.02427151172313926,"A":5.8549158603853,"Mc":0.14871419246132908},"text":{"R":0.08591264222916771,"A":21.41417075659555,"Mc":0.15186269627542873},"tool_call":{"R":0.010256841945416215,"A":5.246482340778621,"Mc":0.1743802151523757},"boxed":{"R":0.08421098528620562,"A":5.059180200862455,"Mc":0.12253724424395335},"terminus_json":{"R":0.0023542205664639705,"A":6.953760444276293,"Mc":0.14347998736991135}},"challenger":{"mean":-1.4479113767926148,"mean_valid":-1.2341526794381592,"sd_valid":1.9518502601261993,"n_turns":987,"n_valid":937,"n_forfeits":44,"n_unscorable":6,"mean_z_R":-0.0039229719570389775,"mean_typ_c":-0.06839362618618451,"mean_z_A":-0.2224350025212153,"bind_frac":{"R":0.33724653148345785,"Gc":0.26040554962646745,"A":0.4023479188900747},"n_leg_dropped":{"R":1,"Gc":21,"A":1},"mean_content_share":0.3671926121972401,"mean_R":0.014776332751780872,"mean_A":2.015029423429038,"mean_mc":-0.684667808188692},"king":{"mean":-0.7642774921180564,"mean_valid":-0.7265328396410496,"sd_valid":1.490059838712187,"n_turns":987,"n_valid":971,"n_forfeits":7,"n_unscorable":9,"mean_z_R":0.09773293120488767,"mean_typ_c":0.5847510160040068,"mean_z_A":-0.12628892926899069,"bind_frac":{"R":0.3728115345005149,"Gc":0.15550978372811536,"A":0.47167868177136973},"n_leg_dropped":{"R":0,"Gc":55,"A":0},"mean_content_share":0.27827542823013485,"mean_R":0.018624939303210943,"mean_A":2.414522290773332,"mean_mc":-0.6721444327983715}},"rejection_reason":null,"reign_number":null,"score":-0.005351858927334285,"score_king":-0.0007386866235382716,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9165462,"blocks_since_crown":11451,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1470.7764102564101,"mean_len_y":926.6834188034188,"n_samples":3000,"think_close_rate":0.9423333333333334,"n_text_fallback":38,"by_dialect":{"tool_call":{"n_turns":317,"zero_ref_turns":5,"mean_refs":2.914826498422713,"ref_pair_agreement":0.2143658810325477,"ref_pair_n":297},"text":{"n_turns":402,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":183,"zero_ref_turns":2,"mean_refs":2.9453551912568305,"ref_pair_agreement":0.18968692449355434,"ref_pair_n":181},"boxed":{"n_turns":69,"zero_ref_turns":4,"mean_refs":2.550724637681159,"ref_pair_agreement":0.631578947368421,"ref_pair_n":57},"terminus_json":{"n_turns":29,"zero_ref_turns":2,"mean_refs":2.7586206896551726,"ref_pair_agreement":0.37037037037037035,"ref_pair_n":27}},"ref_pair_agreement":0.25622775800711745,"ref_pair_n":562},"duel_seconds":2199.318882965017,"challenger":{"reason":-0.005351858927334285,"n_turns":987,"n_pairs":2800,"n_forfeits":44,"forfeit_rate":0.044579533941236066,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-19.93526276309243,"mean_len_z":848.0989285714286,"median_len_z":290.0,"mean_len_y":406.7392857142857,"mean_b":0.10659688723766796,"b_gate_pass_rate":0.4175,"mean_r_leg":0.014776332751780872,"mean_g_leg":0.05216695778028564,"g_bind_frac":0.2682926829268293,"a_match":0.22640382317801672,"a_match_n":558,"a_match_centered":-0.03327283726557773,"n_turns_cap_raised":48,"mean_cap_tokens":4153.474164133739,"max_cap_tokens":6033,"len_z_delta":-622.6774816849816,"len_y_delta":-519.9441330891332,"n_samples":990,"think_close_rate":0.9575757575757575,"n_text_fallback":12,"by_dialect":{"bash":{"n_turns":181,"n_valid":179,"parse_rate":0.988950276243094,"reason":0.006107613583687971,"mean_b":0.11235139685689076,"b_gate_pass_rate":0.8442776735459663,"median_len_z":278.0,"mean_r_leg":0.016475467111243345,"mean_g_leg":0.05446886874719244,"g_bind_frac":0.24581005586592178,"a_match":0.17504655493482307,"a_match_n":179,"a_match_centered":-0.01675977653631285},"boxed":{"n_turns":65,"n_valid":58,"parse_rate":0.8923076923076924,"reason":-0.01631153106281759,"mean_b":1.0193035528709444,"b_gate_pass_rate":0.3148148148148148,"median_len_z":2606.0,"mean_r_leg":0.0656843107868565,"mean_g_leg":0.003752962654708241,"g_bind_frac":0.6206896551724138,"a_match":0.6257309941520467,"a_match_n":57,"a_match_centered":-0.03773584905660377},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.0020824343940515277,"mean_b":0.018414535217078764,"b_gate_pass_rate":0.2625,"median_len_z":501.0,"mean_r_leg":0.0008902451870160642,"mean_g_leg":0.050232464424599936,"g_bind_frac":0.18518518518518517,"a_match":0.3827160493827161,"a_match_n":27,"a_match_centered":0.012345679012345678},"text":{"n_turns":402,"n_valid":368,"parse_rate":0.9154228855721394,"reason":-0.010607673806811746,"mean_b":0.047531890373190964,"b_gate_pass_rate":0.2608695652173913,"median_len_z":347.0,"mean_r_leg":0.015858708891372086,"mean_g_leg":0.0562916016430908,"g_bind_frac":0.25815217391304346,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":312,"n_valid":311,"parse_rate":0.9967948717948718,"reason":-0.0032275727623897635,"mean_b":0.021186150256553092,"b_gate_pass_rate":0.38979370249728557,"median_len_z":220.0,"mean_r_leg":0.004229072843423682,"mean_g_leg":0.055158379109219356,"g_bind_frac":0.2347266881028939,"a_match":0.16610169491525423,"a_match_n":295,"a_match_centered":-0.04680365296803653}}},"king":{"reason":-0.0007386866235382716,"n_turns":987,"n_pairs":2906,"n_forfeits":7,"forfeit_rate":0.0070921985815602835,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-41.612379405809456,"mean_len_z":1109.511355815554,"median_len_z":685.0,"mean_len_y":432.29181004817616,"mean_b":0.12443873768163435,"b_gate_pass_rate":0.4831383344803854,"mean_r_leg":0.018624939303210943,"mean_g_leg":0.05582740795043627,"g_bind_frac":0.25,"a_match":0.1955241460541814,"a_match_n":566,"a_match_centered":-0.06474820143884892,"n_turns_cap_raised":48,"mean_cap_tokens":4153.474164133739,"max_cap_tokens":6033,"len_z_delta":-361.26505444085615,"len_y_delta":-494.39160875524266,"n_samples":987,"think_close_rate":0.9929078014184397,"n_text_fallback":14,"by_dialect":{"bash":{"n_turns":181,"n_valid":181,"parse_rate":1.0,"reason":0.007966855810471123,"mean_b":0.10998717589745532,"b_gate_pass_rate":0.8738404452690167,"median_len_z":502.0,"mean_r_leg":0.016659361219048166,"mean_g_leg":0.05747160209074477,"g_bind_frac":0.24861878453038674,"a_match":0.13627992633517494,"a_match_n":181,"a_match_centered":-0.05340699815837937},"boxed":{"n_turns":65,"n_valid":64,"parse_rate":0.9846153846153847,"reason":0.0006585337529612947,"mean_b":1.0066099669466784,"b_gate_pass_rate":0.7085714285714285,"median_len_z":1905.0,"mean_r_leg":0.06787499941109337,"mean_g_leg":0.014186320106526776,"g_bind_frac":0.59375,"a_match":0.4576719576719577,"a_match_n":63,"a_match_centered":-0.1783625730994152},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.0004959785475421443,"mean_b":0.020619853914820782,"b_gate_pass_rate":0.375,"median_len_z":758.0,"mean_r_leg":0.0010701988492248817,"mean_g_leg":0.05293104900886293,"g_bind_frac":0.1111111111111111,"a_match":0.35802469135802467,"a_match_n":27,"a_match_centered":-0.012345679012345678},"text":{"n_turns":402,"n_valid":396,"parse_rate":0.9850746268656716,"reason":-0.0057148133940346695,"mean_b":0.08052976874900152,"b_gate_pass_rate":0.3005050505050505,"median_len_z":834.0,"mean_r_leg":0.02219046471507092,"mean_g_leg":0.057543737749297594,"g_bind_frac":0.22474747474747475,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":312,"n_valid":312,"parse_rate":1.0,"reason":0.0003104394619087935,"mean_b":0.03123396763142083,"b_gate_pass_rate":0.45670995670995673,"median_len_z":565.0,"mean_r_leg":0.006656335827217541,"mean_g_leg":0.06148755401994832,"g_bind_frac":0.22435897435897437,"a_match":0.16101694915254236,"a_match_n":295,"a_match_centered":-0.05441008018327606}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T09:34:08.580965+00:00","challenge_id":"chal-00720","repo":"r2://affine-private-models/models/registrations/3393f749a86e55dfa3faa111abafb8b42d217a10c6a14f1f423d8e47b7e85d68/","hotkey":"5CUwv6RDUM7hsHrbpz94ZodUn91HuT2SrTYQpy9yDiiRoM68","uid":76,"duration_s":2536.5,"revision":"f2e2f161fb23139ab8e3c0ca0b56d6f8fa9bc72ae7fd5b18b2a56fe892666417","accepted":false,"error_code":null,"error_detail":"","z":0.4263452251300726,"margin":0.013148841165413585,"se":0.030840831303791515,"n_paired_turns":983,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":14732979450084485758,"n":1000,"digest":"a84dfba42ebe186bce859f3e2909c2ba64d88dc0ef9b79aab1303c93bb739df2","n_paired_turns":983,"n_forfeit_turns":8,"margin":0.013148841165413585,"se":0.030840831303791515,"z":0.4263452251300726,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":true,"reasons":[]},"assistant_code_only_he103":{"ok":true,"reasons":[]},"assistant_code_only_he134":{"ok":true,"reasons":[]},"assistant_code_only_he69":{"ok":true,"reasons":[]},"assistant_code_only_he70":{"ok":false,"reasons":["close_only_fence"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":23,"pass_rate":0.9583333333333334,"think_close_rate":1.0,"by_reason":{"close_only_fence":1}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.013148841165413585,"se":0.030840831303791515,"z":0.4263452251300726,"sd_diff":0.9669473660056553,"n_paired_turns":983,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"text":{"R":0.08135022183393131,"A":30.068206359436164,"Mc":0.14485321920925187},"bash":{"R":0.02759061351821467,"A":6.043710774485836,"Mc":0.14830574798622667},"tool_call":{"R":0.008347138071845572,"A":7.609938580530215,"Mc":0.1816897047056423},"boxed":{"R":0.13784935305434862,"A":4.007891888386915,"Mc":0.12154282479153294},"terminus_json":{"R":0.0014156473989012245,"A":6.8047016760225105,"Mc":0.15909676347531307}},"challenger":{"mean":-0.6334677536358431,"mean_valid":-0.5894346685374705,"sd_valid":1.4031886636932307,"n_turns":993,"n_valid":975,"n_forfeits":8,"n_unscorable":10,"mean_z_R":0.19293505169506417,"mean_typ_c":0.6842060005695375,"mean_z_A":-0.09320015147554418,"bind_frac":{"R":0.3507692307692308,"Gc":0.15282051282051282,"A":0.49641025641025643},"n_leg_dropped":{"R":0,"Gc":61,"A":0},"mean_content_share":0.2791826754285504,"mean_R":0.019204754998264132,"mean_A":1.9220803609333044,"mean_mc":-0.675041089019975},"king":{"mean":-0.6466165948012567,"mean_valid":-0.6192475589873571,"sd_valid":1.49217847351487,"n_turns":993,"n_valid":978,"n_forfeits":5,"n_unscorable":10,"mean_z_R":0.2156801063781417,"mean_typ_c":0.5886751894166582,"mean_z_A":-0.0890490599894012,"bind_frac":{"R":0.3323108384458078,"Gc":0.16462167689161555,"A":0.5030674846625767},"n_leg_dropped":{"R":0,"Gc":62,"A":0},"mean_content_share":0.2808817862495854,"mean_R":0.021393069953693413,"mean_A":1.8343264940711885,"mean_mc":-0.6802893372886817}},"rejection_reason":null,"reign_number":null,"score":0.001084386817735719,"score_king":0.0008268139344401668,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9165246,"blocks_since_crown":11235,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1552.0391689373298,"mean_len_y":921.9693460490463,"n_samples":3000,"think_close_rate":0.948,"n_text_fallback":55,"by_dialect":{"tool_call":{"n_turns":311,"zero_ref_turns":1,"mean_refs":2.9389067524115755,"ref_pair_agreement":0.19770114942528735,"ref_pair_n":290},"text":{"n_turns":421,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":194,"zero_ref_turns":1,"mean_refs":2.948453608247423,"ref_pair_agreement":0.13888888888888887,"ref_pair_n":192},"boxed":{"n_turns":49,"zero_ref_turns":4,"mean_refs":2.4693877551020407,"ref_pair_agreement":0.6140350877192983,"ref_pair_n":38},"terminus_json":{"n_turns":25,"zero_ref_turns":1,"mean_refs":2.64,"ref_pair_agreement":0.34782608695652173,"ref_pair_n":23}},"ref_pair_agreement":0.21240024554941683,"ref_pair_n":543},"duel_seconds":2105.7505022538826,"challenger":{"reason":0.001084386817735719,"n_turns":993,"n_pairs":2912,"n_forfeits":8,"forfeit_rate":0.008056394763343404,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":164.53925172943235,"mean_len_z":1161.1816620879122,"median_len_z":726.0,"mean_len_y":439.72733516483515,"mean_b":0.10022036509267081,"b_gate_pass_rate":0.4883241758241758,"mean_r_leg":0.019204754998264132,"mean_g_leg":0.056253387138839726,"g_bind_frac":0.23045685279187816,"a_match":0.1751054852320675,"a_match_n":553,"a_match_centered":-0.03810408921933085,"n_turns_cap_raised":51,"mean_cap_tokens":4152.635448136959,"max_cap_tokens":6041,"len_z_delta":-390.85750684941763,"len_y_delta":-482.24201088421114,"n_samples":996,"think_close_rate":0.9919678714859438,"n_text_fallback":15,"by_dialect":{"bash":{"n_turns":193,"n_valid":193,"parse_rate":1.0,"reason":0.01077137000727616,"mean_b":0.10792947474951635,"b_gate_pass_rate":0.8426573426573427,"median_len_z":596.0,"mean_r_leg":0.026730860498629567,"mean_g_leg":0.0526747747486553,"g_bind_frac":0.25906735751295334,"a_match":0.09671848013816926,"a_match_n":193,"a_match_centered":-0.041666666666666664},"boxed":{"n_turns":45,"n_valid":45,"parse_rate":1.0,"reason":0.007602853230352326,"mean_b":0.9614236186630103,"b_gate_pass_rate":0.7520661157024794,"median_len_z":1988.0,"mean_r_leg":0.1006437414569789,"mean_g_leg":0.02235614234934663,"g_bind_frac":0.6444444444444445,"a_match":0.6098484848484849,"a_match_n":44,"a_match_centered":0.013157894736842101},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.0007341306207683223,"mean_b":0.024319921834297122,"b_gate_pass_rate":0.4393939393939394,"median_len_z":761.0,"mean_r_leg":0.0014142647112453796,"mean_g_leg":0.04014563576673363,"g_bind_frac":0.25,"a_match":0.34722222222222227,"a_match_n":24,"a_match_centered":0.014492753623188404},"text":{"n_turns":421,"n_valid":413,"parse_rate":0.9809976247030879,"reason":-0.004114834016110214,"mean_b":0.06954616279149617,"b_gate_pass_rate":0.3801452784503632,"median_len_z":773.0,"mean_r_leg":0.017405466646254197,"mean_g_leg":0.051131625630176175,"g_bind_frac":0.21549636803874092,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":310,"n_valid":310,"parse_rate":1.0,"reason":0.0013088953513621135,"mean_b":0.028447456449871365,"b_gate_pass_rate":0.38183807439824946,"median_len_z":592.0,"mean_r_leg":0.0064718037210249706,"mean_g_leg":0.07147248953510223,"g_bind_frac":0.17096774193548386,"a_match":0.14726027397260275,"a_match_n":292,"a_match_centered":-0.046783625730994156}}},"king":{"reason":0.0008268139344401668,"n_turns":993,"n_pairs":2921,"n_forfeits":5,"forfeit_rate":0.005035246727089627,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":156.75452555516893,"mean_len_z":1136.0691543991784,"median_len_z":695.0,"mean_len_y":411.38582677165357,"mean_b":0.10403579934218934,"b_gate_pass_rate":0.4929818555289284,"mean_r_leg":0.021393069953693413,"mean_g_leg":0.05497154612398316,"g_bind_frac":0.2408906882591093,"a_match":0.17326139088729017,"a_match_n":556,"a_match_centered":-0.036968576709796676,"n_turns_cap_raised":51,"mean_cap_tokens":4152.635448136959,"max_cap_tokens":6041,"len_z_delta":-415.9700145381514,"len_y_delta":-510.5835192773927,"n_samples":993,"think_close_rate":0.9949647532729103,"n_text_fallback":12,"by_dialect":{"bash":{"n_turns":193,"n_valid":193,"parse_rate":1.0,"reason":0.010295304669572939,"mean_b":0.11493620114796367,"b_gate_pass_rate":0.8234265734265734,"median_len_z":540.0,"mean_r_leg":0.02732336340165658,"mean_g_leg":0.05221470404627654,"g_bind_frac":0.3005181347150259,"a_match":0.1001727115716753,"a_match_n":193,"a_match_centered":-0.03819444444444444},"boxed":{"n_turns":45,"n_valid":45,"parse_rate":1.0,"reason":0.008322915256451794,"mean_b":0.9886378429495856,"b_gate_pass_rate":0.8016528925619835,"median_len_z":2468.0,"mean_r_leg":0.14974048211659027,"mean_g_leg":0.022860742969148022,"g_bind_frac":0.6666666666666666,"a_match":0.4848484848484848,"a_match_n":44,"a_match_centered":-0.10526315789473684},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.00508807494129834,"mean_b":0.02023434469657793,"b_gate_pass_rate":0.42424242424242425,"median_len_z":726.0,"mean_r_leg":0.001407245611068201,"mean_g_leg":0.03420652866899033,"g_bind_frac":0.25,"a_match":0.34722222222222227,"a_match_n":24,"a_match_centered":0.014492753623188404},"text":{"n_turns":421,"n_valid":416,"parse_rate":0.9881235154394299,"reason":-0.004048708558567589,"mean_b":0.07300627459005309,"b_gate_pass_rate":0.3894230769230769,"median_len_z":786.5,"mean_r_leg":0.016939711147299037,"mean_g_leg":0.050044144363039465,"g_bind_frac":0.20432692307692307,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":310,"n_valid":310,"parse_rate":1.0,"reason":0.0009229720996106212,"mean_b":0.028525805674660426,"b_gate_pass_rate":0.3916849015317287,"median_len_z":622.0,"mean_r_leg":0.006593317904970241,"mean_g_leg":0.06956901778345853,"g_bind_frac":0.19032258064516128,"a_match":0.16045197740112996,"a_match_n":295,"a_match_centered":-0.03125}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T08:21:32.334926+00:00","challenge_id":"chal-00719","repo":"r2://affine-private-models/models/registrations/aab33a8b58ff87b819c4b19b4eb98f9b3b7baccee8d081b781da75c190c4995c/","hotkey":"5CoW5RPNtjbkpLkfKhFMXTP2hi9NXjvw95AormuuBi72UB4y","uid":56,"duration_s":2600.0,"revision":"e1303293d35f300a47faad85c88722f7041117312d24c8a883312f9dd5946b23","accepted":false,"error_code":null,"error_detail":"","z":-1.6153122439720509,"margin":-0.05298596101881024,"se":0.03280230259910482,"n_paired_turns":982,"n_forfeit_turns":13,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":7779733597995049139,"n":1000,"digest":"d917d2513a523587126fa2e852c9af1a83c72313296682c485b82151970b6790","n_paired_turns":982,"n_forfeit_turns":13,"margin":-0.05298596101881024,"se":0.03280230259910482,"z":-1.6153122439720509,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":1},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":true,"reasons":[]},"assistant_code_only_he103":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he134":{"ok":true,"reasons":[]},"assistant_code_only_he69":{"ok":true,"reasons":[]},"assistant_code_only_he70":{"ok":false,"reasons":["close_only_fence"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":19,"pass_rate":0.7916666666666666,"think_close_rate":1.0,"by_reason":{"close_only_fence":5}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.05298596101881024,"se":0.03280230259910482,"z":-1.6153122439720509,"sd_diff":1.0279217950791688,"n_paired_turns":982,"n_forfeit_turns":13,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"bash":{"R":0.022197434316454878,"A":6.584738073026401,"Mc":0.1687021411506859},"text":{"R":0.0826159472372538,"A":28.67544695334035,"Mc":0.16410448486956905},"tool_call":{"R":0.00748443715965802,"A":6.4703430161494415,"Mc":0.1846516190340855},"terminus_json":{"R":0.0015177059082978617,"A":10.740574992622276,"Mc":0.13249092014203034},"boxed":{"R":0.07923957019013293,"A":4.23260294504876,"Mc":0.11678378142977032}},"challenger":{"mean":-0.7775742900043272,"mean_valid":-0.7130334985316721,"sd_valid":1.4915836116153476,"n_turns":992,"n_valid":971,"n_forfeits":12,"n_unscorable":9,"mean_z_R":0.10534463996545583,"mean_typ_c":0.5352097769593634,"mean_z_A":-0.0697346572791405,"bind_frac":{"R":0.35633367662203913,"Gc":0.18022657054582905,"A":0.46343975283213185},"n_leg_dropped":{"R":0,"Gc":47,"A":0},"mean_content_share":0.27958007571899796,"mean_R":0.017154680398124,"mean_A":1.7711048787094819,"mean_mc":-0.6882145858169277},"king":{"mean":-0.7192701765313462,"mean_valid":-0.6868066735182192,"sd_valid":1.5167295012731863,"n_turns":992,"n_valid":976,"n_forfeits":6,"n_unscorable":10,"mean_z_R":0.14830047751104639,"mean_typ_c":0.5664804460385428,"mean_z_A":-0.07850482940752396,"bind_frac":{"R":0.3668032786885246,"Gc":0.17008196721311475,"A":0.46311475409836067},"n_leg_dropped":{"R":0,"Gc":48,"A":0},"mean_content_share":0.27731947431192355,"mean_R":0.01869127836063917,"mean_A":1.767852244983652,"mean_mc":-0.6887882187488048}},"rejection_reason":null,"reign_number":null,"score":-0.0003020728563483274,"score_king":0.0003849243116231518,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9164878,"blocks_since_crown":10867,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1572.676008202324,"mean_len_y":894.7744360902255,"n_samples":3000,"think_close_rate":0.9493333333333334,"n_text_fallback":50,"by_dialect":{"bash":{"n_turns":188,"zero_ref_turns":0,"mean_refs":2.9148936170212765,"ref_pair_agreement":0.19819819819819817,"ref_pair_n":185},"terminus_json":{"n_turns":24,"zero_ref_turns":0,"mean_refs":2.5833333333333335,"ref_pair_agreement":0.23809523809523808,"ref_pair_n":21},"text":{"n_turns":410,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":317,"zero_ref_turns":0,"mean_refs":2.968454258675079,"ref_pair_agreement":0.2041942604856512,"ref_pair_n":302},"boxed":{"n_turns":61,"zero_ref_turns":8,"mean_refs":2.377049180327869,"ref_pair_agreement":0.6527777777777778,"ref_pair_n":48}},"ref_pair_agreement":0.2422062350119904,"ref_pair_n":556},"duel_seconds":2147.600544713903,"challenger":{"reason":-0.0003020728563483274,"n_turns":992,"n_pairs":2894,"n_forfeits":12,"forfeit_rate":0.012096774193548387,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-8.940040017517449,"mean_len_z":1116.0490670352453,"median_len_z":698.0,"mean_len_y":447.99481686247407,"mean_b":0.11312457535840081,"b_gate_pass_rate":0.477194194885971,"mean_r_leg":0.017154680398124,"mean_g_leg":0.05930855449413218,"g_bind_frac":0.22551020408163266,"a_match":0.17233154442456766,"a_match_n":559,"a_match_centered":-0.06204379562043796,"n_turns_cap_raised":45,"mean_cap_tokens":4139.072580645161,"max_cap_tokens":6025,"len_z_delta":-456.6269411670787,"len_y_delta":-446.7796192277515,"n_samples":995,"think_close_rate":0.9889447236180905,"n_text_fallback":14,"by_dialect":{"bash":{"n_turns":188,"n_valid":187,"parse_rate":0.9946808510638298,"reason":0.005501389787252137,"mean_b":0.10226528326458008,"b_gate_pass_rate":0.8534798534798534,"median_len_z":515.0,"mean_r_leg":0.01533614470045289,"mean_g_leg":0.05366417880245365,"g_bind_frac":0.2994652406417112,"a_match":0.13101604278074866,"a_match_n":187,"a_match_centered":-0.0661231884057971},"boxed":{"n_turns":53,"n_valid":51,"parse_rate":0.9622641509433962,"reason":0.0005824726697353101,"mean_b":0.972878516981853,"b_gate_pass_rate":0.5915492957746479,"median_len_z":1823.0,"mean_r_leg":0.06598881286166731,"mean_g_leg":0.0212585331805311,"g_bind_frac":0.43137254901960786,"a_match":0.6006944444444444,"a_match_n":48,"a_match_centered":-0.011111111111111113},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.002030809410122204,"mean_b":0.026314284967160276,"b_gate_pass_rate":0.5645161290322581,"median_len_z":683.0,"mean_r_leg":0.0012320337269227121,"mean_g_leg":0.04416928993826118,"g_bind_frac":0.16666666666666666,"a_match":0.18055555555555555,"a_match_n":24,"a_match_centered":-0.03174603174603175},"text":{"n_turns":410,"n_valid":402,"parse_rate":0.9804878048780488,"reason":-0.003501724551086015,"mean_b":0.08778980550824392,"b_gate_pass_rate":0.35572139303482586,"median_len_z":807.0,"mean_r_leg":0.022387172380961023,"mean_g_leg":0.05857030940033054,"g_bind_frac":0.21144278606965175,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":317,"n_valid":316,"parse_rate":0.9968454258675079,"reason":0.00037746967442045754,"mean_b":0.027602277081473364,"b_gate_pass_rate":0.39125799573560766,"median_len_z":560.0,"mean_r_leg":0.004902171419744691,"mean_g_leg":0.0708787007548496,"g_bind_frac":0.17088607594936708,"a_match":0.1288888888888889,"a_match_n":300,"a_match_centered":-0.06935123042505593}}},"king":{"reason":0.0003849243116231518,"n_turns":992,"n_pairs":2909,"n_forfeits":6,"forfeit_rate":0.006048387096774193,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-9.16819435412515,"mean_len_z":1075.9377793056033,"median_len_z":685.0,"mean_len_y":415.1048470264696,"mean_b":0.12254262471940297,"b_gate_pass_rate":0.499140598143692,"mean_r_leg":0.01869127836063917,"mean_g_leg":0.05906808854069692,"g_bind_frac":0.21805273833671399,"a_match":0.17405437352245864,"a_match_n":564,"a_match_centered":-0.06672705314009662,"n_turns_cap_raised":45,"mean_cap_tokens":4139.072580645161,"max_cap_tokens":6025,"len_z_delta":-496.7382288967208,"len_y_delta":-479.66958906375595,"n_samples":992,"think_close_rate":0.9949596774193549,"n_text_fallback":15,"by_dialect":{"bash":{"n_turns":188,"n_valid":187,"parse_rate":0.9946808510638298,"reason":0.0051553470090780545,"mean_b":0.10666018612772363,"b_gate_pass_rate":0.8717948717948718,"median_len_z":502.0,"mean_r_leg":0.014506759521049442,"mean_g_leg":0.053196566846554605,"g_bind_frac":0.25133689839572193,"a_match":0.1372549019607843,"a_match_n":187,"a_match_centered":-0.059782608695652176},"boxed":{"n_turns":53,"n_valid":53,"parse_rate":1.0,"reason":0.004109161304033509,"mean_b":1.0963408225243405,"b_gate_pass_rate":0.7103448275862069,"median_len_z":1859.0,"mean_r_leg":0.06250652732380538,"mean_g_leg":0.02123936135690232,"g_bind_frac":0.4339622641509434,"a_match":0.6025641025641025,"a_match_n":52,"a_match_centered":-0.020833333333333332},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.00453199248346778,"mean_b":0.027539987331891076,"b_gate_pass_rate":0.6290322580645161,"median_len_z":644.0,"mean_r_leg":0.001438872038959718,"mean_g_leg":0.042702335392549855,"g_bind_frac":0.16666666666666666,"a_match":0.18055555555555555,"a_match_n":24,"a_match_centered":-0.03174603174603175},"text":{"n_turns":410,"n_valid":405,"parse_rate":0.9878048780487805,"reason":-0.0029851103982761772,"mean_b":0.09176806526486989,"b_gate_pass_rate":0.35555555555555557,"median_len_z":785.0,"mean_r_leg":0.0262104791820948,"mean_g_leg":0.05735242639775624,"g_bind_frac":0.22469135802469137,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":317,"n_valid":317,"parse_rate":1.0,"reason":0.0016640921552245292,"mean_b":0.027699187997431065,"b_gate_pass_rate":0.42720510095642933,"median_len_z":580.0,"mean_r_leg":0.005533796489933321,"mean_g_leg":0.07228738930092478,"g_bind_frac":0.15772870662460567,"a_match":0.12236987818383167,"a_match_n":301,"a_match_centered":-0.08082497212931995}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T06:49:34.802569+00:00","challenge_id":"chal-00718","repo":"r2://affine-private-models/models/registrations/c589f355928787948c8d563af0decd65788569457f459aba4dda3fc79bb2a044/","hotkey":"5GBsXNJWUpcvegiTtHEQTKc6i3mL5Ri5BE4MTUfZLsucmnMt","uid":110,"duration_s":2586.7,"revision":"4ddc5395cbd9719ccc24a7baed3194c7386daf62dd45a12b5dff85c84a2004e2","accepted":false,"error_code":null,"error_detail":"","z":0.44720676346572025,"margin":0.014038021373142915,"se":0.031390449608481766,"n_paired_turns":979,"n_forfeit_turns":10,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":1351460394803781862,"n":1000,"digest":"4af2c6790c6eabde8de7fe015f73fdc9fba7d53a160f8860236f6d189f334975","n_paired_turns":979,"n_forfeit_turns":10,"margin":0.014038021373142915,"se":0.031390449608481766,"z":0.44720676346572025,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":1},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he103":{"ok":true,"reasons":[]},"assistant_code_only_he134":{"ok":false,"reasons":["no_think_close"]},"assistant_code_only_he69":{"ok":true,"reasons":[]},"assistant_code_only_he70":{"ok":false,"reasons":["close_only_fence"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":20,"pass_rate":0.8333333333333334,"think_close_rate":0.9583333333333334,"by_reason":{"close_only_fence":3,"no_think_close":1}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.014038021373142915,"se":0.031390449608481766,"z":0.44720676346572025,"sd_diff":0.9821750148336893,"n_paired_turns":979,"n_forfeit_turns":10,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"tool_call":{"R":0.008001804726845875,"A":6.169107989339683,"Mc":0.1702239046531891},"text":{"R":0.06769988775324587,"A":39.38982994729815,"Mc":0.1443086314166106},"bash":{"R":0.01669267928257279,"A":5.395160490840646,"Mc":0.1483176384296871},"boxed":{"R":0.1189350914877125,"A":5.473928355196559,"Mc":0.12672032338665576},"terminus_json":{"R":0.0022066560877208067,"A":8.917371499504386,"Mc":0.15455764052827992}},"challenger":{"mean":-0.7006884682677937,"mean_valid":-0.6460000107679774,"sd_valid":1.4697820200457514,"n_turns":991,"n_valid":969,"n_forfeits":10,"n_unscorable":12,"mean_z_R":0.2251175130426433,"mean_typ_c":0.5406910486528104,"mean_z_A":-0.09049457474352893,"bind_frac":{"R":0.3126934984520124,"Gc":0.18472652218782248,"A":0.5025799793601651},"n_leg_dropped":{"R":0,"Gc":58,"A":0},"mean_content_share":0.2855094994662532,"mean_R":0.01679875721028196,"mean_A":1.6796747026482222,"mean_mc":-0.6800734148275542},"king":{"mean":-0.7147264896409367,"mean_valid":-0.6711814967646519,"sd_valid":1.6748712609761842,"n_turns":991,"n_valid":971,"n_forfeits":8,"n_unscorable":12,"mean_z_R":0.26671112556201865,"mean_typ_c":0.47176368194949575,"mean_z_A":-0.052997979371332646,"bind_frac":{"R":0.31513903192584963,"Gc":0.19979402677651906,"A":0.4850669412976313},"n_leg_dropped":{"R":0,"Gc":58,"A":0},"mean_content_share":0.28567741411532077,"mean_R":0.01754163788730091,"mean_A":1.8983372510873662,"mean_mc":-0.6797080881374636}},"rejection_reason":null,"reign_number":null,"score":-0.00045183050277074075,"score_king":-0.00021936325183154862,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9164419,"blocks_since_crown":10408,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1550.628883578013,"mean_len_y":999.3188801638785,"n_samples":3000,"think_close_rate":0.9376666666666666,"n_text_fallback":44,"by_dialect":{"text":{"n_turns":447,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":163,"zero_ref_turns":1,"mean_refs":2.932515337423313,"ref_pair_agreement":0.19077568134171907,"ref_pair_n":159},"tool_call":{"n_turns":293,"zero_ref_turns":2,"mean_refs":2.9180887372013653,"ref_pair_agreement":0.21245421245421245,"ref_pair_n":273},"boxed":{"n_turns":64,"zero_ref_turns":6,"mean_refs":2.578125,"ref_pair_agreement":0.5333333333333333,"ref_pair_n":55},"terminus_json":{"n_turns":33,"zero_ref_turns":0,"mean_refs":2.727272727272727,"ref_pair_agreement":0.36666666666666664,"ref_pair_n":30}},"ref_pair_agreement":0.2488716956802063,"ref_pair_n":517},"duel_seconds":2118.9857808020897,"challenger":{"reason":-0.00045183050277074075,"n_turns":991,"n_pairs":2900,"n_forfeits":10,"forfeit_rate":0.010090817356205853,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":38.363205211406154,"mean_len_z":1132.3020689655173,"median_len_z":677.0,"mean_len_y":431.25827586206896,"mean_b":0.11175802975447105,"b_gate_pass_rate":0.4596551724137931,"mean_r_leg":0.01679875721028196,"mean_g_leg":0.0549369979578605,"g_bind_frac":0.2344546381243629,"a_match":0.19065656565656566,"a_match_n":528,"a_match_centered":-0.05252918287937743,"n_turns_cap_raised":65,"mean_cap_tokens":4165.200807265389,"max_cap_tokens":6067,"len_z_delta":-418.3268146124958,"len_y_delta":-568.0606043018095,"n_samples":994,"think_close_rate":0.9899396378269618,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":162,"n_valid":162,"parse_rate":1.0,"reason":0.007756453111340476,"mean_b":0.10968469778940615,"b_gate_pass_rate":0.8828451882845189,"median_len_z":426.0,"mean_r_leg":0.017385744407409823,"mean_g_leg":0.04659722834157544,"g_bind_frac":0.2839506172839506,"a_match":0.14814814814814814,"a_match_n":162,"a_match_centered":-0.039832285115303984},"boxed":{"n_turns":58,"n_valid":57,"parse_rate":0.9827586206896551,"reason":0.007714447449978667,"mean_b":0.9385154609552526,"b_gate_pass_rate":0.7055214723926381,"median_len_z":1892.0,"mean_r_leg":0.09491223920110609,"mean_g_leg":0.020061284772261854,"g_bind_frac":0.6140350877192983,"a_match":0.45833333333333337,"a_match_n":56,"a_match_centered":-0.06790123456790124},"terminus_json":{"n_turns":33,"n_valid":33,"parse_rate":1.0,"reason":-0.007759934932008384,"mean_b":0.02091871646816484,"b_gate_pass_rate":0.25555555555555554,"median_len_z":798.0,"mean_r_leg":0.0014257551383255623,"mean_g_leg":0.03826983260502546,"g_bind_frac":0.18181818181818182,"a_match":0.3434343434343434,"a_match_n":33,"a_match_centered":0.01111111111111111},"text":{"n_turns":447,"n_valid":438,"parse_rate":0.9798657718120806,"reason":-0.0059735050903977,"mean_b":0.0699932151855081,"b_gate_pass_rate":0.3013698630136986,"median_len_z":755.5,"mean_r_leg":0.014016764185088421,"mean_g_leg":0.054690628076390246,"g_bind_frac":0.21232876712328766,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":291,"n_valid":291,"parse_rate":1.0,"reason":0.002661468191691838,"mean_b":0.029049370026937114,"b_gate_pass_rate":0.4409356725146199,"median_len_z":571.0,"mean_r_leg":0.007102061725737767,"mean_g_leg":0.06867199725045442,"g_bind_frac":0.1718213058419244,"a_match":0.14320096269554752,"a_match_n":277,"a_match_centered":-0.06396063960639606}}},"king":{"reason":-0.00021936325183154862,"n_turns":991,"n_pairs":2906,"n_forfeits":8,"forfeit_rate":0.008072653884964682,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":34.99450253671978,"mean_len_z":1128.6713695801789,"median_len_z":689.0,"mean_len_y":413.4163799036476,"mean_b":0.1204016673093249,"b_gate_pass_rate":0.47900894700619406,"mean_r_leg":0.01754163788730091,"mean_g_leg":0.05356676544868552,"g_bind_frac":0.2644964394710071,"a_match":0.19591194968553458,"a_match_n":530,"a_match_centered":-0.04822006472491909,"n_turns_cap_raised":65,"mean_cap_tokens":4165.200807265389,"max_cap_tokens":6067,"len_z_delta":-421.9575139978342,"len_y_delta":-585.9025002602309,"n_samples":991,"think_close_rate":0.9919273461150353,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":162,"n_valid":162,"parse_rate":1.0,"reason":0.007465637297462723,"mean_b":0.11816515022769054,"b_gate_pass_rate":0.897489539748954,"median_len_z":444.0,"mean_r_leg":0.018228995601928522,"mean_g_leg":0.04553270319347919,"g_bind_frac":0.3148148148148148,"a_match":0.15432098765432098,"a_match_n":162,"a_match_centered":-0.03354297693920335},"boxed":{"n_turns":58,"n_valid":57,"parse_rate":0.9827586206896551,"reason":0.007754065574812364,"mean_b":0.9718548647478614,"b_gate_pass_rate":0.6993865030674846,"median_len_z":1920.0,"mean_r_leg":0.09160825875511476,"mean_g_leg":0.02064637334524329,"g_bind_frac":0.6666666666666666,"a_match":0.40350877192982454,"a_match_n":57,"a_match_centered":-0.11728395061728394},"terminus_json":{"n_turns":33,"n_valid":33,"parse_rate":1.0,"reason":-0.005985026388619212,"mean_b":0.020746963891523147,"b_gate_pass_rate":0.28888888888888886,"median_len_z":889.0,"mean_r_leg":0.0019326886932466605,"mean_g_leg":0.03995150098421415,"g_bind_frac":0.21212121212121213,"a_match":0.3787878787878788,"a_match_n":33,"a_match_centered":0.05},"text":{"n_turns":447,"n_valid":440,"parse_rate":0.9843400447427293,"reason":-0.005239795665277395,"mean_b":0.0807827369945904,"b_gate_pass_rate":0.32954545454545453,"median_len_z":767.0,"mean_r_leg":0.0152772500535111,"mean_g_leg":0.0532000523321571,"g_bind_frac":0.22954545454545455,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":291,"n_valid":291,"parse_rate":1.0,"reason":0.0022788196051899893,"mean_b":0.030984234918203787,"b_gate_pass_rate":0.45380116959064326,"median_len_z":543.0,"mean_r_leg":0.007844994007700373,"mean_g_leg":0.06658613979177726,"g_bind_frac":0.21649484536082475,"a_match":0.15587529976019185,"a_match_n":278,"a_match_centered":-0.053921568627450976}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T03:35:22.749224+00:00","challenge_id":"chal-00717","repo":"r2://affine-private-models/models/registrations/3050f9f27c9a461bf58b8c6f74e64583bf3f87d070c50c1e06b156fbd6bce996/","hotkey":"5FaRcdcYisFdz6EQ6DyJ4EVSaEHNEcyY1whn8gmy134YkUy1","uid":30,"duration_s":645.2,"revision":"c03fe504677f02848237796a442068187de308c4013eede45e2e96265a8808c0","accepted":false,"error_code":null,"error_detail":"","z":null,"margin":null,"se":null,"n_paired_turns":null,"n_forfeit_turns":null,"near_miss":null,"protocol_probe":{"mode":"enforce","passed":false,"pass_rate":0.85,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":3},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":true,"reasons":[]},"assistant_code_only_he103":{"ok":true,"reasons":[]},"assistant_code_only_he134":{"ok":false,"reasons":["no_think_close"]},"assistant_code_only_he69":{"ok":true,"reasons":[]},"assistant_code_only_he70":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":23,"pass_rate":0.9583333333333334,"think_close_rate":0.9583333333333334,"by_reason":{"no_think_close":1}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":null,"rejection_reason":"protocol:pass_rate=0.85<0.9;multiple_tool_calls=3","reign_number":null,"score":null,"score_king":null,"gates":null,"duel_params":null,"teacher":null,"duel_seconds":null,"challenger":null,"king":null,"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T03:23:53.390792+00:00","challenge_id":"chal-00716","repo":"r2://affine-private-models/models/registrations/1c7eb9e7e41f289d2d4d65d35e27a6fba652aef4525e62c9a547226a1eaf7165/","hotkey":"5FxZXWtuWpE5jnZxv2KcZvPGykMXcoEqvDxokmPTYu9qaYt3","uid":216,"duration_s":2496.0,"revision":"932a234705ef8646fac4d00cd187b6727b177cb19672303b4f3a88a2866236b6","accepted":false,"error_code":null,"error_detail":"","z":1.3638234081897318,"margin":0.043271533211426634,"se":0.031728105670852956,"n_paired_turns":976,"n_forfeit_turns":12,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":15605505660609402045,"n":1000,"digest":"173ea2c19c83ff8c6c810531fed45d0a86d6ac4071d9fac30eab753ee60f59c4","n_paired_turns":976,"n_forfeit_turns":12,"margin":0.043271533211426634,"se":0.031728105670852956,"z":1.3638234081897318,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":true,"reasons":[]},"assistant_code_only_he103":{"ok":true,"reasons":[]},"assistant_code_only_he134":{"ok":true,"reasons":[]},"assistant_code_only_he69":{"ok":true,"reasons":[]},"assistant_code_only_he70":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":24,"pass_rate":1.0,"think_close_rate":1.0,"by_reason":{}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.043271533211426634,"se":0.031728105670852956,"z":1.3638234081897318,"sd_diff":0.9912177081316454,"n_paired_turns":976,"n_forfeit_turns":12,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"tool_call":{"R":0.007268617858559674,"A":5.262092239096095,"Mc":0.182016559768358},"text":{"R":0.034704750514413345,"A":34.91311031054316,"Mc":0.1581571653846746},"bash":{"R":0.022335231909543993,"A":6.583703209094397,"Mc":0.1547424484319825},"terminus_json":{"R":0.0016660075173170572,"A":10.460196329721105,"Mc":0.10305635974165119},"boxed":{"R":0.10749476762937345,"A":3.6204318312703303,"Mc":0.11473770985044453}},"challenger":{"mean":-0.6902123190920564,"mean_valid":-0.6463297762746353,"sd_valid":1.450586160756986,"n_turns":988,"n_valid":968,"n_forfeits":8,"n_unscorable":12,"mean_z_R":0.19142275864530006,"mean_typ_c":0.5443727565912223,"mean_z_A":-0.04002098588851651,"bind_frac":{"R":0.35330578512396693,"Gc":0.18078512396694216,"A":0.4659090909090909},"n_leg_dropped":{"R":0,"Gc":47,"A":0},"mean_content_share":0.27675099746069753,"mean_R":0.013805619775350183,"mean_A":1.8739441165682622,"mean_mc":-0.6905385770540975},"king":{"mean":-0.7388743498958029,"mean_valid":-0.6844676730591513,"sd_valid":1.6044425958236503,"n_turns":988,"n_valid":967,"n_forfeits":10,"n_unscorable":11,"mean_z_R":0.17604797252464557,"mean_typ_c":0.546177546109667,"mean_z_A":-0.03055273620601879,"bind_frac":{"R":0.3453981385729059,"Gc":0.1768355739400207,"A":0.47776628748707345},"n_leg_dropped":{"R":0,"Gc":48,"A":0},"mean_content_share":0.27574987443889126,"mean_R":0.012920987612660743,"mean_A":1.9366755437580403,"mean_mc":-0.6889072531815512}},"rejection_reason":null,"reign_number":null,"score":0.0017762329922517595,"score_king":-4.329034526096872e-05,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9163398,"blocks_since_crown":9387,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1574.4948594928032,"mean_len_y":871.46881425634,"n_samples":3000,"think_close_rate":0.9406666666666667,"n_text_fallback":56,"by_dialect":{"tool_call":{"n_turns":318,"zero_ref_turns":0,"mean_refs":2.9371069182389937,"ref_pair_agreement":0.2350282485875706,"ref_pair_n":295},"bash":{"n_turns":187,"zero_ref_turns":2,"mean_refs":2.935828877005348,"ref_pair_agreement":0.20540540540540542,"ref_pair_n":185},"text":{"n_turns":404,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":70,"zero_ref_turns":9,"mean_refs":2.3285714285714287,"ref_pair_agreement":0.6729559748427673,"ref_pair_n":53},"terminus_json":{"n_turns":21,"zero_ref_turns":1,"mean_refs":2.857142857142857,"ref_pair_agreement":0.4166666666666667,"ref_pair_n":20}},"ref_pair_agreement":0.2736588306208559,"ref_pair_n":553},"duel_seconds":2141.773351930082,"challenger":{"reason":0.0017762329922517595,"n_turns":988,"n_pairs":2894,"n_forfeits":8,"forfeit_rate":0.008097165991902834,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":61.36194141756643,"mean_len_z":1164.0970974429854,"median_len_z":660.0,"mean_len_y":439.7608845888044,"mean_b":0.1274975145636401,"b_gate_pass_rate":0.4854872149274361,"mean_r_leg":0.013805619775350183,"mean_g_leg":0.059743336323391245,"g_bind_frac":0.20612244897959184,"a_match":0.20654761904761906,"a_match_n":560,"a_match_centered":-0.06703229737964655,"n_turns_cap_raised":58,"mean_cap_tokens":4156.69028340081,"max_cap_tokens":6066,"len_z_delta":-410.39776204981786,"len_y_delta":-431.7079296675356,"n_samples":991,"think_close_rate":0.9919273461150353,"n_text_fallback":20,"by_dialect":{"bash":{"n_turns":185,"n_valid":185,"parse_rate":1.0,"reason":0.008610557060263998,"mean_b":0.1150336075171449,"b_gate_pass_rate":0.8724954462659381,"median_len_z":494.0,"mean_r_leg":0.018478359351169406,"mean_g_leg":0.04780680344549414,"g_bind_frac":0.2594594594594595,"a_match":0.13333333333333333,"a_match_n":185,"a_match_centered":-0.07207207207207207},"boxed":{"n_turns":61,"n_valid":60,"parse_rate":0.9836065573770492,"reason":0.0013172430489163233,"mean_b":1.1011505364183123,"b_gate_pass_rate":0.725,"median_len_z":2286.0,"mean_r_leg":0.06789044929851822,"mean_g_leg":0.01768794067876826,"g_bind_frac":0.5166666666666667,"a_match":0.632768361581921,"a_match_n":59,"a_match_centered":-0.025641025641025644},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0033087112854315605,"mean_b":0.019076782574927564,"b_gate_pass_rate":0.3,"median_len_z":689.5,"mean_r_leg":0.0007588085590029723,"mean_g_leg":0.026862829367093263,"g_bind_frac":0.4,"a_match":0.4,"a_match_n":20,"a_match_centered":-0.01666666666666667},"text":{"n_turns":404,"n_valid":397,"parse_rate":0.9826732673267327,"reason":-0.002025697266344156,"mean_b":0.08770545805781677,"b_gate_pass_rate":0.3602015113350126,"median_len_z":766.0,"mean_r_leg":0.010356616076398805,"mean_g_leg":0.05991395789644103,"g_bind_frac":0.17380352644836272,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.003038268036237965,"mean_b":0.025737112732308928,"b_gate_pass_rate":0.3886509635974304,"median_len_z":544.0,"mean_r_leg":0.00600890310835019,"mean_g_leg":0.07647747373129546,"g_bind_frac":0.14465408805031446,"a_match":0.15427927927927926,"a_match_n":296,"a_match_centered":-0.07471264367816093}}},"king":{"reason":-4.329034526096872e-05,"n_turns":988,"n_pairs":2891,"n_forfeits":10,"forfeit_rate":0.010121457489878543,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":68.5594282114248,"mean_len_z":1164.6596333448633,"median_len_z":671.0,"mean_len_y":446.7637495676237,"mean_b":0.12704011178696503,"b_gate_pass_rate":0.47388446904185405,"mean_r_leg":0.012920987612660743,"mean_g_leg":0.058287330062209444,"g_bind_frac":0.2147239263803681,"a_match":0.21195973949082297,"a_match_n":563,"a_match_centered":-0.06204379562043796,"n_turns_cap_raised":58,"mean_cap_tokens":4156.69028340081,"max_cap_tokens":6066,"len_z_delta":-409.8352261479399,"len_y_delta":-424.70506468871633,"n_samples":988,"think_close_rate":0.9898785425101214,"n_text_fallback":16,"by_dialect":{"bash":{"n_turns":185,"n_valid":185,"parse_rate":1.0,"reason":0.00859036088790978,"mean_b":0.11195571836886627,"b_gate_pass_rate":0.8888888888888888,"median_len_z":483.0,"mean_r_leg":0.016647819161511875,"mean_g_leg":0.04930522615694662,"g_bind_frac":0.24324324324324326,"a_match":0.14774774774774774,"a_match_n":185,"a_match_centered":-0.05765765765765765},"boxed":{"n_turns":61,"n_valid":59,"parse_rate":0.9672131147540983,"reason":-0.0010525011776072453,"mean_b":1.1074182091996776,"b_gate_pass_rate":0.725,"median_len_z":2349.0,"mean_r_leg":0.07043344524446833,"mean_g_leg":0.01594684475334168,"g_bind_frac":0.5932203389830508,"a_match":0.6440677966101694,"a_match_n":59,"a_match_centered":0.0064102564102564066},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.009185942920188924,"mean_b":0.016675921866412136,"b_gate_pass_rate":0.2,"median_len_z":735.0,"mean_r_leg":0.0010307330878112145,"mean_g_leg":0.02520436928941978,"g_bind_frac":0.4,"a_match":0.4,"a_match_n":20,"a_match_centered":-0.01666666666666667},"text":{"n_turns":404,"n_valid":396,"parse_rate":0.9801980198019802,"reason":-0.004798894087257706,"mean_b":0.08754650117678255,"b_gate_pass_rate":0.33080808080808083,"median_len_z":768.5,"mean_r_leg":0.008607791775924356,"mean_g_leg":0.05651745535101303,"g_bind_frac":0.17676767676767677,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.0017442987927949283,"mean_b":0.025285397869012356,"b_gate_pass_rate":0.38650963597430404,"median_len_z":525.0,"mean_r_leg":0.006201276307725185,"mean_g_leg":0.07565307678166351,"g_bind_frac":0.16352201257861634,"a_match":0.15384615384615385,"a_match_n":299,"a_match_centered":-0.08018327605956471}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T02:39:13.748413+00:00","challenge_id":"chal-00715","repo":"r2://affine-private-models/models/registrations/8de7f2cf28885747b32c7297e15923a86152b9c8a12171af5208f4a241fc07ee/","hotkey":"5DZpZt4imWptQTc2WAgXf74yb7twmNcXiMEC9zPYKGMmgwuq","uid":83,"duration_s":2684.6,"revision":"b8f5187aac04d229f7cc9d7c3e9be3f6e96d4f3d64144cd1a82ae3b68856bf6a","accepted":false,"error_code":null,"error_detail":"","z":0.5844288205763877,"margin":0.023675834052930694,"se":0.040511065196238295,"n_paired_turns":980,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":16036189152182234312,"n":1000,"digest":"4dbdd5b80e6a977b83f0d801104f028e7e30f043cdbd9fc9ecbf5b22f3c4f92a","n_paired_turns":980,"n_forfeit_turns":8,"margin":0.023675834052930694,"se":0.040511065196238295,"z":0.5844288205763877,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he103":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he134":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he69":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he70":{"ok":false,"reasons":["close_only_fence"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":5,"pass_rate":0.20833333333333334,"think_close_rate":1.0,"by_reason":{"close_only_fence":19}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.023675834052930694,"se":0.040511065196238295,"z":0.5844288205763877,"sd_diff":1.2681969386760057,"n_paired_turns":980,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"tool_call":{"R":0.007894715289532254,"A":5.751225031068867,"Mc":0.16292150698030655},"text":{"R":0.2164812846456025,"A":27.290699461705696,"Mc":0.1477360244701612},"bash":{"R":0.026795502388341164,"A":6.3283158914109805,"Mc":0.15293206182237046},"boxed":{"R":0.06600019253406174,"A":4.557238262811023,"Mc":0.1323948418031751},"terminus_json":{"R":0.002927455234624935,"A":11.364655547349095,"Mc":0.1692394766800939}},"challenger":{"mean":-0.7305903652708161,"mean_valid":-0.6927587063548116,"sd_valid":1.3810801633568717,"n_turns":986,"n_valid":975,"n_forfeits":7,"n_unscorable":4,"mean_z_R":0.08924886054871947,"mean_typ_c":0.5245010110548006,"mean_z_A":-0.1113988919678664,"bind_frac":{"R":0.3723076923076923,"Gc":0.19076923076923077,"A":0.4369230769230769},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.2899713839104782,"mean_R":0.021235151235832674,"mean_A":1.887183064235065,"mean_mc":-0.6674624621772687},"king":{"mean":-0.74887059741877,"mean_valid":-0.7165559549413472,"sd_valid":1.450334139601246,"n_turns":986,"n_valid":975,"n_forfeits":6,"n_unscorable":5,"mean_z_R":0.12598091146914617,"mean_typ_c":0.4979305189915385,"mean_z_A":-0.14754188562193493,"bind_frac":{"R":0.3374358974358974,"Gc":0.2,"A":0.4625641025641026},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.2824123660818573,"mean_R":0.022277904759502008,"mean_A":1.3251860036042438,"mean_mc":-0.6772470440207441}},"rejection_reason":null,"reign_number":null,"score":0.0009751205010906692,"score_king":0.001014939171062295,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9163159,"blocks_since_crown":9148,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1423.7932922655716,"mean_len_y":836.5889801505818,"n_samples":3000,"think_close_rate":0.9436666666666667,"n_text_fallback":30,"by_dialect":{"text":{"n_turns":412,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":317,"zero_ref_turns":1,"mean_refs":2.9400630914826498,"ref_pair_agreement":0.19188596491228072,"ref_pair_n":304},"bash":{"n_turns":207,"zero_ref_turns":2,"mean_refs":2.9420289855072466,"ref_pair_agreement":0.17398373983739837,"ref_pair_n":205},"boxed":{"n_turns":43,"zero_ref_turns":7,"mean_refs":2.2790697674418605,"ref_pair_agreement":0.5104166666666666,"ref_pair_n":32},"terminus_json":{"n_turns":21,"zero_ref_turns":4,"mean_refs":2.238095238095238,"ref_pair_agreement":0.375,"ref_pair_n":16}},"ref_pair_agreement":0.20885697187312985,"ref_pair_n":557},"duel_seconds":2176.812940812204,"challenger":{"reason":0.0009751205010906692,"n_turns":986,"n_pairs":2905,"n_forfeits":7,"forfeit_rate":0.007099391480730223,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-17.518980246681892,"mean_len_z":1035.6254733218589,"median_len_z":631.0,"mean_len_y":402.7580034423408,"mean_b":0.09620225312413581,"b_gate_pass_rate":0.504302925989673,"mean_r_leg":0.021235151235832674,"mean_g_leg":0.05308343308291606,"g_bind_frac":0.24821246169560776,"a_match":0.16277678037103532,"a_match_n":557,"a_match_centered":-0.04649758454106281,"n_turns_cap_raised":44,"mean_cap_tokens":4136.871196754564,"max_cap_tokens":6002,"len_z_delta":-388.16781894371275,"len_y_delta":-433.83097670824105,"n_samples":989,"think_close_rate":0.993933265925177,"n_text_fallback":12,"by_dialect":{"bash":{"n_turns":205,"n_valid":205,"parse_rate":1.0,"reason":0.010665395244393106,"mean_b":0.11172983110783691,"b_gate_pass_rate":0.8555008210180624,"median_len_z":506.0,"mean_r_leg":0.021241460618977463,"mean_g_leg":0.05240508711087121,"g_bind_frac":0.28780487804878047,"a_match":0.10569105691056911,"a_match_n":205,"a_match_centered":-0.06829268292682927},"boxed":{"n_turns":36,"n_valid":35,"parse_rate":0.9722222222222222,"reason":0.00040233786924371683,"mean_b":0.8386832871952802,"b_gate_pass_rate":0.7938144329896907,"median_len_z":1901.0,"mean_r_leg":0.051778375641158135,"mean_g_leg":0.015794582179697973,"g_bind_frac":0.6285714285714286,"a_match":0.36363636363636365,"a_match_n":33,"a_match_centered":-0.17204301075268816},"terminus_json":{"n_turns":17,"n_valid":16,"parse_rate":0.9411764705882353,"reason":-0.013591519460351302,"mean_b":0.02825586199394056,"b_gate_pass_rate":0.43478260869565216,"median_len_z":1008.0,"mean_r_leg":0.0022230358156066954,"mean_g_leg":0.01712718935842974,"g_bind_frac":0.375,"a_match":0.375,"a_match_n":16,"a_match_centered":0.0},"text":{"n_turns":412,"n_valid":407,"parse_rate":0.9878640776699029,"reason":-0.0023232207183341985,"mean_b":0.08923748606560217,"b_gate_pass_rate":0.36855036855036855,"median_len_z":739.0,"mean_r_leg":0.032276832421166336,"mean_g_leg":0.05105428093597028,"g_bind_frac":0.2334152334152334,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":-0.0001620209099313253,"mean_b":0.02125864719439715,"b_gate_pass_rate":0.4259656652360515,"median_len_z":504.0,"mean_r_leg":0.004589338978116674,"mean_g_leg":0.06208765944139879,"g_bind_frac":0.1930379746835443,"a_match":0.16831683168316833,"a_match_n":303,"a_match_centered":-0.021111111111111112}}},"king":{"reason":0.001014939171062295,"n_turns":986,"n_pairs":2906,"n_forfeits":6,"forfeit_rate":0.006085192697768763,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-16.44177666684978,"mean_len_z":1070.011355815554,"median_len_z":635.0,"mean_len_y":407.2415691672402,"mean_b":0.09612898389318669,"b_gate_pass_rate":0.5048176187198898,"mean_r_leg":0.022277904759502008,"mean_g_leg":0.053286540627004414,"g_bind_frac":0.25816326530612244,"a_match":0.1681600955794504,"a_match_n":558,"a_match_centered":-0.04076086956521739,"n_turns_cap_raised":44,"mean_cap_tokens":4136.871196754564,"max_cap_tokens":6002,"len_z_delta":-353.7819364500176,"len_y_delta":-429.34741098334166,"n_samples":986,"think_close_rate":0.9939148073022313,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":205,"n_valid":205,"parse_rate":1.0,"reason":0.010829379340191497,"mean_b":0.11000163530292946,"b_gate_pass_rate":0.8637110016420362,"median_len_z":535.0,"mean_r_leg":0.021418051736378174,"mean_g_leg":0.0540897421104251,"g_bind_frac":0.3073170731707317,"a_match":0.12845528455284552,"a_match_n":205,"a_match_centered":-0.04552845528455285},"boxed":{"n_turns":36,"n_valid":35,"parse_rate":0.9722222222222222,"reason":0.0024139830244867978,"mean_b":0.8641578446060966,"b_gate_pass_rate":0.6494845360824743,"median_len_z":1942.0,"mean_r_leg":0.04232897482909411,"mean_g_leg":0.020668579871566832,"g_bind_frac":0.5714285714285714,"a_match":0.4292929292929293,"a_match_n":33,"a_match_centered":-0.10215053763440861},"terminus_json":{"n_turns":17,"n_valid":17,"parse_rate":1.0,"reason":-0.007967579568062582,"mean_b":0.027661816469721545,"b_gate_pass_rate":0.46808510638297873,"median_len_z":1041.0,"mean_r_leg":0.0013469293937513264,"mean_g_leg":0.013274765627313773,"g_bind_frac":0.35294117647058826,"a_match":0.35294117647058826,"a_match_n":17,"a_match_centered":0.0},"text":{"n_turns":412,"n_valid":407,"parse_rate":0.9878640776699029,"reason":-0.003476419297436179,"mean_b":0.08427517675546609,"b_gate_pass_rate":0.3783783783783784,"median_len_z":757.0,"mean_r_leg":0.03481140471815755,"mean_g_leg":0.05029571965686618,"g_bind_frac":0.24324324324324326,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.0008276502286310473,"mean_b":0.026112043106034474,"b_gate_pass_rate":0.4227467811158798,"median_len_z":498.0,"mean_r_leg":0.00559807727643118,"mean_g_leg":0.06238285908327047,"g_bind_frac":0.20569620253164558,"a_match":0.15621562156215624,"a_match_n":303,"a_match_centered":-0.03333333333333333}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T01:53:22.928872+00:00","challenge_id":"chal-00714","repo":"r2://affine-private-models/models/registrations/3f7e904098869a3f6cb93ea3a0ac9bc681731d9b96ba42bd1a157427b4250797/","hotkey":"5FJpuexkiB64wSQGY6pTmAZv4YcstCs5rFvSe7oKGBknBeU5","uid":74,"duration_s":2611.5,"revision":"e77871d611d999f16471394fa4525a3b13e359714eec761f599559ccee2bec5d","accepted":false,"error_code":null,"error_detail":"","z":2.6223051801623147,"margin":0.09411213813788324,"se":0.035889086766040676,"n_paired_turns":980,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":17958488209225508472,"n":1000,"digest":"52672a885fdd916f89d16b98bbd160f19711f92ba2e084fcef866ff471ebd015","n_paired_turns":980,"n_forfeit_turns":8,"margin":0.09411213813788324,"se":0.035889086766040676,"z":2.6223051801623147,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":true,"reasons":[]},"assistant_code_only_he103":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he134":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he69":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he70":{"ok":false,"reasons":["close_only_fence"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":11,"pass_rate":0.4583333333333333,"think_close_rate":0.9583333333333334,"by_reason":{"close_only_fence":12,"no_think_close":1}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.09411213813788324,"se":0.035889086766040676,"z":2.6223051801623147,"sd_diff":1.1235061272295706,"n_paired_turns":980,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"text":{"R":0.09095937293087107,"A":19.055487772687123,"Mc":0.14713070362832772},"bash":{"R":0.024538279349392844,"A":6.353510455240933,"Mc":0.15782697029545312},"tool_call":{"R":0.00848206863705974,"A":5.836984053351361,"Mc":0.18080144126021178},"terminus_json":{"R":0.001304431611052345,"A":9.819844353248088,"Mc":0.13023991492003498},"boxed":{"R":0.16136146443835997,"A":4.68137856989514,"Mc":0.12729153930838197}},"challenger":{"mean":-0.7168730477853078,"mean_valid":-0.7006505494673507,"sd_valid":1.4637782366837662,"n_turns":990,"n_valid":977,"n_forfeits":3,"n_unscorable":10,"mean_z_R":0.14602589046985753,"mean_typ_c":0.5287642076293616,"mean_z_A":-0.10921953259935122,"bind_frac":{"R":0.3623336745138178,"Gc":0.17604912998976457,"A":0.4616171954964176},"n_leg_dropped":{"R":0,"Gc":52,"A":0},"mean_content_share":0.28215679572000046,"mean_R":0.0212680913378231,"mean_A":2.3676000307151095,"mean_mc":-0.67679984013143},"king":{"mean":-0.810985185923191,"mean_valid":-0.7790200022635803,"sd_valid":1.5655154129339932,"n_turns":990,"n_valid":974,"n_forfeits":6,"n_unscorable":10,"mean_z_R":0.16749912692971303,"mean_typ_c":0.5075436116411738,"mean_z_A":-0.16003319915225767,"bind_frac":{"R":0.34188911704312114,"Gc":0.17659137577002054,"A":0.4815195071868583},"n_leg_dropped":{"R":0,"Gc":52,"A":0},"mean_content_share":0.27881881721214785,"mean_R":0.021487036413883383,"mean_A":1.9033742239471616,"mean_mc":-0.6927008786599133}},"rejection_reason":null,"reign_number":null,"score":0.0007818610575748115,"score_king":0.0007210398064131743,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9162936,"blocks_since_crown":8925,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1456.1773752563226,"mean_len_y":923.0659603554341,"n_samples":3000,"think_close_rate":0.9423333333333334,"n_text_fallback":24,"by_dialect":{"bash":{"n_turns":223,"zero_ref_turns":1,"mean_refs":2.914798206278027,"ref_pair_agreement":0.1582952815829528,"ref_pair_n":219},"text":{"n_turns":382,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":54,"zero_ref_turns":6,"mean_refs":2.574074074074074,"ref_pair_agreement":0.6737588652482269,"ref_pair_n":47},"tool_call":{"n_turns":314,"zero_ref_turns":3,"mean_refs":2.9203821656050954,"ref_pair_agreement":0.1890380313199105,"ref_pair_n":298},"terminus_json":{"n_turns":27,"zero_ref_turns":0,"mean_refs":2.740740740740741,"ref_pair_agreement":0.25641025641025644,"ref_pair_n":26}},"ref_pair_agreement":0.21920903954802257,"ref_pair_n":590},"duel_seconds":2124.624438086059,"challenger":{"reason":0.0007818610575748115,"n_turns":990,"n_pairs":2917,"n_forfeits":3,"forfeit_rate":0.0030303030303030303,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":7.859122479919597,"mean_len_z":1071.5913609873157,"median_len_z":646.0,"mean_len_y":404.80836475831336,"mean_b":0.12154143865162689,"b_gate_pass_rate":0.5138841275282825,"mean_r_leg":0.0212680913378231,"mean_g_leg":0.05790875194155413,"g_bind_frac":0.2077001013171226,"a_match":0.15997770345596432,"a_match_n":598,"a_match_centered":-0.0572562358276644,"n_turns_cap_raised":55,"mean_cap_tokens":4149.341414141414,"max_cap_tokens":5975,"len_z_delta":-384.5860142690069,"len_y_delta":-518.2575955971207,"n_samples":993,"think_close_rate":0.9969788519637462,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":222,"n_valid":222,"parse_rate":1.0,"reason":0.010057220434465854,"mean_b":0.11408339942100927,"b_gate_pass_rate":0.8353846153846154,"median_len_z":507.0,"mean_r_leg":0.019919989948813333,"mean_g_leg":0.05813183959803219,"g_bind_frac":0.20270270270270271,"a_match":0.09159159159159158,"a_match_n":222,"a_match_centered":-0.0654490106544901},"boxed":{"n_turns":48,"n_valid":48,"parse_rate":1.0,"reason":0.0037244516101930555,"mean_b":1.0872576149703304,"b_gate_pass_rate":0.6618705035971223,"median_len_z":1755.0,"mean_r_leg":0.10456519950921403,"mean_g_leg":0.016594784877404473,"g_bind_frac":0.6458333333333334,"a_match":0.5886524822695036,"a_match_n":47,"a_match_centered":-0.0851063829787234},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.008731143158453292,"mean_b":0.020011891476895312,"b_gate_pass_rate":0.4189189189189189,"median_len_z":608.0,"mean_r_leg":0.001517593641738996,"mean_g_leg":0.028822130238782426,"g_bind_frac":0.18518518518518517,"a_match":0.2839506172839506,"a_match_n":27,"a_match_centered":0.038461538461538464},"text":{"n_turns":382,"n_valid":379,"parse_rate":0.9921465968586387,"reason":-0.0037273319987836335,"mean_b":0.09337878291267424,"b_gate_pass_rate":0.37467018469656993,"median_len_z":828.0,"mean_r_leg":0.026255305324901126,"mean_g_leg":0.051296841289598036,"g_bind_frac":0.17941952506596306,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":311,"n_valid":311,"parse_rate":1.0,"reason":7.121389733750524e-05,"mean_b":0.02355594580290388,"b_gate_pass_rate":0.44383860414394766,"median_len_z":488.0,"mean_r_leg":0.005011263854945614,"mean_g_leg":0.07470874513257422,"g_bind_frac":0.18006430868167203,"a_match":0.13245033112582782,"a_match_n":302,"a_match_centered":-0.05518018018018018}}},"king":{"reason":0.0007210398064131743,"n_turns":990,"n_pairs":2908,"n_forfeits":6,"forfeit_rate":0.006060606060606061,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-10.697324075105925,"mean_len_z":1096.5134112792298,"median_len_z":666.0,"mean_len_y":399.937757909216,"mean_b":0.12000419655081677,"b_gate_pass_rate":0.5092847317744154,"mean_r_leg":0.021487036413883383,"mean_g_leg":0.05812889428920576,"g_bind_frac":0.21747967479674796,"a_match":0.154082774049217,"a_match_n":596,"a_match_centered":-0.06171786120591581,"n_turns_cap_raised":55,"mean_cap_tokens":4149.341414141414,"max_cap_tokens":5975,"len_z_delta":-359.66396397709286,"len_y_delta":-523.1282024462181,"n_samples":990,"think_close_rate":0.9939393939393939,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":222,"n_valid":222,"parse_rate":1.0,"reason":0.00952592979847215,"mean_b":0.1153105226662993,"b_gate_pass_rate":0.8384615384615385,"median_len_z":504.0,"mean_r_leg":0.018908139164516273,"mean_g_leg":0.058263171632963275,"g_bind_frac":0.1981981981981982,"a_match":0.10810810810810811,"a_match_n":222,"a_match_centered":-0.0487062404870624},"boxed":{"n_turns":48,"n_valid":47,"parse_rate":0.9791666666666666,"reason":-0.00014319384858106906,"mean_b":1.037620041002274,"b_gate_pass_rate":0.6691176470588235,"median_len_z":2094.5,"mean_r_leg":0.0908568133504374,"mean_g_leg":0.01727823662583027,"g_bind_frac":0.6170212765957447,"a_match":0.571969696969697,"a_match_n":44,"a_match_centered":-0.11742424242424243},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.008913177895883848,"mean_b":0.019442608665740286,"b_gate_pass_rate":0.2702702702702703,"median_len_z":560.0,"mean_r_leg":0.0013981162018503349,"mean_g_leg":0.02618866149140846,"g_bind_frac":0.2222222222222222,"a_match":0.2345679012345679,"a_match_n":27,"a_match_centered":-0.012820512820512822},"text":{"n_turns":382,"n_valid":377,"parse_rate":0.9869109947643979,"reason":-0.004090168687892602,"mean_b":0.09401582415272677,"b_gate_pass_rate":0.3793103448275862,"median_len_z":843.0,"mean_r_leg":0.028923069561866646,"mean_g_leg":0.050712488362248745,"g_bind_frac":0.21485411140583555,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":311,"n_valid":311,"parse_rate":1.0,"reason":0.0013152621858004965,"mean_b":0.027408274920798906,"b_gate_pass_rate":0.4318429661941112,"median_len_z":501.0,"mean_r_leg":0.005574341951750465,"mean_g_leg":0.07596986747206042,"g_bind_frac":0.17363344051446947,"a_match":0.11991199119911992,"a_match_n":303,"a_match_centered":-0.06734006734006734}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T00:56:29.148037+00:00","challenge_id":"chal-00713","repo":"r2://affine-private-models/models/registrations/d2b141ac7bf1f6b1df8c509c39b3c468a325fb2fbb4fbddd717227571239551b/","hotkey":"5GgDQwoGY7HkzmtGtVbwATub5poFhLzDpdcyQhwFGKV72YC3","uid":247,"duration_s":2795.0,"revision":"99927b02f9bfb49311ebb9948399338a01e89d233fcf4c27b891db8921d20011","accepted":false,"error_code":null,"error_detail":"","z":0.8482035246202568,"margin":0.027421105119926553,"se":0.032328449863731776,"n_paired_turns":985,"n_forfeit_turns":11,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":15570788863022916031,"n":1000,"digest":"0c4b7b02fddc25ee17d970e1b4b78b2d54939a52a43fc09125d60333a2a0834a","n_paired_turns":985,"n_forfeit_turns":11,"margin":0.027421105119926553,"se":0.032328449863731776,"z":0.8482035246202568,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":true,"reasons":[]},"assistant_code_only_he103":{"ok":true,"reasons":[]},"assistant_code_only_he134":{"ok":true,"reasons":[]},"assistant_code_only_he69":{"ok":true,"reasons":[]},"assistant_code_only_he70":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":24,"pass_rate":1.0,"think_close_rate":1.0,"by_reason":{}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.027421105119926553,"se":0.032328449863731776,"z":0.8482035246202568,"sd_diff":1.0146190125031866,"n_paired_turns":985,"n_forfeit_turns":11,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"text":{"R":0.09256933448862917,"A":24.814709381020826,"Mc":0.1599788310748096},"bash":{"R":0.025840196352999865,"A":6.167019234132192,"Mc":0.15727369684549677},"tool_call":{"R":0.0071941094588574665,"A":5.741249924368938,"Mc":0.1682176842135129},"boxed":{"R":0.07710048209343685,"A":4.957321367327098,"Mc":0.12754086333248293},"terminus_json":{"R":0.0014763871144513976,"A":11.485377231628595,"Mc":0.1331799827316738}},"challenger":{"mean":-0.7447215543179861,"mean_valid":-0.7125135148143169,"sd_valid":1.470641620876,"n_turns":992,"n_valid":979,"n_forfeits":6,"n_unscorable":7,"mean_z_R":0.12046064166892684,"mean_typ_c":0.6286202899817944,"mean_z_A":-0.1393753597005385,"bind_frac":{"R":0.3687436159346272,"Gc":0.14300306435137897,"A":0.4882533197139939},"n_leg_dropped":{"R":0,"Gc":62,"A":0},"mean_content_share":0.2737256139307591,"mean_R":0.018735243765003504,"mean_A":2.116498066627138,"mean_mc":-0.6880850623500375},"king":{"mean":-0.7721426594379126,"mean_valid":-0.7347244576138486,"sd_valid":1.4599179401992846,"n_turns":992,"n_valid":978,"n_forfeits":7,"n_unscorable":7,"mean_z_R":0.1461511118892658,"mean_typ_c":0.5657314521847706,"mean_z_A":-0.12138369194933263,"bind_frac":{"R":0.34662576687116564,"Gc":0.17484662576687116,"A":0.4785276073619632},"n_leg_dropped":{"R":0,"Gc":60,"A":0},"mean_content_share":0.27402247814389347,"mean_R":0.018710739523502835,"mean_A":2.227135168141348,"mean_mc":-0.6991261252553616}},"rejection_reason":null,"reign_number":null,"score":0.00033102511052105046,"score_king":0.0004832578662409743,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9162636,"blocks_since_crown":8625,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1469.6521591295477,"mean_len_y":878.3849030941857,"n_samples":3000,"think_close_rate":0.9493333333333334,"n_text_fallback":31,"by_dialect":{"boxed":{"n_turns":53,"zero_ref_turns":5,"mean_refs":2.4716981132075473,"ref_pair_agreement":0.5317460317460317,"ref_pair_n":42},"text":{"n_turns":389,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":208,"zero_ref_turns":0,"mean_refs":2.9615384615384617,"ref_pair_agreement":0.18284789644012944,"ref_pair_n":206},"tool_call":{"n_turns":319,"zero_ref_turns":1,"mean_refs":2.9529780564263324,"ref_pair_agreement":0.16337719298245612,"ref_pair_n":304},"terminus_json":{"n_turns":31,"zero_ref_turns":2,"mean_refs":2.7419354838709675,"ref_pair_agreement":0.26436781609195403,"ref_pair_n":29}},"ref_pair_agreement":0.20195065978198504,"ref_pair_n":581},"duel_seconds":2451.1805420611054,"challenger":{"reason":0.00033102511052105046,"n_turns":992,"n_pairs":2925,"n_forfeits":6,"forfeit_rate":0.006048387096774193,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-88.77223093258414,"mean_len_z":1183.5815384615385,"median_len_z":704.0,"mean_len_y":416.3425641025641,"mean_b":0.11403782927165955,"b_gate_pass_rate":0.4741880341880342,"mean_r_leg":0.018735243765003504,"mean_g_leg":0.05594724566862676,"g_bind_frac":0.22008113590263692,"a_match":0.18027210884353742,"a_match_n":588,"a_match_centered":-0.022608695652173914,"n_turns_cap_raised":54,"mean_cap_tokens":4161.384072580645,"max_cap_tokens":6056,"len_z_delta":-286.07062066800927,"len_y_delta":-462.0423389916216,"n_samples":995,"think_close_rate":0.992964824120603,"n_text_fallback":11,"by_dialect":{"bash":{"n_turns":208,"n_valid":208,"parse_rate":1.0,"reason":0.00819722205957453,"mean_b":0.11585395537328542,"b_gate_pass_rate":0.8668831168831169,"median_len_z":537.0,"mean_r_leg":0.021022329967612743,"mean_g_leg":0.054760453406438626,"g_bind_frac":0.27884615384615385,"a_match":0.1778846153846154,"a_match_n":208,"a_match_centered":-0.008090614886731393},"boxed":{"n_turns":48,"n_valid":46,"parse_rate":0.9583333333333334,"reason":0.0028691035064182424,"mean_b":1.0939966650998323,"b_gate_pass_rate":0.6377952755905512,"median_len_z":2240.0,"mean_r_leg":0.08174394543246989,"mean_g_leg":0.020980196129393634,"g_bind_frac":0.6304347826086957,"a_match":0.4621212121212121,"a_match_n":44,"a_match_centered":-0.04878048780487805},"terminus_json":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":-0.0016042891768258693,"mean_b":0.018735485713023244,"b_gate_pass_rate":0.35294117647058826,"median_len_z":770.0,"mean_r_leg":0.0007402583065153801,"mean_g_leg":0.04142095374720235,"g_bind_frac":0.13793103448275862,"a_match":0.2413793103448276,"a_match_n":29,"a_match_centered":-0.02298850574712644},"text":{"n_turns":389,"n_valid":385,"parse_rate":0.9897172236503856,"reason":-0.0038795702618193875,"mean_b":0.0844903251195997,"b_gate_pass_rate":0.3012987012987013,"median_len_z":798.0,"mean_r_leg":0.0230973381256091,"mean_g_leg":0.05369193403222462,"g_bind_frac":0.2,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.00012992129217923265,"mean_b":0.025560717455665675,"b_gate_pass_rate":0.4182590233545648,"median_len_z":596.0,"mean_r_leg":0.0044847218864400625,"mean_g_leg":0.06583685106194746,"g_bind_frac":0.1540880503144654,"a_match":0.13572204125950055,"a_match_n":307,"a_match_centered":-0.02898550724637681}}},"king":{"reason":0.0004832578662409743,"n_turns":992,"n_pairs":2922,"n_forfeits":7,"forfeit_rate":0.007056451612903226,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-97.62112280095522,"mean_len_z":1116.6649555099248,"median_len_z":722.0,"mean_len_y":407.78747433264886,"mean_b":0.11900724888796031,"b_gate_pass_rate":0.5078713210130048,"mean_r_leg":0.018710739523502835,"mean_g_leg":0.05559934964952997,"g_bind_frac":0.22436548223350253,"a_match":0.17176004527447652,"a_match_n":589,"a_match_centered":-0.03090699017908723,"n_turns_cap_raised":54,"mean_cap_tokens":4161.384072580645,"max_cap_tokens":6056,"len_z_delta":-352.98720361962296,"len_y_delta":-470.59742876153683,"n_samples":992,"think_close_rate":0.9929435483870968,"n_text_fallback":11,"by_dialect":{"bash":{"n_turns":208,"n_valid":208,"parse_rate":1.0,"reason":0.008377013254864014,"mean_b":0.11584915584325527,"b_gate_pass_rate":0.8603896103896104,"median_len_z":519.0,"mean_r_leg":0.01887261017518153,"mean_g_leg":0.055395579426493625,"g_bind_frac":0.2932692307692308,"a_match":0.16826923076923078,"a_match_n":208,"a_match_centered":-0.01779935275080906},"boxed":{"n_turns":48,"n_valid":47,"parse_rate":0.9791666666666666,"reason":0.003764213454433232,"mean_b":1.1029138819185833,"b_gate_pass_rate":0.6692307692307692,"median_len_z":2149.5,"mean_r_leg":0.08977927600512764,"mean_g_leg":0.020824185996393758,"g_bind_frac":0.574468085106383,"a_match":0.4444444444444444,"a_match_n":45,"a_match_centered":-0.07936507936507937},"terminus_json":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":-0.0038565847459831196,"mean_b":0.019402912387149973,"b_gate_pass_rate":0.4470588235294118,"median_len_z":673.0,"mean_r_leg":0.0009014505567541013,"mean_g_leg":0.0317150827224728,"g_bind_frac":0.20689655172413793,"a_match":0.25862068965517243,"a_match_n":29,"a_match_centered":-0.00574712643678161},"text":{"n_turns":389,"n_valid":383,"parse_rate":0.9845758354755784,"reason":-0.004488963846636206,"mean_b":0.08992975763013479,"b_gate_pass_rate":0.381201044386423,"median_len_z":795.0,"mean_r_leg":0.022371779855648446,"mean_g_leg":0.05379568356556439,"g_bind_frac":0.2010443864229765,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.001302951869375884,"mean_b":0.029743903961599073,"b_gate_pass_rate":0.4150743099787686,"median_len_z":594.0,"mean_r_leg":0.005315772928026144,"mean_g_leg":0.06522282370340557,"g_bind_frac":0.15723270440251572,"a_match":0.1259500542888165,"a_match_n":307,"a_match_centered":-0.035555555555555556}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-28T00:08:48.132641+00:00","challenge_id":"chal-00712","repo":"r2://affine-private-models/models/registrations/a51c099e5402ebe3559fee95cbbdf0727126eb0e5c8c271a423f3d0c3e06f14e/","hotkey":"5FK3g8Rvhy8DZPu52DGnQAYNwmrceGGjW6H2HhRs6oHg9hyv","uid":50,"duration_s":2713.3,"revision":"25d44531755a0eac8c3cb703f70dbca20eb87ab915b0764b876514bbab0729c8","accepted":false,"error_code":null,"error_detail":"","z":-1.9392222803376382,"margin":-0.0641637004908288,"se":0.03308733668203175,"n_paired_turns":984,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":7499556637729598419,"n":1000,"digest":"1668917ff804b00ee13cbe1cb60511d6e4a8285a023028d1efe07df1cda582f3","n_paired_turns":984,"n_forfeit_turns":8,"margin":-0.0641637004908288,"se":0.03308733668203175,"z":-1.9392222803376382,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":true,"reasons":[]},"assistant_code_only_he103":{"ok":true,"reasons":[]},"assistant_code_only_he134":{"ok":true,"reasons":[]},"assistant_code_only_he69":{"ok":false,"reasons":["close_only_fence"]},"assistant_code_only_he70":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":23,"pass_rate":0.9583333333333334,"think_close_rate":1.0,"by_reason":{"close_only_fence":1}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.0641637004908288,"se":0.03308733668203175,"z":-1.9392222803376382,"sd_diff":1.0379091959948914,"n_paired_turns":984,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"bash":{"R":0.02510981939014925,"A":6.796468503500629,"Mc":0.14747745678524812},"tool_call":{"R":0.010988664844233413,"A":8.857671737633037,"Mc":0.18575987622145668},"text":{"R":0.056447642710583217,"A":34.484486994770165,"Mc":0.15578138413794554},"terminus_json":{"R":0.002694090959485453,"A":9.460546975431207,"Mc":0.16088095522444934},"boxed":{"R":0.1296086192622417,"A":5.881781733993902,"Mc":0.133618608542577}},"challenger":{"mean":-0.6195042706475357,"mean_valid":-0.5920247214680031,"sd_valid":1.2696445752435361,"n_turns":995,"n_valid":979,"n_forfeits":5,"n_unscorable":11,"mean_z_R":0.1776537149277751,"mean_typ_c":0.5580294144752966,"mean_z_A":-0.04852871197953651,"bind_frac":{"R":0.33605720122574056,"Gc":0.19101123595505617,"A":0.4729315628192033},"n_leg_dropped":{"R":0,"Gc":49,"A":0},"mean_content_share":0.2823482461929356,"mean_R":0.019467029045235854,"mean_A":2.0211091034349464,"mean_mc":-0.7000431119263412},"king":{"mean":-0.5553405701567069,"mean_valid":-0.5275333207703775,"sd_valid":1.1931729223857535,"n_turns":995,"n_valid":979,"n_forfeits":5,"n_unscorable":11,"mean_z_R":0.23370738103032487,"mean_typ_c":0.6402833901139103,"mean_z_A":-0.01807951853166982,"bind_frac":{"R":0.3472931562819203,"Gc":0.17160367722165476,"A":0.4811031664964249},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.28039934357889884,"mean_R":0.020232077205915217,"mean_A":2.0840219935102438,"mean_mc":-0.6710281229509788}},"rejection_reason":null,"reign_number":null,"score":0.0003458855771159277,"score_king":0.0011470717911293057,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9162405,"blocks_since_crown":8394,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1587.9409959072307,"mean_len_y":801.3628922237381,"n_samples":3000,"think_close_rate":0.9546666666666667,"n_text_fallback":40,"by_dialect":{"text":{"n_turns":388,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":329,"zero_ref_turns":0,"mean_refs":2.9209726443768997,"ref_pair_agreement":0.15053763440860216,"ref_pair_n":310},"bash":{"n_turns":195,"zero_ref_turns":2,"mean_refs":2.923076923076923,"ref_pair_agreement":0.18324607329842932,"ref_pair_n":191},"boxed":{"n_turns":63,"zero_ref_turns":3,"mean_refs":2.634920634920635,"ref_pair_agreement":0.48484848484848486,"ref_pair_n":55},"terminus_json":{"n_turns":25,"zero_ref_turns":0,"mean_refs":2.84,"ref_pair_agreement":0.4666666666666666,"ref_pair_n":25}},"ref_pair_agreement":0.20654044750430292,"ref_pair_n":581},"duel_seconds":2242.228667927906,"challenger":{"reason":0.0003458855771159277,"n_turns":995,"n_pairs":2917,"n_forfeits":5,"forfeit_rate":0.005025125628140704,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.0464976629017064,"mean_len_z":1035.7956804936578,"median_len_z":728.0,"mean_len_y":469.42920809050395,"mean_b":0.12126662535023656,"b_gate_pass_rate":0.4545766198148783,"mean_r_leg":0.019467029045235854,"mean_g_leg":0.05437905916910168,"g_bind_frac":0.24646464646464647,"a_match":0.16495726495726495,"a_match_n":585,"a_match_centered":-0.04101221640488656,"n_turns_cap_raised":54,"mean_cap_tokens":4157.259296482412,"max_cap_tokens":6067,"len_z_delta":-552.1453154135729,"len_y_delta":-331.9336841332341,"n_samples":998,"think_close_rate":0.9949899799599199,"n_text_fallback":19,"by_dialect":{"bash":{"n_turns":193,"n_valid":193,"parse_rate":1.0,"reason":0.008339543322110421,"mean_b":0.11589224052017744,"b_gate_pass_rate":0.8175438596491228,"median_len_z":601.0,"mean_r_leg":0.019592658033439635,"mean_g_leg":0.04693463766835705,"g_bind_frac":0.29533678756476683,"a_match":0.1390328151986183,"a_match_n":193,"a_match_centered":-0.042757417102966835},"boxed":{"n_turns":60,"n_valid":60,"parse_rate":1.0,"reason":0.008083535241225086,"mean_b":1.0054973889558891,"b_gate_pass_rate":0.6686746987951807,"median_len_z":1877.0,"mean_r_leg":0.10687940668838784,"mean_g_leg":0.020240265410267615,"g_bind_frac":0.5666666666666667,"a_match":0.43678160919540227,"a_match_n":58,"a_match_centered":-0.024242424242424246},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.006612141793674342,"mean_b":0.022228214079688637,"b_gate_pass_rate":0.4647887323943662,"median_len_z":728.0,"mean_r_leg":0.0019994363541294196,"mean_g_leg":0.045151576818839294,"g_bind_frac":0.32,"a_match":0.42666666666666664,"a_match_n":25,"a_match_centered":-0.04},"text":{"n_turns":388,"n_valid":383,"parse_rate":0.9871134020618557,"reason":-0.003444726390665295,"mean_b":0.08183447231430262,"b_gate_pass_rate":0.30548302872062666,"median_len_z":726.0,"mean_r_leg":0.01764669786692168,"mean_g_leg":0.058410329825986464,"g_bind_frac":0.19843342036553524,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":329,"n_valid":329,"parse_rate":1.0,"reason":-0.0007554116777826003,"mean_b":0.026178554208813445,"b_gate_pass_rate":0.3798126951092612,"median_len_z":674.0,"mean_r_leg":0.006898298362134149,"mean_g_leg":0.06098030954096625,"g_bind_frac":0.20972644376899696,"a_match":0.10895361380798273,"a_match_n":309,"a_match_centered":-0.04304635761589404}}},"king":{"reason":0.0011470717911293057,"n_turns":995,"n_pairs":2918,"n_forfeits":5,"forfeit_rate":0.005025125628140704,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-10.264824740780062,"mean_len_z":1098.9763536668952,"median_len_z":699.0,"mean_len_y":435.77861549006167,"mean_b":0.12040417938323919,"b_gate_pass_rate":0.47601096641535295,"mean_r_leg":0.020232077205915217,"mean_g_leg":0.05612052736978094,"g_bind_frac":0.24242424242424243,"a_match":0.15817770232031694,"a_match_n":589,"a_match_centered":-0.04137731481481481,"n_turns_cap_raised":54,"mean_cap_tokens":4157.259296482412,"max_cap_tokens":6067,"len_z_delta":-488.9646422403355,"len_y_delta":-365.5842767336764,"n_samples":995,"think_close_rate":0.9949748743718593,"n_text_fallback":11,"by_dialect":{"bash":{"n_turns":193,"n_valid":193,"parse_rate":1.0,"reason":0.009040918128061255,"mean_b":0.11362127687723679,"b_gate_pass_rate":0.8631578947368421,"median_len_z":507.0,"mean_r_leg":0.02453769611963476,"mean_g_leg":0.04808428531242521,"g_bind_frac":0.32124352331606215,"a_match":0.13471502590673576,"a_match_n":193,"a_match_centered":-0.04712041884816754},"boxed":{"n_turns":60,"n_valid":57,"parse_rate":0.95,"reason":0.0018417632945712517,"mean_b":1.026290830314125,"b_gate_pass_rate":0.6835443037974683,"median_len_z":2358.0,"mean_r_leg":0.09477328421043059,"mean_g_leg":0.019081906215057665,"g_bind_frac":0.6666666666666666,"a_match":0.40606060606060607,"a_match_n":55,"a_match_centered":-0.025641025641025644},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.0019637648328358266,"mean_b":0.021149851471368466,"b_gate_pass_rate":0.30985915492957744,"median_len_z":615.0,"mean_r_leg":0.0015597013725769688,"mean_g_leg":0.04835599938849981,"g_bind_frac":0.24,"a_match":0.44,"a_match_n":25,"a_match_centered":-0.02666666666666667},"text":{"n_turns":388,"n_valid":386,"parse_rate":0.9948453608247423,"reason":-0.0032869952274974536,"mean_b":0.08204825448772261,"b_gate_pass_rate":0.3160621761658031,"median_len_z":827.5,"mean_r_leg":0.019180413824036478,"mean_g_leg":0.057579015137773505,"g_bind_frac":0.17616580310880828,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":329,"n_valid":329,"parse_rate":1.0,"reason":0.0018552635406488434,"mean_b":0.029040372819339542,"b_gate_pass_rate":0.4172736732570239,"median_len_z":562.0,"mean_r_leg":0.007444594566503058,"mean_g_leg":0.06613065820253407,"g_bind_frac":0.2006079027355623,"a_match":0.10706751054852322,"a_match_n":316,"a_match_centered":-0.04166666666666667}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-27T13:21:03.378619+00:00","challenge_id":"chal-00711","repo":"r2://affine-private-models/models/registrations/f8ea3bfb9aad257452224f2e8c0237a6769c281822a20fef3a1b937acacdda5d/","hotkey":"5Ff18XjySzdiv7zPNUCyGRA8wAFGSGjST9qHQhyUnKJqcg3t","uid":79,"duration_s":2623.3,"revision":"55fecf5360a7c953ec80e119d96c217995dd36c0a1e030f635f9cbdae6a1e53d","accepted":false,"error_code":null,"error_detail":"","z":-0.033596345400921754,"margin":-0.00113721266216699,"se":0.033849296659981036,"n_paired_turns":978,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2877780391593119998,"n":1000,"digest":"c4884b58d531b9103bb2d9b88b08415886bae1ae74312780b31f3663cd300689","n_paired_turns":978,"n_forfeit_turns":5,"margin":-0.00113721266216699,"se":0.033849296659981036,"z":-0.033596345400921754,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_code_block_only":{"ok":true,"reasons":[]},"assistant_code_only_he103":{"ok":true,"reasons":[]},"assistant_code_only_he134":{"ok":true,"reasons":[]},"assistant_code_only_he69":{"ok":true,"reasons":[]},"assistant_code_only_he70":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_block_only":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"shadow":{"ids":["assistant_code_block_only","assistant_code_only_he103","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he70","ide_code_block_only"],"n":24,"n_ok":24,"pass_rate":1.0,"think_close_rate":1.0,"by_reason":{}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024,"shadow_ids":["ide_code_block_only","assistant_code_block_only","assistant_code_only_he70","assistant_code_only_he134","assistant_code_only_he69","assistant_code_only_he103"],"shadow_n_samples":4}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.00113721266216699,"se":0.033849296659981036,"z":-0.033596345400921754,"sd_diff":1.0585687681578104,"n_paired_turns":978,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false},"sigma_by_dialect":{"bash":{"R":0.01860271238352678,"A":5.8632061267742435,"Mc":0.1598998629055916},"tool_call":{"R":0.007714159391151412,"A":5.720538631736128,"Mc":0.18232261909204373},"text":{"R":0.05244189376684894,"A":35.6123460388527,"Mc":0.1393338151315764},"terminus_json":{"R":0.00109369914175936,"A":8.704457814942531,"Mc":0.14062706900292068},"boxed":{"R":0.08809316347140206,"A":5.721741977683632,"Mc":0.14216855084003868}},"challenger":{"mean":-0.7339063355535879,"mean_valid":-0.7123018487250897,"sd_valid":1.508889047058251,"n_turns":989,"n_valid":975,"n_forfeits":4,"n_unscorable":10,"mean_z_R":0.2915693800136134,"mean_typ_c":0.5034879382554555,"mean_z_A":-0.09503646933249421,"bind_frac":{"R":0.3343589743589744,"Gc":0.18666666666666668,"A":0.47897435897435897},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.28377730181216565,"mean_R":0.017701654784325387,"mean_A":1.5932838655028305,"mean_mc":-0.671408608396958},"king":{"mean":-0.7273845690422936,"mean_valid":-0.7111611369470391,"sd_valid":1.5224630339847818,"n_turns":989,"n_valid":975,"n_forfeits":3,"n_unscorable":11,"mean_z_R":0.2363589996540323,"mean_typ_c":0.531457560472443,"mean_z_A":-0.10518797875946857,"bind_frac":{"R":0.3230769230769231,"Gc":0.18871794871794872,"A":0.4882051282051282},"n_leg_dropped":{"R":0,"Gc":52,"A":0},"mean_content_share":0.2855616514092449,"mean_R":0.01663963884794702,"mean_A":1.5024864753060516,"mean_mc":-0.6696819777502571}},"rejection_reason":null,"reign_number":null,"score":0.001314144131446293,"score_king":0.001404679461196086,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"seq_enabled":false,"seq_look_every":100,"seq_k":2.6,"seq_consecutive":2,"seq_shadow_full_first_n":5,"min_context_tokens":0,"miner_max_model_len":131072,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9159174,"blocks_since_crown":5163,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.1,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2,"miner_empty_rule":"floor","empty_gate_ratio":0.0,"r_cap_teacher":false}},"teacher":{"mean_len_z":1532.8390410958905,"mean_len_y":805.4595890410959,"n_samples":3000,"think_close_rate":0.954,"n_text_fallback":33,"by_dialect":{"tool_call":{"n_turns":321,"zero_ref_turns":3,"mean_refs":2.9158878504672896,"ref_pair_agreement":0.17660044150110377,"ref_pair_n":302},"text":{"n_turns":393,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":207,"zero_ref_turns":1,"mean_refs":2.9613526570048307,"ref_pair_agreement":0.19093851132686085,"ref_pair_n":206},"boxed":{"n_turns":46,"zero_ref_turns":6,"mean_refs":2.3043478260869565,"ref_pair_agreement":0.5523809523809523,"ref_pair_n":35},"terminus_json":{"n_turns":33,"zero_ref_turns":1,"mean_refs":2.606060606060606,"ref_pair_agreement":0.3333333333333333,"ref_pair_n":29}},"ref_pair_agreement":0.21270396270396272,"ref_pair_n":572},"duel_seconds":2108.4161499100737,"challenger":{"reason":0.001314144131446293,"n_turns":989,"n_pairs":2910,"n_forfeits":4,"forfeit_rate":0.004044489383215369,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":2.939331090274258,"mean_len_z":1063.9374570446735,"median_len_z":662.0,"mean_len_y":417.90137457044676,"mean_b":0.1035023260910895,"b_gate_pass_rate":0.5106529209621993,"mean_r_leg":0.017701654784325387,"mean_g_leg":0.05724843502012673,"g_bind_frac":0.22944162436548224,"a_match":0.15203671830177853,"a_match_n":581,"a_match_centered":-0.061511423550087874,"n_turns_cap_raised":59,"mean_cap_tokens":4153.669362992922,"max_cap_tokens":5948,"len_z_delta":-468.901584051217,"len_y_delta":-387.55821447064915,"n_samples":992,"think_close_rate":0.9969758064516129,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":206,"n_valid":206,"parse_rate":1.0,"reason":0.0065116716083526305,"mean_b":0.10768736342182915,"b_gate_pass_rate":0.8417618270799347,"median_len_z":475.0,"mean_r_leg":0.01894069672243609,"mean_g_leg":0.05077767498563453,"g_bind_frac":0.30097087378640774,"a_match":0.13106796116504854,"a_match_n":206,"a_match_centered":-0.0598705501618123},"boxed":{"n_turns":40,"n_valid":39,"parse_rate":0.975,"reason":0.004607268130205956,"mean_b":0.9753139882569841,"b_gate_pass_rate":0.7047619047619048,"median_len_z":1993.0,"mean_r_leg":0.08413445663207861,"mean_g_leg":0.020212412258186842,"g_bind_frac":0.5384615384615384,"a_match":0.3935185185185185,"a_match_n":36,"a_match_centered":-0.20098039215686272},"terminus_json":{"n_turns":32,"n_valid":32,"parse_rate":1.0,"reason":-0.0072220691725705145,"mean_b":0.02215434705647821,"b_gate_pass_rate":0.37209302325581395,"median_len_z":681.0,"mean_r_leg":0.000863580531255185,"mean_g_leg":0.029723437134249027,"g_bind_frac":0.25,"a_match":0.3385416666666667,"a_match_n":32,"a_match_centered":0.04022988505747126},"text":{"n_turns":393,"n_valid":390,"parse_rate":0.9923664122137404,"reason":-0.0013411090292060849,"mean_b":0.08955574139632594,"b_gate_pass_rate":0.3923076923076923,"median_len_z":766.5,"mean_r_leg":0.020377574960044133,"mean_g_leg":0.053674822527443586,"g_bind_frac":0.21025641025641026,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.0016734450675212308,"mean_b":0.027869610149516433,"b_gate_pass_rate":0.4326923076923077,"median_len_z":516.0,"mean_r_leg":0.007164194395189393,"mean_g_leg":0.07313488237646497,"g_bind_frac":0.16666666666666666,"a_match":0.11834961997828448,"a_match_n":307,"a_match_centered":-0.056666666666666664}}},"king":{"reason":0.001404679461196086,"n_turns":989,"n_pairs":2911,"n_forfeits":3,"forfeit_rate":0.003033367037411527,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":2.2730614176259936,"mean_len_z":1080.8107179663346,"median_len_z":633.0,"mean_len_y":423.9835108210237,"mean_b":0.10651832065698252,"b_gate_pass_rate":0.49501889385091036,"mean_r_leg":0.01663963884794702,"mean_g_leg":0.05696900188865412,"g_bind_frac":0.23225152129817445,"a_match":0.15060240963855423,"a_match_n":581,"a_match_centered":-0.06345029239766081,"n_turns_cap_raised":59,"mean_cap_tokens":4153.669362992922,"max_cap_tokens":5948,"len_z_delta":-452.02832312955593,"len_y_delta":-381.4760782200722,"n_samples":989,"think_close_rate":0.9969666329625885,"n_text_fallback":12,"by_dialect":{"bash":{"n_turns":206,"n_valid":206,"parse_rate":1.0,"reason":0.00526565152068669,"mean_b":0.11057288815353078,"b_gate_pass_rate":0.8417618270799347,"median_len_z":502.0,"mean_r_leg":0.015864921783641787,"mean_g_leg":0.04915273286479663,"g_bind_frac":0.2912621359223301,"a_match":0.1407766990291262,"a_match_n":206,"a_match_centered":-0.05016181229773463},"boxed":{"n_turns":40,"n_valid":40,"parse_rate":1.0,"reason":0.004034906709166717,"mean_b":1.0169819615381268,"b_gate_pass_rate":0.7358490566037735,"median_len_z":2207.5,"mean_r_leg":0.07460788396597651,"mean_g_leg":0.014336772211789436,"g_bind_frac":0.625,"a_match":0.3991228070175438,"a_match_n":38,"a_match_centered":-0.1761904761904762},"terminus_json":{"n_turns":32,"n_valid":32,"parse_rate":1.0,"reason":-0.005701658600272311,"mean_b":0.020418940019167622,"b_gate_pass_rate":0.38372093023255816,"median_len_z":634.0,"mean_r_leg":0.0006754559449048384,"mean_g_leg":0.03407647234005849,"g_bind_frac":0.1875,"a_match":0.3020833333333333,"a_match_n":32,"a_match_centered":0.0},"text":{"n_turns":393,"n_valid":390,"parse_rate":0.9923664122137404,"reason":-0.0010855670110831018,"mean_b":0.09179120981878118,"b_gate_pass_rate":0.36153846153846153,"median_len_z":782.0,"mean_r_leg":0.020256142749747866,"mean_g_leg":0.054156975264870275,"g_bind_frac":0.23333333333333334,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.0023653723775445765,"mean_b":0.027074592672754205,"b_gate_pass_rate":0.41773504273504275,"median_len_z":516.0,"mean_r_leg":0.007021020111219722,"mean_g_leg":0.0731472784132453,"g_bind_frac":0.14779874213836477,"a_match":0.11038251366120218,"a_match_n":305,"a_match_centered":-0.06555555555555556}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-27T05:29:20.422449+00:00","challenge_id":"chal-00710","repo":"r2://affine-private-models/models/registrations/494c7d2c144f6f77576c93c93281037662b90b2dcaf2e9faee947989928eab41/","hotkey":"5DAqeJRe6WJn5ZbNvhkNeKuPFzyaBeei3wrs7kftAJaFCaTk","uid":72,"duration_s":2637.4,"revision":"39c3812a0b364f83aa40a81c2989f0ecd32fb7c71383967ba6e8418d5911fd1c","accepted":false,"error_code":null,"error_detail":"","z":0.5367085631491808,"margin":0.015615835439516047,"se":0.029095558580039923,"n_paired_turns":981,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":13217214903359517340,"n":1000,"digest":"90a7c89b9595039555d3a9257913047a55e1c3c2af1a2d7a7f00cc2822bfa019","n_paired_turns":981,"n_forfeit_turns":4,"margin":0.015615835439516047,"se":0.029095558580039923,"z":0.5367085631491808,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.015615835439516047,"se":0.029095558580039923,"z":0.5367085631491808,"sd_diff":0.911299648870737,"n_paired_turns":981,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.00845747185972415,"A":6.124797527136497,"Mc":0.17232016242452192},"text":{"R":0.08298765150247675,"A":19.159775380849975,"Mc":0.13614048081712277},"bash":{"R":0.025096068452169506,"A":7.8096084396050545,"Mc":0.15244896344329295},"boxed":{"R":0.0519536148681812,"A":4.87752066603898,"Mc":0.12163015178629652},"terminus_json":{"R":0.0015144900851803908,"A":9.157993316697452,"Mc":0.1606903737787417}},"challenger":{"mean":-0.6941488131882404,"mean_valid":-0.6724257786465342,"sd_valid":1.371829387483125,"n_turns":992,"n_valid":977,"n_forfeits":4,"n_unscorable":11,"mean_z_R":0.07116905035721707,"mean_typ_c":0.6027613004995165,"mean_z_A":-0.08037169229630005,"bind_frac":{"R":0.36745138178096215,"Gc":0.1617195496417605,"A":0.47082906857727735},"n_leg_dropped":{"R":0,"Gc":45,"A":0},"mean_content_share":0.28645257655483597,"mean_R":0.014562075245661643,"mean_A":2.634820231227365,"mean_mc":-0.6692177700760318},"king":{"mean":-0.7097646486277565,"mean_valid":-0.6935369328260012,"sd_valid":1.4024096064411247,"n_turns":992,"n_valid":978,"n_forfeits":3,"n_unscorable":11,"mean_z_R":0.09103813069902579,"mean_typ_c":0.51710138242038,"mean_z_A":-0.09261178815504265,"bind_frac":{"R":0.3333333333333333,"Gc":0.19325153374233128,"A":0.4734151329243354},"n_leg_dropped":{"R":0,"Gc":48,"A":0},"mean_content_share":0.28114716575728077,"mean_R":0.014296186342683587,"mean_A":2.2342525696420066,"mean_mc":-0.6714016307429648}},"rejection_reason":null,"reign_number":null,"score":0.0006649495023414298,"score_king":0.00037969720805148226,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9156815,"blocks_since_crown":2804,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1547.9501876492664,"mean_len_y":816.8399863527807,"n_samples":3000,"think_close_rate":0.953,"n_text_fallback":26,"by_dialect":{"bash":{"n_turns":231,"zero_ref_turns":1,"mean_refs":2.948051948051948,"ref_pair_agreement":0.21542940320232898,"ref_pair_n":229},"tool_call":{"n_turns":324,"zero_ref_turns":1,"mean_refs":2.925925925925926,"ref_pair_agreement":0.20388349514563106,"ref_pair_n":309},"text":{"n_turns":376,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":54,"zero_ref_turns":6,"mean_refs":2.4444444444444446,"ref_pair_agreement":0.6166666666666667,"ref_pair_n":40},"terminus_json":{"n_turns":15,"zero_ref_turns":0,"mean_refs":2.8,"ref_pair_agreement":0.3095238095238095,"ref_pair_n":14}},"ref_pair_agreement":0.23873873873873874,"ref_pair_n":592},"duel_seconds":2185.518449207768,"challenger":{"reason":0.0006649495023414298,"n_turns":992,"n_pairs":2921,"n_forfeits":4,"forfeit_rate":0.004032258064516129,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-30.83353531559767,"mean_len_z":1026.4186922286888,"median_len_z":665.0,"mean_len_y":403.87024991441285,"mean_b":0.10377267283495582,"b_gate_pass_rate":0.5255049640534064,"mean_r_leg":0.014562075245661643,"mean_g_leg":0.0542300957754055,"g_bind_frac":0.23684210526315788,"a_match":0.18429752066115704,"a_match_n":605,"a_match_centered":-0.05555555555555556,"n_turns_cap_raised":54,"mean_cap_tokens":4150.720766129032,"max_cap_tokens":6017,"len_z_delta":-521.5314954205776,"len_y_delta":-412.9697364383678,"n_samples":995,"think_close_rate":0.9959798994974874,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":230,"n_valid":230,"parse_rate":1.0,"reason":0.006812410457513686,"mean_b":0.1206792263732464,"b_gate_pass_rate":0.8678414096916299,"median_len_z":471.0,"mean_r_leg":0.01768684605003713,"mean_g_leg":0.042777383764034366,"g_bind_frac":0.3173913043478261,"a_match":0.16159420289855073,"a_match_n":230,"a_match_centered":-0.05312954876273653},"boxed":{"n_turns":48,"n_valid":47,"parse_rate":0.9791666666666666,"reason":0.005121759318501401,"mean_b":0.853869174148792,"b_gate_pass_rate":0.7251908396946565,"median_len_z":2089.0,"mean_r_leg":0.04983940162642239,"mean_g_leg":0.019537602519331704,"g_bind_frac":0.5531914893617021,"a_match":0.5813953488372093,"a_match_n":43,"a_match_centered":-0.04166666666666667},"terminus_json":{"n_turns":15,"n_valid":15,"parse_rate":1.0,"reason":-0.0021846521393137017,"mean_b":0.026030348379731023,"b_gate_pass_rate":0.5,"median_len_z":624.0,"mean_r_leg":0.0010710673251283353,"mean_g_leg":0.02458231226771867,"g_bind_frac":0.26666666666666666,"a_match":0.3111111111111111,"a_match_n":15,"a_match_centered":-0.04761904761904762},"text":{"n_turns":376,"n_valid":373,"parse_rate":0.9920212765957447,"reason":-0.003221701935955695,"mean_b":0.07598116203860257,"b_gate_pass_rate":0.34584450402144773,"median_len_z":845.0,"mean_r_leg":0.01638329716257805,"mean_g_leg":0.05353535341191501,"g_bind_frac":0.19302949061662197,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":323,"n_valid":323,"parse_rate":1.0,"reason":0.00028192186939792575,"mean_b":0.02422401627013547,"b_gate_pass_rate":0.4651898734177215,"median_len_z":519.0,"mean_r_leg":0.005727145582801156,"mean_g_leg":0.06961253106905284,"g_bind_frac":0.1826625386996904,"a_match":0.1409043112513144,"a_match_n":317,"a_match_centered":-0.05952380952380952}}},"king":{"reason":0.00037969720805148226,"n_turns":992,"n_pairs":2924,"n_forfeits":3,"forfeit_rate":0.0030241935483870967,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-42.77004350816416,"mean_len_z":1083.9596443228454,"median_len_z":687.5,"mean_len_y":402.08207934336525,"mean_b":0.10479931326333959,"b_gate_pass_rate":0.5106019151846786,"mean_r_leg":0.014296186342683587,"mean_g_leg":0.052727600360332055,"g_bind_frac":0.24772497472194135,"a_match":0.17440574903261472,"a_match_n":603,"a_match_centered":-0.06660997732426303,"n_turns_cap_raised":54,"mean_cap_tokens":4150.720766129032,"max_cap_tokens":6017,"len_z_delta":-463.99054332642095,"len_y_delta":-414.7579070094154,"n_samples":992,"think_close_rate":0.9979838709677419,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":230,"n_valid":230,"parse_rate":1.0,"reason":0.006767608581767863,"mean_b":0.1201068422231618,"b_gate_pass_rate":0.8604992657856094,"median_len_z":496.0,"mean_r_leg":0.01810210195848788,"mean_g_leg":0.0410613678739903,"g_bind_frac":0.34782608695652173,"a_match":0.15434782608695652,"a_match_n":230,"a_match_centered":-0.0604075691411936},"boxed":{"n_turns":48,"n_valid":47,"parse_rate":0.9791666666666666,"reason":0.004615587147009186,"mean_b":0.8956482402432733,"b_gate_pass_rate":0.7633587786259542,"median_len_z":2097.0,"mean_r_leg":0.04394596130935322,"mean_g_leg":0.02072762016746976,"g_bind_frac":0.5531914893617021,"a_match":0.5348837209302325,"a_match_n":43,"a_match_centered":-0.09401709401709402},"terminus_json":{"n_turns":15,"n_valid":15,"parse_rate":1.0,"reason":-0.002880669416095225,"mean_b":0.027093822677214524,"b_gate_pass_rate":0.5,"median_len_z":622.0,"mean_r_leg":0.0005221760922122865,"mean_g_leg":0.02531176187176637,"g_bind_frac":0.3333333333333333,"a_match":0.3111111111111111,"a_match_n":15,"a_match_centered":-0.04761904761904762},"text":{"n_turns":376,"n_valid":374,"parse_rate":0.9946808510638298,"reason":-0.00459561545911637,"mean_b":0.07065765098848938,"b_gate_pass_rate":0.3315508021390374,"median_len_z":820.5,"mean_r_leg":0.015498383108166564,"mean_g_leg":0.05189913155084556,"g_bind_frac":0.20053475935828877,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":323,"n_valid":323,"parse_rate":1.0,"reason":0.0011446530259851524,"mean_b":0.028369924044973502,"b_gate_pass_rate":0.43670886075949367,"median_len_z":587.0,"mean_r_leg":0.006519370703048835,"mean_g_leg":0.06792362962658459,"g_bind_frac":0.1826625386996904,"a_match":0.13333333333333333,"a_match_n":315,"a_match_centered":-0.06862745098039216}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-27T03:32:52.066805+00:00","challenge_id":"chal-00709","repo":"r2://affine-private-models/models/registrations/8e4e9180f4c5e13ad49f63cbbb6dd936800b5da76b69d63dcfe4724e25b44ce0/","hotkey":"5H9MJsgD1tBL4H6vMyGXhyZ9mefcFKHfDMAVhfnJqQrwfyej","uid":65,"duration_s":2767.7,"revision":"6dc57de4457e649b0bc4e1f92ed5a9ba96dc9ff77206e2a93113edd16842a333","accepted":false,"error_code":null,"error_detail":"","z":-0.6668689455514788,"margin":-0.025055115611860832,"se":0.03757127360480262,"n_paired_turns":985,"n_forfeit_turns":11,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":1925644960048717301,"n":1000,"digest":"a3e5311a08fc715240ae51f606b668ff70ae2eaef1b2356100fabcf00ebd6cfb","n_paired_turns":985,"n_forfeit_turns":11,"margin":-0.025055115611860832,"se":0.03757127360480262,"z":-0.6668689455514788,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.025055115611860832,"se":0.03757127360480262,"z":-0.6668689455514788,"sd_diff":1.1791635133782905,"n_paired_turns":985,"n_forfeit_turns":11,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.029394865835127543,"A":6.0591806808879936,"Mc":0.163171097071103},"text":{"R":0.07456155441434205,"A":30.297376844032286,"Mc":0.16360869876089143},"tool_call":{"R":0.007449706456696414,"A":6.226879301455096,"Mc":0.17997875438095115},"terminus_json":{"R":0.0020231835736764753,"A":9.055011246087258,"Mc":0.1269890457033201},"boxed":{"R":0.12779235439188563,"A":5.991461782950868,"Mc":0.09995270667874702}},"challenger":{"mean":-0.7129856667995614,"mean_valid":-0.6479813922110315,"sd_valid":1.3737817344543668,"n_turns":995,"n_valid":976,"n_forfeits":12,"n_unscorable":7,"mean_z_R":0.18560623297867815,"mean_typ_c":0.6106712115066012,"mean_z_A":-0.07800931209250422,"bind_frac":{"R":0.3668032786885246,"Gc":0.1557377049180328,"A":0.4774590163934426},"n_leg_dropped":{"R":0,"Gc":47,"A":0},"mean_content_share":0.2833919396590202,"mean_R":0.016613862595228988,"mean_A":1.6029262276510545,"mean_mc":-0.6566310188615757},"king":{"mean":-0.671827969462217,"mean_valid":-0.633691768834646,"sd_valid":1.4146177937460505,"n_turns":995,"n_valid":978,"n_forfeits":7,"n_unscorable":10,"mean_z_R":0.2017513497101132,"mean_typ_c":0.6141307308714384,"mean_z_A":-0.07181249911852675,"bind_frac":{"R":0.35173824130879344,"Gc":0.16257668711656442,"A":0.48568507157464214},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.28401416668954993,"mean_R":0.019423490855012868,"mean_A":1.6444205733381874,"mean_mc":-0.6602935294569381}},"rejection_reason":null,"reign_number":null,"score":0.0019945059194933566,"score_king":0.0016282018543154863,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9156221,"blocks_since_crown":2210,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1458.0404899625723,"mean_len_y":852.2902347737325,"n_samples":3000,"think_close_rate":0.9486666666666667,"n_text_fallback":36,"by_dialect":{"tool_call":{"n_turns":324,"zero_ref_turns":0,"mean_refs":2.941358024691358,"ref_pair_agreement":0.2121212121212121,"ref_pair_n":308},"boxed":{"n_turns":45,"zero_ref_turns":1,"mean_refs":2.6666666666666665,"ref_pair_agreement":0.5462962962962963,"ref_pair_n":36},"text":{"n_turns":396,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":208,"zero_ref_turns":2,"mean_refs":2.923076923076923,"ref_pair_agreement":0.1477832512315271,"ref_pair_n":203},"terminus_json":{"n_turns":27,"zero_ref_turns":2,"mean_refs":2.5925925925925926,"ref_pair_agreement":0.4166666666666667,"ref_pair_n":24}},"ref_pair_agreement":0.21891418563922943,"ref_pair_n":571},"duel_seconds":2301.3101529441774,"challenger":{"reason":0.0019945059194933566,"n_turns":995,"n_pairs":2911,"n_forfeits":12,"forfeit_rate":0.012060301507537688,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":43.450295720119286,"mean_len_z":1109.6080384747509,"median_len_z":660.0,"mean_len_y":421.0882858124356,"mean_b":0.09339217469649924,"b_gate_pass_rate":0.48436963242871867,"mean_r_leg":0.016613862595228988,"mean_g_leg":0.060053664240113706,"g_bind_frac":0.21871820956256358,"a_match":0.18341998844598498,"a_match_n":577,"a_match_centered":-0.03463587921847247,"n_turns_cap_raised":58,"mean_cap_tokens":4159.318592964824,"max_cap_tokens":6056,"len_z_delta":-348.4324514878215,"len_y_delta":-431.201948961297,"n_samples":998,"think_close_rate":0.9889779559118237,"n_text_fallback":12,"by_dialect":{"bash":{"n_turns":206,"n_valid":206,"parse_rate":1.0,"reason":0.010828322163600936,"mean_b":0.10663557699499104,"b_gate_pass_rate":0.8075657894736842,"median_len_z":437.0,"mean_r_leg":0.023500934641173577,"mean_g_leg":0.051683996245171095,"g_bind_frac":0.27184466019417475,"a_match":0.12944983818770225,"a_match_n":206,"a_match_centered":-0.02134646962233169},"boxed":{"n_turns":44,"n_valid":40,"parse_rate":0.9090909090909091,"reason":-0.002826123522912563,"mean_b":0.9028393391171835,"b_gate_pass_rate":0.646551724137931,"median_len_z":2120.0,"mean_r_leg":0.09241282211798858,"mean_g_leg":0.021465801439929006,"g_bind_frac":0.6,"a_match":0.4809523809523809,"a_match_n":35,"a_match_centered":-0.045454545454545456},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.004516559828648276,"mean_b":0.02161099476058166,"b_gate_pass_rate":0.44285714285714284,"median_len_z":537.0,"mean_r_leg":0.0008360120130444245,"mean_g_leg":0.03576421941522459,"g_bind_frac":0.2,"a_match":0.3066666666666667,"a_match_n":25,"a_match_centered":-0.09722222222222222},"text":{"n_turns":396,"n_valid":389,"parse_rate":0.9823232323232324,"reason":-0.002281761631815577,"mean_b":0.06390028163683659,"b_gate_pass_rate":0.35218508997429304,"median_len_z":799.0,"mean_r_leg":0.014471121630017883,"mean_g_leg":0.061118332895719905,"g_bind_frac":0.19794344473007713,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":324,"n_valid":323,"parse_rate":0.9969135802469136,"reason":0.002761543398510571,"mean_b":0.027596240092139408,"b_gate_pass_rate":0.4231578947368421,"median_len_z":519.0,"mean_r_leg":0.006636392866581204,"mean_g_leg":0.07076804855143563,"g_bind_frac":0.16408668730650156,"a_match":0.1757770632368703,"a_match_n":311,"a_match_centered":-0.0374037403740374}}},"king":{"reason":0.0016282018543154863,"n_turns":995,"n_pairs":2920,"n_forfeits":7,"forfeit_rate":0.007035175879396985,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":37.174916417708666,"mean_len_z":1057.498287671233,"median_len_z":665.0,"mean_len_y":422.861301369863,"mean_b":0.10053897300656824,"b_gate_pass_rate":0.49006849315068496,"mean_r_leg":0.019423490855012868,"mean_g_leg":0.05853793778507061,"g_bind_frac":0.23481781376518218,"a_match":0.16121629374641425,"a_match_n":581,"a_match_centered":-0.05604719764011799,"n_turns_cap_raised":58,"mean_cap_tokens":4159.318592964824,"max_cap_tokens":6056,"len_z_delta":-400.54220229133944,"len_y_delta":-429.42893340386956,"n_samples":995,"think_close_rate":0.992964824120603,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":206,"n_valid":206,"parse_rate":1.0,"reason":0.010653278112118227,"mean_b":0.10568348535751013,"b_gate_pass_rate":0.7976973684210527,"median_len_z":474.0,"mean_r_leg":0.023312196493916935,"mean_g_leg":0.049833060733328195,"g_bind_frac":0.2766990291262136,"a_match":0.12459546925566342,"a_match_n":206,"a_match_centered":-0.026272577996715927},"boxed":{"n_turns":44,"n_valid":43,"parse_rate":0.9772727272727273,"reason":0.0048546395621897,"mean_b":0.901295198319542,"b_gate_pass_rate":0.6218487394957983,"median_len_z":2331.0,"mean_r_leg":0.11038586081696655,"mean_g_leg":0.018059103677303887,"g_bind_frac":0.6744186046511628,"a_match":0.3508771929824562,"a_match_n":38,"a_match_centered":-0.14705882352941177},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.008985322327428255,"mean_b":0.020844995442618617,"b_gate_pass_rate":0.35714285714285715,"median_len_z":586.5,"mean_r_leg":0.0008434036756409844,"mean_g_leg":0.030216876792834767,"g_bind_frac":0.32,"a_match":0.3466666666666666,"a_match_n":25,"a_match_centered":-0.05555555555555556},"text":{"n_turns":396,"n_valid":391,"parse_rate":0.9873737373737373,"reason":-0.0028075516671016935,"mean_b":0.080852915227482,"b_gate_pass_rate":0.36828644501278773,"median_len_z":799.0,"mean_r_leg":0.019467414715336695,"mean_g_leg":0.05999549758227721,"g_bind_frac":0.20460358056265984,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":324,"n_valid":323,"parse_rate":0.9969135802469136,"reason":0.0016922991715098287,"mean_b":0.02712052025154515,"b_gate_pass_rate":0.4368421052631579,"median_len_z":553.0,"mean_r_leg":0.0062187623104909915,"mean_g_leg":0.06990609624758153,"g_bind_frac":0.17956656346749225,"a_match":0.14743589743589744,"a_match_n":312,"a_match_centered":-0.06578947368421052}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-27T02:32:03.715893+00:00","challenge_id":"chal-00708","repo":"r2://affine-private-models/models/registrations/332375cd81ac01b6a4d96c2045928b43f484eff987ab7ea5c96425e5907b0a55/","hotkey":"5Ecf5BwUXk5narqU9PTqigbnmRCbnhwyT9J2Vf6tEKNmHh7B","uid":206,"duration_s":2558.3,"revision":"87e3e835e4b3e3ae81efa734a9aac11da180f85dcb2269d1f8d834759dadcfba","accepted":false,"error_code":null,"error_detail":"","z":0.4258605296949735,"margin":0.01648169455082163,"se":0.03870209470369746,"n_paired_turns":988,"n_forfeit_turns":15,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":13884534534506476477,"n":1000,"digest":"914c4051ef91fc13f24e65de8eeb0f8a27f76d2f1cf7518372b8740c6133dd20","n_paired_turns":988,"n_forfeit_turns":15,"margin":0.01648169455082163,"se":0.03870209470369746,"z":0.4258605296949735,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.01648169455082163,"se":0.03870209470369746,"z":0.4258605296949735,"sd_diff":1.2165023258672873,"n_paired_turns":988,"n_forfeit_turns":15,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.008151243888258754,"A":5.916019992023934,"Mc":0.1740341121256078},"bash":{"R":0.0214073020144098,"A":4.980243670402867,"Mc":0.1624298399051611},"text":{"R":0.08987705849669506,"A":28.88665777148501,"Mc":0.1493711390408761},"terminus_json":{"R":0.001122998820877535,"A":6.099213923665325,"Mc":0.12318980205196213},"boxed":{"R":0.09864797215454021,"A":6.003491658264116,"Mc":0.1117619255314595}},"challenger":{"mean":-0.6628684014468859,"mean_valid":-0.6192999802342074,"sd_valid":1.3141997720973226,"n_turns":992,"n_valid":980,"n_forfeits":8,"n_unscorable":4,"mean_z_R":0.13991077159187,"mean_typ_c":0.5920952838293645,"mean_z_A":0.004559694872666018,"bind_frac":{"R":0.3551020408163265,"Gc":0.1663265306122449,"A":0.4785714285714286},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.2822870409707247,"mean_R":0.016362095443459162,"mean_A":2.8095390955572044,"mean_mc":-0.6687816266249503},"king":{"mean":-0.6793500959977075,"mean_valid":-0.6249467227461503,"sd_valid":1.3496192763188855,"n_turns":992,"n_valid":978,"n_forfeits":10,"n_unscorable":4,"mean_z_R":0.2120917287145113,"mean_typ_c":0.5769921380411952,"mean_z_A":0.03395242309786641,"bind_frac":{"R":0.33026584867075665,"Gc":0.18813905930470348,"A":0.4815950920245399},"n_leg_dropped":{"R":0,"Gc":48,"A":0},"mean_content_share":0.28209728899409414,"mean_R":0.01751060067400904,"mean_A":2.7683624696423506,"mean_mc":-0.6631318175270953}},"rejection_reason":null,"reign_number":null,"score":0.0018767728315747419,"score_king":0.0023904579915882316,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9155935,"blocks_since_crown":1924,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1460.9755600814665,"mean_len_y":940.8129667345553,"n_samples":3000,"think_close_rate":0.948,"n_text_fallback":22,"by_dialect":{"text":{"n_turns":405,"zero_ref_turns":0,"mean_refs":2.9975308641975307,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":212,"zero_ref_turns":0,"mean_refs":2.9622641509433962,"ref_pair_agreement":0.1650943396226415,"ref_pair_n":212},"tool_call":{"n_turns":300,"zero_ref_turns":3,"mean_refs":2.933333333333333,"ref_pair_agreement":0.20557491289198607,"ref_pair_n":287},"boxed":{"n_turns":56,"zero_ref_turns":4,"mean_refs":2.6964285714285716,"ref_pair_agreement":0.6339869281045752,"ref_pair_n":51},"terminus_json":{"n_turns":27,"zero_ref_turns":1,"mean_refs":2.7037037037037037,"ref_pair_agreement":0.4166666666666667,"ref_pair_n":24}},"ref_pair_agreement":0.2375145180023229,"ref_pair_n":574},"duel_seconds":2110.4858526149765,"challenger":{"reason":0.0018767728315747419,"n_turns":992,"n_pairs":2923,"n_forfeits":8,"forfeit_rate":0.008064516129032258,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-26.879527385768167,"mean_len_z":1106.043448511803,"median_len_z":680.0,"mean_len_y":397.7030448169689,"mean_b":0.11844833263846984,"b_gate_pass_rate":0.5285665412247691,"mean_r_leg":0.016362095443459162,"mean_g_leg":0.05702999006345797,"g_bind_frac":0.2266260162601626,"a_match":0.17332175925925924,"a_match_n":576,"a_match_centered":-0.063922942206655,"n_turns_cap_raised":52,"mean_cap_tokens":4148.2550403225805,"max_cap_tokens":6048,"len_z_delta":-354.93211156966345,"len_y_delta":-543.1099219175865,"n_samples":995,"think_close_rate":0.9919597989949749,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":212,"n_valid":212,"parse_rate":1.0,"reason":0.009455604343985782,"mean_b":0.12284943200413069,"b_gate_pass_rate":0.8343949044585988,"median_len_z":492.0,"mean_r_leg":0.01944768917248105,"mean_g_leg":0.04899799047413111,"g_bind_frac":0.28773584905660377,"a_match":0.12342767295597484,"a_match_n":212,"a_match_centered":-0.04166666666666667},"boxed":{"n_turns":52,"n_valid":52,"parse_rate":1.0,"reason":0.008630835083574389,"mean_b":0.9935117729436276,"b_gate_pass_rate":0.7549668874172185,"median_len_z":2272.0,"mean_r_leg":0.06931291206215173,"mean_g_leg":0.021023358341809753,"g_bind_frac":0.5769230769230769,"a_match":0.5,"a_match_n":50,"a_match_centered":-0.14666666666666667},"terminus_json":{"n_turns":26,"n_valid":26,"parse_rate":1.0,"reason":-0.008351892577966353,"mean_b":0.025495745780772235,"b_gate_pass_rate":0.5205479452054794,"median_len_z":740.0,"mean_r_leg":0.0014501084236666648,"mean_g_leg":0.03551159028145103,"g_bind_frac":0.34615384615384615,"a_match":0.37179487179487175,"a_match_n":26,"a_match_centered":-0.013888888888888888},"text":{"n_turns":405,"n_valid":398,"parse_rate":0.9827160493827161,"reason":-0.0023635349811984506,"mean_b":0.08077892418971967,"b_gate_pass_rate":0.37720033528918695,"median_len_z":795.0,"mean_r_leg":0.016748879002885898,"mean_g_leg":0.05739841728186271,"g_bind_frac":0.1984924623115578,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":297,"n_valid":296,"parse_rate":0.9966329966329966,"reason":0.001962114404255178,"mean_b":0.023717892128512,"b_gate_pass_rate":0.4772209567198178,"median_len_z":476.0,"mean_r_leg":0.00563974230541224,"mean_g_leg":0.07050287223869478,"g_bind_frac":0.14864864864864866,"a_match":0.13541666666666666,"a_match_n":288,"a_match_centered":-0.07017543859649122}}},"king":{"reason":0.0023904579915882316,"n_turns":992,"n_pairs":2917,"n_forfeits":10,"forfeit_rate":0.010080645161290322,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.436755472575307,"mean_len_z":1092.1439835447377,"median_len_z":648.0,"mean_len_y":407.1782653411039,"mean_b":0.11846729921319821,"b_gate_pass_rate":0.5046280425094275,"mean_r_leg":0.01751060067400904,"mean_g_leg":0.057639502246390036,"g_bind_frac":0.23014256619144602,"a_match":0.17329873125720877,"a_match_n":578,"a_match_centered":-0.06333917104495038,"n_turns_cap_raised":52,"mean_cap_tokens":4148.2550403225805,"max_cap_tokens":6048,"len_z_delta":-368.8315765367288,"len_y_delta":-533.6347013934515,"n_samples":992,"think_close_rate":0.9899193548387096,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":212,"n_valid":212,"parse_rate":1.0,"reason":0.00990857461538929,"mean_b":0.1251542856304572,"b_gate_pass_rate":0.8264331210191083,"median_len_z":515.0,"mean_r_leg":0.020957018386629774,"mean_g_leg":0.0505602443706833,"g_bind_frac":0.2688679245283019,"a_match":0.13757861635220126,"a_match_n":212,"a_match_centered":-0.02751572327044025},"boxed":{"n_turns":52,"n_valid":51,"parse_rate":0.9807692307692307,"reason":0.003756727054838183,"mean_b":0.9188732405267414,"b_gate_pass_rate":0.8053691275167785,"median_len_z":2055.0,"mean_r_leg":0.07986037159762774,"mean_g_leg":0.0195796560792847,"g_bind_frac":0.5686274509803921,"a_match":0.5102040816326531,"a_match_n":49,"a_match_centered":-0.1292517006802721},"terminus_json":{"n_turns":26,"n_valid":26,"parse_rate":1.0,"reason":-0.0065359432043451396,"mean_b":0.02099069977753964,"b_gate_pass_rate":0.3698630136986301,"median_len_z":646.0,"mean_r_leg":0.0014726491072599376,"mean_g_leg":0.03655037751632161,"g_bind_frac":0.2692307692307692,"a_match":0.38461538461538464,"a_match_n":26,"a_match_centered":-2.3129646346357427e-18},"text":{"n_turns":405,"n_valid":396,"parse_rate":0.9777777777777777,"reason":-0.002203673473107976,"mean_b":0.0880594612221954,"b_gate_pass_rate":0.38163437236731257,"median_len_z":835.0,"mean_r_leg":0.016496478199193466,"mean_g_leg":0.0572097291355714,"g_bind_frac":0.23484848484848486,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":297,"n_valid":297,"parse_rate":1.0,"reason":0.0038309393342192406,"mean_b":0.0272740977681605,"b_gate_pass_rate":0.4011363636363636,"median_len_z":450.0,"mean_r_leg":0.007100164204589153,"mean_g_leg":0.07164745584584511,"g_bind_frac":0.13468013468013468,"a_match":0.12371134020618557,"a_match_n":291,"a_match_centered":-0.08391608391608392}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-27T01:48:20.166177+00:00","challenge_id":"chal-00707","repo":"r2://affine-private-models/models/registrations/f62d3039ea055d401896e503c271d85215c35a557094c480835430c4ac88ab06/","hotkey":"5G3BF2Dwu1e8Khp2kpKk1tznFQWx4r59WFLqpCWiNNM954UK","uid":238,"duration_s":2744.3,"revision":"613020a88e632e0d6c02c83e809ddc60a43ff692ff3b79a1efbe6836c8649a60","accepted":false,"error_code":null,"error_detail":"","z":-12.148194930930323,"margin":-0.748263749002988,"se":0.06159464457537191,"n_paired_turns":986,"n_forfeit_turns":42,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":13218437497830685277,"n":1000,"digest":"57eee13d40826d1428581c158b8d44759795cc46711016a7cd4682092bea35f4","n_paired_turns":986,"n_forfeit_turns":42,"margin":-0.748263749002988,"se":0.06159464457537191,"z":-12.148194930930323,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"empty_content":1},"by_prompt":{"assistant_bash":{"ok":false,"reasons":["empty_content"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.748263749002988,"se":0.06159464457537191,"z":-12.148194930930323,"sd_diff":1.9341110715264682,"n_paired_turns":986,"n_forfeit_turns":42,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"text":{"R":0.10739447685968782,"A":26.10571873782229,"Mc":0.1562242318126739},"tool_call":{"R":0.034776908495431524,"A":7.512972077156135,"Mc":0.17440712008203788},"bash":{"R":0.026621209319219002,"A":6.1579032822824225,"Mc":0.17300387260224523},"terminus_json":{"R":0.0035925135745585434,"A":11.043396095989428,"Mc":0.17234657735304645},"boxed":{"R":0.12078431135283862,"A":5.568322520081244,"Mc":0.11663731965869167}},"challenger":{"mean":-1.3914003914430226,"mean_valid":-1.1668288003480851,"sd_valid":1.9293991755863715,"n_turns":994,"n_valid":944,"n_forfeits":46,"n_unscorable":4,"mean_z_R":0.044017012989668494,"mean_typ_c":-0.043688085951352915,"mean_z_A":-0.17663722700455115,"bind_frac":{"R":0.3072033898305085,"Gc":0.2574152542372881,"A":0.4353813559322034},"n_leg_dropped":{"R":0,"Gc":24,"A":0},"mean_content_share":0.3329203443569016,"mean_R":0.013797901414494369,"mean_A":1.207799799318353,"mean_mc":-0.7135868601714201},"king":{"mean":-0.6244404979834141,"mean_valid":-0.6135145640362258,"sd_valid":1.2791804528046933,"n_turns":994,"n_valid":984,"n_forfeits":2,"n_unscorable":8,"mean_z_R":0.10450032509627556,"mean_typ_c":0.6190521359599878,"mean_z_A":-0.07390089761710575,"bind_frac":{"R":0.3546747967479675,"Gc":0.16565040650406504,"A":0.4796747967479675},"n_leg_dropped":{"R":0,"Gc":49,"A":0},"mean_content_share":0.28131958148520503,"mean_R":0.01670545666430934,"mean_A":2.0206023447835983,"mean_mc":-0.6828319124400986}},"rejection_reason":null,"reign_number":null,"score":-0.003081369693874382,"score_king":0.0042837755811207445,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9155701,"blocks_since_crown":1690,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1484.4808149405771,"mean_len_y":768.2230899830221,"n_samples":3000,"think_close_rate":0.9583333333333334,"n_text_fallback":36,"by_dialect":{"tool_call":{"n_turns":345,"zero_ref_turns":1,"mean_refs":2.9507246376811596,"ref_pair_agreement":0.1808080808080808,"ref_pair_n":330},"boxed":{"n_turns":56,"zero_ref_turns":4,"mean_refs":2.5892857142857144,"ref_pair_agreement":0.5629629629629629,"ref_pair_n":45},"bash":{"n_turns":209,"zero_ref_turns":1,"mean_refs":2.9330143540669855,"ref_pair_agreement":0.15934959349593494,"ref_pair_n":205},"text":{"n_turns":367,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":23,"zero_ref_turns":0,"mean_refs":2.9565217391304346,"ref_pair_agreement":0.34782608695652173,"ref_pair_n":23}},"ref_pair_agreement":0.2084024322830293,"ref_pair_n":603},"duel_seconds":2286.87310350826,"challenger":{"reason":-0.003081369693874382,"n_turns":994,"n_pairs":2819,"n_forfeits":46,"forfeit_rate":0.04627766599597585,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":0.46406581124923707,"mean_len_z":1129.9464349059951,"median_len_z":384.0,"mean_len_y":525.0,"mean_b":0.09074998485334321,"b_gate_pass_rate":0.4224902447676481,"mean_r_leg":0.013797901414494369,"mean_g_leg":0.05752313142507658,"g_bind_frac":0.22468354430379747,"a_match":0.17210767468499427,"a_match_n":582,"a_match_centered":-0.03373702422145329,"n_turns_cap_raised":59,"mean_cap_tokens":4157.896378269617,"max_cap_tokens":6052,"len_z_delta":-354.534380034582,"len_y_delta":-243.22308998302208,"n_samples":997,"think_close_rate":0.954864593781344,"n_text_fallback":20,"by_dialect":{"bash":{"n_turns":208,"n_valid":204,"parse_rate":0.9807692307692307,"reason":0.007339547043188147,"mean_b":0.11354072536631982,"b_gate_pass_rate":0.8126036484245439,"median_len_z":374.0,"mean_r_leg":0.021252427211796595,"mean_g_leg":0.054372587432386474,"g_bind_frac":0.27941176470588236,"a_match":0.14787581699346405,"a_match_n":204,"a_match_centered":-0.010726072607260728},"boxed":{"n_turns":52,"n_valid":42,"parse_rate":0.8076923076923077,"reason":-0.015345203813333614,"mean_b":1.028123678176421,"b_gate_pass_rate":0.48333333333333334,"median_len_z":2747.0,"mean_r_leg":0.07054833339608889,"mean_g_leg":0.017664216898956028,"g_bind_frac":0.5714285714285714,"a_match":0.4333333333333333,"a_match_n":40,"a_match_centered":-0.14912280701754388},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0020124915838226477,"mean_b":0.017040599716777724,"b_gate_pass_rate":0.3088235294117647,"median_len_z":581.0,"mean_r_leg":0.0010578998784700586,"mean_g_leg":0.059933118707790806,"g_bind_frac":0.13043478260869565,"a_match":0.3333333333333333,"a_match_n":23,"a_match_centered":-0.014492753623188408},"text":{"n_turns":367,"n_valid":343,"parse_rate":0.9346049046321526,"reason":-0.007697977813059275,"mean_b":0.043008986555454334,"b_gate_pass_rate":0.26822157434402333,"median_len_z":498.0,"mean_r_leg":0.012057606599881098,"mean_g_leg":0.05347619331399745,"g_bind_frac":0.23323615160349853,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":344,"n_valid":336,"parse_rate":0.9767441860465116,"reason":-0.002674742728430952,"mean_b":0.01858788846667642,"b_gate_pass_rate":0.34634634634634637,"median_len_z":251.0,"mean_r_leg":0.0048267697206380794,"mean_g_leg":0.06838460597627766,"g_bind_frac":0.14583333333333334,"a_match":0.14285714285714285,"a_match_n":315,"a_match_centered":-0.03597883597883598}}},"king":{"reason":0.0042837755811207445,"n_turns":994,"n_pairs":2939,"n_forfeits":2,"forfeit_rate":0.002012072434607646,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":60.86747445578229,"mean_len_z":1040.5923783599865,"median_len_z":675.0,"mean_len_y":406.1636611092208,"mean_b":0.10481697046065375,"b_gate_pass_rate":0.5168424634229329,"mean_r_leg":0.01670545666430934,"mean_g_leg":0.06178587168734935,"g_bind_frac":0.21169354838709678,"a_match":0.1650273224043716,"a_match_n":610,"a_match_centered":-0.04326123128119801,"n_turns_cap_raised":59,"mean_cap_tokens":4157.896378269617,"max_cap_tokens":6052,"len_z_delta":-443.8884365805907,"len_y_delta":-362.05942887380127,"n_samples":994,"think_close_rate":0.9979879275653923,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":208,"n_valid":208,"parse_rate":1.0,"reason":0.01258807444706546,"mean_b":0.11199267252624139,"b_gate_pass_rate":0.8727569331158238,"median_len_z":505.0,"mean_r_leg":0.025388541720082584,"mean_g_leg":0.055967806754811535,"g_bind_frac":0.3076923076923077,"a_match":0.12179487179487179,"a_match_n":208,"a_match_centered":-0.03577235772357724},"boxed":{"n_turns":52,"n_valid":52,"parse_rate":1.0,"reason":0.005978184787118646,"mean_b":0.9412711102515015,"b_gate_pass_rate":0.6206896551724138,"median_len_z":2103.0,"mean_r_leg":0.0698650794224663,"mean_g_leg":0.02063630779225419,"g_bind_frac":0.5192307692307693,"a_match":0.5208333333333334,"a_match_n":48,"a_match_centered":-0.029629629629629634},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.001855459474229387,"mean_b":0.017280002412502403,"b_gate_pass_rate":0.25,"median_len_z":579.0,"mean_r_leg":0.0008853598247389718,"mean_g_leg":0.06256813337878361,"g_bind_frac":0.17391304347826086,"a_match":0.3188405797101449,"a_match_n":23,"a_match_centered":-0.028985507246376815},"text":{"n_turns":367,"n_valid":365,"parse_rate":0.9945504087193461,"reason":0.0009553399606165027,"mean_b":0.06964308962807625,"b_gate_pass_rate":0.37534246575342467,"median_len_z":794.0,"mean_r_leg":0.013783955028587216,"mean_g_leg":0.05978639775801987,"g_bind_frac":0.1780821917808219,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":344,"n_valid":344,"parse_rate":1.0,"reason":0.002967888476962948,"mean_b":0.025036378813373315,"b_gate_pass_rate":0.4577603143418468,"median_len_z":546.0,"mean_r_leg":0.007577050412343343,"mean_g_leg":0.07359328678564903,"g_bind_frac":0.14534883720930233,"a_match":0.1299093655589124,"a_match_n":331,"a_match_centered":-0.05081300813008131}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T23:51:23.541931+00:00","challenge_id":"chal-00706","repo":"r2://affine-private-models/models/registrations/3e743a276a7fbb4950e362190274fd8692c721df4a51c8faf423467886c31f42/","hotkey":"5CdYyibTywHFQcuPHA2DocQ4TeHPFQnx4r56WLSKV4AyxW96","uid":116,"duration_s":2640.0,"revision":"526ab6953b3e9915229c2d0f94f0361cb0e6e808ea38876f6c9dd339625dc9f1","accepted":false,"error_code":null,"error_detail":"","z":-3.1160382528315456,"margin":-0.11756335364948266,"se":0.0377284693288514,"n_paired_turns":990,"n_forfeit_turns":7,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":215291671901296282,"n":1000,"digest":"7c2a4ac35727310a080ee85d13defd61ec3197d2987cf2482baf311698727431","n_paired_turns":990,"n_forfeit_turns":7,"margin":-0.11756335364948266,"se":0.0377284693288514,"z":-3.1160382528315456,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.11756335364948266,"se":0.0377284693288514,"z":-3.1160382528315456,"sd_diff":1.1870985738004658,"n_paired_turns":990,"n_forfeit_turns":7,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.007439496604392071,"A":7.087030150130295,"Mc":0.16467530333814467},"bash":{"R":0.028068526877837296,"A":6.454033695385375,"Mc":0.14641311808195162},"text":{"R":0.05258665756008045,"A":11.7405450292788,"Mc":0.16335057651525464},"boxed":{"R":0.0953364859971082,"A":5.136110663995703,"Mc":0.11538912714316614},"terminus_json":{"R":0.0008927885379585578,"A":5.7454610532977615,"Mc":0.1337430786257413}},"challenger":{"mean":-0.8560201144316103,"mean_valid":-0.8194267615871198,"sd_valid":1.4063899815383039,"n_turns":994,"n_valid":984,"n_forfeits":7,"n_unscorable":3,"mean_z_R":0.17896672749104808,"mean_typ_c":0.42137307638741833,"mean_z_A":-0.15633195893572036,"bind_frac":{"R":0.3170731707317073,"Gc":0.20934959349593496,"A":0.4735772357723577},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.24540405863501308,"mean_R":0.01359228594537855,"mean_A":1.8716828819241855,"mean_mc":-0.7228053063341533},"king":{"mean":-0.7332608215037758,"mean_valid":-0.706526104861663,"sd_valid":1.3533353140646334,"n_turns":994,"n_valid":985,"n_forfeits":5,"n_unscorable":4,"mean_z_R":0.16796663968032635,"mean_typ_c":0.5920472560772857,"mean_z_A":-0.14917028740440158,"bind_frac":{"R":0.33096446700507615,"Gc":0.1736040609137056,"A":0.4954314720812183},"n_leg_dropped":{"R":0,"Gc":49,"A":0},"mean_content_share":0.2839710030930707,"mean_R":0.01399257419126703,"mean_A":1.9754426717762292,"mean_mc":-0.6611523024122127}},"rejection_reason":null,"reign_number":null,"score":0.0004359478837448603,"score_king":0.002162751538000654,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9155125,"blocks_since_crown":1114,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1344.445909398242,"mean_len_y":807.9114266396214,"n_samples":3000,"think_close_rate":0.966,"n_text_fallback":29,"by_dialect":{"tool_call":{"n_turns":335,"zero_ref_turns":0,"mean_refs":2.967164179104478,"ref_pair_agreement":0.17598343685300205,"ref_pair_n":322},"bash":{"n_turns":218,"zero_ref_turns":1,"mean_refs":2.967889908256881,"ref_pair_agreement":0.16897081413210444,"ref_pair_n":217},"text":{"n_turns":383,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":39,"zero_ref_turns":4,"mean_refs":2.5384615384615383,"ref_pair_agreement":0.607843137254902,"ref_pair_n":34},"terminus_json":{"n_turns":25,"zero_ref_turns":1,"mean_refs":2.76,"ref_pair_agreement":0.375,"ref_pair_n":24}},"ref_pair_agreement":0.20603015075376882,"ref_pair_n":597},"duel_seconds":2148.396506352816,"challenger":{"reason":0.0004359478837448603,"n_turns":994,"n_pairs":2939,"n_forfeits":7,"forfeit_rate":0.007042253521126761,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.15798814250621,"mean_len_z":1261.2255869343314,"median_len_z":824.0,"mean_len_y":498.21742089145965,"mean_b":0.09121012772200977,"b_gate_pass_rate":0.5079959169785642,"mean_r_leg":0.01359228594537855,"mean_g_leg":0.05654331334875518,"g_bind_frac":0.24214792299898683,"a_match":0.13573021181716835,"a_match_n":598,"a_match_centered":-0.07054525014052838,"n_turns_cap_raised":38,"mean_cap_tokens":4137.562374245473,"max_cap_tokens":6073,"len_z_delta":-83.22032246391063,"len_y_delta":-309.6940057481617,"n_samples":997,"think_close_rate":0.9929789368104313,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":217,"n_valid":217,"parse_rate":1.0,"reason":0.005680914423453383,"mean_b":0.10650523751136474,"b_gate_pass_rate":0.8547140649149922,"median_len_z":686.0,"mean_r_leg":0.023514697513931416,"mean_g_leg":0.04262349567516697,"g_bind_frac":0.3778801843317972,"a_match":0.1044546850998464,"a_match_n":217,"a_match_centered":-0.06451612903225806},"boxed":{"n_turns":35,"n_valid":35,"parse_rate":1.0,"reason":0.005355064125712857,"mean_b":0.9717079071234219,"b_gate_pass_rate":0.5151515151515151,"median_len_z":1825.0,"mean_r_leg":0.05357103677246954,"mean_g_leg":0.022574077344356028,"g_bind_frac":0.5142857142857142,"a_match":0.4380952380952381,"a_match_n":35,"a_match_centered":-0.1568627450980392},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.0071162706635177955,"mean_b":0.03071891170043117,"b_gate_pass_rate":0.43478260869565216,"median_len_z":809.0,"mean_r_leg":0.0015888080081393522,"mean_g_leg":0.04475706394518773,"g_bind_frac":0.125,"a_match":0.375,"a_match_n":24,"a_match_centered":0.0},"text":{"n_turns":383,"n_valid":377,"parse_rate":0.9843342036553525,"reason":-0.0028210509055698113,"mean_b":0.06146811643826423,"b_gate_pass_rate":0.3925729442970822,"median_len_z":859.0,"mean_r_leg":0.011257550230634907,"mean_g_leg":0.061968371301319165,"g_bind_frac":0.18037135278514588,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":335,"n_valid":334,"parse_rate":0.9970149253731343,"reason":0.0007892522833155874,"mean_b":0.03153932457291882,"b_gate_pass_rate":0.4179254783484391,"median_len_z":833.0,"mean_r_leg":0.006454139974204713,"mean_g_leg":0.06387010027358037,"g_bind_frac":0.20359281437125748,"a_match":0.10610766045548653,"a_match_n":322,"a_match_centered":-0.07075471698113207}}},"king":{"reason":0.002162751538000654,"n_turns":994,"n_pairs":2943,"n_forfeits":5,"forfeit_rate":0.005030181086519115,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":0.060599004984927984,"mean_len_z":1005.224260958206,"median_len_z":649.0,"mean_len_y":431.6455997281685,"mean_b":0.0902985834503473,"b_gate_pass_rate":0.507305470608223,"mean_r_leg":0.01399257419126703,"mean_g_leg":0.05896742457944919,"g_bind_frac":0.20626895854398383,"a_match":0.1530328324986088,"a_match_n":599,"a_match_centered":-0.051066217732884396,"n_turns_cap_raised":38,"mean_cap_tokens":4137.562374245473,"max_cap_tokens":6073,"len_z_delta":-339.2216484400361,"len_y_delta":-376.26582691145285,"n_samples":994,"think_close_rate":0.9949698189134809,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":217,"n_valid":217,"parse_rate":1.0,"reason":0.009806892475482967,"mean_b":0.1199144900205263,"b_gate_pass_rate":0.8717156105100463,"median_len_z":493.0,"mean_r_leg":0.024098109972354682,"mean_g_leg":0.04910866152646593,"g_bind_frac":0.29493087557603687,"a_match":0.11981566820276497,"a_match_n":217,"a_match_centered":-0.04915514592933948},"boxed":{"n_turns":35,"n_valid":35,"parse_rate":1.0,"reason":0.004021725646731414,"mean_b":0.9574018131117416,"b_gate_pass_rate":0.6868686868686869,"median_len_z":1818.0,"mean_r_leg":0.0625077046963107,"mean_g_leg":0.023552687912779507,"g_bind_frac":0.4857142857142857,"a_match":0.3904761904761905,"a_match_n":35,"a_match_centered":-0.20588235294117646},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.00465290018607865,"mean_b":0.027123535971112712,"b_gate_pass_rate":0.5217391304347826,"median_len_z":351.0,"mean_r_leg":0.001484331496845214,"mean_g_leg":0.04892787919081395,"g_bind_frac":0.20833333333333334,"a_match":0.4236111111111111,"a_match_n":24,"a_match_centered":0.048611111111111105},"text":{"n_turns":383,"n_valid":378,"parse_rate":0.9869451697127938,"reason":-0.0019780878184528713,"mean_b":0.05753139894951437,"b_gate_pass_rate":0.36507936507936506,"median_len_z":787.5,"mean_r_leg":0.011543733157004746,"mean_g_leg":0.061419160317951374,"g_bind_frac":0.16666666666666666,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":335,"n_valid":335,"parse_rate":1.0,"reason":0.002239391650419654,"mean_b":0.026427712436894464,"b_gate_pass_rate":0.4134808853118712,"median_len_z":571.0,"mean_r_leg":0.006037138082146787,"mean_g_leg":0.06700641068692449,"g_bind_frac":0.16417910447761194,"a_match":0.12951496388028896,"a_match_n":323,"a_match_centered":-0.04336468129571577}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T22:34:47.356676+00:00","challenge_id":"chal-00705","repo":"r2://affine-private-models/models/registrations/0ced2ff2cb23431a0b1afd15e004e44d039c4606ab0260110e0c1a6f8436e4f4/","hotkey":"5Fr3Q9DzD4SKaMj1sptc7U6gFJAJAr8YnU7J5sQZmkmHEDKG","uid":210,"duration_s":2613.6,"revision":"6263f1e1e8f7f8c7124c395e31b59bb7d27d864b2b40f6612a2c64b57ccacd90","accepted":false,"error_code":null,"error_detail":"","z":-0.30596416888578387,"margin":-0.009485042844927408,"se":0.031000502050513523,"n_paired_turns":983,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":7666021404118204098,"n":1000,"digest":"3c84ed12c8dc9e6e88baecf63ace13dd4b1943a7e678864582f288cc99291654","n_paired_turns":983,"n_forfeit_turns":5,"margin":-0.009485042844927408,"se":0.031000502050513523,"z":-0.30596416888578387,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.009485042844927408,"se":0.031000502050513523,"z":-0.30596416888578387,"sd_diff":0.9719534959134448,"n_paired_turns":983,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"text":{"R":0.028382125471014156,"A":32.71381869789543,"Mc":0.14896827417218617},"tool_call":{"R":0.007671865213110865,"A":6.042985422862469,"Mc":0.17793184916535487},"bash":{"R":0.025656969210738567,"A":7.091682497659378,"Mc":0.14528935200598203},"terminus_json":{"R":0.0017572464004930947,"A":13.055001469271216,"Mc":0.1494571926827467},"boxed":{"R":0.1336058609595862,"A":5.634600519102223,"Mc":0.13397558049567004}},"challenger":{"mean":-0.7094048194829417,"mean_valid":-0.6769471803386652,"sd_valid":1.454297666163599,"n_turns":992,"n_valid":978,"n_forfeits":6,"n_unscorable":8,"mean_z_R":0.33262346483442506,"mean_typ_c":0.5648350981513262,"mean_z_A":-0.048917369483183926,"bind_frac":{"R":0.36400817995910023,"Gc":0.1656441717791411,"A":0.4703476482617587},"n_leg_dropped":{"R":0,"Gc":45,"A":0},"mean_content_share":0.2711775414204043,"mean_R":0.018859387134150037,"mean_A":2.480754212071428,"mean_mc":-0.6716240141777192},"king":{"mean":-0.7053101982280721,"mean_valid":-0.6728606182376414,"sd_valid":1.3779578367327543,"n_turns":992,"n_valid":979,"n_forfeits":6,"n_unscorable":7,"mean_z_R":0.3766815102101631,"mean_typ_c":0.5417527671150736,"mean_z_A":-0.037784710869297716,"bind_frac":{"R":0.33605720122574056,"Gc":0.18896833503575078,"A":0.47497446373850866},"n_leg_dropped":{"R":0,"Gc":46,"A":0},"mean_content_share":0.2762041494522251,"mean_R":0.02141473373086968,"mean_A":2.4502237914796234,"mean_mc":-0.6743040898536613}},"rejection_reason":null,"reign_number":null,"score":0.0013283798305730975,"score_king":0.0015926674157597967,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9154744,"blocks_since_crown":733,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1514.0132969655642,"mean_len_y":816.6968973747016,"n_samples":3000,"think_close_rate":0.9476666666666667,"n_text_fallback":21,"by_dialect":{"bash":{"n_turns":224,"zero_ref_turns":1,"mean_refs":2.96875,"ref_pair_agreement":0.16591928251121077,"ref_pair_n":223},"tool_call":{"n_turns":317,"zero_ref_turns":1,"mean_refs":2.952681388012618,"ref_pair_agreement":0.16344086021505375,"ref_pair_n":310},"text":{"n_turns":379,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":62,"zero_ref_turns":5,"mean_refs":2.403225806451613,"ref_pair_agreement":0.5757575757575757,"ref_pair_n":44},"terminus_json":{"n_turns":18,"zero_ref_turns":1,"mean_refs":2.5555555555555554,"ref_pair_agreement":0.2916666666666667,"ref_pair_n":16}},"ref_pair_agreement":0.19842608206857784,"ref_pair_n":593},"duel_seconds":2153.642497721128,"challenger":{"reason":0.0013283798305730975,"n_turns":992,"n_pairs":2919,"n_forfeits":6,"forfeit_rate":0.006048387096774193,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-10.99093460965201,"mean_len_z":1149.892771497088,"median_len_z":691.0,"mean_len_y":403.8725590955807,"mean_b":0.1070745995161958,"b_gate_pass_rate":0.5059952038369304,"mean_r_leg":0.018859387134150037,"mean_g_leg":0.05615047611328818,"g_bind_frac":0.23123732251521298,"a_match":0.15358931552587646,"a_match_n":599,"a_match_centered":-0.04342921601804851,"n_turns_cap_raised":55,"mean_cap_tokens":4162.004032258064,"max_cap_tokens":6036,"len_z_delta":-364.1205254684762,"len_y_delta":-412.8243382791209,"n_samples":995,"think_close_rate":0.9949748743718593,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":223,"n_valid":222,"parse_rate":0.9955156950672646,"reason":0.006487659349800637,"mean_b":0.12199626484863527,"b_gate_pass_rate":0.8836858006042296,"median_len_z":485.0,"mean_r_leg":0.018855824176311986,"mean_g_leg":0.05008202780690338,"g_bind_frac":0.2747747747747748,"a_match":0.11411411411411411,"a_match_n":222,"a_match_centered":-0.04804804804804805},"boxed":{"n_turns":57,"n_valid":54,"parse_rate":0.9473684210526315,"reason":-0.0010560533007957847,"mean_b":0.9345891682464671,"b_gate_pass_rate":0.7430555555555556,"median_len_z":2360.0,"mean_r_leg":0.0672080571848806,"mean_g_leg":0.015083381187545984,"g_bind_frac":0.5740740740740741,"a_match":0.45751633986928103,"a_match_n":51,"a_match_centered":-0.06818181818181818},"terminus_json":{"n_turns":17,"n_valid":17,"parse_rate":1.0,"reason":-0.009021843696541243,"mean_b":0.01504716835213077,"b_gate_pass_rate":0.10869565217391304,"median_len_z":601.0,"mean_r_leg":0.001566614209927254,"mean_g_leg":0.05003843679619119,"g_bind_frac":0.29411764705882354,"a_match":0.37254901960784315,"a_match_n":17,"a_match_centered":0.10416666666666666},"text":{"n_turns":379,"n_valid":377,"parse_rate":0.9947229551451188,"reason":-0.0010415221741501561,"mean_b":0.06417532523898868,"b_gate_pass_rate":0.363395225464191,"median_len_z":854.0,"mean_r_leg":0.023408213295844645,"mean_g_leg":0.05648175944595477,"g_bind_frac":0.20159151193633953,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.0015167976009887365,"mean_b":0.02557043359080504,"b_gate_pass_rate":0.3942307692307692,"median_len_z":589.5,"mean_r_leg":0.006103160775458638,"mean_g_leg":0.06736512643601872,"g_bind_frac":0.17405063291139242,"a_match":0.11974110032362459,"a_match_n":309,"a_match_centered":-0.04422869471413161}}},"king":{"reason":0.0015926674157597967,"n_turns":992,"n_pairs":2921,"n_forfeits":6,"forfeit_rate":0.006048387096774193,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-10.458652734492125,"mean_len_z":1068.2547072920233,"median_len_z":688.0,"mean_len_y":415.6929133858268,"mean_b":0.11200482107419248,"b_gate_pass_rate":0.4964053406367682,"mean_r_leg":0.02141473373086968,"mean_g_leg":0.056113399120422784,"g_bind_frac":0.2302231237322515,"a_match":0.1524526198439242,"a_match_n":598,"a_match_centered":-0.044763513513513514,"n_turns_cap_raised":55,"mean_cap_tokens":4162.004032258064,"max_cap_tokens":6036,"len_z_delta":-445.7585896735409,"len_y_delta":-401.00398398887484,"n_samples":992,"think_close_rate":0.9949596774193549,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":223,"n_valid":222,"parse_rate":0.9955156950672646,"reason":0.0075345583289542495,"mean_b":0.11923780831014888,"b_gate_pass_rate":0.8761329305135952,"median_len_z":490.0,"mean_r_leg":0.020032512314647952,"mean_g_leg":0.05010713107617261,"g_bind_frac":0.2747747747747748,"a_match":0.13063063063063063,"a_match_n":222,"a_match_centered":-0.03153153153153153},"boxed":{"n_turns":57,"n_valid":54,"parse_rate":0.9473684210526315,"reason":-8.050464840590232e-05,"mean_b":0.9486512841504707,"b_gate_pass_rate":0.6164383561643836,"median_len_z":2013.0,"mean_r_leg":0.09098412620839293,"mean_g_leg":0.017192086798820835,"g_bind_frac":0.6111111111111112,"a_match":0.5,"a_match_n":49,"a_match_centered":-0.041666666666666664},"terminus_json":{"n_turns":17,"n_valid":17,"parse_rate":1.0,"reason":-0.004491777686248575,"mean_b":0.025200400312036516,"b_gate_pass_rate":0.41304347826086957,"median_len_z":812.0,"mean_r_leg":0.0014113703690769432,"mean_g_leg":0.05393179438719198,"g_bind_frac":0.23529411764705882,"a_match":0.36274509803921573,"a_match_n":17,"a_match_centered":0.09375},"text":{"n_turns":379,"n_valid":377,"parse_rate":0.9947229551451188,"reason":-0.0017087198726443945,"mean_b":0.07581863796248248,"b_gate_pass_rate":0.35543766578249336,"median_len_z":849.0,"mean_r_leg":0.026153340633437317,"mean_g_leg":0.05611099309042194,"g_bind_frac":0.19363395225464192,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.001988206919096546,"mean_b":0.024377636560371344,"b_gate_pass_rate":0.38354700854700857,"median_len_z":545.0,"mean_r_leg":0.00592013985586159,"mean_g_leg":0.06710433812347748,"g_bind_frac":0.17721518987341772,"a_match":0.10161290322580645,"a_match_n":310,"a_match_centered":-0.06182795698924731}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T21:50:05.096842+00:00","challenge_id":"chal-00704","repo":"r2://affine-private-models/models/registrations/04b3641f4a9d496ca0af94ece5ce92e8453baff22ae0d12c477db7b2c4d96d69/","hotkey":"5DwNyN2eMVFGpimjsrTCLMgPK45HoxYx7dWYsgNQTuJsto2P","uid":59,"duration_s":2947.0,"revision":"fd61451f7b2663891fe434f6934a0b40c52c02e95bc972b881acca52d0f3dfdb","accepted":false,"error_code":null,"error_detail":"","z":0.4951153302978627,"margin":0.014223945737444127,"se":0.02872855043467744,"n_paired_turns":981,"n_forfeit_turns":10,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":5673904596499987399,"n":1000,"digest":"0452cd83958a753f75019423bc15141173958f7722a66093cb7903e4f97df8b1","n_paired_turns":981,"n_forfeit_turns":10,"margin":0.014223945737444127,"se":0.02872855043467744,"z":0.4951153302978627,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":1},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.014223945737444127,"se":0.02872855043467744,"z":0.4951153302978627,"sd_diff":0.8998046162841836,"n_paired_turns":981,"n_forfeit_turns":10,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"text":{"R":0.07129875965895828,"A":25.874990316275174,"Mc":0.15328343575717332},"tool_call":{"R":0.009209458807536725,"A":6.243251440302233,"Mc":0.1757082513042615},"bash":{"R":0.022361574490119832,"A":6.022193163564238,"Mc":0.17012447318971888},"boxed":{"R":0.06882565844757414,"A":5.722640920798071,"Mc":0.11514156229625111},"terminus_json":{"R":0.0013062103435641174,"A":6.30379206769016,"Mc":0.12623105953876188}},"challenger":{"mean":-0.750455782485122,"mean_valid":-0.7018488915822064,"sd_valid":1.5253283216760338,"n_turns":989,"n_valid":972,"n_forfeits":9,"n_unscorable":8,"mean_z_R":0.17235859693174505,"mean_typ_c":0.5527557434797132,"mean_z_A":-0.07207004060939293,"bind_frac":{"R":0.3549382716049383,"Gc":0.1800411522633745,"A":0.46502057613168724},"n_leg_dropped":{"R":0,"Gc":43,"A":0},"mean_content_share":0.27340099326239975,"mean_R":0.013788421540230368,"mean_A":2.1456254315582894,"mean_mc":-0.667873949240111},"king":{"mean":-0.7646797282225661,"mean_valid":-0.7216349572315903,"sd_valid":1.5233883887604438,"n_turns":989,"n_valid":973,"n_forfeits":8,"n_unscorable":8,"mean_z_R":0.2038258026234297,"mean_typ_c":0.5587485556141399,"mean_z_A":-0.06843332518090608,"bind_frac":{"R":0.36896197327852004,"Gc":0.18602261048304214,"A":0.4450154162384378},"n_leg_dropped":{"R":0,"Gc":44,"A":0},"mean_content_share":0.27443974402387344,"mean_R":0.015073122963594558,"mean_A":2.2103035027547433,"mean_mc":-0.6766091169295589}},"rejection_reason":null,"reign_number":null,"score":0.0010548110521257101,"score_king":0.0010019556501720463,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9154011,"crown_block_source":"king","decision_block":9154492,"blocks_since_crown":481,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1526.5616860863606,"mean_len_y":858.60932145305,"n_samples":3000,"think_close_rate":0.9416666666666667,"n_text_fallback":36,"by_dialect":{"bash":{"n_turns":210,"zero_ref_turns":1,"mean_refs":2.9380952380952383,"ref_pair_agreement":0.20833333333333334,"ref_pair_n":208},"text":{"n_turns":363,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":349,"zero_ref_turns":4,"mean_refs":2.9054441260744985,"ref_pair_agreement":0.1641337386018237,"ref_pair_n":329},"boxed":{"n_turns":56,"zero_ref_turns":4,"mean_refs":2.482142857142857,"ref_pair_agreement":0.5347222222222222,"ref_pair_n":48},"terminus_json":{"n_turns":22,"zero_ref_turns":2,"mean_refs":2.6818181818181817,"ref_pair_agreement":0.4166666666666667,"ref_pair_n":20}},"ref_pair_agreement":0.21707988980716256,"ref_pair_n":605},"duel_seconds":2304.033085643314,"challenger":{"reason":0.0010548110521257101,"n_turns":989,"n_pairs":2892,"n_forfeits":9,"forfeit_rate":0.00910010111223458,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-224.78827384348023,"mean_len_z":1087.59785615491,"median_len_z":700.0,"mean_len_y":402.86237897648687,"mean_b":0.10171086459684739,"b_gate_pass_rate":0.4996542185338866,"mean_r_leg":0.013788421540230368,"mean_g_leg":0.05912653521350128,"g_bind_frac":0.2193877551020408,"a_match":0.16991869918699187,"a_match_n":615,"a_match_centered":-0.04608167770419426,"n_turns_cap_raised":58,"mean_cap_tokens":4156.797775530839,"max_cap_tokens":5988,"len_z_delta":-438.9638299314506,"len_y_delta":-455.74694247656316,"n_samples":992,"think_close_rate":0.9919354838709677,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":209,"n_valid":209,"parse_rate":1.0,"reason":0.008195576878284948,"mean_b":0.11677072322274258,"b_gate_pass_rate":0.8152350081037277,"median_len_z":521.0,"mean_r_leg":0.020816480289162748,"mean_g_leg":0.05679803489448553,"g_bind_frac":0.2679425837320574,"a_match":0.16427432216905902,"a_match_n":209,"a_match_centered":-0.04326923076923077},"boxed":{"n_turns":52,"n_valid":51,"parse_rate":0.9807692307692307,"reason":0.003652446633051522,"mean_b":0.9655110294864904,"b_gate_pass_rate":0.6496350364963503,"median_len_z":2464.0,"mean_r_leg":0.050090830240995914,"mean_g_leg":0.02388565308984988,"g_bind_frac":0.5686274509803921,"a_match":0.39542483660130723,"a_match_n":51,"a_match_centered":-0.11702127659574468},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.002213488558068633,"mean_b":0.020667900353283697,"b_gate_pass_rate":0.4067796610169492,"median_len_z":449.0,"mean_r_leg":0.0009651999959313062,"mean_g_leg":0.06853134450634749,"g_bind_frac":0.15,"a_match":0.4333333333333333,"a_match_n":20,"a_match_centered":0.016666666666666666},"text":{"n_turns":363,"n_valid":355,"parse_rate":0.977961432506887,"reason":-0.004465267261507709,"mean_b":0.05918554651970924,"b_gate_pass_rate":0.4084507042253521,"median_len_z":794.0,"mean_r_leg":0.0118632323054422,"mean_g_leg":0.05483173760216348,"g_bind_frac":0.18873239436619718,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":345,"n_valid":345,"parse_rate":1.0,"reason":0.00233497717437903,"mean_b":0.025220177496713233,"b_gate_pass_rate":0.388560157790927,"median_len_z":566.0,"mean_r_leg":0.006888767879273472,"mean_g_leg":0.06962073382552593,"g_bind_frac":0.17391304347826086,"a_match":0.12338308457711443,"a_match_n":335,"a_match_centered":-0.041540020263424515}}},"king":{"reason":0.0010019556501720463,"n_turns":989,"n_pairs":2895,"n_forfeits":8,"forfeit_rate":0.008088978766430738,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-206.80414210145744,"mean_len_z":1103.4918825561313,"median_len_z":682.0,"mean_len_y":419.5578583765112,"mean_b":0.10720000831354158,"b_gate_pass_rate":0.48601036269430054,"mean_r_leg":0.015073122963594558,"mean_g_leg":0.059254705001435544,"g_bind_frac":0.22120285423037717,"a_match":0.16639254385964913,"a_match_n":608,"a_match_centered":-0.05108877721943048,"n_turns_cap_raised":58,"mean_cap_tokens":4156.797775530839,"max_cap_tokens":5988,"len_z_delta":-423.06980353022936,"len_y_delta":-439.0514630765388,"n_samples":989,"think_close_rate":0.9919110212335692,"n_text_fallback":11,"by_dialect":{"bash":{"n_turns":209,"n_valid":209,"parse_rate":1.0,"reason":0.007949932777330476,"mean_b":0.11864683836821491,"b_gate_pass_rate":0.8038897893030794,"median_len_z":503.0,"mean_r_leg":0.024001899834156296,"mean_g_leg":0.05663756717856562,"g_bind_frac":0.2966507177033493,"a_match":0.16267942583732056,"a_match_n":209,"a_match_centered":-0.04487179487179487},"boxed":{"n_turns":52,"n_valid":51,"parse_rate":0.9807692307692307,"reason":0.0042274356158747755,"mean_b":0.9727863371143735,"b_gate_pass_rate":0.708029197080292,"median_len_z":2295.0,"mean_r_leg":0.05629786797074537,"mean_g_leg":0.026831263531330442,"g_bind_frac":0.43137254901960786,"a_match":0.45666666666666667,"a_match_n":50,"a_match_centered":-0.08333333333333334},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0033208966963707387,"mean_b":0.019310564271419067,"b_gate_pass_rate":0.4067796610169492,"median_len_z":422.0,"mean_r_leg":0.0009196361651504895,"mean_g_leg":0.07084366715248404,"g_bind_frac":0.2,"a_match":0.4333333333333333,"a_match_n":20,"a_match_centered":0.016666666666666666},"text":{"n_turns":363,"n_valid":356,"parse_rate":0.9807162534435262,"reason":-0.004070798576571814,"mean_b":0.06921986255712954,"b_gate_pass_rate":0.34831460674157305,"median_len_z":797.0,"mean_r_leg":0.012839998390106348,"mean_g_leg":0.05624289943746759,"g_bind_frac":0.17696629213483145,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":345,"n_valid":345,"parse_rate":1.0,"reason":0.0018947517471176209,"mean_b":0.028403412334139087,"b_gate_pass_rate":0.41222879684418146,"median_len_z":560.0,"mean_r_leg":0.0066948207108948185,"mean_g_leg":0.06806920024116539,"g_bind_frac":0.19130434782608696,"a_match":0.10840932117527861,"a_match_n":329,"a_match_centered":-0.05469556243550052}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"crown_note":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"crowned","at":"2026-09-26T19:24:46.006361+00:00","challenge_id":"chal-00687","repo":"r2://affine-models/models/sha256/7f066f2c5f95b34105c23faa313e25908c8610fbb65091e797e8b9391e926dfc/","hotkey":"5EzaX8pVDyqCFE3Gcw8r2SAb8SKy4ZZydLQeTFDjbFBzPyqT","uid":62,"duration_s":null,"revision":"7f066f2c5f95b34105c23faa313e25908c8610fbb65091e797e8b9391e926dfc","accepted":true,"error_code":null,"error_detail":"","z":2.726644372131751,"margin":0.07280288925143412,"se":0.02670054444779508,"n_paired_turns":987,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":13865707148065924770,"n":1000,"digest":"321ede32d06ca0280042e8cec30d1e0266ad9ad7f9068d7418547cc29398ea5b","n_paired_turns":987,"n_forfeit_turns":4,"margin":0.07280288925143412,"se":0.02670054444779508,"z":2.726644372131751,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.07280288925143412,"se":0.02670054444779508,"z":2.726644372131751,"sd_diff":0.8388391537411495,"n_paired_turns":987,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.0248704564434324,"A":6.60007009745041,"Mc":0.15039783968323348},"text":{"R":0.08700263531240472,"A":14.692052491200977,"Mc":0.1525101867637208},"tool_call":{"R":0.046441287190392325,"A":5.3906892020893,"Mc":0.1902426272344548},"terminus_json":{"R":0.002221507541752901,"A":5.706521715219618,"Mc":0.12804367599941946},"boxed":{"R":0.14093367988486832,"A":8.289466136606043,"Mc":0.12568339535124765}},"challenger":{"mean":-0.6588686833799752,"mean_valid":-0.6425847464390605,"sd_valid":1.413567530918181,"n_turns":996,"n_valid":984,"n_forfeits":3,"n_unscorable":9,"mean_z_R":0.09639314946587477,"mean_typ_c":0.7206320725788616,"mean_z_A":-0.10739164368683621,"bind_frac":{"R":0.3780487804878049,"Gc":0.13617886178861788,"A":0.48577235772357724},"n_leg_dropped":{"R":0,"Gc":39,"A":0},"mean_content_share":0.2836986720945388,"mean_R":0.021675251910647973,"mean_A":2.2577284774010904,"mean_mc":-0.6462748185508179},"king":{"mean":-0.7316715726314093,"mean_valid":-0.7209744590733005,"sd_valid":1.4740642939146047,"n_turns":996,"n_valid":985,"n_forfeits":2,"n_unscorable":9,"mean_z_R":0.10794032105621179,"mean_typ_c":0.6297379057177107,"mean_z_A":-0.16550226531432521,"bind_frac":{"R":0.3553299492385787,"Gc":0.15634517766497463,"A":0.4883248730964467},"n_leg_dropped":{"R":0,"Gc":37,"A":0},"mean_content_share":0.27812696063296066,"mean_R":0.022919688891845817,"mean_A":1.753868222989525,"mean_mc":-0.6688916418090859}},"rejection_reason":null,"reign_number":22,"score":0.003144942563729151,"score_king":0.003268179347234281,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9139486,"blocks_since_crown":16176,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1408.2648849797024,"mean_len_y":704.7357916102842,"n_samples":3000,"think_close_rate":0.9643333333333334,"n_text_fallback":19,"by_dialect":{"tool_call":{"n_turns":312,"zero_ref_turns":0,"mean_refs":2.9711538461538463,"ref_pair_agreement":0.1716171617161716,"ref_pair_n":303},"terminus_json":{"n_turns":20,"zero_ref_turns":1,"mean_refs":2.85,"ref_pair_agreement":0.543859649122807,"ref_pair_n":19},"text":{"n_turns":367,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":256,"zero_ref_turns":2,"mean_refs":2.93359375,"ref_pair_agreement":0.15670650730411687,"ref_pair_n":251},"boxed":{"n_turns":45,"zero_ref_turns":1,"mean_refs":2.6666666666666665,"ref_pair_agreement":0.40196078431372545,"ref_pair_n":34}},"ref_pair_agreement":0.19000549148819332,"ref_pair_n":607},"duel_seconds":2243.9056344972923,"challenger":{"reason":0.003144942563729151,"n_turns":996,"n_pairs":2947,"n_forfeits":3,"forfeit_rate":0.0030120481927710845,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-4.31993063874057,"mean_len_z":1033.321343739396,"median_len_z":698.0,"mean_len_y":453.4882931795046,"mean_b":0.10340976790618457,"b_gate_pass_rate":0.513742789277231,"mean_r_leg":0.021675251910647973,"mean_g_leg":0.05911659372325195,"g_bind_frac":0.22457200402819738,"a_match":0.16019417475728157,"a_match_n":618,"a_match_centered":-0.028697571743929357,"n_turns_cap_raised":43,"mean_cap_tokens":4147.582329317269,"max_cap_tokens":6075,"len_z_delta":-374.94354124030633,"len_y_delta":-251.24749843077961,"n_samples":999,"think_close_rate":0.997997997997998,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":254,"n_valid":253,"parse_rate":0.9960629921259843,"reason":0.009283883371481448,"mean_b":0.12363393469150717,"b_gate_pass_rate":0.9050802139037433,"median_len_z":552.0,"mean_r_leg":0.01919814384916325,"mean_g_leg":0.050453599733904037,"g_bind_frac":0.2608695652173913,"a_match":0.12582345191040842,"a_match_n":253,"a_match_centered":-0.03},"boxed":{"n_turns":44,"n_valid":44,"parse_rate":1.0,"reason":0.009114190890368523,"mean_b":0.930845684892032,"b_gate_pass_rate":0.8333333333333334,"median_len_z":2882.0,"mean_r_leg":0.12095818827425903,"mean_g_leg":0.01798455966286845,"g_bind_frac":0.75,"a_match":0.4458333333333333,"a_match_n":40,"a_match_centered":0.09313725490196079},"terminus_json":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":-0.0006446774866778505,"mean_b":0.014763071392030742,"b_gate_pass_rate":0.2631578947368421,"median_len_z":752.0,"mean_r_leg":0.0017382974654390653,"mean_g_leg":0.037874851034359745,"g_bind_frac":0.10526315789473684,"a_match":0.5614035087719298,"a_match_n":19,"a_match_centered":0.017543859649122806},"text":{"n_turns":367,"n_valid":365,"parse_rate":0.9945504087193461,"reason":9.526184760719051e-05,"mean_b":0.07142450590034091,"b_gate_pass_rate":0.3589041095890411,"median_len_z":848.0,"mean_r_leg":0.02504003134599533,"mean_g_leg":0.05850944264857803,"g_bind_frac":0.20273972602739726,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":312,"n_valid":312,"parse_rate":1.0,"reason":0.0011234608721691411,"mean_b":0.023212072980599442,"b_gate_pass_rate":0.35490830636461707,"median_len_z":600.0,"mean_r_leg":0.006960241590500325,"mean_g_leg":0.07394592138769693,"g_bind_frac":0.15384615384615385,"a_match":0.12636165577342048,"a_match_n":306,"a_match_centered":-0.044296788482835}}},"king":{"reason":0.003268179347234281,"n_turns":996,"n_pairs":2950,"n_forfeits":2,"forfeit_rate":0.002008032128514056,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.5957204162318908,"mean_len_z":1008.1271186440678,"median_len_z":693.0,"mean_len_y":358.01898305084745,"mean_b":0.10794455768350512,"b_gate_pass_rate":0.5549152542372882,"mean_r_leg":0.022919688891845817,"mean_g_leg":0.0585020882589682,"g_bind_frac":0.22535211267605634,"a_match":0.16052350427350429,"a_match_n":624,"a_match_centered":-0.02828116419549698,"n_turns_cap_raised":43,"mean_cap_tokens":4147.582329317269,"max_cap_tokens":6075,"len_z_delta":-400.13776633563464,"len_y_delta":-346.71680855943674,"n_samples":996,"think_close_rate":0.9979919678714859,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":254,"n_valid":254,"parse_rate":1.0,"reason":0.008672531737415128,"mean_b":0.12977446299999756,"b_gate_pass_rate":0.9054593874833555,"median_len_z":521.0,"mean_r_leg":0.019949730533899798,"mean_g_leg":0.048546080905758515,"g_bind_frac":0.27165354330708663,"a_match":0.11876640419947505,"a_match_n":254,"a_match_centered":-0.036520584329349265},"boxed":{"n_turns":44,"n_valid":44,"parse_rate":1.0,"reason":0.011484229790349559,"mean_b":0.9794332673583384,"b_gate_pass_rate":0.7416666666666667,"median_len_z":2717.0,"mean_r_leg":0.11846228551189783,"mean_g_leg":0.0205927722582478,"g_bind_frac":0.7045454545454546,"a_match":0.47967479674796754,"a_match_n":41,"a_match_centered":0.11764705882352941},"terminus_json":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":-0.0018507744944574482,"mean_b":0.01748032810573182,"b_gate_pass_rate":0.2631578947368421,"median_len_z":752.0,"mean_r_leg":0.00118320014397382,"mean_g_leg":0.03277032448104651,"g_bind_frac":0.21052631578947367,"a_match":0.5614035087719298,"a_match_n":19,"a_match_centered":0.017543859649122806},"text":{"n_turns":367,"n_valid":365,"parse_rate":0.9945504087193461,"reason":0.0003898816956786672,"mean_b":0.07101796369267822,"b_gate_pass_rate":0.4136986301369863,"median_len_z":848.0,"mean_r_leg":0.029573244093229503,"mean_g_leg":0.05756974659986626,"g_bind_frac":0.1917808219178082,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":312,"n_valid":312,"parse_rate":1.0,"reason":0.0014072294578434013,"mean_b":0.026626518257639696,"b_gate_pass_rate":0.43149946062567424,"median_len_z":589.0,"mean_r_leg":0.005403473537168009,"mean_g_leg":0.07461120360864666,"g_bind_frac":0.16025641025641027,"a_match":0.12795698924731183,"a_match_n":310,"a_match_centered":-0.04070407040704071}}},"challenger_wins":true,"crown_mode":null,"window_id":null,"outcome":null,"via":"operator_crown","crown_note":"operator crown 2026-09-26; did not clear δ under wvk 24","revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T18:41:44.082221+00:00","challenge_id":"chal-00702","repo":"r2://affine-private-models/models/registrations/a2d053c3f9c2e6b4ae8c2b4691b7132890c294988b0572b4b35dbb795127fb1d/","hotkey":"5HSAN2bxDhfBYiZA16WZqzJ9dc8NygE33bFt69yG271cFzZv","uid":26,"duration_s":2561.7,"revision":"d7aac1f97ebcf790a7794f5d2b5b9e256d2e78836737fa4233d8e98a89e062b9","accepted":false,"error_code":null,"error_detail":"","z":-4.0441657233111785,"margin":-0.19565929126460627,"se":0.048380631420912534,"n_paired_turns":982,"n_forfeit_turns":25,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":12865045435608852217,"n":1000,"digest":"e4ca2ca1dc2af5501df17e9be00925539c62f2e78d494f5b36ad0612a9669464","n_paired_turns":982,"n_forfeit_turns":25,"margin":-0.19565929126460627,"se":0.048380631420912534,"z":-4.0441657233111785,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.19565929126460627,"se":0.048380631420912534,"z":-4.0441657233111785,"sd_diff":1.516098004004305,"n_paired_turns":982,"n_forfeit_turns":25,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.0256961487215162,"A":6.259324371126922,"Mc":0.15315221970915868},"tool_call":{"R":0.007864852443005926,"A":7.039174472153447,"Mc":0.17049483967637727},"text":{"R":0.04171409240749709,"A":36.60977099986994,"Mc":0.14909548437856374},"boxed":{"R":0.05948136887802148,"A":3.192134299599418,"Mc":0.09931764364467013},"terminus_json":{"R":0.0024835509454433765,"A":7.994026661362359,"Mc":0.11856810039153903}},"challenger":{"mean":-0.9783350660586191,"mean_valid":-0.847289530204199,"sd_valid":1.662637729665187,"n_turns":991,"n_valid":958,"n_forfeits":25,"n_unscorable":8,"mean_z_R":0.36772177849511567,"mean_typ_c":0.3394997011262962,"mean_z_A":-0.1261371320663268,"bind_frac":{"R":0.3079331941544885,"Gc":0.22025052192066805,"A":0.4718162839248434},"n_leg_dropped":{"R":0,"Gc":33,"A":0},"mean_content_share":0.30171060237624386,"mean_R":0.02296306969709916,"mean_A":1.6008324870722184,"mean_mc":-0.6687341791149162},"king":{"mean":-0.777562063048655,"mean_valid":-0.750835154466509,"sd_valid":1.558519850757309,"n_turns":991,"n_valid":977,"n_forfeits":5,"n_unscorable":9,"mean_z_R":0.2932289417503227,"mean_typ_c":0.4246132334625281,"mean_z_A":-0.10589075961417443,"bind_frac":{"R":0.32446264073694986,"Gc":0.2016376663254862,"A":0.47389969293756395},"n_leg_dropped":{"R":0,"Gc":44,"A":0},"mean_content_share":0.2733241430019746,"mean_R":0.020746211880930367,"mean_A":1.6120041946561998,"mean_mc":-0.7007422185601103}},"rejection_reason":null,"reign_number":null,"score":0.0006717646814707977,"score_king":0.0021206097018820107,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9153583,"blocks_since_crown":30273,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1566.463247863248,"mean_len_y":742.6252991452991,"n_samples":3000,"think_close_rate":0.9533333333333334,"n_text_fallback":11,"by_dialect":{"tool_call":{"n_turns":349,"zero_ref_turns":2,"mean_refs":2.9169054441260744,"ref_pair_agreement":0.15732546705998035,"ref_pair_n":339},"bash":{"n_turns":225,"zero_ref_turns":1,"mean_refs":2.92,"ref_pair_agreement":0.1787878787878788,"ref_pair_n":220},"text":{"n_turns":356,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":46,"zero_ref_turns":4,"mean_refs":2.5434782608695654,"ref_pair_agreement":0.6403508771929824,"ref_pair_n":38},"terminus_json":{"n_turns":24,"zero_ref_turns":2,"mean_refs":2.7083333333333335,"ref_pair_agreement":0.6363636363636364,"ref_pair_n":22}},"ref_pair_agreement":0.21163166397415187,"ref_pair_n":619},"duel_seconds":2096.5054626851343,"challenger":{"reason":0.0006717646814707977,"n_turns":991,"n_pairs":2856,"n_forfeits":25,"forfeit_rate":0.025227043390514632,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":3.5856621480224975,"mean_len_z":1185.7429971988795,"median_len_z":535.0,"mean_len_y":434.51050420168065,"mean_b":0.10602414521031499,"b_gate_pass_rate":0.46113445378151263,"mean_r_leg":0.02296306969709916,"mean_g_leg":0.05506986512067706,"g_bind_frac":0.2463768115942029,"a_match":0.18010752688172044,"a_match_n":620,"a_match_centered":-0.03159041394335512,"n_turns_cap_raised":53,"mean_cap_tokens":4150.981836528759,"max_cap_tokens":6020,"len_z_delta":-380.72025066436845,"len_y_delta":-308.11479494361845,"n_samples":994,"think_close_rate":0.9748490945674044,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":224,"n_valid":222,"parse_rate":0.9910714285714286,"reason":0.006884898673357934,"mean_b":0.12924919084592676,"b_gate_pass_rate":0.8571428571428571,"median_len_z":447.0,"mean_r_leg":0.02391343847935426,"mean_g_leg":0.04434755814111833,"g_bind_frac":0.32432432432432434,"a_match":0.1276276276276276,"a_match_n":222,"a_match_centered":-0.05045871559633028},"boxed":{"n_turns":42,"n_valid":40,"parse_rate":0.9523809523809523,"reason":-0.0005158378567497147,"mean_b":0.9991942695052671,"b_gate_pass_rate":0.5614035087719298,"median_len_z":2531.5,"mean_r_leg":0.062230222247875056,"mean_g_leg":0.018037760949678367,"g_bind_frac":0.55,"a_match":0.6126126126126127,"a_match_n":37,"a_match_centered":-0.01801801801801802},"terminus_json":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":-0.00099712283989616,"mean_b":0.01843861238420945,"b_gate_pass_rate":0.18461538461538463,"median_len_z":756.0,"mean_r_leg":0.004204185278743711,"mean_g_leg":0.03661309445294623,"g_bind_frac":0.2727272727272727,"a_match":0.5606060606060607,"a_match_n":22,"a_match_centered":-0.07575757575757576},"text":{"n_turns":356,"n_valid":340,"parse_rate":0.9550561797752809,"reason":-3.4732202562849075e-05,"mean_b":0.0772951887901441,"b_gate_pass_rate":0.29411764705882354,"median_len_z":764.0,"mean_r_leg":0.03695207227780537,"mean_g_leg":0.06025915449488316,"g_bind_frac":0.18823529411764706,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":347,"n_valid":342,"parse_rate":0.9855907780979827,"reason":-0.002364645380175905,"mean_b":0.024568574935825264,"b_gate_pass_rate":0.38071570576540753,"median_len_z":372.0,"mean_r_leg":0.005053030539415063,"mean_g_leg":0.06238953437144312,"g_bind_frac":0.21637426900584794,"a_match":0.14257620452310718,"a_match_n":339,"a_match_centered":-0.01791044776119403}}},"king":{"reason":0.0021206097018820107,"n_turns":991,"n_pairs":2913,"n_forfeits":5,"forfeit_rate":0.005045408678102927,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":191.98303828641374,"mean_len_z":1026.4092001373156,"median_len_z":689.0,"mean_len_y":345.0700308959835,"mean_b":0.10661046491410864,"b_gate_pass_rate":0.5413662890490902,"mean_r_leg":0.020746211880930367,"mean_g_leg":0.05705176130540392,"g_bind_frac":0.24543610547667344,"a_match":0.1621477937267411,"a_match_n":627,"a_match_centered":-0.045921123716909776,"n_turns_cap_raised":53,"mean_cap_tokens":4150.981836528759,"max_cap_tokens":6020,"len_z_delta":-540.0540477259324,"len_y_delta":-397.5552682493156,"n_samples":991,"think_close_rate":0.9949545913218971,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":224,"n_valid":224,"parse_rate":1.0,"reason":0.008359408550971743,"mean_b":0.13657835409815666,"b_gate_pass_rate":0.8873668188736682,"median_len_z":552.0,"mean_r_leg":0.024450557620040492,"mean_g_leg":0.04218450222168358,"g_bind_frac":0.35267857142857145,"a_match":0.13392857142857142,"a_match_n":224,"a_match_centered":-0.04242424242424243},"boxed":{"n_turns":42,"n_valid":40,"parse_rate":0.9523809523809523,"reason":0.0013105145322873113,"mean_b":1.0027335307917529,"b_gate_pass_rate":0.6754385964912281,"median_len_z":1947.5,"mean_r_leg":0.06177480942651696,"mean_g_leg":0.021916705983624125,"g_bind_frac":0.5,"a_match":0.5945945945945946,"a_match_n":37,"a_match_centered":-0.03603603603603604},"terminus_json":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":-0.0038368453471942956,"mean_b":0.014233536749402158,"b_gate_pass_rate":0.27692307692307694,"median_len_z":669.0,"mean_r_leg":0.0020907113690856022,"mean_g_leg":0.03468831371606591,"g_bind_frac":0.36363636363636365,"a_match":0.5151515151515151,"a_match_n":22,"a_match_centered":-0.1212121212121212},"text":{"n_turns":356,"n_valid":353,"parse_rate":0.9915730337078652,"reason":0.0010121503957800843,"mean_b":0.07010424060357603,"b_gate_pass_rate":0.37677053824362605,"median_len_z":833.0,"mean_r_leg":0.030261092389961355,"mean_g_leg":0.06305195217209365,"g_bind_frac":0.21246458923512748,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":347,"n_valid":347,"parse_rate":1.0,"reason":-0.0002937747967380409,"mean_b":0.03079284131056146,"b_gate_pass_rate":0.4911591355599214,"median_len_z":583.0,"mean_r_leg":0.005128779155248856,"mean_g_leg":0.06601313513436215,"g_bind_frac":0.1729106628242075,"a_match":0.11143410852713179,"a_match_n":344,"a_match_centered":-0.04437869822485207}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T15:47:55.747616+00:00","challenge_id":"chal-00701","repo":"r2://affine-private-models/models/registrations/a21105e5852ccf6cb7885eeb758f6c75f010d737b1e15cec812dc560ec878cc1/","hotkey":"5GhdjLtoRvzCE4366pcf3xPy7ZFhtpNnvT6rCS4sNxbZgs2M","uid":229,"duration_s":2601.4,"revision":"0c37703358909e5f2d6bab80949960f1e2738b455988d47be8a26d5cf8728610","accepted":false,"error_code":null,"error_detail":"","z":-4.116008706410196,"margin":-0.1797722676075681,"se":0.043676357469213827,"n_paired_turns":993,"n_forfeit_turns":21,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":16695929002303104403,"n":1000,"digest":"b56a1294016fe86c6086e5fd206d956bc2df26a690e165add61286ea47ce036f","n_paired_turns":993,"n_forfeit_turns":21,"margin":-0.1797722676075681,"se":0.043676357469213827,"z":-4.116008706410196,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":0.95,"n":20,"by_reason":{"no_think_close":1},"by_prompt":{"assistant_bash":{"ok":false,"reasons":["no_think_close"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.1797722676075681,"se":0.043676357469213827,"z":-4.116008706410196,"sd_diff":1.3763251187005563,"n_paired_turns":993,"n_forfeit_turns":21,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.008776615280683782,"A":6.582737217538429,"Mc":0.1832025208628963},"bash":{"R":0.027922996421179465,"A":6.24762123747654,"Mc":0.14718341663963},"text":{"R":0.03997458542803353,"A":35.75817214875265,"Mc":0.172924748322419},"boxed":{"R":0.11243502443647735,"A":6.2669059372515745,"Mc":0.11604259012787348},"terminus_json":{"R":0.0016609012439958728,"A":11.714042331285277,"Mc":0.16491423119842766}},"challenger":{"mean":-0.756488198942714,"mean_valid":-0.6324133312222227,"sd_valid":1.3088315421991599,"n_turns":998,"n_valid":972,"n_forfeits":23,"n_unscorable":3,"mean_z_R":0.1083142088735784,"mean_typ_c":0.5868015533701014,"mean_z_A":-0.04749476627987904,"bind_frac":{"R":0.3405349794238683,"Gc":0.18415637860082304,"A":0.47530864197530864},"n_leg_dropped":{"R":1,"Gc":38,"A":1},"mean_content_share":0.30053460478470334,"mean_R":0.014203053496194615,"mean_A":1.6733356194843052,"mean_mc":-0.6906713421778111},"king":{"mean":-0.5661549810812542,"mean_valid":-0.5496887840542276,"sd_valid":1.15553186386275,"n_turns":998,"n_valid":990,"n_forfeits":3,"n_unscorable":5,"mean_z_R":0.13727974549060895,"mean_typ_c":0.6719083381174051,"mean_z_A":-0.023918706785136593,"bind_frac":{"R":0.3484848484848485,"Gc":0.1787878787878788,"A":0.4727272727272727},"n_leg_dropped":{"R":1,"Gc":47,"A":1},"mean_content_share":0.28682902603047516,"mean_R":0.015233061788508877,"mean_A":1.7041449867280463,"mean_mc":-0.6883533306424978}},"rejection_reason":null,"reign_number":null,"score":-7.724334463755452e-05,"score_king":0.002777697788122511,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9152710,"blocks_since_crown":29400,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1592.0885733603786,"mean_len_y":751.6646382691007,"n_samples":3000,"think_close_rate":0.9633333333333334,"n_text_fallback":25,"by_dialect":{"bash":{"n_turns":229,"zero_ref_turns":0,"mean_refs":2.982532751091703,"ref_pair_agreement":0.16739446870451238,"ref_pair_n":229},"text":{"n_turns":388,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":306,"zero_ref_turns":1,"mean_refs":2.9444444444444446,"ref_pair_agreement":0.14864864864864866,"ref_pair_n":296},"boxed":{"n_turns":48,"zero_ref_turns":1,"mean_refs":2.7291666666666665,"ref_pair_agreement":0.446969696969697,"ref_pair_n":44},"terminus_json":{"n_turns":29,"zero_ref_turns":0,"mean_refs":2.7241379310344827,"ref_pair_agreement":0.37037037037037035,"ref_pair_n":27}},"ref_pair_agreement":0.18791946308724833,"ref_pair_n":596},"duel_seconds":2223.580788483843,"challenger":{"reason":-7.724334463755452e-05,"n_turns":998,"n_pairs":2895,"n_forfeits":23,"forfeit_rate":0.023046092184368736,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":2.9893582181811826,"mean_len_z":1209.660103626943,"median_len_z":565.0,"mean_len_y":415.85354058721936,"mean_b":0.10040032177985869,"b_gate_pass_rate":0.49844559585492226,"mean_r_leg":0.014203053496194615,"mean_g_leg":0.05734749091468527,"g_bind_frac":0.24512820512820513,"a_match":0.1635698198198198,"a_match_n":592,"a_match_centered":-0.021899886234357225,"n_turns_cap_raised":64,"mean_cap_tokens":4165.055110220441,"max_cap_tokens":6055,"len_z_delta":-382.4284697334356,"len_y_delta":-335.81109768188134,"n_samples":1001,"think_close_rate":0.977022977022977,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":229,"n_valid":228,"parse_rate":0.9956331877729258,"reason":0.010516454621990187,"mean_b":0.12213724976999026,"b_gate_pass_rate":0.8441176470588235,"median_len_z":391.0,"mean_r_leg":0.023839801565257245,"mean_g_leg":0.05033134768462569,"g_bind_frac":0.2894736842105263,"a_match":0.1154970760233918,"a_match_n":228,"a_match_centered":-0.05263157894736842},"boxed":{"n_turns":47,"n_valid":42,"parse_rate":0.8936170212765957,"reason":-0.006558555456043037,"mean_b":0.9394808756345822,"b_gate_pass_rate":0.4672131147540984,"median_len_z":2436.0,"mean_r_leg":0.08355798517833231,"mean_g_leg":0.011609398762596904,"g_bind_frac":0.7142857142857143,"a_match":0.540650406504065,"a_match_n":41,"a_match_centered":0.0625},"terminus_json":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":-0.006362772681069218,"mean_b":0.02119927047655909,"b_gate_pass_rate":0.3670886075949367,"median_len_z":665.0,"mean_r_leg":0.001545205947420415,"mean_g_leg":0.050024911084167206,"g_bind_frac":0.20689655172413793,"a_match":0.367816091954023,"a_match_n":29,"a_match_centered":0.024691358024691353},"text":{"n_turns":388,"n_valid":372,"parse_rate":0.9587628865979382,"reason":-0.005197157326439752,"mean_b":0.06065007122481965,"b_gate_pass_rate":0.3763440860215054,"median_len_z":740.5,"mean_r_leg":0.007879713657449737,"mean_g_leg":0.058539931780139026,"g_bind_frac":0.21774193548387097,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":305,"n_valid":304,"parse_rate":0.9967213114754099,"reason":7.840193593318581e-05,"mean_b":0.026312598025759037,"b_gate_pass_rate":0.4042316258351893,"median_len_z":459.0,"mean_r_leg":0.006338824247942918,"mean_g_leg":0.06816804137513766,"g_bind_frac":0.18421052631578946,"a_match":0.12811791383219953,"a_match_n":294,"a_match_centered":-0.013745704467353952}}},"king":{"reason":0.002777697788122511,"n_turns":998,"n_pairs":2950,"n_forfeits":3,"forfeit_rate":0.003006012024048096,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":0.9117904037861432,"mean_len_z":1007.5722033898305,"median_len_z":702.0,"mean_len_y":365.0457627118644,"mean_b":0.10369327379534511,"b_gate_pass_rate":0.5559322033898305,"mean_r_leg":0.015233061788508877,"mean_g_leg":0.05863844209900954,"g_bind_frac":0.23316582914572864,"a_match":0.16249304396215913,"a_match_n":599,"a_match_centered":-0.022484541877459248,"n_turns_cap_raised":64,"mean_cap_tokens":4165.055110220441,"max_cap_tokens":6055,"len_z_delta":-584.5163699705481,"len_y_delta":-386.61887555723627,"n_samples":998,"think_close_rate":0.996993987975952,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":229,"n_valid":229,"parse_rate":1.0,"reason":0.011864828000566445,"mean_b":0.12378655711957161,"b_gate_pass_rate":0.8814055636896047,"median_len_z":488.0,"mean_r_leg":0.02277289070618601,"mean_g_leg":0.05150874133354745,"g_bind_frac":0.3056768558951965,"a_match":0.13537117903930132,"a_match_n":229,"a_match_centered":-0.03202328966521106},"boxed":{"n_turns":47,"n_valid":46,"parse_rate":0.9787234042553191,"reason":0.0077874050678972745,"mean_b":0.910595276683953,"b_gate_pass_rate":0.7209302325581395,"median_len_z":2118.0,"mean_r_leg":0.06685907418961974,"mean_g_leg":0.01886815062691156,"g_bind_frac":0.6521739130434783,"a_match":0.42045454545454547,"a_match_n":44,"a_match_centered":-0.027131782945736437},"terminus_json":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":-0.007663020682801173,"mean_b":0.025299428895665492,"b_gate_pass_rate":0.35443037974683544,"median_len_z":882.0,"mean_r_leg":0.001404944842048625,"mean_g_leg":0.04580834315410309,"g_bind_frac":0.3103448275862069,"a_match":0.37356321839080464,"a_match_n":29,"a_match_centered":0.030864197530864196},"text":{"n_turns":388,"n_valid":386,"parse_rate":0.9948453608247423,"reason":-0.0015542139794769024,"mean_b":0.06518232732106786,"b_gate_pass_rate":0.4170984455958549,"median_len_z":847.5,"mean_r_leg":0.012121108109594787,"mean_g_leg":0.05981610272126402,"g_bind_frac":0.17098445595854922,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":305,"n_valid":305,"parse_rate":1.0,"reason":0.0016863979215201638,"mean_b":0.029303394640195976,"b_gate_pass_rate":0.4816870144284129,"median_len_z":553.0,"mean_r_leg":0.0070390031619810825,"mean_g_leg":0.06971919866366326,"g_bind_frac":0.18688524590163935,"a_match":0.12457912457912458,"a_match_n":297,"a_match_centered":-0.01927437641723356}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T15:03:24.564397+00:00","challenge_id":"chal-00700","repo":"r2://affine-private-models/models/registrations/e4d0e7f394bea8188aebc45eca1e16d4428e457de45a3fbdd6ab3b68bfb6e267/","hotkey":"5DdGqmnoKqtqT3HTFDnkUiM7gBUXMQFdpzuzqhGYWcZEzjrC","uid":27,"duration_s":2530.4,"revision":"4d59585190b7d567c538683e4c3d07b8fad834247f2b1d3185b364bcc9f15b3e","accepted":false,"error_code":null,"error_detail":"","z":0.23270445838487694,"margin":0.008677314925487093,"se":0.037288993024514466,"n_paired_turns":982,"n_forfeit_turns":9,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":1760077271757576608,"n":1000,"digest":"ae9abed84eda66c7ec699dee69d2c4233339ca75da5450e14edfc71c2e5e387e","n_paired_turns":982,"n_forfeit_turns":9,"margin":0.008677314925487093,"se":0.037288993024514466,"z":0.23270445838487694,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.008677314925487093,"se":0.037288993024514466,"z":0.23270445838487694,"sd_diff":1.1685206710915332,"n_paired_turns":982,"n_forfeit_turns":9,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.008333437758301483,"A":5.400465580853601,"Mc":0.17253497425249623},"text":{"R":0.056503553505782594,"A":20.196504148970053,"Mc":0.15006053490301494},"bash":{"R":0.033411849326941266,"A":6.290547648469895,"Mc":0.160144401686641},"boxed":{"R":0.14699416805548707,"A":6.215869765769327,"Mc":0.11768475314811967},"terminus_json":{"R":0.0018965426182564727,"A":7.8702083658248485,"Mc":0.11315105597581586}},"challenger":{"mean":-0.7074839231368795,"mean_valid":-0.6694863718158109,"sd_valid":1.384646720688736,"n_turns":992,"n_valid":975,"n_forfeits":7,"n_unscorable":10,"mean_z_R":0.1573099586871494,"mean_typ_c":0.6057582926265991,"mean_z_A":-0.09801229693414931,"bind_frac":{"R":0.36615384615384616,"Gc":0.16923076923076924,"A":0.4646153846153846},"n_leg_dropped":{"R":1,"Gc":44,"A":1},"mean_content_share":0.2832631200073855,"mean_R":0.021342081640334343,"mean_A":2.0343106397290525,"mean_mc":-0.6601925041629216},"king":{"mean":-0.7161612380623666,"mean_valid":-0.6891200980319795,"sd_valid":1.5502332085814576,"n_turns":992,"n_valid":977,"n_forfeits":5,"n_unscorable":10,"mean_z_R":0.1772520896372014,"mean_typ_c":0.5396595177783593,"mean_z_A":-0.0972358038690702,"bind_frac":{"R":0.3203684749232344,"Gc":0.1811668372569089,"A":0.4984646878198567},"n_leg_dropped":{"R":1,"Gc":45,"A":1},"mean_content_share":0.27678798053038395,"mean_R":0.019770084819413766,"mean_A":1.4825746700459663,"mean_mc":-0.6804605744721244}},"rejection_reason":null,"reign_number":null,"score":0.002324789363111151,"score_king":0.0018580784383219436,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9152494,"blocks_since_crown":29184,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1540.4135466303608,"mean_len_y":794.9948944860449,"n_samples":3000,"think_close_rate":0.9536666666666667,"n_text_fallback":14,"by_dialect":{"bash":{"n_turns":230,"zero_ref_turns":2,"mean_refs":2.9260869565217393,"ref_pair_agreement":0.15634218289085547,"ref_pair_n":226},"text":{"n_turns":393,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":302,"zero_ref_turns":2,"mean_refs":2.9304635761589406,"ref_pair_agreement":0.18036529680365296,"ref_pair_n":292},"terminus_json":{"n_turns":21,"zero_ref_turns":1,"mean_refs":2.857142857142857,"ref_pair_agreement":0.5833333333333333,"ref_pair_n":20},"boxed":{"n_turns":54,"zero_ref_turns":3,"mean_refs":2.611111111111111,"ref_pair_agreement":0.44202898550724634,"ref_pair_n":46}},"ref_pair_agreement":0.2054794520547945,"ref_pair_n":584},"duel_seconds":2156.323369402904,"challenger":{"reason":0.002324789363111151,"n_turns":992,"n_pairs":2917,"n_forfeits":7,"forfeit_rate":0.007056451612903226,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.076158891778637,"mean_len_z":1083.1775797051766,"median_len_z":687.0,"mean_len_y":449.2039766883785,"mean_b":0.10693749353510207,"b_gate_pass_rate":0.5193692149468632,"mean_r_leg":0.021342081640334343,"mean_g_leg":0.058965918528682285,"g_bind_frac":0.2416243654822335,"a_match":0.16186440677966102,"a_match_n":590,"a_match_centered":-0.04864709268854347,"n_turns_cap_raised":55,"mean_cap_tokens":4152.945564516129,"max_cap_tokens":6017,"len_z_delta":-457.23596692518413,"len_y_delta":-345.79091779766645,"n_samples":995,"think_close_rate":0.992964824120603,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":228,"n_valid":228,"parse_rate":1.0,"reason":0.008063816724319748,"mean_b":0.12592053407178988,"b_gate_pass_rate":0.8588410104011887,"median_len_z":486.0,"mean_r_leg":0.024413859598779,"mean_g_leg":0.05072397512117098,"g_bind_frac":0.3201754385964912,"a_match":0.1154970760233918,"a_match_n":228,"a_match_centered":-0.03982300884955752},"boxed":{"n_turns":51,"n_valid":51,"parse_rate":1.0,"reason":0.008925035049164766,"mean_b":0.9659181367718745,"b_gate_pass_rate":0.6737588652482269,"median_len_z":2338.0,"mean_r_leg":0.12702649053796233,"mean_g_leg":0.020067610416547452,"g_bind_frac":0.7254901960784313,"a_match":0.42857142857142855,"a_match_n":49,"a_match_centered":-0.06818181818181818},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.006904822495270149,"mean_b":0.01888203452295453,"b_gate_pass_rate":0.35,"median_len_z":628.0,"mean_r_leg":0.0003331654463122808,"mean_g_leg":0.031193504398299366,"g_bind_frac":0.25,"a_match":0.5666666666666667,"a_match_n":20,"a_match_centered":-0.016666666666666666},"text":{"n_turns":393,"n_valid":386,"parse_rate":0.9821882951653944,"reason":-0.0012767585830780921,"mean_b":0.05918251623215887,"b_gate_pass_rate":0.37305699481865284,"median_len_z":805.0,"mean_r_leg":0.019207713199471517,"mean_g_leg":0.05940467040088343,"g_bind_frac":0.19430051813471502,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":300,"n_valid":300,"parse_rate":1.0,"reason":0.0021744220686968304,"mean_b":0.024103294981385998,"b_gate_pass_rate":0.43954802259887005,"median_len_z":590.0,"mean_r_leg":0.0051879960194979495,"mean_g_leg":0.07312947476391386,"g_bind_frac":0.16,"a_match":0.12571103526734928,"a_match_n":293,"a_match_centered":-0.05478662053056517}}},"king":{"reason":0.0018580784383219436,"n_turns":992,"n_pairs":2923,"n_forfeits":5,"forfeit_rate":0.005040322580645161,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.0613808961655167,"mean_len_z":1073.1279507355457,"median_len_z":690.0,"mean_len_y":379.1919261033185,"mean_b":0.11088909644736994,"b_gate_pass_rate":0.5354088265480671,"mean_r_leg":0.019770084819413766,"mean_g_leg":0.05738514268186926,"g_bind_frac":0.2512664640324215,"a_match":0.1607644744238336,"a_match_n":593,"a_match_centered":-0.0441008018327606,"n_turns_cap_raised":55,"mean_cap_tokens":4152.945564516129,"max_cap_tokens":6017,"len_z_delta":-467.28559589481506,"len_y_delta":-415.8029683827264,"n_samples":992,"think_close_rate":0.9949596774193549,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":228,"n_valid":228,"parse_rate":1.0,"reason":0.008266044902800213,"mean_b":0.12847708972889532,"b_gate_pass_rate":0.8632986627043091,"median_len_z":518.0,"mean_r_leg":0.02486057117685061,"mean_g_leg":0.051567293383908225,"g_bind_frac":0.2982456140350877,"a_match":0.1111111111111111,"a_match_n":228,"a_match_centered":-0.04424778761061947},"boxed":{"n_turns":51,"n_valid":51,"parse_rate":1.0,"reason":0.008629722286608622,"mean_b":0.9941222324641459,"b_gate_pass_rate":0.723404255319149,"median_len_z":2194.0,"mean_r_leg":0.10386560989054186,"mean_g_leg":0.020835580932939093,"g_bind_frac":0.6862745098039216,"a_match":0.39666666666666667,"a_match_n":50,"a_match_centered":-0.05555555555555555},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.007473923631363243,"mean_b":0.019408564684576458,"b_gate_pass_rate":0.25,"median_len_z":591.5,"mean_r_leg":0.0005440262114099451,"mean_g_leg":0.027508173811637306,"g_bind_frac":0.2,"a_match":0.5666666666666667,"a_match_n":20,"a_match_centered":-0.016666666666666666},"text":{"n_turns":393,"n_valid":388,"parse_rate":0.9872773536895675,"reason":-0.0020336732236522033,"mean_b":0.061213595795949954,"b_gate_pass_rate":0.38144329896907214,"median_len_z":799.5,"mean_r_leg":0.01722782248821326,"mean_g_leg":0.05695726295900341,"g_bind_frac":0.22422680412371135,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":300,"n_valid":300,"parse_rate":1.0,"reason":0.0015571726196082017,"mean_b":0.028333755212554684,"b_gate_pass_rate":0.47796610169491527,"median_len_z":599.0,"mean_r_leg":0.006174805781222902,"mean_g_leg":0.07056532267855975,"g_bind_frac":0.18,"a_match":0.13163841807909604,"a_match_n":295,"a_match_centered":-0.0441008018327606}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T14:20:05.469514+00:00","challenge_id":"chal-00699","repo":"r2://affine-private-models/models/registrations/f8cc6b817178aad8b5427305906a828e002938d3953a74d07c58d7d7aa32fa5b/","hotkey":"5D49kDjJL964sAyBEBpqLyx98xEvcSCaLaPGQXCmncPxaeVs","uid":159,"duration_s":2570.6,"revision":"771383395ebcb2b3526bc501b89c319571ea68d99d83a5b0fd7291898a4d2bc4","accepted":false,"error_code":null,"error_detail":"","z":-0.4124536018714298,"margin":-0.012398456080103336,"se":0.030060244410153526,"n_paired_turns":985,"n_forfeit_turns":10,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":8291670597854911602,"n":1000,"digest":"264bae689e3e1b2476b8ac71917c32df9ff4f42cdbfe249a7e63d614b19a5cbf","n_paired_turns":985,"n_forfeit_turns":10,"margin":-0.012398456080103336,"se":0.030060244410153526,"z":-0.4124536018714298,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.012398456080103336,"se":0.030060244410153526,"z":-0.4124536018714298,"sd_diff":0.9434320429093945,"n_paired_turns":985,"n_forfeit_turns":10,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.0077611297939163965,"A":7.08882403273158,"Mc":0.19420629708828055},"text":{"R":0.02698225537460833,"A":36.90065632494195,"Mc":0.15568413811011048},"bash":{"R":0.02227440308385707,"A":7.335340689469012,"Mc":0.1416699892370434},"boxed":{"R":0.09176133095861495,"A":3.7138755211504932,"Mc":0.11605178270221383},"terminus_json":{"R":0.0059746775393677,"A":17.154124640284675,"Mc":0.10997476960127386}},"challenger":{"mean":-0.611028517905935,"mean_valid":-0.5613351333374447,"sd_valid":1.2650886114672435,"n_turns":994,"n_valid":976,"n_forfeits":9,"n_unscorable":9,"mean_z_R":0.2920374198715108,"mean_typ_c":0.6459329961440438,"mean_z_A":-0.05562484134109547,"bind_frac":{"R":0.3422131147540984,"Gc":0.1711065573770492,"A":0.48668032786885246},"n_leg_dropped":{"R":0,"Gc":45,"A":0},"mean_content_share":0.28551394065917335,"mean_R":0.01641516878692902,"mean_A":2.6636965663278596,"mean_mc":-0.6625504074093058},"king":{"mean":-0.5986300618258317,"mean_valid":-0.5821289316684768,"sd_valid":1.2517054338053115,"n_turns":994,"n_valid":982,"n_forfeits":3,"n_unscorable":9,"mean_z_R":0.25060829371409615,"mean_typ_c":0.628886946686608,"mean_z_A":-0.08388131201963377,"bind_frac":{"R":0.3095723014256619,"Gc":0.17820773930753564,"A":0.5122199592668024},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.2763052044101392,"mean_R":0.015098368694648158,"mean_A":2.193036970101116,"mean_mc":-0.6698109395702989}},"rejection_reason":null,"reign_number":null,"score":0.0030184994378575844,"score_king":0.0020704744388637428,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9152274,"blocks_since_crown":28964,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1487.68,"mean_len_y":898.368813559322,"n_samples":3000,"think_close_rate":0.9553333333333334,"n_text_fallback":28,"by_dialect":{"tool_call":{"n_turns":302,"zero_ref_turns":2,"mean_refs":2.947019867549669,"ref_pair_agreement":0.1718931475029036,"ref_pair_n":287},"text":{"n_turns":401,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":223,"zero_ref_turns":0,"mean_refs":2.9730941704035874,"ref_pair_agreement":0.2066365007541478,"ref_pair_n":221},"boxed":{"n_turns":54,"zero_ref_turns":4,"mean_refs":2.574074074074074,"ref_pair_agreement":0.6363636363636364,"ref_pair_n":44},"terminus_json":{"n_turns":20,"zero_ref_turns":0,"mean_refs":2.75,"ref_pair_agreement":0.22807017543859648,"ref_pair_n":19}},"ref_pair_agreement":0.2230005837711617,"ref_pair_n":571},"duel_seconds":2160.4626921280287,"challenger":{"reason":0.0030184994378575844,"n_turns":994,"n_pairs":2923,"n_forfeits":9,"forfeit_rate":0.009054325955734407,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":12.147873254505056,"mean_len_z":1129.6363325350667,"median_len_z":594.0,"mean_len_y":416.5176188847075,"mean_b":0.10783437812470743,"b_gate_pass_rate":0.5001710571330824,"mean_r_leg":0.01641516878692902,"mean_g_leg":0.059193921278713736,"g_bind_frac":0.2131979695431472,"a_match":0.1703767123287671,"a_match_n":584,"a_match_centered":-0.050673696543643815,"n_turns_cap_raised":52,"mean_cap_tokens":4152.36921529175,"max_cap_tokens":6028,"len_z_delta":-358.0436674649334,"len_y_delta":-481.85119467461453,"n_samples":997,"think_close_rate":0.9909729187562688,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":223,"n_valid":222,"parse_rate":0.9955156950672646,"reason":0.00874805363173331,"mean_b":0.11913053148181475,"b_gate_pass_rate":0.8287878787878787,"median_len_z":491.0,"mean_r_leg":0.01843029165474579,"mean_g_leg":0.04160310670902774,"g_bind_frac":0.28378378378378377,"a_match":0.13963963963963963,"a_match_n":222,"a_match_centered":-0.06666666666666667},"boxed":{"n_turns":50,"n_valid":50,"parse_rate":1.0,"reason":0.010318131447018191,"mean_b":0.9951704746057443,"b_gate_pass_rate":0.7122302158273381,"median_len_z":2104.0,"mean_r_leg":0.07345595805376051,"mean_g_leg":0.02251678050244997,"g_bind_frac":0.62,"a_match":0.5748299319727891,"a_match_n":49,"a_match_centered":-0.04166666666666667},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0030975049132561504,"mean_b":0.027859106878546872,"b_gate_pass_rate":0.5272727272727272,"median_len_z":705.0,"mean_r_leg":0.0017586456228978525,"mean_g_leg":0.03434678923327199,"g_bind_frac":0.15,"a_match":0.2833333333333333,"a_match_n":20,"a_match_centered":0.07017543859649122},"text":{"n_turns":401,"n_valid":393,"parse_rate":0.9800498753117207,"reason":-0.0013828045283128044,"mean_b":0.05961984592801711,"b_gate_pass_rate":0.361323155216285,"median_len_z":706.0,"mean_r_leg":0.016066017617354225,"mean_g_leg":0.06195351863538041,"g_bind_frac":0.178117048346056,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":300,"n_valid":300,"parse_rate":1.0,"reason":0.0038337354104051955,"mean_b":0.029686507059406064,"b_gate_pass_rate":0.40561797752808987,"median_len_z":512.0,"mean_r_leg":0.006851669230017753,"mean_g_leg":0.07636538378878811,"g_bind_frac":0.14333333333333334,"a_match":0.11831626848691694,"a_match_n":293,"a_match_centered":-0.047785547785547784}}},"king":{"reason":0.0020704744388637428,"n_turns":994,"n_pairs":2941,"n_forfeits":3,"forfeit_rate":0.0030181086519114686,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":27.332267912425117,"mean_len_z":1058.1870112206732,"median_len_z":668.0,"mean_len_y":351.97993879632776,"mean_b":0.11853368141758074,"b_gate_pass_rate":0.5413124787487249,"mean_r_leg":0.015098368694648158,"mean_g_leg":0.0571275991107052,"g_bind_frac":0.23814328960645811,"a_match":0.16238584474885845,"a_match_n":584,"a_match_centered":-0.05721830985915493,"n_turns_cap_raised":52,"mean_cap_tokens":4152.36921529175,"max_cap_tokens":6028,"len_z_delta":-429.4929887793269,"len_y_delta":-546.3888747629942,"n_samples":994,"think_close_rate":0.9969818913480886,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":223,"n_valid":223,"parse_rate":1.0,"reason":0.008426976652263909,"mean_b":0.12745867724345525,"b_gate_pass_rate":0.8491704374057315,"median_len_z":517.0,"mean_r_leg":0.01786316028641424,"mean_g_leg":0.041584219551092566,"g_bind_frac":0.3094170403587444,"a_match":0.14499252615844546,"a_match_n":223,"a_match_centered":-0.06033182503770739},"boxed":{"n_turns":50,"n_valid":50,"parse_rate":1.0,"reason":0.006679215110643494,"mean_b":1.0432334199804159,"b_gate_pass_rate":0.8489208633093526,"median_len_z":2043.0,"mean_r_leg":0.07967544508578156,"mean_g_leg":0.01846927730729526,"g_bind_frac":0.68,"a_match":0.5272108843537415,"a_match_n":49,"a_match_centered":-0.09469696969696971},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0023002079803796254,"mean_b":0.024951486161062242,"b_gate_pass_rate":0.509090909090909,"median_len_z":818.0,"mean_r_leg":0.0016580684868891756,"mean_g_leg":0.030640242491701258,"g_bind_frac":0.1,"a_match":0.2833333333333333,"a_match_n":20,"a_match_centered":0.07017543859649122},"text":{"n_turns":401,"n_valid":398,"parse_rate":0.9925187032418953,"reason":-0.002476258112657779,"mean_b":0.07485966494070972,"b_gate_pass_rate":0.39195979899497485,"median_len_z":832.0,"mean_r_leg":0.01186328298520243,"mean_g_leg":0.05964183170822635,"g_bind_frac":0.20100502512562815,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":300,"n_valid":300,"parse_rate":1.0,"reason":0.00294619568675632,"mean_b":0.03184071570938256,"b_gate_pass_rate":0.46629213483146065,"median_len_z":586.0,"mean_r_leg":0.007468261267961736,"mean_g_leg":0.07355484007914112,"g_bind_frac":0.17,"a_match":0.10616438356164383,"a_match_n":292,"a_match_centered":-0.057511737089201875}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T13:36:08.980832+00:00","challenge_id":"chal-00698","repo":"r2://affine-private-models/models/registrations/51be2c37365e1e8479b517213c3d0a0e46ffb9ebbf7bc62a4de070f9bc44cc51/","hotkey":"5Fw4n66XmRDjNS9CenPR5iANiXxHTEtyr5eDktbYinHd1tZf","uid":19,"duration_s":2480.9,"revision":"01baa2c3a7921f344ba50bebe3d7822e6eea2bf2d1dd10ae90e5f089a75451d8","accepted":false,"error_code":null,"error_detail":"","z":-8.432667007701285,"margin":-0.44921199955930263,"se":0.05327045395591355,"n_paired_turns":981,"n_forfeit_turns":38,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2793618338184664475,"n":1000,"digest":"aa3f4bdea02be7d962f45d7bfbd58d4f460dbc2339d66241254d3e826d23a4b6","n_paired_turns":981,"n_forfeit_turns":38,"margin":-0.44921199955930263,"se":0.05327045395591355,"z":-8.432667007701285,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.44921199955930263,"se":0.05327045395591355,"z":-8.432667007701285,"sd_diff":1.668479601505632,"n_paired_turns":981,"n_forfeit_turns":38,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.0071075688389797545,"A":6.42279131542236,"Mc":0.17539823673324692},"bash":{"R":0.02401007442095402,"A":11.681329390280126,"Mc":0.14785434697919728},"text":{"R":0.05996141505723779,"A":22.351697595027364,"Mc":0.14844224105076012},"terminus_json":{"R":0.0026573339419794003,"A":12.545226616684571,"Mc":0.11939206232522662},"boxed":{"R":0.12182060191160321,"A":4.8450717847833324,"Mc":0.12125152226256523}},"challenger":{"mean":-1.146374549633476,"mean_valid":-0.925053346700538,"sd_valid":1.714225094793195,"n_turns":990,"n_valid":943,"n_forfeits":43,"n_unscorable":4,"mean_z_R":0.07743025599996023,"mean_typ_c":0.19160037531928434,"mean_z_A":-0.15823431325652917,"bind_frac":{"R":0.28844114528101805,"Gc":0.22799575821845175,"A":0.4835630965005302},"n_leg_dropped":{"R":0,"Gc":29,"A":0},"mean_content_share":0.3179123324064903,"mean_R":0.01669289095266028,"mean_A":1.519215957459642,"mean_mc":-0.6783886677803915},"king":{"mean":-0.6724243979316324,"mean_valid":-0.6615406888364979,"sd_valid":1.2926675614904948,"n_turns":990,"n_valid":979,"n_forfeits":2,"n_unscorable":9,"mean_z_R":0.21019888423710736,"mean_typ_c":0.581990593154635,"mean_z_A":-0.1163282116478972,"bind_frac":{"R":0.3115423901940756,"Gc":0.17568947906026558,"A":0.5127681307456589},"n_leg_dropped":{"R":0,"Gc":43,"A":0},"mean_content_share":0.2754314659714691,"mean_R":0.019241305348751132,"mean_A":1.8670706862974573,"mean_mc":-0.6623049190541762}},"rejection_reason":null,"reign_number":null,"score":-0.0031451121596146,"score_king":0.003163251123603174,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9152062,"blocks_since_crown":28752,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1415.492160872529,"mean_len_y":697.5126107702795,"n_samples":3000,"think_close_rate":0.9596666666666667,"n_text_fallback":20,"by_dialect":{"tool_call":{"n_turns":320,"zero_ref_turns":4,"mean_refs":2.928125,"ref_pair_agreement":0.1758957654723127,"ref_pair_n":307},"text":{"n_turns":358,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":252,"zero_ref_turns":3,"mean_refs":2.9325396825396823,"ref_pair_agreement":0.1927710843373494,"ref_pair_n":249},"terminus_json":{"n_turns":23,"zero_ref_turns":0,"mean_refs":2.9565217391304346,"ref_pair_agreement":0.44927536231884063,"ref_pair_n":23},"boxed":{"n_turns":47,"zero_ref_turns":3,"mean_refs":2.4680851063829787,"ref_pair_agreement":0.5833333333333334,"ref_pair_n":36}},"ref_pair_agreement":0.21680216802168023,"ref_pair_n":615},"duel_seconds":2096.093183015939,"challenger":{"reason":-0.0031451121596146,"n_turns":990,"n_pairs":2819,"n_forfeits":43,"forfeit_rate":0.043434343434343436,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":2.3844424457136237,"mean_len_z":1195.0542745654488,"median_len_z":477.0,"mean_len_y":487.1908478183753,"mean_b":0.0916964864250071,"b_gate_pass_rate":0.4707343029443065,"mean_r_leg":0.01669289095266028,"mean_g_leg":0.05300854512931798,"g_bind_frac":0.23020063357972545,"a_match":0.1846240179573513,"a_match_n":594,"a_match_centered":-0.03338992642897567,"n_turns_cap_raised":49,"mean_cap_tokens":4147.60202020202,"max_cap_tokens":6046,"len_z_delta":-220.43788630708013,"len_y_delta":-210.3217629519042,"n_samples":993,"think_close_rate":0.9607250755287009,"n_text_fallback":8,"by_dialect":{"bash":{"n_turns":249,"n_valid":244,"parse_rate":0.9799196787148594,"reason":0.006407869172564011,"mean_b":0.108864743561625,"b_gate_pass_rate":0.8204419889502762,"median_len_z":363.0,"mean_r_leg":0.0198629313115347,"mean_g_leg":0.04735644061605784,"g_bind_frac":0.30327868852459017,"a_match":0.17896174863387976,"a_match_n":244,"a_match_centered":-0.017759562841530057},"boxed":{"n_turns":44,"n_valid":33,"parse_rate":0.75,"reason":-0.018860791589120334,"mean_b":0.8591368329252757,"b_gate_pass_rate":0.3368421052631579,"median_len_z":2264.0,"mean_r_leg":0.1170941766442023,"mean_g_leg":0.021893230600665156,"g_bind_frac":0.5454545454545454,"a_match":0.5,"a_match_n":31,"a_match_centered":-0.10555555555555556},"terminus_json":{"n_turns":23,"n_valid":21,"parse_rate":0.9130434782608695,"reason":-0.009627462362704984,"mean_b":0.020854495443294405,"b_gate_pass_rate":0.42857142857142855,"median_len_z":632.0,"mean_r_leg":0.001215143799462847,"mean_g_leg":0.03105118515185422,"g_bind_frac":0.14285714285714285,"a_match":0.42857142857142855,"a_match_n":21,"a_match_centered":-0.0634920634920635},"text":{"n_turns":358,"n_valid":342,"parse_rate":0.9553072625698324,"reason":-0.007106897619063433,"mean_b":0.07613373719834403,"b_gate_pass_rate":0.2894736842105263,"median_len_z":725.0,"mean_r_leg":0.017524628440563586,"mean_g_leg":0.05057145786976916,"g_bind_frac":0.22514619883040934,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":316,"n_valid":307,"parse_rate":0.9715189873417721,"reason":-0.0035241919306920073,"mean_b":0.020449258163719918,"b_gate_pass_rate":0.4138309549945115,"median_len_z":285.0,"mean_r_leg":0.003513236861350731,"mean_g_leg":0.0650623147806973,"g_bind_frac":0.1498371335504886,"a_match":0.13926174496644295,"a_match_n":298,"a_match_centered":-0.03684807256235828}}},"king":{"reason":0.003163251123603174,"n_turns":990,"n_pairs":2928,"n_forfeits":2,"forfeit_rate":0.00202020202020202,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-36.801204261890526,"mean_len_z":960.1427595628415,"median_len_z":667.0,"mean_len_y":350.0382513661202,"mean_b":0.10948684670902253,"b_gate_pass_rate":0.5273224043715847,"mean_r_leg":0.019241305348751132,"mean_g_leg":0.05669401678965984,"g_bind_frac":0.23785425101214575,"a_match":0.18055555555555555,"a_match_n":624,"a_match_centered":-0.03534529635671561,"n_turns_cap_raised":49,"mean_cap_tokens":4147.60202020202,"max_cap_tokens":6046,"len_z_delta":-455.34940130968744,"len_y_delta":-347.47435940415926,"n_samples":990,"think_close_rate":0.997979797979798,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":249,"n_valid":249,"parse_rate":1.0,"reason":0.010726014902148888,"mean_b":0.13082735692563013,"b_gate_pass_rate":0.8728010825439784,"median_len_z":543.0,"mean_r_leg":0.02423509844854478,"mean_g_leg":0.04896656660897012,"g_bind_frac":0.3172690763052209,"a_match":0.1606425702811245,"a_match_n":249,"a_match_centered":-0.0321285140562249},"boxed":{"n_turns":44,"n_valid":44,"parse_rate":1.0,"reason":0.0064586620495783904,"mean_b":0.9150218779360487,"b_gate_pass_rate":0.7758620689655172,"median_len_z":1947.0,"mean_r_leg":0.06837346533067999,"mean_g_leg":0.020965029598794486,"g_bind_frac":0.6363636363636364,"a_match":0.4689922480620155,"a_match_n":43,"a_match_centered":-0.0787037037037037},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.00037095850159430397,"mean_b":0.019847094304147637,"b_gate_pass_rate":0.3382352941176471,"median_len_z":772.0,"mean_r_leg":0.0011351419297977179,"mean_g_leg":0.04159552611699267,"g_bind_frac":0.08695652173913043,"a_match":0.45652173913043476,"a_match_n":23,"a_match_centered":0.007246376811594201},"text":{"n_turns":358,"n_valid":356,"parse_rate":0.994413407821229,"reason":-0.0004907368188029937,"mean_b":0.083720240504749,"b_gate_pass_rate":0.3455056179775281,"median_len_z":796.5,"mean_r_leg":0.023359984164499213,"mean_g_leg":0.057144224466583224,"g_bind_frac":0.21348314606741572,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.001142011386768229,"mean_b":0.028805457079660316,"b_gate_pass_rate":0.4450373532550694,"median_len_z":564.0,"mean_r_leg":0.005142959080321145,"mean_g_leg":0.06834971895382577,"g_bind_frac":0.15822784810126583,"a_match":0.13592233009708737,"a_match_n":309,"a_match_centered":-0.036065573770491806}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T12:53:43.324711+00:00","challenge_id":"chal-00697","repo":"r2://affine-private-models/models/registrations/0d4141b4670d8315632bcf0cff0c7401cde225d2749d89e7bd91fe305c8346df/","hotkey":"5EgMPCAJZRsZypZe81tLU3e3tyYMsZNNhTWMxfk1HEZqtTAd","uid":77,"duration_s":2699.2,"revision":"43f770e8d742a348233e49e26debc4410ed07d9fa988738cc4a39f92540ab679","accepted":false,"error_code":null,"error_detail":"","z":-2.0385995848479537,"margin":-0.09371552734594019,"se":0.04597054175939599,"n_paired_turns":987,"n_forfeit_turns":15,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":1848223120575745357,"n":1000,"digest":"dba5de3ba8884cfd89a083997b3254d7e9b150b9861f256b4e6986a96cf1a9db","n_paired_turns":987,"n_forfeit_turns":15,"margin":-0.09371552734594019,"se":0.04597054175939599,"z":-2.0385995848479537,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.09371552734594019,"se":0.04597054175939599,"z":-2.0385995848479537,"sd_diff":1.4442361061913975,"n_paired_turns":987,"n_forfeit_turns":15,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"text":{"R":0.17887394578786736,"A":35.86291148322842,"Mc":0.13744960332078135},"bash":{"R":0.017745726440282224,"A":6.681779603490182,"Mc":0.1443660723959977},"tool_call":{"R":0.007985659750651653,"A":6.553971709309615,"Mc":0.17655077232753535},"terminus_json":{"R":0.0023532701387636414,"A":8.653354634126465,"Mc":0.14248124273893495},"boxed":{"R":0.10078677813250533,"A":5.710940688511448,"Mc":0.11492361458421321}},"challenger":{"mean":-0.7030039466296257,"mean_valid":-0.6268664263553082,"sd_valid":1.3485661688423234,"n_turns":993,"n_valid":974,"n_forfeits":14,"n_unscorable":5,"mean_z_R":0.1696640238382022,"mean_typ_c":0.6139933160127716,"mean_z_A":0.007449852329202286,"bind_frac":{"R":0.3757700205338809,"Gc":0.16632443531827515,"A":0.45790554414784396},"n_leg_dropped":{"R":0,"Gc":45,"A":0},"mean_content_share":0.2924315497609066,"mean_R":0.017262279682813107,"mean_A":6.698803836242679,"mean_mc":-0.6626521286964627},"king":{"mean":-0.6039216552985078,"mean_valid":-0.576446714643205,"sd_valid":1.36400690548643,"n_turns":993,"n_valid":982,"n_forfeits":5,"n_unscorable":6,"mean_z_R":0.19999536543978663,"mean_typ_c":0.6054259831433146,"mean_z_A":-0.10723587690470972,"bind_frac":{"R":0.33095723014256617,"Gc":0.17515274949083504,"A":0.4938900203665988},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.27514684749010254,"mean_R":0.019796330014951524,"mean_A":1.644961724186798,"mean_mc":-0.6904342758833836}},"rejection_reason":null,"reign_number":null,"score":0.0005638919295255117,"score_king":0.0007255518488387018,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9151831,"blocks_since_crown":28521,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1334.9486394557823,"mean_len_y":916.587074829932,"n_samples":3000,"think_close_rate":0.9486666666666667,"n_text_fallback":35,"by_dialect":{"tool_call":{"n_turns":333,"zero_ref_turns":1,"mean_refs":2.948948948948949,"ref_pair_agreement":0.16300940438871472,"ref_pair_n":319},"bash":{"n_turns":200,"zero_ref_turns":1,"mean_refs":2.925,"ref_pair_agreement":0.15824915824915825,"ref_pair_n":198},"text":{"n_turns":394,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":49,"zero_ref_turns":4,"mean_refs":2.5510204081632653,"ref_pair_agreement":0.4552845528455285,"ref_pair_n":41},"terminus_json":{"n_turns":24,"zero_ref_turns":1,"mean_refs":2.75,"ref_pair_agreement":0.3939393939393939,"ref_pair_n":22}},"ref_pair_agreement":0.19080459770114944,"ref_pair_n":580},"duel_seconds":2187.416659230832,"challenger":{"reason":0.0005638919295255117,"n_turns":993,"n_pairs":2901,"n_forfeits":14,"forfeit_rate":0.014098690835850957,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-8.581613153290208,"mean_len_z":1054.3274732850741,"median_len_z":570.0,"mean_len_y":441.8583247156153,"mean_b":0.10987326635510904,"b_gate_pass_rate":0.49396759738021373,"mean_r_leg":0.017262279682813107,"mean_g_leg":0.05517263481079348,"g_bind_frac":0.21961184882533197,"a_match":0.17094017094017094,"a_match_n":585,"a_match_centered":-0.019641825534373197,"n_turns_cap_raised":42,"mean_cap_tokens":4140.497482376636,"max_cap_tokens":6040,"len_z_delta":-280.6211661707082,"len_y_delta":-474.7287501143167,"n_samples":996,"think_close_rate":0.9859437751004017,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":199,"n_valid":199,"parse_rate":1.0,"reason":0.009445535511388636,"mean_b":0.11768972546647094,"b_gate_pass_rate":0.864957264957265,"median_len_z":476.0,"mean_r_leg":0.01624304780452538,"mean_g_leg":0.0493413753096061,"g_bind_frac":0.24623115577889448,"a_match":0.13149078726968175,"a_match_n":199,"a_match_centered":-0.026094276094276097},"boxed":{"n_turns":45,"n_valid":43,"parse_rate":0.9555555555555556,"reason":-0.00028038761920708654,"mean_b":1.0178653164500835,"b_gate_pass_rate":0.5327868852459017,"median_len_z":2142.0,"mean_r_leg":0.061375061661002824,"mean_g_leg":0.015450097427753244,"g_bind_frac":0.6511627906976745,"a_match":0.4146341463414634,"a_match_n":41,"a_match_centered":-0.04166666666666667},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.002457631046472973,"mean_b":0.028738987585111234,"b_gate_pass_rate":0.36363636363636365,"median_len_z":668.5,"mean_r_leg":0.002529979006220653,"mean_g_leg":0.03784234806875641,"g_bind_frac":0.21739130434782608,"a_match":0.4057971014492754,"a_match_n":23,"a_match_centered":0.0303030303030303},"text":{"n_turns":394,"n_valid":382,"parse_rate":0.9695431472081218,"reason":-0.0051101277322312105,"mean_b":0.08510283178457333,"b_gate_pass_rate":0.3743455497382199,"median_len_z":688.0,"mean_r_leg":0.02304497060521467,"mean_g_leg":0.050397631424481476,"g_bind_frac":0.21204188481675393,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":332,"n_valid":332,"parse_rate":1.0,"reason":0.0022976397671228585,"mean_b":0.026771557317349544,"b_gate_pass_rate":0.4164969450101833,"median_len_z":493.5,"mean_r_leg":0.006526835411491801,"mean_g_leg":0.07050738672900148,"g_bind_frac":0.1566265060240964,"a_match":0.14751552795031056,"a_match_n":322,"a_match_centered":-0.01629863301787592}}},"king":{"reason":0.0007255518488387018,"n_turns":993,"n_pairs":2925,"n_forfeits":5,"forfeit_rate":0.005035246727089627,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":3.8838705620554532,"mean_len_z":1038.8328205128205,"median_len_z":648.0,"mean_len_y":370.1158974358974,"mean_b":0.11197927283255797,"b_gate_pass_rate":0.5336752136752136,"mean_r_leg":0.019796330014951524,"mean_g_leg":0.05398825713875723,"g_bind_frac":0.23987854251012145,"a_match":0.15506508205998867,"a_match_n":589,"a_match_centered":-0.036395147313691506,"n_turns_cap_raised":42,"mean_cap_tokens":4140.497482376636,"max_cap_tokens":6040,"len_z_delta":-296.1158189429618,"len_y_delta":-546.4711773940346,"n_samples":993,"think_close_rate":0.9949647532729103,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":199,"n_valid":199,"parse_rate":1.0,"reason":0.009185770364650368,"mean_b":0.12892721978287577,"b_gate_pass_rate":0.8769230769230769,"median_len_z":479.0,"mean_r_leg":0.015310353358973142,"mean_g_leg":0.04848811461860521,"g_bind_frac":0.24120603015075376,"a_match":0.11306532663316583,"a_match_n":199,"a_match_centered":-0.04461279461279462},"boxed":{"n_turns":45,"n_valid":45,"parse_rate":1.0,"reason":0.006816926600097695,"mean_b":1.0284084041425845,"b_gate_pass_rate":0.616,"median_len_z":1979.0,"mean_r_leg":0.053656206701306865,"mean_g_leg":0.018480700866039482,"g_bind_frac":0.6222222222222222,"a_match":0.4444444444444445,"a_match_n":42,"a_match_centered":-0.04166666666666667},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0037738816952803686,"mean_b":0.022470357550228953,"b_gate_pass_rate":0.4090909090909091,"median_len_z":482.0,"mean_r_leg":0.0028649560907488022,"mean_g_leg":0.034998532585239786,"g_bind_frac":0.21739130434782608,"a_match":0.391304347826087,"a_match_n":23,"a_match_centered":0.01515151515151515},"text":{"n_turns":394,"n_valid":389,"parse_rate":0.9873096446700508,"reason":-0.0050730680202395045,"mean_b":0.07941662387966612,"b_gate_pass_rate":0.4087403598971722,"median_len_z":791.0,"mean_r_leg":0.029966947955820503,"mean_g_leg":0.04809791169687732,"g_bind_frac":0.2390745501285347,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":332,"n_valid":332,"parse_rate":1.0,"reason":0.002022081521966339,"mean_b":0.029942622483239534,"b_gate_pass_rate":0.4755600814663951,"median_len_z":549.0,"mean_r_leg":0.007151950873121213,"mean_g_leg":0.07031499338997632,"g_bind_frac":0.1897590361445783,"a_match":0.12666666666666665,"a_match_n":325,"a_match_centered":-0.0341745531019979}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-26T06:18:21.306665+00:00","challenge_id":"chal-00696","repo":"r2://affine-private-models/models/registrations/afe925bb724c86ae2ca1396c235ed5b207601769866df001cd0a8541c4ee701f/","hotkey":"5G7Nd1x4765SkgfGmNc1cCyCY5Z8fhvFDHt7z9dHKKq8VA8s","uid":178,"duration_s":2815.1,"revision":"5498a4aa9c3cd02e3639c414623cfb38bdb1dfe6ca488872a3d6497f784e3689","accepted":false,"error_code":null,"error_detail":"","z":-15.815865015252447,"margin":-1.1857243363872951,"se":0.07497056501454777,"n_paired_turns":982,"n_forfeit_turns":31,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":16962367179011265096,"n":1000,"digest":"86169da6a40a9f6753075d864b0d37ff92a15412c95b961dd090a503790d23b5","n_paired_turns":982,"n_forfeit_turns":31,"margin":-1.1857243363872951,"se":0.07497056501454777,"z":-15.815865015252447,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-1.1857243363872951,"se":0.07497056501454777,"z":-15.815865015252447,"sd_diff":2.349343541814548,"n_paired_turns":982,"n_forfeit_turns":31,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.027451514394350427,"A":5.2776981795640685,"Mc":0.15393908752811372},"text":{"R":0.136446050839787,"A":34.356809860885235,"Mc":0.15046203983043835},"tool_call":{"R":0.007005092933573563,"A":5.9552847300325435,"Mc":0.16907690973086756},"terminus_json":{"R":0.0024338002597814254,"A":13.98588652912039,"Mc":0.15212408872672845},"boxed":{"R":0.09172379618979909,"A":6.1200684993535726,"Mc":0.13271879080493254}},"challenger":{"mean":-1.8910856476043831,"mean_valid":-1.7571462733412244,"sd_valid":2.267819546353002,"n_turns":989,"n_valid":951,"n_forfeits":31,"n_unscorable":7,"mean_z_R":0.013599222377699383,"mean_typ_c":-0.9087237485569652,"mean_z_A":-0.175446079516263,"bind_frac":{"R":0.23554153522607782,"Gc":0.41430073606729756,"A":0.3501577287066246},"n_leg_dropped":{"R":0,"Gc":28,"A":0},"mean_content_share":0.32541268198491197,"mean_R":0.01294813935316743,"mean_A":1.8752071059606206,"mean_mc":-0.9337796442937729},"king":{"mean":-0.7053613112170881,"mean_valid":-0.6891366778500312,"sd_valid":1.353642388935726,"n_turns":989,"n_valid":979,"n_forfeits":3,"n_unscorable":7,"mean_z_R":0.1282165200794545,"mean_typ_c":0.6048332106263633,"mean_z_A":-0.1676263329551218,"bind_frac":{"R":0.34831460674157305,"Gc":0.15934627170582227,"A":0.4923391215526047},"n_leg_dropped":{"R":0,"Gc":46,"A":0},"mean_content_share":0.2811984787676001,"mean_R":0.018034587727689542,"mean_A":1.878917136411233,"mean_mc":-0.6949783717575863}},"rejection_reason":null,"reign_number":null,"score":-0.012728495684855375,"score_king":0.0005260926955597693,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9149845,"blocks_since_crown":26535,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1416.8974096796182,"mean_len_y":820.412406271302,"n_samples":3000,"think_close_rate":0.9516666666666667,"n_text_fallback":27,"by_dialect":{"text":{"n_turns":356,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":315,"zero_ref_turns":3,"mean_refs":2.9523809523809526,"ref_pair_agreement":0.1716500553709856,"ref_pair_n":301},"bash":{"n_turns":244,"zero_ref_turns":1,"mean_refs":2.9672131147540983,"ref_pair_agreement":0.18457300275482091,"ref_pair_n":242},"terminus_json":{"n_turns":29,"zero_ref_turns":3,"mean_refs":2.5172413793103448,"ref_pair_agreement":0.29333333333333333,"ref_pair_n":25},"boxed":{"n_turns":56,"zero_ref_turns":4,"mean_refs":2.482142857142857,"ref_pair_agreement":0.553030303030303,"ref_pair_n":44}},"ref_pair_agreement":0.20915032679738563,"ref_pair_n":612},"duel_seconds":2270.474388821982,"challenger":{"reason":-0.012728495684855375,"n_turns":989,"n_pairs":2843,"n_forfeits":31,"forfeit_rate":0.03134479271991911,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":2373.245832621233,"mean_len_z":1222.7868448821666,"median_len_z":458.0,"mean_len_y":469.91136123812873,"mean_b":0.09150284505041621,"b_gate_pass_rate":0.4650017587055927,"mean_r_leg":0.01294813935316743,"mean_g_leg":0.033309577318534206,"g_bind_frac":0.3768267223382046,"a_match":0.16998892580287928,"a_match_n":602,"a_match_centered":-0.03653738055087128,"n_turns_cap_raised":53,"mean_cap_tokens":4153.205257836198,"max_cap_tokens":6075,"len_z_delta":-194.11056479745162,"len_y_delta":-350.5010450331732,"n_samples":992,"think_close_rate":0.96875,"n_text_fallback":8,"by_dialect":{"bash":{"n_turns":243,"n_valid":240,"parse_rate":0.9876543209876543,"reason":-0.019296153024061825,"mean_b":0.09944165407785553,"b_gate_pass_rate":0.7804195804195804,"median_len_z":295.0,"mean_r_leg":0.01570373157547186,"mean_g_leg":0.009497508964984235,"g_bind_frac":0.575,"a_match":0.14166666666666666,"a_match_n":240,"a_match_centered":-0.0404463040446304},"boxed":{"n_turns":52,"n_valid":47,"parse_rate":0.9038461538461539,"reason":-0.010402422633214909,"mean_b":0.7322543231994182,"b_gate_pass_rate":0.29365079365079366,"median_len_z":3123.0,"mean_r_leg":0.06948246157983431,"mean_g_leg":0.005967716769632613,"g_bind_frac":0.6808510638297872,"a_match":0.4407407407407407,"a_match_n":45,"a_match_centered":-0.11538461538461539},"terminus_json":{"n_turns":26,"n_valid":25,"parse_rate":0.9615384615384616,"reason":-0.008110187529930288,"mean_b":0.017999883218864768,"b_gate_pass_rate":0.3,"median_len_z":576.0,"mean_r_leg":0.0012889439718018459,"mean_g_leg":0.03240392148434848,"g_bind_frac":0.16,"a_match":0.24666666666666667,"a_match_n":25,"a_match_centered":-0.04861111111111111},"text":{"n_turns":356,"n_valid":342,"parse_rate":0.9606741573033708,"reason":-0.005941981949605379,"mean_b":0.07547355255267439,"b_gate_pass_rate":0.3391812865497076,"median_len_z":610.0,"mean_r_leg":0.012574603754126237,"mean_g_leg":0.052433106354705473,"g_bind_frac":0.2134502923976608,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":312,"n_valid":304,"parse_rate":0.9743589743589743,"reason":-0.01612942506637841,"mean_b":0.01995795181586694,"b_gate_pass_rate":0.39514348785871967,"median_len_z":317.0,"mean_r_leg":0.003411211002508945,"mean_g_leg":0.03489628230581854,"g_bind_frac":0.375,"a_match":0.1449771689497717,"a_match_n":292,"a_match_centered":-0.021764032073310426}}},"king":{"reason":0.0005260926955597693,"n_turns":989,"n_pairs":2927,"n_forfeits":3,"forfeit_rate":0.003033367037411527,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":1678.6597980890665,"mean_len_z":979.9087803211479,"median_len_z":627.0,"mean_len_y":339.0560300649129,"mean_b":0.11008627624544942,"b_gate_pass_rate":0.5688418175606423,"mean_r_leg":0.018034587727689542,"mean_g_leg":0.05337366913960194,"g_bind_frac":0.23123732251521298,"a_match":0.15749730312837107,"a_match_n":618,"a_match_centered":-0.05191256830601093,"n_turns_cap_raised":53,"mean_cap_tokens":4153.205257836198,"max_cap_tokens":6075,"len_z_delta":-436.98862935847035,"len_y_delta":-481.3563762063891,"n_samples":989,"think_close_rate":0.9969666329625885,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":243,"n_valid":243,"parse_rate":1.0,"reason":0.0068109640125046346,"mean_b":0.11734585118105911,"b_gate_pass_rate":0.8549723756906077,"median_len_z":438.0,"mean_r_leg":0.017561656776205473,"mean_g_leg":0.05132550824727766,"g_bind_frac":0.2716049382716049,"a_match":0.11796982167352536,"a_match_n":243,"a_match_centered":-0.06611570247933884},"boxed":{"n_turns":52,"n_valid":51,"parse_rate":0.9807692307692307,"reason":0.007780675093551694,"mean_b":0.969318392693422,"b_gate_pass_rate":0.7318840579710145,"median_len_z":2035.5,"mean_r_leg":0.08309737367479667,"mean_g_leg":0.018835912511042375,"g_bind_frac":0.6274509803921569,"a_match":0.4479166666666667,"a_match_n":48,"a_match_centered":-0.08914728682170542},"terminus_json":{"n_turns":26,"n_valid":26,"parse_rate":1.0,"reason":-0.002104747009692676,"mean_b":0.02647646111640506,"b_gate_pass_rate":0.4931506849315068,"median_len_z":504.0,"mean_r_leg":0.0011170458251032987,"mean_g_leg":0.037244537139447746,"g_bind_frac":0.19230769230769232,"a_match":0.28846153846153844,"a_match_n":26,"a_match_centered":0.006666666666666665},"text":{"n_turns":356,"n_valid":354,"parse_rate":0.9943820224719101,"reason":-0.00480885760840616,"mean_b":0.07371663443340955,"b_gate_pass_rate":0.4576271186440678,"median_len_z":778.5,"mean_r_leg":0.021511106217349623,"mean_g_leg":0.05085269384533312,"g_bind_frac":0.21468926553672316,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":312,"n_valid":312,"parse_rate":1.0,"reason":0.000728599509134296,"mean_b":0.025030482466530005,"b_gate_pass_rate":0.45483870967741935,"median_len_z":566.0,"mean_r_leg":0.005232948888060504,"mean_g_leg":0.06481889789302024,"g_bind_frac":0.15705128205128205,"a_match":0.1317829457364341,"a_match_n":301,"a_match_centered":-0.04}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-25T15:48:39.117486+00:00","challenge_id":"chal-00695","repo":"r2://affine-private-models/models/registrations/95df9d67070327aea8efac5bdcb942208e67ad6f847053f8954f3495ebd0d575/","hotkey":"5EGcPxC8FUW8pqVtCbA7WpnjTQZyH7vUTnSW9EnJFa4PN7wu","uid":64,"duration_s":2685.6,"revision":"28245cbe29c0982e527048efa285b1bbe968f1a6d7e33273026dbd271ef97376","accepted":false,"error_code":null,"error_detail":"","z":0.6552223051725851,"margin":0.02162758131587287,"se":0.033008005290931265,"n_paired_turns":983,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":13339096925486442094,"n":1000,"digest":"797650f786217ec95b9a14301e4deca8b0048c17eccf9359f70dbd81784799bb","n_paired_turns":983,"n_forfeit_turns":4,"margin":0.02162758131587287,"se":0.033008005290931265,"z":0.6552223051725851,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.02162758131587287,"se":0.033008005290931265,"z":0.6552223051725851,"sd_diff":1.0348944053671765,"n_paired_turns":983,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.008376398701560902,"A":6.343784749860326,"Mc":0.1777078997924721},"text":{"R":0.1048055393835384,"A":26.190117852887326,"Mc":0.14862738199898212},"bash":{"R":0.02756240734055523,"A":5.83134922131898,"Mc":0.15732257470258662},"boxed":{"R":0.10652849874300557,"A":5.3811421715658465,"Mc":0.12145297543794864},"terminus_json":{"R":0.002219445474570163,"A":12.850032640088152,"Mc":0.14445578209938895}},"challenger":{"mean":-0.6044493484018352,"mean_valid":-0.5879323566112286,"sd_valid":1.3419414066176358,"n_turns":992,"n_valid":980,"n_forfeits":3,"n_unscorable":9,"mean_z_R":0.13935735493778054,"mean_typ_c":0.6158223659997402,"mean_z_A":-0.01312296440305321,"bind_frac":{"R":0.36020408163265305,"Gc":0.17653061224489797,"A":0.463265306122449},"n_leg_dropped":{"R":0,"Gc":56,"A":0},"mean_content_share":0.2765418352501473,"mean_R":0.01998505381608011,"mean_A":2.6305597213805902,"mean_mc":-0.6636419728372346},"king":{"mean":-0.6315382336509218,"mean_valid":-0.6151209193807411,"sd_valid":1.401292980056281,"n_turns":992,"n_valid":981,"n_forfeits":3,"n_unscorable":8,"mean_z_R":0.1512777620678145,"mean_typ_c":0.5942130877183203,"mean_z_A":-0.0480303808464269,"bind_frac":{"R":0.327217125382263,"Gc":0.18246687054026503,"A":0.49031600407747195},"n_leg_dropped":{"R":0,"Gc":56,"A":0},"mean_content_share":0.2726905162382487,"mean_R":0.020293418198705723,"mean_A":2.003078994736973,"mean_mc":-0.6819660568790586}},"rejection_reason":null,"reign_number":null,"score":0.0023827721333728237,"score_king":0.002531690346044754,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9145507,"blocks_since_crown":22197,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1579.5846994535518,"mean_len_y":771.8579234972677,"n_samples":3000,"think_close_rate":0.956,"n_text_fallback":40,"by_dialect":{"bash":{"n_turns":229,"zero_ref_turns":2,"mean_refs":2.903930131004367,"ref_pair_agreement":0.1898355754857997,"ref_pair_n":223},"tool_call":{"n_turns":318,"zero_ref_turns":2,"mean_refs":2.9339622641509435,"ref_pair_agreement":0.17,"ref_pair_n":300},"text":{"n_turns":378,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":57,"zero_ref_turns":4,"mean_refs":2.508771929824561,"ref_pair_agreement":0.4296296296296296,"ref_pair_n":45},"terminus_json":{"n_turns":18,"zero_ref_turns":0,"mean_refs":2.9444444444444446,"ref_pair_agreement":0.4444444444444444,"ref_pair_n":18}},"ref_pair_agreement":0.20591581342434587,"ref_pair_n":586},"duel_seconds":2179.9920513830148,"challenger":{"reason":0.0023827721333728237,"n_turns":992,"n_pairs":2919,"n_forfeits":3,"forfeit_rate":0.0030241935483870967,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-21.373242660145088,"mean_len_z":1077.1534772182254,"median_len_z":701.0,"mean_len_y":444.6718054128126,"mean_b":0.10983990589581781,"b_gate_pass_rate":0.49777321000342584,"mean_r_leg":0.01998505381608011,"mean_g_leg":0.05885176248836856,"g_bind_frac":0.23660262891809908,"a_match":0.1574539363484087,"a_match_n":597,"a_match_centered":-0.049086757990867584,"n_turns_cap_raised":66,"mean_cap_tokens":4157.876008064516,"max_cap_tokens":6031,"len_z_delta":-502.43122223532646,"len_y_delta":-327.18611808445513,"n_samples":995,"think_close_rate":0.9969849246231156,"n_text_fallback":13,"by_dialect":{"bash":{"n_turns":227,"n_valid":227,"parse_rate":1.0,"reason":0.007875196569776467,"mean_b":0.10897859133289126,"b_gate_pass_rate":0.8466165413533835,"median_len_z":507.0,"mean_r_leg":0.01817336764761219,"mean_g_leg":0.051181971223267966,"g_bind_frac":0.2643171806167401,"a_match":0.13509544787077826,"a_match_n":227,"a_match_centered":-0.052316890881913304},"boxed":{"n_turns":53,"n_valid":53,"parse_rate":1.0,"reason":0.009369903425832219,"mean_b":0.9697903138843101,"b_gate_pass_rate":0.7482517482517482,"median_len_z":2174.0,"mean_r_leg":0.09885518211710384,"mean_g_leg":0.02116774296967774,"g_bind_frac":0.660377358490566,"a_match":0.445578231292517,"a_match_n":49,"a_match_centered":-0.011363636363636364},"terminus_json":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":0.0011127159504590645,"mean_b":0.013902788944453131,"b_gate_pass_rate":0.20754716981132076,"median_len_z":632.0,"mean_r_leg":0.0019894395700216032,"mean_g_leg":0.057412567452565476,"g_bind_frac":0.1111111111111111,"a_match":0.462962962962963,"a_match_n":18,"a_match_centered":0.018518518518518517},"text":{"n_turns":378,"n_valid":375,"parse_rate":0.9920634920634921,"reason":-0.0016473539896174443,"mean_b":0.0749707000360717,"b_gate_pass_rate":0.34933333333333333,"median_len_z":824.0,"mean_r_leg":0.021857844739730438,"mean_g_leg":0.05577936862838771,"g_bind_frac":0.216,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.0021585644758373625,"mean_b":0.026144717935076615,"b_gate_pass_rate":0.4062165058949625,"median_len_z":569.0,"mean_r_leg":0.0068608779311058726,"mean_g_leg":0.074409828500412,"g_bind_frac":0.17721518987341772,"a_match":0.10946094609460945,"a_match_n":303,"a_match_centered":-0.05629877369007803}}},"king":{"reason":0.002531690346044754,"n_turns":992,"n_pairs":2921,"n_forfeits":3,"forfeit_rate":0.0030241935483870967,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-20.170245780893662,"mean_len_z":1017.3861691201644,"median_len_z":689.0,"mean_len_y":367.4655939746662,"mean_b":0.11394373391678694,"b_gate_pass_rate":0.5515234508729887,"mean_r_leg":0.020293418198705723,"mean_g_leg":0.05889947723169004,"g_bind_frac":0.23154701718907988,"a_match":0.1572379367720466,"a_match_n":601,"a_match_centered":-0.048065984072810014,"n_turns_cap_raised":66,"mean_cap_tokens":4157.876008064516,"max_cap_tokens":6031,"len_z_delta":-562.1985303333875,"len_y_delta":-404.39232952260153,"n_samples":992,"think_close_rate":0.9969758064516129,"n_text_fallback":8,"by_dialect":{"bash":{"n_turns":227,"n_valid":227,"parse_rate":1.0,"reason":0.009189890408347015,"mean_b":0.11459934389139587,"b_gate_pass_rate":0.8706766917293233,"median_len_z":463.0,"mean_r_leg":0.01949407513377754,"mean_g_leg":0.05266439346426778,"g_bind_frac":0.2643171806167401,"a_match":0.1527165932452276,"a_match_n":227,"a_match_centered":-0.034379671150971604},"boxed":{"n_turns":53,"n_valid":52,"parse_rate":0.9811320754716981,"reason":0.010421918550608743,"mean_b":1.0507089451643252,"b_gate_pass_rate":0.823943661971831,"median_len_z":2263.0,"mean_r_leg":0.09710307314778253,"mean_g_leg":0.023578167278400085,"g_bind_frac":0.6923076923076923,"a_match":0.3707482993197279,"a_match_n":49,"a_match_centered":-0.07037037037037036},"terminus_json":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":-0.0007309972707289907,"mean_b":0.020299407377145046,"b_gate_pass_rate":0.4528301886792453,"median_len_z":598.0,"mean_r_leg":0.0019786171425353713,"mean_g_leg":0.05374310307145695,"g_bind_frac":0.1111111111111111,"a_match":0.462962962962963,"a_match_n":18,"a_match_centered":0.018518518518518517},"text":{"n_turns":378,"n_valid":376,"parse_rate":0.9947089947089947,"reason":-0.0016585275439335398,"mean_b":0.07045664185667812,"b_gate_pass_rate":0.39893617021276595,"median_len_z":876.0,"mean_r_leg":0.02226191130670753,"mean_g_leg":0.05540540826196586,"g_bind_frac":0.2047872340425532,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.0016235803160739247,"mean_b":0.028798984206324353,"b_gate_pass_rate":0.47266881028938906,"median_len_z":595.0,"mean_r_leg":0.006929056897405374,"mean_g_leg":0.07364206204269136,"g_bind_frac":0.17088607594936708,"a_match":0.10857763300760044,"a_match_n":307,"a_match_centered":-0.05888888888888889}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-25T07:42:45.181007+00:00","challenge_id":"chal-00694","repo":"r2://affine-private-models/models/registrations/6ad1363ab60c580a569558cb2f07b0504c2b482391763818d2739edec6289f2d/","hotkey":"5H7FaFJ7ebvWBnfNBXP6nXCYg9erGf1z796k8beMe1xjKygE","uid":176,"duration_s":2777.2,"revision":"2d25bb927b50ec53ce889f405e871ca3cc6a4eeb3f085fb9372e215fe9e265d4","accepted":false,"error_code":null,"error_detail":"","z":0.07396257102025255,"margin":0.0024603362364916956,"se":0.0332646121214202,"n_paired_turns":981,"n_forfeit_turns":6,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":7222152838135990550,"n":1000,"digest":"d6056c5b902f1dd0da3a51c37ef4d230f9fbca5904245b19d865d9d493ca6f06","n_paired_turns":981,"n_forfeit_turns":6,"margin":0.0024603362364916956,"se":0.0332646121214202,"z":0.07396257102025255,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.0024603362364916956,"se":0.0332646121214202,"z":0.07396257102025255,"sd_diff":1.0418782393429442,"n_paired_turns":981,"n_forfeit_turns":6,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"text":{"R":0.20906520590169636,"A":42.43428038876734,"Mc":0.15771513977958898},"tool_call":{"R":0.008809274747925271,"A":5.6518453394024135,"Mc":0.1849184312982667},"bash":{"R":0.021157212342145616,"A":6.068243267922199,"Mc":0.13801364499683777},"terminus_json":{"R":0.0008161849760081249,"A":6.811272161885079,"Mc":0.21359401256070815},"boxed":{"R":0.11681756110882867,"A":5.424916705698227,"Mc":0.10705344769036024}},"challenger":{"mean":-0.6955783881321608,"mean_valid":-0.6629357935975895,"sd_valid":1.3570525360718317,"n_turns":990,"n_valid":975,"n_forfeits":6,"n_unscorable":9,"mean_z_R":0.1630435004342209,"mean_typ_c":0.5978700087404328,"mean_z_A":-0.07444526974341209,"bind_frac":{"R":0.37333333333333335,"Gc":0.18769230769230769,"A":0.438974358974359},"n_leg_dropped":{"R":0,"Gc":34,"A":0},"mean_content_share":0.2805763916750169,"mean_R":0.01890757030734618,"mean_A":2.1701867488528825,"mean_mc":-0.6593417538551247},"king":{"mean":-0.6980387243686524,"mean_valid":-0.6817750394740778,"sd_valid":1.4151258296072524,"n_turns":990,"n_valid":978,"n_forfeits":3,"n_unscorable":9,"mean_z_R":0.16648440150248967,"mean_typ_c":0.5806508964875825,"mean_z_A":-0.11989196099643962,"bind_frac":{"R":0.30879345603271985,"Gc":0.19222903885480572,"A":0.49897750511247446},"n_leg_dropped":{"R":0,"Gc":37,"A":0},"mean_content_share":0.2737646125668395,"mean_R":0.020467162641320983,"mean_A":1.5264609469820998,"mean_mc":-0.6839858069452641}},"rejection_reason":null,"reign_number":null,"score":0.0005504208629200374,"score_king":0.0004951549408162249,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9143070,"blocks_since_crown":19760,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1579.6216308427158,"mean_len_y":809.2224496758786,"n_samples":3000,"think_close_rate":0.9573333333333334,"n_text_fallback":9,"by_dialect":{"boxed":{"n_turns":47,"zero_ref_turns":7,"mean_refs":2.404255319148936,"ref_pair_agreement":0.6403508771929824,"ref_pair_n":38},"tool_call":{"n_turns":319,"zero_ref_turns":1,"mean_refs":2.9404388714733543,"ref_pair_agreement":0.19337606837606838,"ref_pair_n":312},"bash":{"n_turns":216,"zero_ref_turns":2,"mean_refs":2.949074074074074,"ref_pair_agreement":0.1884735202492212,"ref_pair_n":214},"text":{"n_turns":387,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":31,"zero_ref_turns":0,"mean_refs":2.6451612903225805,"ref_pair_agreement":0.2839506172839506,"ref_pair_n":27}},"ref_pair_agreement":0.22447828539199097,"ref_pair_n":591},"duel_seconds":2271.8527877349406,"challenger":{"reason":0.0005504208629200374,"n_turns":990,"n_pairs":2913,"n_forfeits":6,"forfeit_rate":0.006060606060606061,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-33.32768548137728,"mean_len_z":1049.4994850669414,"median_len_z":683.0,"mean_len_y":451.8135942327497,"mean_b":0.11096299747815476,"b_gate_pass_rate":0.5214555441125986,"mean_r_leg":0.01890757030734618,"mean_g_leg":0.05691276214820993,"g_bind_frac":0.23780487804878048,"a_match":0.17445742904841402,"a_match_n":599,"a_match_centered":-0.051216751556310135,"n_turns_cap_raised":58,"mean_cap_tokens":4159.079797979798,"max_cap_tokens":6050,"len_z_delta":-530.1221457757745,"len_y_delta":-357.40885544312886,"n_samples":993,"think_close_rate":0.9939577039274925,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":214,"n_valid":214,"parse_rate":1.0,"reason":0.007067004714535195,"mean_b":0.11374158761458247,"b_gate_pass_rate":0.8445839874411303,"median_len_z":490.0,"mean_r_leg":0.020965148849000383,"mean_g_leg":0.04176814354385832,"g_bind_frac":0.3037383177570093,"a_match":0.14953271028037382,"a_match_n":214,"a_match_centered":-0.038940809968847356},"boxed":{"n_turns":40,"n_valid":40,"parse_rate":1.0,"reason":0.005494487390720253,"mean_b":1.0434032052317481,"b_gate_pass_rate":0.6283185840707964,"median_len_z":2583.0,"mean_r_leg":0.05081199839643532,"mean_g_leg":0.021134959784631313,"g_bind_frac":0.525,"a_match":0.6,"a_match_n":40,"a_match_centered":-0.06140350877192983},"terminus_json":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":-0.009979410379353086,"mean_b":0.02119944129173249,"b_gate_pass_rate":0.524390243902439,"median_len_z":657.0,"mean_r_leg":0.0008915815270698126,"mean_g_leg":0.03181085377190053,"g_bind_frac":0.2903225806451613,"a_match":0.23655913978494622,"a_match_n":31,"a_match_centered":-0.01234567901234568},"text":{"n_turns":387,"n_valid":381,"parse_rate":0.9844961240310077,"reason":-0.0036733317418641987,"mean_b":0.08902260960077775,"b_gate_pass_rate":0.3543307086614173,"median_len_z":830.0,"mean_r_leg":0.02628498139298038,"mean_g_leg":0.056208872840493904,"g_bind_frac":0.2178477690288714,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.001709871872996496,"mean_b":0.03132842344624435,"b_gate_pass_rate":0.4925373134328358,"median_len_z":531.5,"mean_r_leg":0.006427076901951119,"mean_g_leg":0.07489515668210862,"g_bind_frac":0.1761006289308176,"a_match":0.131104033970276,"a_match_n":314,"a_match_centered":-0.06182795698924731}}},"king":{"reason":0.0004951549408162249,"n_turns":990,"n_pairs":2922,"n_forfeits":3,"forfeit_rate":0.0030303030303030303,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-33.8832173935356,"mean_len_z":1065.1351813826147,"median_len_z":694.0,"mean_len_y":363.8456536618754,"mean_b":0.11382027382206963,"b_gate_pass_rate":0.5492813141683778,"mean_r_leg":0.020467162641320983,"mean_g_leg":0.05602282910140672,"g_bind_frac":0.24417426545086118,"a_match":0.16444814198557958,"a_match_n":601,"a_match_centered":-0.060631697687535256,"n_turns_cap_raised":58,"mean_cap_tokens":4159.079797979798,"max_cap_tokens":6050,"len_z_delta":-514.4864494601011,"len_y_delta":-445.37679601400316,"n_samples":990,"think_close_rate":0.996969696969697,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":214,"n_valid":214,"parse_rate":1.0,"reason":0.008449179497805622,"mean_b":0.12492019519448766,"b_gate_pass_rate":0.8634222919937206,"median_len_z":498.0,"mean_r_leg":0.02251775180475917,"mean_g_leg":0.0440688111254218,"g_bind_frac":0.29439252336448596,"a_match":0.1277258566978193,"a_match_n":214,"a_match_centered":-0.06074766355140187},"boxed":{"n_turns":40,"n_valid":40,"parse_rate":1.0,"reason":0.006128370002535,"mean_b":1.0886827809042945,"b_gate_pass_rate":0.7610619469026548,"median_len_z":2480.0,"mean_r_leg":0.06970260761161404,"mean_g_leg":0.01957775779180979,"g_bind_frac":0.525,"a_match":0.525,"a_match_n":40,"a_match_centered":-0.14035087719298245},"terminus_json":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":-0.008380745220216992,"mean_b":0.02061079793150711,"b_gate_pass_rate":0.4878048780487805,"median_len_z":679.0,"mean_r_leg":0.0010213672367025014,"mean_g_leg":0.0341041286100414,"g_bind_frac":0.3225806451612903,"a_match":0.22580645161290322,"a_match_n":31,"a_match_centered":-0.02469135802469136},"text":{"n_turns":387,"n_valid":384,"parse_rate":0.9922480620155039,"reason":-0.004776219119338284,"mean_b":0.08542598023311718,"b_gate_pass_rate":0.4088541666666667,"median_len_z":861.0,"mean_r_leg":0.028007018781759842,"mean_g_leg":0.05285884897522069,"g_bind_frac":0.24739583333333334,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.0017142895590783092,"mean_b":0.031862160840169504,"b_gate_pass_rate":0.488272921108742,"median_len_z":574.0,"mean_r_leg":0.005684996037003862,"mean_g_leg":0.07460902653201179,"g_bind_frac":0.16352201257861634,"a_match":0.13765822784810128,"a_match_n":316,"a_match_centered":-0.05395299145299145}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-25T01:36:24.255497+00:00","challenge_id":"chal-00693","repo":"r2://affine-private-models/models/registrations/fa9c325aa933e0020145a8bf16e781c4441eaecdad797100a1a85748b3b2cfa9/","hotkey":"5E4KtsJ459MjZY7K6NgTcswL4AJtrUvSZVX4ReZTiZkxvDtG","uid":192,"duration_s":2665.4,"revision":"e6223086f5a4a2b8cfef86b5baabcb02f759596e4b27c8daa72af5c0793fa67d","accepted":false,"error_code":null,"error_detail":"","z":-2.9823513068250547,"margin":-0.14052911518501324,"se":0.04712024195922694,"n_paired_turns":987,"n_forfeit_turns":19,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":11805315362924427170,"n":1000,"digest":"33ef05faaa292805ca738498669962ef480fbb5d35d4bdf4cafeb859a4d4b81e","n_paired_turns":987,"n_forfeit_turns":19,"margin":-0.14052911518501324,"se":0.04712024195922694,"z":-2.9823513068250547,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.14052911518501324,"se":0.04712024195922694,"z":-2.9823513068250547,"sd_diff":1.480355727069086,"n_paired_turns":987,"n_forfeit_turns":19,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.00850214588831965,"A":5.74706458510963,"Mc":0.16638061884610775},"bash":{"R":0.023039344586368807,"A":6.028011660210125,"Mc":0.1458622472666263},"text":{"R":0.04702475837612789,"A":16.919360087363632,"Mc":0.1589702901187799},"terminus_json":{"R":0.0017717788042426173,"A":8.331238439046016,"Mc":0.18514223117036854},"boxed":{"R":0.0797159662914248,"A":5.6288632007645845,"Mc":0.1041230028070232}},"challenger":{"mean":-0.8142535670175538,"mean_valid":-0.6963956935406801,"sd_valid":1.4079309065198768,"n_turns":993,"n_valid":968,"n_forfeits":22,"n_unscorable":3,"mean_z_R":0.20215961707604513,"mean_typ_c":0.5460644627723653,"mean_z_A":-0.06228253473148462,"bind_frac":{"R":0.35537190082644626,"Gc":0.18078512396694216,"A":0.46384297520661155},"n_leg_dropped":{"R":0,"Gc":33,"A":0},"mean_content_share":0.28832684736863956,"mean_R":0.017237711247526745,"mean_A":2.733693930857861,"mean_mc":-0.6659166060843119},"king":{"mean":-0.657962304619828,"mean_valid":-0.657962304619828,"sd_valid":1.3434444055494903,"n_turns":993,"n_valid":987,"n_forfeits":0,"n_unscorable":6,"mean_z_R":0.2665797162715296,"mean_typ_c":0.6256866745604056,"mean_z_A":-0.11399116202739643,"bind_frac":{"R":0.3292806484295846,"Gc":0.16312056737588654,"A":0.5075987841945289},"n_leg_dropped":{"R":0,"Gc":43,"A":0},"mean_content_share":0.27406390842983036,"mean_R":0.017988712204995254,"mean_A":1.8119690311472252,"mean_mc":-0.6741944211980525}},"rejection_reason":null,"reign_number":null,"score":0.0011759666614689494,"score_king":0.002725270485335925,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9141248,"blocks_since_crown":17938,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1386.2481381178063,"mean_len_y":723.0629654705484,"n_samples":3000,"think_close_rate":0.966,"n_text_fallback":21,"by_dialect":{"tool_call":{"n_turns":321,"zero_ref_turns":3,"mean_refs":2.931464174454829,"ref_pair_agreement":0.19913419913419914,"ref_pair_n":308},"text":{"n_turns":378,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":237,"zero_ref_turns":0,"mean_refs":2.978902953586498,"ref_pair_agreement":0.2245762711864407,"ref_pair_n":236},"terminus_json":{"n_turns":19,"zero_ref_turns":1,"mean_refs":2.789473684210526,"ref_pair_agreement":0.462962962962963,"ref_pair_n":18},"boxed":{"n_turns":45,"zero_ref_turns":3,"mean_refs":2.6666666666666665,"ref_pair_agreement":0.55,"ref_pair_n":40}},"ref_pair_agreement":0.24031007751937983,"ref_pair_n":602},"duel_seconds":2191.735942668747,"challenger":{"reason":0.0011759666614689494,"n_turns":993,"n_pairs":2896,"n_forfeits":22,"forfeit_rate":0.022155085599194362,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.2695158710622514,"mean_len_z":1195.4388812154696,"median_len_z":648.0,"mean_len_y":450.4599447513812,"mean_b":0.09319759749426404,"b_gate_pass_rate":0.4796270718232044,"mean_r_leg":0.017237711247526745,"mean_g_leg":0.05877040027547828,"g_bind_frac":0.223480947476828,"a_match":0.19187675070028012,"a_match_n":595,"a_match_centered":-0.046045197740112995,"n_turns_cap_raised":40,"mean_cap_tokens":4138.915407854985,"max_cap_tokens":6045,"len_z_delta":-190.80925690233676,"len_y_delta":-272.6030207191672,"n_samples":996,"think_close_rate":0.9779116465863453,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":237,"n_valid":236,"parse_rate":0.9957805907172996,"reason":0.00750134671310705,"mean_b":0.1099427171650479,"b_gate_pass_rate":0.8250355618776671,"median_len_z":524.0,"mean_r_leg":0.018129771018024363,"mean_g_leg":0.04487399917953138,"g_bind_frac":0.2838983050847458,"a_match":0.18008474576271186,"a_match_n":236,"a_match_centered":-0.04468085106382979},"boxed":{"n_turns":42,"n_valid":37,"parse_rate":0.8809523809523809,"reason":-0.007741564496934156,"mean_b":0.9473567097655258,"b_gate_pass_rate":0.2727272727272727,"median_len_z":2867.0,"mean_r_leg":0.111635829685157,"mean_g_leg":0.013648278951998665,"g_bind_frac":0.5945945945945946,"a_match":0.5945945945945946,"a_match_n":37,"a_match_centered":0.027027027027027025},"terminus_json":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":-0.0009473068351676904,"mean_b":0.01796888954342727,"b_gate_pass_rate":0.16981132075471697,"median_len_z":857.0,"mean_r_leg":0.0005989155919072698,"mean_g_leg":0.04183507908617163,"g_bind_frac":0.16666666666666666,"a_match":0.5,"a_match_n":18,"a_match_centered":0.037037037037037035},"text":{"n_turns":378,"n_valid":367,"parse_rate":0.9708994708994709,"reason":-0.0007123720932104213,"mean_b":0.0553532170100463,"b_gate_pass_rate":0.3215258855585831,"median_len_z":761.0,"mean_r_leg":0.016975639549458434,"mean_g_leg":0.06469357540643202,"g_bind_frac":0.1907356948228883,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":313,"parse_rate":0.9842767295597484,"reason":4.369833239270768e-06,"mean_b":0.028530711548212604,"b_gate_pass_rate":0.4477933261571582,"median_len_z":486.0,"mean_r_leg":0.006670369864020235,"mean_g_leg":0.06861097425618023,"g_bind_frac":0.1757188498402556,"a_match":0.1337719298245614,"a_match_n":304,"a_match_centered":-0.06111111111111111}}},"king":{"reason":0.002725270485335925,"n_turns":993,"n_pairs":2954,"n_forfeits":0,"forfeit_rate":0.0,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-14.2995649378287,"mean_len_z":1010.22951929587,"median_len_z":708.0,"mean_len_y":339.74779959377116,"mean_b":0.10200293119296884,"b_gate_pass_rate":0.527758970886933,"mean_r_leg":0.017988712204995254,"mean_g_leg":0.057984076277476905,"g_bind_frac":0.2326283987915408,"a_match":0.18442622950819673,"a_match_n":610,"a_match_centered":-0.05352190793122573,"n_turns_cap_raised":40,"mean_cap_tokens":4138.915407854985,"max_cap_tokens":6045,"len_z_delta":-376.01861882193634,"len_y_delta":-383.31516587677726,"n_samples":993,"think_close_rate":1.0,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":237,"n_valid":237,"parse_rate":1.0,"reason":0.007341493446955833,"mean_b":0.12286503306538697,"b_gate_pass_rate":0.8640226628895185,"median_len_z":570.0,"mean_r_leg":0.01885548921620434,"mean_g_leg":0.04374141751704605,"g_bind_frac":0.27848101265822783,"a_match":0.1828410689170183,"a_match_n":237,"a_match_centered":-0.04096045197740113},"boxed":{"n_turns":42,"n_valid":42,"parse_rate":1.0,"reason":0.009730113129377297,"mean_b":0.9158150051113488,"b_gate_pass_rate":0.7916666666666666,"median_len_z":1855.0,"mean_r_leg":0.07805115397666103,"mean_g_leg":0.017709151784475144,"g_bind_frac":0.6904761904761905,"a_match":0.4227642276422764,"a_match_n":41,"a_match_centered":-0.11965811965811966},"terminus_json":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":-0.0012892469847956625,"mean_b":0.025889443659317835,"b_gate_pass_rate":0.2830188679245283,"median_len_z":872.0,"mean_r_leg":0.0012286257600981699,"mean_g_leg":0.038773168118319594,"g_bind_frac":0.16666666666666666,"a_match":0.5,"a_match_n":18,"a_match_centered":0.037037037037037035},"text":{"n_turns":378,"n_valid":378,"parse_rate":1.0,"reason":-0.0012892210745293496,"mean_b":0.06568433404783179,"b_gate_pass_rate":0.36507936507936506,"median_len_z":780.5,"mean_r_leg":0.020130120881469517,"mean_g_leg":0.06079619170883261,"g_bind_frac":0.20899470899470898,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.003358889639857265,"mean_b":0.03062483471022294,"b_gate_pass_rate":0.45164718384697133,"median_len_z":617.0,"mean_r_leg":0.007813178778059286,"mean_g_leg":0.07166292429238433,"g_bind_frac":0.16981132075471697,"a_match":0.13641188959660297,"a_match_n":314,"a_match_centered":-0.060064935064935064}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-25T00:04:21.600009+00:00","challenge_id":"chal-00692","repo":"r2://affine-private-models/models/registrations/ec7d930661572c7c186beea9ee0f00c8ec6e78260ca8c1028c6c9f619b7f4441/","hotkey":"5CeL2bQE9yCGtigCdGyxazj7HdbgEBu7JkxUtqxMnLgM8kus","uid":142,"duration_s":2727.3,"revision":"280679452a3a63f358a24acdd1b06e97e069702d6c7beac3f58d1e66a04efa78","accepted":false,"error_code":null,"error_detail":"","z":0.9114863674718782,"margin":0.029097384289792735,"se":0.03192300546468729,"n_paired_turns":986,"n_forfeit_turns":2,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":1350250803006280680,"n":1000,"digest":"15d2765a7989f07aa6bb71234548e1cc026f460b5bd6f32f9d1ab1a4cfa30a82","n_paired_turns":986,"n_forfeit_turns":2,"margin":0.029097384289792735,"se":0.03192300546468729,"z":0.9114863674718782,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.029097384289792735,"se":0.03192300546468729,"z":0.9114863674718782,"sd_diff":1.0024027045094583,"n_paired_turns":986,"n_forfeit_turns":2,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.006877731939426374,"A":5.120248322474776,"Mc":0.16022479398334133},"bash":{"R":0.02254385217477685,"A":6.846681087185038,"Mc":0.14321743160920755},"text":{"R":0.05655121091797769,"A":13.523932886504483,"Mc":0.1582797349616194},"boxed":{"R":0.17467127745017952,"A":6.312145455060424,"Mc":0.12595993621832016},"terminus_json":{"R":0.0019135779198680863,"A":12.45058110078469,"Mc":0.12450857728098144}},"challenger":{"mean":-0.7263940288345238,"mean_valid":-0.7156753175110168,"sd_valid":1.4428284192985987,"n_turns":996,"n_valid":984,"n_forfeits":2,"n_unscorable":10,"mean_z_R":0.2815088660865608,"mean_typ_c":0.5931031757213582,"mean_z_A":-0.13880030730715656,"bind_frac":{"R":0.32113821138211385,"Gc":0.16971544715447154,"A":0.5091463414634146},"n_leg_dropped":{"R":1,"Gc":41,"A":1},"mean_content_share":0.24059620971674842,"mean_R":0.021437199700080994,"mean_A":2.654649594392213,"mean_mc":-0.6729208270310919},"king":{"mean":-0.7554914131243166,"mean_valid":-0.7501670389244427,"sd_valid":1.521327084948327,"n_turns":996,"n_valid":985,"n_forfeits":1,"n_unscorable":10,"mean_z_R":0.2833168422880487,"mean_typ_c":0.5662065045924565,"mean_z_A":-0.1769174674261713,"bind_frac":{"R":0.3177664974619289,"Gc":0.17055837563451776,"A":0.5116751269035533},"n_leg_dropped":{"R":1,"Gc":41,"A":1},"mean_content_share":0.276135916757151,"mean_R":0.021869937884907986,"mean_A":2.1987560043057446,"mean_mc":-0.6516708614556255}},"rejection_reason":null,"reign_number":null,"score":0.0025401081878493065,"score_king":0.002693016928462297,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9140782,"blocks_since_crown":17472,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1421.88520149001,"mean_len_y":695.0396207246868,"n_samples":3000,"think_close_rate":0.967,"n_text_fallback":21,"by_dialect":{"tool_call":{"n_turns":285,"zero_ref_turns":1,"mean_refs":2.9263157894736844,"ref_pair_agreement":0.2610294117647059,"ref_pair_n":272},"text":{"n_turns":372,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":40,"zero_ref_turns":3,"mean_refs":2.7,"ref_pair_agreement":0.4722222222222222,"ref_pair_n":36},"bash":{"n_turns":286,"zero_ref_turns":0,"mean_refs":2.958041958041958,"ref_pair_agreement":0.19267139479905437,"ref_pair_n":282},"terminus_json":{"n_turns":17,"zero_ref_turns":0,"mean_refs":2.8823529411764706,"ref_pair_agreement":0.45098039215686275,"ref_pair_n":17}},"ref_pair_agreement":0.2471169686985173,"ref_pair_n":607},"duel_seconds":2232.8077832320705,"challenger":{"reason":0.0025401081878493065,"n_turns":996,"n_pairs":2947,"n_forfeits":2,"forfeit_rate":0.002008032128514056,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":3.4224627599192448,"mean_len_z":1258.5286732270106,"median_len_z":916.0,"mean_len_y":458.25721072276895,"mean_b":0.0939225703651521,"b_gate_pass_rate":0.5144214455378351,"mean_r_leg":0.021437199700080994,"mean_g_leg":0.05670396022319648,"g_bind_frac":0.24446680080482897,"a_match":0.19336569579288027,"a_match_n":618,"a_match_centered":-0.05363036303630363,"n_turns_cap_raised":48,"mean_cap_tokens":4149.472891566265,"max_cap_tokens":6016,"len_z_delta":-163.35652826299952,"len_y_delta":-236.7824100019178,"n_samples":999,"think_close_rate":0.997997997997998,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":286,"n_valid":286,"parse_rate":1.0,"reason":0.006840128244263071,"mean_b":0.11112236688833056,"b_gate_pass_rate":0.8747044917257684,"median_len_z":683.0,"mean_r_leg":0.02494774176555729,"mean_g_leg":0.043773243027605685,"g_bind_frac":0.3321678321678322,"a_match":0.15034965034965034,"a_match_n":286,"a_match_centered":-0.04018912529550828},"boxed":{"n_turns":37,"n_valid":37,"parse_rate":1.0,"reason":0.009889763322267212,"mean_b":0.8074453559772865,"b_gate_pass_rate":0.6111111111111112,"median_len_z":1842.0,"mean_r_leg":0.12441826331898997,"mean_g_leg":0.024932146845488615,"g_bind_frac":0.5405405405405406,"a_match":0.4074074074074074,"a_match_n":36,"a_match_centered":-0.09523809523809525},"terminus_json":{"n_turns":17,"n_valid":17,"parse_rate":1.0,"reason":0.0003215764226539451,"mean_b":0.018560712328094957,"b_gate_pass_rate":0.10204081632653061,"median_len_z":855.0,"mean_r_leg":0.001985540255204434,"mean_g_leg":0.05317324617527137,"g_bind_frac":0.11764705882352941,"a_match":0.42156862745098034,"a_match_n":17,"a_match_centered":-0.029411764705882353},"text":{"n_turns":372,"n_valid":370,"parse_rate":0.9946236559139785,"reason":0.0009866623855044052,"mean_b":0.06357687912813131,"b_gate_pass_rate":0.3054054054054054,"median_len_z":983.0,"mean_r_leg":0.02215511958531342,"mean_g_leg":0.0624520805463658,"g_bind_frac":0.1972972972972973,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":-0.0005801245502745486,"mean_b":0.028892545919336012,"b_gate_pass_rate":0.43884892086330934,"median_len_z":817.0,"mean_r_leg":0.004714430222619907,"mean_g_leg":0.0665876216040283,"g_bind_frac":0.18661971830985916,"a_match":0.19593787335722818,"a_match_n":279,"a_match_centered":-0.06372549019607843}}},"king":{"reason":0.002693016928462297,"n_turns":996,"n_pairs":2950,"n_forfeits":1,"forfeit_rate":0.001004016064257028,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":22.040144962258587,"mean_len_z":973.0942372881356,"median_len_z":687.0,"mean_len_y":335.7827118644068,"mean_b":0.09657205038272394,"b_gate_pass_rate":0.5620338983050848,"mean_r_leg":0.021869937884907986,"mean_g_leg":0.05663321221087592,"g_bind_frac":0.23919597989949748,"a_match":0.19193548387096773,"a_match_n":620,"a_match_centered":-0.054365733113673806,"n_turns_cap_raised":48,"mean_cap_tokens":4149.472891566265,"max_cap_tokens":6016,"len_z_delta":-448.79096420187454,"len_y_delta":-359.25690886027996,"n_samples":996,"think_close_rate":0.998995983935743,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":286,"n_valid":286,"parse_rate":1.0,"reason":0.006178329404893268,"mean_b":0.11706034059839264,"b_gate_pass_rate":0.8829787234042553,"median_len_z":506.0,"mean_r_leg":0.023075891120238088,"mean_g_leg":0.044296158506356806,"g_bind_frac":0.32867132867132864,"a_match":0.16200466200466201,"a_match_n":286,"a_match_centered":-0.028368794326241134},"boxed":{"n_turns":37,"n_valid":37,"parse_rate":1.0,"reason":0.009431549754372746,"mean_b":0.7997732175375104,"b_gate_pass_rate":0.7592592592592593,"median_len_z":1728.0,"mean_r_leg":0.08912200951009852,"mean_g_leg":0.02388927787267381,"g_bind_frac":0.6216216216216216,"a_match":0.41441441441441446,"a_match_n":37,"a_match_centered":-0.07407407407407407},"terminus_json":{"n_turns":17,"n_valid":17,"parse_rate":1.0,"reason":-6.625848328376716e-06,"mean_b":0.015775363718000774,"b_gate_pass_rate":0.3469387755102041,"median_len_z":866.0,"mean_r_leg":0.0016828510344963593,"mean_g_leg":0.05098419780907334,"g_bind_frac":0.17647058823529413,"a_match":0.5098039215686274,"a_match_n":17,"a_match_centered":0.058823529411764705},"text":{"n_turns":372,"n_valid":371,"parse_rate":0.9973118279569892,"reason":0.0015184771990455655,"mean_b":0.06720203797271858,"b_gate_pass_rate":0.37735849056603776,"median_len_z":852.0,"mean_r_leg":0.02838928856335963,"mean_g_leg":0.0613572692449174,"g_bind_frac":0.1967654986522911,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":5.332504978216118e-06,"mean_b":0.028669222905187676,"b_gate_pass_rate":0.47002398081534774,"median_len_z":520.0,"mean_r_leg":0.004585684713481858,"mean_g_leg":0.06749001156019704,"g_bind_frac":0.15845070422535212,"a_match":0.1738095238095238,"a_match_n":280,"a_match_centered":-0.0857843137254902}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T23:15:46.303102+00:00","challenge_id":"chal-00691","repo":"r2://affine-private-models/models/registrations/0b4ad900d68a3ae268ce910301f76e3708575fb8d934a7fe4f11beda1db9889c/","hotkey":"5GH4ATP4h7anHizMHeHgmbXYfQQrnLGx54R5hs8uE8z67SVq","uid":2,"duration_s":2560.3,"revision":"2a757b2bf4276a72a69b1ce0a90e6f7417fa6d8c6f68f1626f0a3855c6668dc2","accepted":false,"error_code":null,"error_detail":"","z":-1.2641503104048564,"margin":-0.044329400793578576,"se":0.035066558484949197,"n_paired_turns":980,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":11649624760014642261,"n":1000,"digest":"41e6d8d6cab7d9b49b72d4ac1970bfc423734f6a1f24bfd8ae81f66b9626e7cc","n_paired_turns":980,"n_forfeit_turns":5,"margin":-0.044329400793578576,"se":0.035066558484949197,"z":-1.2641503104048564,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.044329400793578576,"se":0.035066558484949197,"z":-1.2641503104048564,"sd_diff":1.0977569191304581,"n_paired_turns":980,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.008172460656891747,"A":5.702149744702104,"Mc":0.16614377817857548},"bash":{"R":0.026917702520634513,"A":5.369346061979578,"Mc":0.15049310880025824},"text":{"R":0.09650896937642003,"A":13.731087879159833,"Mc":0.15451003306678673},"terminus_json":{"R":0.0008687011373890145,"A":6.8845674977081694,"Mc":0.14270579425090058},"boxed":{"R":0.10358154600828241,"A":6.604498028997983,"Mc":0.11655180544765044}},"challenger":{"mean":-0.7779064388772887,"mean_valid":-0.7511264718971723,"sd_valid":1.4829380077543806,"n_turns":993,"n_valid":975,"n_forfeits":5,"n_unscorable":13,"mean_z_R":0.14192064436092178,"mean_typ_c":0.6264301162435049,"mean_z_A":-0.20017942801984923,"bind_frac":{"R":0.32205128205128203,"Gc":0.16307692307692306,"A":0.5148717948717949},"n_leg_dropped":{"R":0,"Gc":41,"A":0},"mean_content_share":0.27678123830243134,"mean_R":0.015704439671065967,"mean_A":2.412884708761786,"mean_mc":-0.63333373704535},"king":{"mean":-0.7389454610826055,"mean_valid":-0.7174058314452774,"sd_valid":1.3823628629504165,"n_turns":993,"n_valid":977,"n_forfeits":4,"n_unscorable":12,"mean_z_R":0.25749356904249515,"mean_typ_c":0.6356469996881882,"mean_z_A":-0.18703653847501564,"bind_frac":{"R":0.31832139201637666,"Gc":0.1750255885363357,"A":0.5066530194472876},"n_leg_dropped":{"R":0,"Gc":42,"A":0},"mean_content_share":0.27804263578810506,"mean_R":0.019297204390239037,"mean_A":2.4650100274632343,"mean_mc":-0.6805764509641647}},"rejection_reason":null,"reign_number":null,"score":0.0030240528294702513,"score_king":0.0030277395520472857,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9140553,"blocks_since_crown":17243,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1353.4309523809525,"mean_len_y":716.2428571428571,"n_samples":3000,"think_close_rate":0.9576666666666667,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":264,"zero_ref_turns":2,"mean_refs":2.962121212121212,"ref_pair_agreement":0.1979565772669221,"ref_pair_n":261},"tool_call":{"n_turns":308,"zero_ref_turns":1,"mean_refs":2.935064935064935,"ref_pair_agreement":0.19666666666666666,"ref_pair_n":300},"text":{"n_turns":343,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":25,"zero_ref_turns":0,"mean_refs":2.84,"ref_pair_agreement":0.4583333333333333,"ref_pair_n":24},"boxed":{"n_turns":60,"zero_ref_turns":4,"mean_refs":2.566666666666667,"ref_pair_agreement":0.5733333333333334,"ref_pair_n":50}},"ref_pair_agreement":0.236745406824147,"ref_pair_n":635},"duel_seconds":2080.088378359098,"challenger":{"reason":0.0030240528294702513,"n_turns":993,"n_pairs":2925,"n_forfeits":5,"forfeit_rate":0.005035246727089627,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":2.6633526866469666,"mean_len_z":1010.1740170940171,"median_len_z":667.0,"mean_len_y":382.911452991453,"mean_b":0.12023290339149877,"b_gate_pass_rate":0.55008547008547,"mean_r_leg":0.015704439671065967,"mean_g_leg":0.05471188263436477,"g_bind_frac":0.2236842105263158,"a_match":0.19582043343653252,"a_match_n":646,"a_match_centered":-0.03916929547844374,"n_turns_cap_raised":41,"mean_cap_tokens":4142.041289023162,"max_cap_tokens":6032,"len_z_delta":-343.25693528693535,"len_y_delta":-333.3314041514041,"n_samples":996,"think_close_rate":0.9959839357429718,"n_text_fallback":0,"by_dialect":{"bash":{"n_turns":262,"n_valid":262,"parse_rate":1.0,"reason":0.009711211125186891,"mean_b":0.12384721645645555,"b_gate_pass_rate":0.8976982097186701,"median_len_z":480.0,"mean_r_leg":0.02078085073901691,"mean_g_leg":0.04432505036246741,"g_bind_frac":0.2900763358778626,"a_match":0.1577608142493639,"a_match_n":262,"a_match_centered":-0.03959131545338442},"boxed":{"n_turns":56,"n_valid":55,"parse_rate":0.9821428571428571,"reason":0.003585164894308453,"mean_b":0.9984972022798847,"b_gate_pass_rate":0.695364238410596,"median_len_z":2318.0,"mean_r_leg":0.07482469638144844,"mean_g_leg":0.01750890528807092,"g_bind_frac":0.6545454545454545,"a_match":0.4104938271604939,"a_match_n":54,"a_match_centered":-0.15306122448979592},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.0014388497717520447,"mean_b":0.01636083214704199,"b_gate_pass_rate":0.28169014084507044,"median_len_z":731.0,"mean_r_leg":0.0005294535816205116,"mean_g_leg":0.05601780068492438,"g_bind_frac":0.16,"a_match":0.48,"a_match_n":25,"a_match_centered":0.041666666666666664},"text":{"n_turns":343,"n_valid":339,"parse_rate":0.9883381924198251,"reason":-0.0011498144667592266,"mean_b":0.07610921721897415,"b_gate_pass_rate":0.3333333333333333,"median_len_z":877.0,"mean_r_leg":0.011454906821697617,"mean_g_leg":0.059924699770827684,"g_bind_frac":0.1504424778761062,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":307,"n_valid":307,"parse_rate":1.0,"reason":0.0022414837693027242,"mean_b":0.02820237678405571,"b_gate_pass_rate":0.49004424778761063,"median_len_z":526.0,"mean_r_leg":0.006708779961938357,"mean_g_leg":0.06437872578992945,"g_bind_frac":0.1758957654723127,"a_match":0.16721311475409836,"a_match_n":305,"a_match_centered":-0.02666666666666667}}},"king":{"reason":0.0030277395520472857,"n_turns":993,"n_pairs":2930,"n_forfeits":4,"forfeit_rate":0.004028197381671702,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":4.390201036159403,"mean_len_z":960.277133105802,"median_len_z":686.0,"mean_len_y":347.3436860068259,"mean_b":0.11732882200232886,"b_gate_pass_rate":0.5733788395904437,"mean_r_leg":0.019297204390239037,"mean_g_leg":0.055103999807025114,"g_bind_frac":0.24671385237613752,"a_match":0.1821705426356589,"a_match_n":645,"a_match_centered":-0.0517875920084122,"n_turns_cap_raised":41,"mean_cap_tokens":4142.041289023162,"max_cap_tokens":6032,"len_z_delta":-393.15381927515045,"len_y_delta":-368.8991711360312,"n_samples":993,"think_close_rate":0.9959718026183283,"n_text_fallback":0,"by_dialect":{"bash":{"n_turns":262,"n_valid":262,"parse_rate":1.0,"reason":0.008687160210245745,"mean_b":0.12274397192103732,"b_gate_pass_rate":0.9168797953964194,"median_len_z":510.0,"mean_r_leg":0.02296804772569775,"mean_g_leg":0.04364219668268235,"g_bind_frac":0.33587786259541985,"a_match":0.1361323155216285,"a_match_n":262,"a_match_centered":-0.06130268199233716},"boxed":{"n_turns":56,"n_valid":55,"parse_rate":0.9821428571428571,"reason":0.003929131192535802,"mean_b":0.991021268067447,"b_gate_pass_rate":0.7581699346405228,"median_len_z":2262.0,"mean_r_leg":0.07134850502757431,"mean_g_leg":0.01757921594868578,"g_bind_frac":0.6181818181818182,"a_match":0.3930817610062893,"a_match_n":53,"a_match_centered":-0.15986394557823128},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.004688051778079191,"mean_b":0.01929747418270939,"b_gate_pass_rate":0.3380281690140845,"median_len_z":594.0,"mean_r_leg":0.0009275518167694474,"mean_g_leg":0.04870367031073939,"g_bind_frac":0.2,"a_match":0.49333333333333335,"a_match_n":25,"a_match_centered":0.05555555555555555},"text":{"n_turns":343,"n_valid":340,"parse_rate":0.9912536443148688,"reason":-0.0010381921277827417,"mean_b":0.0668807072474482,"b_gate_pass_rate":0.4147058823529412,"median_len_z":871.0,"mean_r_leg":0.019374429595626682,"mean_g_leg":0.05927669880847186,"g_bind_frac":0.17058823529411765,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":307,"n_valid":307,"parse_rate":1.0,"reason":0.0032044926631857483,"mean_b":0.029394874281950728,"b_gate_pass_rate":0.4424778761061947,"median_len_z":565.0,"mean_r_leg":0.008249654734086984,"mean_g_leg":0.06750838452266589,"g_bind_frac":0.19218241042345277,"a_match":0.15956284153005465,"a_match_n":305,"a_match_centered":-0.034444444444444444}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T21:24:42.655782+00:00","challenge_id":"chal-00690","repo":"r2://affine-private-models/models/registrations/a0381b0025086d1b0c78da67c1f1908394cd004f33337692f42da7ae7284df45/","hotkey":"5FTTSRxmYYwv3XoQ8pZHUfoAXrzdtLKqQy7hVvf4BQDxr7Z3","uid":145,"duration_s":2705.1,"revision":"6a46a4987b3cc4b7ea85d5f83d5c78204b0f0a86af0db047653f87bd9a209f75","accepted":false,"error_code":null,"error_detail":"","z":-0.793881373186071,"margin":-0.02514677307414573,"se":0.03167573131641142,"n_paired_turns":991,"n_forfeit_turns":7,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":8730858680435943189,"n":1000,"digest":"d74d298c3cef66884710d1f41e2d9b32bb0441ae46cbd89702c19366b02ecd4f","n_paired_turns":991,"n_forfeit_turns":7,"margin":-0.02514677307414573,"se":0.03167573131641142,"z":-0.793881373186071,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.02514677307414573,"se":0.03167573131641142,"z":-0.793881373186071,"sd_diff":0.9971568516736079,"n_paired_turns":991,"n_forfeit_turns":7,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.02088270459172399,"A":6.477536730912185,"Mc":0.14578070056481385},"text":{"R":0.045354898469070724,"A":37.45796186819443,"Mc":0.15293214399477537},"tool_call":{"R":0.007307437148018759,"A":5.950371024998246,"Mc":0.17048832958734383},"boxed":{"R":0.10159607802787846,"A":7.325644156639336,"Mc":0.11700226115116136},"terminus_json":{"R":0.002694083028665807,"A":6.9254337135215085,"Mc":0.11157440172282612}},"challenger":{"mean":-0.6941276538869605,"mean_valid":-0.6563826270345304,"sd_valid":1.360485142062269,"n_turns":996,"n_valid":984,"n_forfeits":7,"n_unscorable":5,"mean_z_R":0.20985554584915903,"mean_typ_c":0.5897510689895515,"mean_z_A":-0.06741720600215763,"bind_frac":{"R":0.34247967479674796,"Gc":0.17886178861788618,"A":0.47865853658536583},"n_leg_dropped":{"R":0,"Gc":48,"A":0},"mean_content_share":0.2753140814156912,"mean_R":0.014926143798696617,"mean_A":2.1690195558365217,"mean_mc":-0.6356135807065423},"king":{"mean":-0.6689808808128148,"mean_valid":-0.6582002556981794,"sd_valid":1.3682761865580289,"n_turns":996,"n_valid":989,"n_forfeits":2,"n_unscorable":5,"mean_z_R":0.33753549260691107,"mean_typ_c":0.5547920900761008,"mean_z_A":-0.08142033905295692,"bind_frac":{"R":0.31243680485338726,"Gc":0.19514661274014156,"A":0.4924165824064712},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.27235715290353557,"mean_R":0.019957329597023322,"mean_A":1.7576916834018108,"mean_mc":-0.6998370568965372}},"rejection_reason":null,"reign_number":null,"score":0.0027929871006447853,"score_king":0.0026586711092834387,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9139986,"blocks_since_crown":16676,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1295.262339418526,"mean_len_y":770.1636240703178,"n_samples":3000,"think_close_rate":0.9666666666666667,"n_text_fallback":22,"by_dialect":{"text":{"n_turns":355,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":286,"zero_ref_turns":2,"mean_refs":2.9405594405594404,"ref_pair_agreement":0.23286052009456265,"ref_pair_n":282},"tool_call":{"n_turns":313,"zero_ref_turns":0,"mean_refs":2.9584664536741214,"ref_pair_agreement":0.210239651416122,"ref_pair_n":306},"boxed":{"n_turns":35,"zero_ref_turns":2,"mean_refs":2.742857142857143,"ref_pair_agreement":0.5376344086021506,"ref_pair_n":31},"terminus_json":{"n_turns":11,"zero_ref_turns":0,"mean_refs":2.727272727272727,"ref_pair_agreement":0.5,"ref_pair_n":10}},"ref_pair_agreement":0.24112347641759405,"ref_pair_n":629},"duel_seconds":2220.2388115702197,"challenger":{"reason":0.0027929871006447853,"n_turns":996,"n_pairs":2937,"n_forfeits":7,"forfeit_rate":0.007028112449799197,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-12.696713358475916,"mean_len_z":1030.9257745999319,"median_len_z":694.0,"mean_len_y":395.6394279877426,"mean_b":0.10124991587135754,"b_gate_pass_rate":0.5726932243786176,"mean_r_leg":0.014926143798696617,"mean_g_leg":0.060129669597127,"g_bind_frac":0.21739130434782608,"a_match":0.19448860625331213,"a_match_n":629,"a_match_centered":-0.04387372926698769,"n_turns_cap_raised":38,"mean_cap_tokens":4125.097389558233,"max_cap_tokens":6030,"len_z_delta":-264.33656481859407,"len_y_delta":-374.52419608257526,"n_samples":999,"think_close_rate":0.993993993993994,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":284,"n_valid":283,"parse_rate":0.9964788732394366,"reason":0.00840533548303178,"mean_b":0.1248356208070425,"b_gate_pass_rate":0.8806682577565632,"median_len_z":487.5,"mean_r_leg":0.019322720059155276,"mean_g_leg":0.04636847672951662,"g_bind_frac":0.26148409893992935,"a_match":0.18374558303886926,"a_match_n":283,"a_match_centered":-0.045077105575326216},"boxed":{"n_turns":33,"n_valid":33,"parse_rate":1.0,"reason":0.017172825798433083,"mean_b":0.9582197469872213,"b_gate_pass_rate":0.78125,"median_len_z":2213.5,"mean_r_leg":0.062381344106093216,"mean_g_leg":0.03256451571385382,"g_bind_frac":0.5454545454545454,"a_match":0.4166666666666667,"a_match_n":32,"a_match_centered":-0.10752688172043011},"terminus_json":{"n_turns":11,"n_valid":11,"parse_rate":1.0,"reason":-0.0032985171081177877,"mean_b":0.01877738212354602,"b_gate_pass_rate":0.3,"median_len_z":627.5,"mean_r_leg":0.0007420354038131815,"mean_g_leg":0.03446439450091705,"g_bind_frac":0.18181818181818182,"a_match":0.4848484848484848,"a_match_n":11,"a_match_centered":0.03333333333333333},"text":{"n_turns":355,"n_valid":350,"parse_rate":0.9859154929577465,"reason":-0.001457555225854928,"mean_b":0.07019546288768343,"b_gate_pass_rate":0.3942857142857143,"median_len_z":855.5,"mean_r_leg":0.01559546849923644,"mean_g_leg":0.06203907992060299,"g_bind_frac":0.19428571428571428,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":313,"n_valid":312,"parse_rate":0.9968051118210862,"reason":0.001219528489075669,"mean_b":0.028711917087029536,"b_gate_pass_rate":0.48320693391115926,"median_len_z":604.0,"mean_r_leg":0.005668159360558451,"mean_g_leg":0.07429022111162527,"g_bind_frac":0.16987179487179488,"a_match":0.1705170517051705,"a_match_n":303,"a_match_centered":-0.03875968992248062}}},"king":{"reason":0.0026586711092834387,"n_turns":996,"n_pairs":2952,"n_forfeits":2,"forfeit_rate":0.002008032128514056,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-13.753198124453952,"mean_len_z":961.1937669376694,"median_len_z":699.5,"mean_len_y":341.58265582655827,"mean_b":0.10016249657363908,"b_gate_pass_rate":0.5836720867208672,"mean_r_leg":0.019957329597023322,"mean_g_leg":0.057819965498733424,"g_bind_frac":0.23641851106639838,"a_match":0.19194312796208532,"a_match_n":633,"a_match_centered":-0.04811270600744285,"n_turns_cap_raised":38,"mean_cap_tokens":4125.097389558233,"max_cap_tokens":6030,"len_z_delta":-334.0685724808566,"len_y_delta":-428.58096824375957,"n_samples":996,"think_close_rate":0.9979919678714859,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.008611175277026074,"mean_b":0.12584444980317447,"b_gate_pass_rate":0.915576694411415,"median_len_z":484.0,"mean_r_leg":0.020299052081264028,"mean_g_leg":0.04563466486018419,"g_bind_frac":0.3028169014084507,"a_match":0.1807511737089202,"a_match_n":284,"a_match_centered":-0.050827423167848704},"boxed":{"n_turns":33,"n_valid":33,"parse_rate":1.0,"reason":0.018333731180590382,"mean_b":0.9438390409333234,"b_gate_pass_rate":0.6875,"median_len_z":2089.5,"mean_r_leg":0.07139834258218253,"mean_g_leg":0.032462672299632636,"g_bind_frac":0.48484848484848486,"a_match":0.46875,"a_match_n":32,"a_match_centered":-0.053763440860215055},"terminus_json":{"n_turns":11,"n_valid":11,"parse_rate":1.0,"reason":-0.005583191706189409,"mean_b":0.02257001147620106,"b_gate_pass_rate":0.6666666666666666,"median_len_z":643.0,"mean_r_leg":0.0005915951497843247,"mean_g_leg":0.024154314350455744,"g_bind_frac":0.2727272727272727,"a_match":0.4848484848484848,"a_match_n":11,"a_match_centered":0.03333333333333333},"text":{"n_turns":355,"n_valid":353,"parse_rate":0.9943661971830986,"reason":-0.002037172738873171,"mean_b":0.06742146446033344,"b_gate_pass_rate":0.3937677053824363,"median_len_z":864.0,"mean_r_leg":0.027590075117541548,"mean_g_leg":0.05888668889680509,"g_bind_frac":0.19830028328611898,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":313,"n_valid":313,"parse_rate":1.0,"reason":0.0012206420072826728,"mean_b":0.029329944345069865,"b_gate_pass_rate":0.48596112311015116,"median_len_z":623.0,"mean_r_leg":0.006296183578307918,"mean_g_leg":0.07152982128157709,"g_bind_frac":0.19169329073482427,"a_match":0.16285403050108932,"a_match_n":306,"a_match_centered":-0.047697368421052634}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T20:38:51.835570+00:00","challenge_id":"chal-00689","repo":"r2://affine-private-models/models/registrations/bff7f5d7665a14b9da62bb95a717c99e1d18f5617c4a673db4727f71420b694b/","hotkey":"5DAPYeATvCtyY71spWAiRmNMr12RHWPmeBAz3vWd7Z2skw51","uid":75,"duration_s":2417.9,"revision":"93f43de3cd3c57e5e380208f304ecef5bb9542f1fc325619775c47cf7443182b","accepted":false,"error_code":null,"error_detail":"","z":0.3820589423253344,"margin":0.012418986994915865,"se":0.032505421596285354,"n_paired_turns":982,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":10217061827820033154,"n":1000,"digest":"077464ad6a8572ad074a20a2e197da9eb5eb03e1eb82a8e924ebe26a94400531","n_paired_turns":982,"n_forfeit_turns":4,"margin":0.012418986994915865,"se":0.032505421596285354,"z":0.3820589423253344,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.012418986994915865,"se":0.032505421596285354,"z":0.3820589423253344,"sd_diff":1.0186184709475445,"n_paired_turns":982,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.028657601650554414,"A":5.671334197401667,"Mc":0.16550326578871963},"text":{"R":0.06944635538598742,"A":25.32467239491327,"Mc":0.1574420572047263},"tool_call":{"R":0.007831937090939123,"A":5.779345755325699,"Mc":0.17175692442571983},"boxed":{"R":0.08677727493497574,"A":4.680715051186155,"Mc":0.1002850751541941},"terminus_json":{"R":0.00246434024283483,"A":12.039996583200695,"Mc":0.13072657872076626}},"challenger":{"mean":-0.6961457607235582,"mean_valid":-0.6744531053481944,"sd_valid":1.3851454321056247,"n_turns":994,"n_valid":978,"n_forfeits":4,"n_unscorable":12,"mean_z_R":0.15736425381359995,"mean_typ_c":0.6193808290616017,"mean_z_A":-0.0885791855801916,"bind_frac":{"R":0.3394683026584867,"Gc":0.17280163599182005,"A":0.48773006134969327},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.2847837631391347,"mean_R":0.02026538935304546,"mean_A":1.9097813200324247,"mean_mc":-0.6724577220029256},"king":{"mean":-0.708564747718474,"mean_valid":-0.708564747718474,"sd_valid":1.4372570285464237,"n_turns":994,"n_valid":982,"n_forfeits":0,"n_unscorable":12,"mean_z_R":0.20316705214748118,"mean_typ_c":0.5591807641269647,"mean_z_A":-0.09319475895622503,"bind_frac":{"R":0.34012219959266804,"Gc":0.164969450101833,"A":0.49490835030549896},"n_leg_dropped":{"R":0,"Gc":51,"A":0},"mean_content_share":0.2753177390477844,"mean_R":0.022531387380267456,"mean_A":1.8187115663685745,"mean_mc":-0.690668874178419}},"rejection_reason":null,"reign_number":null,"score":0.0020311458559773552,"score_king":0.0021961074290742966,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9139780,"blocks_since_crown":16470,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1464.3819727891157,"mean_len_y":675.3295918367347,"n_samples":3000,"think_close_rate":0.9653333333333334,"n_text_fallback":16,"by_dialect":{"text":{"n_turns":362,"zero_ref_turns":0,"mean_refs":2.9972375690607733,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":312,"zero_ref_turns":1,"mean_refs":2.9583333333333335,"ref_pair_agreement":0.14426229508196722,"ref_pair_n":305},"bash":{"n_turns":248,"zero_ref_turns":1,"mean_refs":2.9233870967741935,"ref_pair_agreement":0.16049382716049382,"ref_pair_n":243},"boxed":{"n_turns":57,"zero_ref_turns":4,"mean_refs":2.5964912280701755,"ref_pair_agreement":0.5602836879432623,"ref_pair_n":47},"terminus_json":{"n_turns":21,"zero_ref_turns":0,"mean_refs":2.8095238095238093,"ref_pair_agreement":0.5263157894736842,"ref_pair_n":19}},"ref_pair_agreement":0.19435396308360478,"ref_pair_n":614},"duel_seconds":2050.115172463935,"challenger":{"reason":0.0020311458559773552,"n_turns":994,"n_pairs":2929,"n_forfeits":4,"forfeit_rate":0.004024144869215292,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-20.53601653678239,"mean_len_z":874.83031751451,"median_len_z":635.0,"mean_len_y":315.2690337999317,"mean_b":0.1131347623785869,"b_gate_pass_rate":0.5606008876749744,"mean_r_leg":0.02026538935304546,"mean_g_leg":0.05755014410324346,"g_bind_frac":0.23636363636363636,"a_match":0.16613247863247865,"a_match_n":624,"a_match_centered":-0.03387978142076503,"n_turns_cap_raised":51,"mean_cap_tokens":4147.781690140845,"max_cap_tokens":6066,"len_z_delta":-589.5516552746057,"len_y_delta":-360.060558036803,"n_samples":997,"think_close_rate":0.995987963891675,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":247,"n_valid":246,"parse_rate":0.9959514170040485,"reason":0.006217175179150576,"mean_b":0.12228271863123297,"b_gate_pass_rate":0.8587257617728532,"median_len_z":442.5,"mean_r_leg":0.02151532007203549,"mean_g_leg":0.05017608297616901,"g_bind_frac":0.32113821138211385,"a_match":0.12601626016260162,"a_match_n":246,"a_match_centered":-0.0371900826446281},"boxed":{"n_turns":53,"n_valid":53,"parse_rate":1.0,"reason":0.007276995643272453,"mean_b":0.8250058126957203,"b_gate_pass_rate":0.7972972972972973,"median_len_z":1721.0,"mean_r_leg":0.0739850057878317,"mean_g_leg":0.019908797642276602,"g_bind_frac":0.4716981132075472,"a_match":0.5294117647058824,"a_match_n":51,"a_match_centered":-0.07092198581560284},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":-0.006249123062170866,"mean_b":0.017540932921219946,"b_gate_pass_rate":0.3220338983050847,"median_len_z":661.0,"mean_r_leg":0.0017052135862001042,"mean_g_leg":0.036004144266128205,"g_bind_frac":0.3333333333333333,"a_match":0.4603174603174603,"a_match_n":21,"a_match_centered":-0.017543859649122806},"text":{"n_turns":362,"n_valid":359,"parse_rate":0.9917127071823204,"reason":-0.00034275137211716214,"mean_b":0.08853996115424405,"b_gate_pass_rate":0.42896935933147634,"median_len_z":802.0,"mean_r_leg":0.02574626300377496,"mean_g_leg":0.059182954332783526,"g_bind_frac":0.2116991643454039,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":311,"n_valid":311,"parse_rate":1.0,"reason":0.0011348666350799344,"mean_b":0.02664169303433522,"b_gate_pass_rate":0.4582881906825569,"median_len_z":515.0,"mean_r_leg":0.0050483714192083,"mean_g_leg":0.06936782102885793,"g_bind_frac":0.15112540192926044,"a_match":0.11764705882352941,"a_match_n":306,"a_match_centered":-0.026490066225165563}}},"king":{"reason":0.0021961074290742966,"n_turns":994,"n_pairs":2940,"n_forfeits":0,"forfeit_rate":0.0,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-219.49273846249864,"mean_len_z":958.9687074829932,"median_len_z":676.0,"mean_len_y":344.478231292517,"mean_b":0.10987038113214913,"b_gate_pass_rate":0.5452380952380952,"mean_r_leg":0.022531387380267456,"mean_g_leg":0.05558598451538137,"g_bind_frac":0.23843058350100604,"a_match":0.1688,"a_match_n":625,"a_match_centered":-0.02918712493180578,"n_turns_cap_raised":51,"mean_cap_tokens":4147.781690140845,"max_cap_tokens":6066,"len_z_delta":-505.4132653061225,"len_y_delta":-330.8513605442177,"n_samples":994,"think_close_rate":1.0,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":247,"n_valid":247,"parse_rate":1.0,"reason":0.007721769563215231,"mean_b":0.12270847253060801,"b_gate_pass_rate":0.8648275862068966,"median_len_z":493.0,"mean_r_leg":0.02033506518005233,"mean_g_leg":0.05041062928935179,"g_bind_frac":0.2834008097165992,"a_match":0.12483130904183536,"a_match_n":247,"a_match_centered":-0.0336076817558299},"boxed":{"n_turns":53,"n_valid":53,"parse_rate":1.0,"reason":0.008194958703314496,"mean_b":0.8396733831183557,"b_gate_pass_rate":0.7635135135135135,"median_len_z":1646.0,"mean_r_leg":0.0770476807574389,"mean_g_leg":0.020509660201112202,"g_bind_frac":0.5471698113207547,"a_match":0.5466666666666666,"a_match_n":50,"a_match_centered":-0.06521739130434782},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":-0.005075101342839251,"mean_b":0.019494093798429007,"b_gate_pass_rate":0.3220338983050847,"median_len_z":638.0,"mean_r_leg":0.0019998954494145752,"mean_g_leg":0.03416665308251611,"g_bind_frac":0.2857142857142857,"a_match":0.4920634920634921,"a_match_n":21,"a_match_centered":0.017543859649122806},"text":{"n_turns":362,"n_valid":362,"parse_rate":1.0,"reason":-0.0011744559400520191,"mean_b":0.07944477722909428,"b_gate_pass_rate":0.4,"median_len_z":844.0,"mean_r_leg":0.03184753299725761,"mean_g_leg":0.05476470257530358,"g_bind_frac":0.21823204419889503,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":311,"n_valid":311,"parse_rate":1.0,"reason":0.0011995211241430078,"mean_b":0.02430756491293215,"b_gate_pass_rate":0.4442036836403034,"median_len_z":559.0,"mean_r_leg":0.00552767243383828,"mean_g_leg":0.06807623516452575,"g_bind_frac":0.17041800643086816,"a_match":0.12052117263843648,"a_match_n":307,"a_match_centered":-0.0231023102310231}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T19:57:26.310300+00:00","challenge_id":"chal-00688","repo":"r2://affine-private-models/models/registrations/f2a88ca4dc33af0d75c72dc1371627d4ad8cd5b8c3bcfdcc27767be45b73d83e/","hotkey":"5GMFTJH35QSzDDiwS3k1B3gm6WfsszjezM3hTCCEnXS9Mryo","uid":68,"duration_s":572.4,"revision":"4de69796c2ad8740bfe3d102893b354396f4a336ce9181b6aa9c8f0b71c560cc","accepted":false,"error_code":null,"error_detail":"","z":null,"margin":null,"se":null,"n_paired_turns":null,"n_forfeit_turns":null,"near_miss":null,"protocol_probe":{"mode":"enforce","passed":false,"pass_rate":0.85,"min_pass_rate":0.9,"think_close_rate":0.95,"n":20,"by_reason":{"multiple_tool_calls":2,"no_think_close":1},"by_prompt":{"assistant_bash":{"ok":false,"reasons":["no_think_close"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":null,"rejection_reason":"protocol:pass_rate=0.85<0.9;multiple_tool_calls=2,no_think_close=1","reign_number":null,"score":null,"score_king":null,"gates":null,"duel_params":null,"teacher":null,"duel_seconds":null,"challenger":null,"king":null,"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T19:46:42.406297+00:00","challenge_id":"chal-00687","repo":"r2://affine-private-models/models/registrations/80d608bf120d28062d44f0abb9cfd0e34b995ac92485542bbaf3a4c5ca27ba05/","hotkey":"5EzaX8pVDyqCFE3Gcw8r2SAb8SKy4ZZydLQeTFDjbFBzPyqT","uid":62,"duration_s":2827.2,"revision":"7f066f2c5f95b34105c23faa313e25908c8610fbb65091e797e8b9391e926dfc","accepted":false,"error_code":null,"error_detail":"","z":2.726644372131751,"margin":0.07280288925143412,"se":0.02670054444779508,"n_paired_turns":987,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":13865707148065924770,"n":1000,"digest":"321ede32d06ca0280042e8cec30d1e0266ad9ad7f9068d7418547cc29398ea5b","n_paired_turns":987,"n_forfeit_turns":4,"margin":0.07280288925143412,"se":0.02670054444779508,"z":2.726644372131751,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.07280288925143412,"se":0.02670054444779508,"z":2.726644372131751,"sd_diff":0.8388391537411495,"n_paired_turns":987,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.0248704564434324,"A":6.60007009745041,"Mc":0.15039783968323348},"text":{"R":0.08700263531240472,"A":14.692052491200977,"Mc":0.1525101867637208},"tool_call":{"R":0.046441287190392325,"A":5.3906892020893,"Mc":0.1902426272344548},"terminus_json":{"R":0.002221507541752901,"A":5.706521715219618,"Mc":0.12804367599941946},"boxed":{"R":0.14093367988486832,"A":8.289466136606043,"Mc":0.12568339535124765}},"challenger":{"mean":-0.6588686833799752,"mean_valid":-0.6425847464390605,"sd_valid":1.413567530918181,"n_turns":996,"n_valid":984,"n_forfeits":3,"n_unscorable":9,"mean_z_R":0.09639314946587477,"mean_typ_c":0.7206320725788616,"mean_z_A":-0.10739164368683621,"bind_frac":{"R":0.3780487804878049,"Gc":0.13617886178861788,"A":0.48577235772357724},"n_leg_dropped":{"R":0,"Gc":39,"A":0},"mean_content_share":0.2836986720945388,"mean_R":0.021675251910647973,"mean_A":2.2577284774010904,"mean_mc":-0.6462748185508179},"king":{"mean":-0.7316715726314093,"mean_valid":-0.7209744590733005,"sd_valid":1.4740642939146047,"n_turns":996,"n_valid":985,"n_forfeits":2,"n_unscorable":9,"mean_z_R":0.10794032105621179,"mean_typ_c":0.6297379057177107,"mean_z_A":-0.16550226531432521,"bind_frac":{"R":0.3553299492385787,"Gc":0.15634517766497463,"A":0.4883248730964467},"n_leg_dropped":{"R":0,"Gc":37,"A":0},"mean_content_share":0.27812696063296066,"mean_R":0.022919688891845817,"mean_A":1.753868222989525,"mean_mc":-0.6688916418090859}},"rejection_reason":null,"reign_number":null,"score":0.003144942563729151,"score_king":0.003268179347234281,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9139486,"blocks_since_crown":16176,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1408.2648849797024,"mean_len_y":704.7357916102842,"n_samples":3000,"think_close_rate":0.9643333333333334,"n_text_fallback":19,"by_dialect":{"tool_call":{"n_turns":312,"zero_ref_turns":0,"mean_refs":2.9711538461538463,"ref_pair_agreement":0.1716171617161716,"ref_pair_n":303},"terminus_json":{"n_turns":20,"zero_ref_turns":1,"mean_refs":2.85,"ref_pair_agreement":0.543859649122807,"ref_pair_n":19},"text":{"n_turns":367,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":256,"zero_ref_turns":2,"mean_refs":2.93359375,"ref_pair_agreement":0.15670650730411687,"ref_pair_n":251},"boxed":{"n_turns":45,"zero_ref_turns":1,"mean_refs":2.6666666666666665,"ref_pair_agreement":0.40196078431372545,"ref_pair_n":34}},"ref_pair_agreement":0.19000549148819332,"ref_pair_n":607},"duel_seconds":2243.9056344972923,"challenger":{"reason":0.003144942563729151,"n_turns":996,"n_pairs":2947,"n_forfeits":3,"forfeit_rate":0.0030120481927710845,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-4.31993063874057,"mean_len_z":1033.321343739396,"median_len_z":698.0,"mean_len_y":453.4882931795046,"mean_b":0.10340976790618457,"b_gate_pass_rate":0.513742789277231,"mean_r_leg":0.021675251910647973,"mean_g_leg":0.05911659372325195,"g_bind_frac":0.22457200402819738,"a_match":0.16019417475728157,"a_match_n":618,"a_match_centered":-0.028697571743929357,"n_turns_cap_raised":43,"mean_cap_tokens":4147.582329317269,"max_cap_tokens":6075,"len_z_delta":-374.94354124030633,"len_y_delta":-251.24749843077961,"n_samples":999,"think_close_rate":0.997997997997998,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":254,"n_valid":253,"parse_rate":0.9960629921259843,"reason":0.009283883371481448,"mean_b":0.12363393469150717,"b_gate_pass_rate":0.9050802139037433,"median_len_z":552.0,"mean_r_leg":0.01919814384916325,"mean_g_leg":0.050453599733904037,"g_bind_frac":0.2608695652173913,"a_match":0.12582345191040842,"a_match_n":253,"a_match_centered":-0.03},"boxed":{"n_turns":44,"n_valid":44,"parse_rate":1.0,"reason":0.009114190890368523,"mean_b":0.930845684892032,"b_gate_pass_rate":0.8333333333333334,"median_len_z":2882.0,"mean_r_leg":0.12095818827425903,"mean_g_leg":0.01798455966286845,"g_bind_frac":0.75,"a_match":0.4458333333333333,"a_match_n":40,"a_match_centered":0.09313725490196079},"terminus_json":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":-0.0006446774866778505,"mean_b":0.014763071392030742,"b_gate_pass_rate":0.2631578947368421,"median_len_z":752.0,"mean_r_leg":0.0017382974654390653,"mean_g_leg":0.037874851034359745,"g_bind_frac":0.10526315789473684,"a_match":0.5614035087719298,"a_match_n":19,"a_match_centered":0.017543859649122806},"text":{"n_turns":367,"n_valid":365,"parse_rate":0.9945504087193461,"reason":9.526184760719051e-05,"mean_b":0.07142450590034091,"b_gate_pass_rate":0.3589041095890411,"median_len_z":848.0,"mean_r_leg":0.02504003134599533,"mean_g_leg":0.05850944264857803,"g_bind_frac":0.20273972602739726,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":312,"n_valid":312,"parse_rate":1.0,"reason":0.0011234608721691411,"mean_b":0.023212072980599442,"b_gate_pass_rate":0.35490830636461707,"median_len_z":600.0,"mean_r_leg":0.006960241590500325,"mean_g_leg":0.07394592138769693,"g_bind_frac":0.15384615384615385,"a_match":0.12636165577342048,"a_match_n":306,"a_match_centered":-0.044296788482835}}},"king":{"reason":0.003268179347234281,"n_turns":996,"n_pairs":2950,"n_forfeits":2,"forfeit_rate":0.002008032128514056,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.5957204162318908,"mean_len_z":1008.1271186440678,"median_len_z":693.0,"mean_len_y":358.01898305084745,"mean_b":0.10794455768350512,"b_gate_pass_rate":0.5549152542372882,"mean_r_leg":0.022919688891845817,"mean_g_leg":0.0585020882589682,"g_bind_frac":0.22535211267605634,"a_match":0.16052350427350429,"a_match_n":624,"a_match_centered":-0.02828116419549698,"n_turns_cap_raised":43,"mean_cap_tokens":4147.582329317269,"max_cap_tokens":6075,"len_z_delta":-400.13776633563464,"len_y_delta":-346.71680855943674,"n_samples":996,"think_close_rate":0.9979919678714859,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":254,"n_valid":254,"parse_rate":1.0,"reason":0.008672531737415128,"mean_b":0.12977446299999756,"b_gate_pass_rate":0.9054593874833555,"median_len_z":521.0,"mean_r_leg":0.019949730533899798,"mean_g_leg":0.048546080905758515,"g_bind_frac":0.27165354330708663,"a_match":0.11876640419947505,"a_match_n":254,"a_match_centered":-0.036520584329349265},"boxed":{"n_turns":44,"n_valid":44,"parse_rate":1.0,"reason":0.011484229790349559,"mean_b":0.9794332673583384,"b_gate_pass_rate":0.7416666666666667,"median_len_z":2717.0,"mean_r_leg":0.11846228551189783,"mean_g_leg":0.0205927722582478,"g_bind_frac":0.7045454545454546,"a_match":0.47967479674796754,"a_match_n":41,"a_match_centered":0.11764705882352941},"terminus_json":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":-0.0018507744944574482,"mean_b":0.01748032810573182,"b_gate_pass_rate":0.2631578947368421,"median_len_z":752.0,"mean_r_leg":0.00118320014397382,"mean_g_leg":0.03277032448104651,"g_bind_frac":0.21052631578947367,"a_match":0.5614035087719298,"a_match_n":19,"a_match_centered":0.017543859649122806},"text":{"n_turns":367,"n_valid":365,"parse_rate":0.9945504087193461,"reason":0.0003898816956786672,"mean_b":0.07101796369267822,"b_gate_pass_rate":0.4136986301369863,"median_len_z":848.0,"mean_r_leg":0.029573244093229503,"mean_g_leg":0.05756974659986626,"g_bind_frac":0.1917808219178082,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":312,"n_valid":312,"parse_rate":1.0,"reason":0.0014072294578434013,"mean_b":0.026626518257639696,"b_gate_pass_rate":0.43149946062567424,"median_len_z":589.0,"mean_r_leg":0.005403473537168009,"mean_g_leg":0.07461120360864666,"g_bind_frac":0.16025641025641027,"a_match":0.12795698924731183,"a_match_n":310,"a_match_centered":-0.04070407040704071}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T17:32:18.591606+00:00","challenge_id":"chal-00686","repo":"r2://affine-private-models/models/registrations/4769d61b408a4e50c5beba9aefb8a97dbb3a0f125f1f504d71d56c26d8445578/","hotkey":"5EfoxjPgxFfM1dbp2CgiQxN4CwwwiDQPh6XmvXHvfzapwYNn","uid":63,"duration_s":2777.2,"revision":"0ff9f452a4a07a1d980abaf0d2fd5d06656047b9bfc9bc29bf1247096e3b642a","accepted":false,"error_code":null,"error_detail":"","z":-2.8263735919557793,"margin":-0.09930883667624593,"se":0.035136486188128695,"n_paired_turns":989,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":4324360069168885862,"n":1000,"digest":"67f863209d82f90df11dd3c952e74951d8642b8427fc0ec9e13f58423506c994","n_paired_turns":989,"n_forfeit_turns":4,"margin":-0.09930883667624593,"se":0.035136486188128695,"z":-2.8263735919557793,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.09930883667624593,"se":0.035136486188128695,"z":-2.8263735919557793,"sd_diff":1.1049852317431326,"n_paired_turns":989,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.02092241917107541,"A":5.912741574764976,"Mc":0.14709991607861334},"text":{"R":0.054237961578041685,"A":13.175652071081414,"Mc":0.16321415436915945},"tool_call":{"R":0.007500704056577005,"A":5.1131192968254116,"Mc":0.1805250401256553},"boxed":{"R":0.10999249071628067,"A":5.433280414218917,"Mc":0.1172340929553059},"terminus_json":{"R":0.0011275721954735736,"A":6.4752588036069,"Mc":0.13374307777595204}},"challenger":{"mean":-0.8082509442255787,"mean_valid":-0.7977306827143843,"sd_valid":1.392556261606754,"n_turns":998,"n_valid":987,"n_forfeits":2,"n_unscorable":9,"mean_z_R":0.332374676374016,"mean_typ_c":0.5093845053574892,"mean_z_A":-0.21458504134838252,"bind_frac":{"R":0.315096251266464,"Gc":0.17831813576494426,"A":0.5065856129685917},"n_leg_dropped":{"R":0,"Gc":38,"A":0},"mean_content_share":0.23582329077600228,"mean_R":0.02260419048571407,"mean_A":2.2137856085183953,"mean_mc":-0.7159238674356487},"king":{"mean":-0.7089421075493327,"mean_valid":-0.6928435541240265,"sd_valid":1.3639176452128456,"n_turns":998,"n_valid":986,"n_forfeits":3,"n_unscorable":9,"mean_z_R":0.3467482596144282,"mean_typ_c":0.6224933287259046,"mean_z_A":-0.13600705046072764,"bind_frac":{"R":0.3225152129817444,"Gc":0.16835699797160245,"A":0.5091277890466531},"n_leg_dropped":{"R":0,"Gc":36,"A":0},"mean_content_share":0.275140961798073,"mean_R":0.022259810055767753,"mean_A":2.845697627111444,"mean_mc":-0.6710303771115783}},"rejection_reason":null,"reign_number":null,"score":0.0012713650434765813,"score_king":0.0028159208036717467,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9138818,"blocks_since_crown":15508,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1432.2503378378378,"mean_len_y":607.2074324324325,"n_samples":3000,"think_close_rate":0.972,"n_text_fallback":15,"by_dialect":{"tool_call":{"n_turns":313,"zero_ref_turns":2,"mean_refs":2.94888178913738,"ref_pair_agreement":0.17211328976034856,"ref_pair_n":306},"text":{"n_turns":333,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":288,"zero_ref_turns":0,"mean_refs":2.954861111111111,"ref_pair_agreement":0.1938534278959811,"ref_pair_n":282},"boxed":{"n_turns":51,"zero_ref_turns":0,"mean_refs":2.823529411764706,"ref_pair_agreement":0.5144927536231885,"ref_pair_n":46},"terminus_json":{"n_turns":15,"zero_ref_turns":0,"mean_refs":2.8666666666666667,"ref_pair_agreement":0.3777777777777778,"ref_pair_n":15}},"ref_pair_agreement":0.2105803800719055,"ref_pair_n":649},"duel_seconds":2281.843720499426,"challenger":{"reason":0.0012713650434765813,"n_turns":998,"n_pairs":2955,"n_forfeits":2,"forfeit_rate":0.002004008016032064,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":411.8540567143489,"mean_len_z":1218.6033840947546,"median_len_z":864.0,"mean_len_y":428.6846023688663,"mean_b":0.1207411538255925,"b_gate_pass_rate":0.5346869712351946,"mean_r_leg":0.02260419048571407,"mean_g_leg":0.05452107099524137,"g_bind_frac":0.27309236947791166,"a_match":0.14974358974358973,"a_match_n":650,"a_match_centered":-0.06079664570230608,"n_turns_cap_raised":55,"mean_cap_tokens":4151.539078156313,"max_cap_tokens":6052,"len_z_delta":-213.64695374308326,"len_y_delta":-178.52283006356618,"n_samples":1001,"think_close_rate":0.998001998001998,"n_text_fallback":12,"by_dialect":{"bash":{"n_turns":288,"n_valid":288,"parse_rate":1.0,"reason":0.006186008425426665,"mean_b":0.12618508026772976,"b_gate_pass_rate":0.8836662749706228,"median_len_z":684.0,"mean_r_leg":0.018291893214924276,"mean_g_leg":0.04342410176147673,"g_bind_frac":0.3020833333333333,"a_match":0.1284722222222222,"a_match_n":288,"a_match_centered":-0.06264775413711585},"boxed":{"n_turns":51,"n_valid":51,"parse_rate":1.0,"reason":0.005579778431561425,"mean_b":0.920059802987955,"b_gate_pass_rate":0.6666666666666666,"median_len_z":2035.0,"mean_r_leg":0.07228137199456715,"mean_g_leg":0.012756873958331163,"g_bind_frac":0.6470588235294118,"a_match":0.39115646258503406,"a_match_n":49,"a_match_centered":-0.1},"terminus_json":{"n_turns":15,"n_valid":15,"parse_rate":1.0,"reason":-0.007954928570371663,"mean_b":0.030247074334006547,"b_gate_pass_rate":0.7209302325581395,"median_len_z":661.0,"mean_r_leg":0.0010033386514242144,"mean_g_leg":0.03356370144900691,"g_bind_frac":0.3333333333333333,"a_match":0.3888888888888889,"a_match_n":15,"a_match_centered":0.011111111111111112},"text":{"n_turns":333,"n_valid":332,"parse_rate":0.996996996996997,"reason":-0.0016836968087964022,"mean_b":0.08965647186647903,"b_gate_pass_rate":0.2921686746987952,"median_len_z":1018.0,"mean_r_leg":0.03468430689060856,"mean_g_leg":0.061091606585963035,"g_bind_frac":0.25301204819277107,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":311,"n_valid":310,"parse_rate":0.9967845659163987,"reason":-0.00037724066642478226,"mean_b":0.028577116657054206,"b_gate_pass_rate":0.44516829533116176,"median_len_z":808.0,"mean_r_leg":0.006545543673215138,"mean_g_leg":0.06567863201227545,"g_bind_frac":0.2032258064516129,"a_match":0.11856823266219241,"a_match_n":298,"a_match_centered":-0.05668934240362812}}},"king":{"reason":0.0028159208036717467,"n_turns":998,"n_pairs":2951,"n_forfeits":3,"forfeit_rate":0.003006012024048096,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":373.8717663202998,"mean_len_z":929.8837682141647,"median_len_z":669.0,"mean_len_y":341.1860386309726,"mean_b":0.10642257714403294,"b_gate_pass_rate":0.5869196882412742,"mean_r_leg":0.022259810055767753,"mean_g_leg":0.05655878508231027,"g_bind_frac":0.2522613065326633,"a_match":0.15476190476190477,"a_match_n":658,"a_match_centered":-0.054005167958656335,"n_turns_cap_raised":55,"mean_cap_tokens":4151.539078156313,"max_cap_tokens":6052,"len_z_delta":-502.3665696236732,"len_y_delta":-266.0213938014599,"n_samples":998,"think_close_rate":0.996993987975952,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":288,"n_valid":288,"parse_rate":1.0,"reason":0.008195723866255323,"mean_b":0.11487346353132791,"b_gate_pass_rate":0.881316098707403,"median_len_z":493.0,"mean_r_leg":0.019829347259125277,"mean_g_leg":0.046221625398259435,"g_bind_frac":0.3159722222222222,"a_match":0.1261574074074074,"a_match_n":288,"a_match_centered":-0.06501182033096926},"boxed":{"n_turns":51,"n_valid":51,"parse_rate":1.0,"reason":0.006283382094108125,"mean_b":0.8762313371852484,"b_gate_pass_rate":0.7777777777777778,"median_len_z":2134.0,"mean_r_leg":0.06245021530026717,"mean_g_leg":0.01447197935083542,"g_bind_frac":0.6666666666666666,"a_match":0.4375,"a_match_n":48,"a_match_centered":-0.05925925925925927},"terminus_json":{"n_turns":15,"n_valid":15,"parse_rate":1.0,"reason":-0.007661298981721193,"mean_b":0.025486914202561658,"b_gate_pass_rate":0.46511627906976744,"median_len_z":422.0,"mean_r_leg":0.0006366661678960784,"mean_g_leg":0.036618306620428615,"g_bind_frac":0.2,"a_match":0.36666666666666664,"a_match_n":15,"a_match_centered":-0.011111111111111108},"text":{"n_turns":333,"n_valid":330,"parse_rate":0.990990990990991,"reason":-0.0007168781636574676,"mean_b":0.06306318306892647,"b_gate_pass_rate":0.45151515151515154,"median_len_z":801.0,"mean_r_leg":0.03379378294352744,"mean_g_leg":0.06355477111371766,"g_bind_frac":0.21515151515151515,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":311,"n_valid":311,"parse_rate":1.0,"reason":0.0015534016559714153,"mean_b":0.028808132809597004,"b_gate_pass_rate":0.43661971830985913,"median_len_z":601.0,"mean_r_leg":0.0067241146323624235,"mean_g_leg":0.06657152099187826,"g_bind_frac":0.16720257234726688,"a_match":0.1270358306188925,"a_match_n":307,"a_match_centered":-0.045104510451045104}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T15:03:34.258256+00:00","challenge_id":"chal-00685","repo":"r2://affine-private-models/models/registrations/a3476c61471edc449757c47a284f16a2b5664a426b04ca8c8ebab5c81b8f9b5c/","hotkey":"5DDWwwZzwoCwpfd2pNMoWs9oQ3RjZgvKCAEUxbiqfmw5HXdw","uid":164,"duration_s":2651.1,"revision":"2c55499cd2332bc52d58600132a418d1ea8af54edc3019e625aef274b6dcc13d","accepted":false,"error_code":null,"error_detail":"","z":-3.350096090312114,"margin":-0.13778737662517732,"se":0.041129380444827855,"n_paired_turns":982,"n_forfeit_turns":20,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":10613534620408389973,"n":1000,"digest":"df11dc679abef9012cacbabaa58880f0f1c63962043228421e6508735e11687c","n_paired_turns":982,"n_forfeit_turns":20,"margin":-0.13778737662517732,"se":0.041129380444827855,"z":-3.350096090312114,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":0.95,"n":20,"by_reason":{"no_think_close":1},"by_prompt":{"assistant_bash":{"ok":false,"reasons":["no_think_close"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.13778737662517732,"se":0.041129380444827855,"z":-3.350096090312114,"sd_diff":1.2888664278859276,"n_paired_turns":982,"n_forfeit_turns":20,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"text":{"R":0.10255719469391461,"A":21.009507250550964,"Mc":0.15329802401215667},"bash":{"R":0.022323909821226392,"A":6.877235495622558,"Mc":0.15758760198701174},"tool_call":{"R":0.009492434899845668,"A":6.233247046551943,"Mc":0.18676429076201614},"boxed":{"R":0.08285378234361197,"A":5.127103731627152,"Mc":0.12331447204098553},"terminus_json":{"R":0.0029731360616376485,"A":7.959751788739944,"Mc":0.12711782647444678}},"challenger":{"mean":-0.7626305468397627,"mean_valid":-0.6374127740511084,"sd_valid":1.3860481489531837,"n_turns":995,"n_valid":962,"n_forfeits":23,"n_unscorable":10,"mean_z_R":0.06623156249307005,"mean_typ_c":0.620477646327583,"mean_z_A":-0.05821402571136818,"bind_frac":{"R":0.3627858627858628,"Gc":0.16216216216216217,"A":0.47505197505197505},"n_leg_dropped":{"R":0,"Gc":32,"A":0},"mean_content_share":0.2873090406960629,"mean_R":0.0132761855451315,"mean_A":2.546480138720065,"mean_mc":-0.6368019588694888},"king":{"mean":-0.6088430598688821,"mean_valid":-0.5923226606652117,"sd_valid":1.2389792298246234,"n_turns":995,"n_valid":979,"n_forfeits":3,"n_unscorable":13,"mean_z_R":0.10292216230332962,"mean_typ_c":0.6867399725859767,"mean_z_A":-0.09405906534384709,"bind_frac":{"R":0.3258426966292135,"Gc":0.1470888661899898,"A":0.5270684371807968},"n_leg_dropped":{"R":0,"Gc":41,"A":0},"mean_content_share":0.27616324225771016,"mean_R":0.013649581754739199,"mean_A":1.9326475212910816,"mean_mc":-0.6708709704734711}},"rejection_reason":null,"reign_number":null,"score":0.0016915808340065347,"score_king":0.0027973656659667414,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9138085,"blocks_since_crown":14775,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1364.3334474495036,"mean_len_y":709.974666210202,"n_samples":3000,"think_close_rate":0.9586666666666667,"n_text_fallback":25,"by_dialect":{"text":{"n_turns":355,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":277,"zero_ref_turns":0,"mean_refs":2.927797833935018,"ref_pair_agreement":0.1897810218978102,"ref_pair_n":274},"tool_call":{"n_turns":303,"zero_ref_turns":2,"mean_refs":2.881188118811881,"ref_pair_agreement":0.1807511737089202,"ref_pair_n":284},"boxed":{"n_turns":42,"zero_ref_turns":1,"mean_refs":2.642857142857143,"ref_pair_agreement":0.6190476190476191,"ref_pair_n":35},"terminus_json":{"n_turns":23,"zero_ref_turns":2,"mean_refs":2.652173913043478,"ref_pair_agreement":0.3492063492063492,"ref_pair_n":21}},"ref_pair_agreement":0.21552660152008687,"ref_pair_n":614},"duel_seconds":2164.9901792928576,"challenger":{"reason":0.0016915808340065347,"n_turns":995,"n_pairs":2862,"n_forfeits":23,"forfeit_rate":0.023115577889447236,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-21.993441083185864,"mean_len_z":1198.927672955975,"median_len_z":618.0,"mean_len_y":442.64709993011877,"mean_b":0.08707118129724208,"b_gate_pass_rate":0.506638714185884,"mean_r_leg":0.0132761855451315,"mean_g_leg":0.057130479043187146,"g_bind_frac":0.21296296296296297,"a_match":0.1874662344678552,"a_match_n":617,"a_match_centered":-0.024322830292979547,"n_turns_cap_raised":36,"mean_cap_tokens":4134.4150753768845,"max_cap_tokens":6010,"len_z_delta":-165.40577449352872,"len_y_delta":-267.32756628008326,"n_samples":998,"think_close_rate":0.9799599198396793,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":277,"n_valid":272,"parse_rate":0.9819494584837545,"reason":0.005101219302172243,"mean_b":0.1078881505970385,"b_gate_pass_rate":0.8621553884711779,"median_len_z":499.0,"mean_r_leg":0.016828149093087236,"mean_g_leg":0.04478592234188751,"g_bind_frac":0.27941176470588236,"a_match":0.16850490196078433,"a_match_n":272,"a_match_centered":-0.021685254027261465},"boxed":{"n_turns":41,"n_valid":36,"parse_rate":0.8780487804878049,"reason":-0.0075373539249493915,"mean_b":0.8441351649114446,"b_gate_pass_rate":0.3137254901960784,"median_len_z":2787.0,"mean_r_leg":0.05593999825253472,"mean_g_leg":0.028283784949186132,"g_bind_frac":0.4444444444444444,"a_match":0.47058823529411764,"a_match_n":34,"a_match_centered":-0.14583333333333334},"terminus_json":{"n_turns":21,"n_valid":20,"parse_rate":0.9523809523809523,"reason":-0.007173940493001595,"mean_b":0.01926408534021607,"b_gate_pass_rate":0.41379310344827586,"median_len_z":593.5,"mean_r_leg":0.0008046828387052007,"mean_g_leg":0.03499979301001787,"g_bind_frac":0.35,"a_match":0.375,"a_match_n":20,"a_match_centered":0.008333333333333331},"text":{"n_turns":355,"n_valid":346,"parse_rate":0.9746478873239437,"reason":0.0023992025727732165,"mean_b":0.052779173592114315,"b_gate_pass_rate":0.3352601156069364,"median_len_z":781.5,"mean_r_leg":0.013276863657395775,"mean_g_leg":0.06183679868043455,"g_bind_frac":0.16184971098265896,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":301,"n_valid":298,"parse_rate":0.9900332225913622,"reason":-0.000405141092769909,"mean_b":0.024363846116576878,"b_gate_pass_rate":0.4133949191685912,"median_len_z":474.0,"mean_r_leg":0.005716333480616772,"mean_g_leg":0.06790372580933923,"g_bind_frac":0.174496644295302,"a_match":0.15922107674684996,"a_match_n":291,"a_match_centered":-0.015366430260047281}}},"king":{"reason":0.0027973656659667414,"n_turns":995,"n_pairs":2912,"n_forfeits":3,"forfeit_rate":0.003015075376884422,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-22.3444979988909,"mean_len_z":931.1167582417582,"median_len_z":660.0,"mean_len_y":351.6909340659341,"mean_b":0.09917047578478666,"b_gate_pass_rate":0.5903159340659341,"mean_r_leg":0.013649581754739199,"mean_g_leg":0.05632053302956885,"g_bind_frac":0.21673387096774194,"a_match":0.17987321711568938,"a_match_n":631,"a_match_centered":-0.03072321914083741,"n_turns_cap_raised":36,"mean_cap_tokens":4134.4150753768845,"max_cap_tokens":6010,"len_z_delta":-433.2166892077454,"len_y_delta":-358.28373214426796,"n_samples":995,"think_close_rate":0.9969849246231156,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":277,"n_valid":277,"parse_rate":1.0,"reason":0.0075732725327640905,"mean_b":0.11170250536679797,"b_gate_pass_rate":0.8828606658446363,"median_len_z":508.0,"mean_r_leg":0.01929218133967246,"mean_g_leg":0.04323206144321031,"g_bind_frac":0.2743682310469314,"a_match":0.1835138387484958,"a_match_n":277,"a_match_centered":-0.004257907542579076},"boxed":{"n_turns":41,"n_valid":41,"parse_rate":1.0,"reason":0.007772170942186845,"mean_b":0.9243815744390581,"b_gate_pass_rate":0.8198198198198198,"median_len_z":1857.0,"mean_r_leg":0.05262482575329237,"mean_g_leg":0.030875328999604542,"g_bind_frac":0.5121951219512195,"a_match":0.39316239316239315,"a_match_n":39,"a_match_centered":-0.20952380952380953},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":-0.001463039290288267,"mean_b":0.02693056698603535,"b_gate_pass_rate":0.6065573770491803,"median_len_z":673.0,"mean_r_leg":0.0013010954512395515,"mean_g_leg":0.034888492600847545,"g_bind_frac":0.2857142857142857,"a_match":0.3253968253968254,"a_match_n":21,"a_match_centered":-0.023809523809523808},"text":{"n_turns":355,"n_valid":352,"parse_rate":0.9915492957746479,"reason":-8.78330229602393e-05,"mean_b":0.06310819023867253,"b_gate_pass_rate":0.4147727272727273,"median_len_z":791.5,"mean_r_leg":0.011933738079032903,"mean_g_leg":0.05941416252812566,"g_bind_frac":0.17613636363636365,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":301,"n_valid":301,"parse_rate":1.0,"reason":0.001424677361058248,"mean_b":0.03127414134238694,"b_gate_pass_rate":0.5005727376861397,"median_len_z":586.0,"mean_r_leg":0.0060160604831608466,"mean_g_leg":0.06970882293043597,"g_bind_frac":0.16611295681063123,"a_match":0.1377551020408163,"a_match_n":294,"a_match_centered":-0.03474676089517079}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T11:37:46.066004+00:00","challenge_id":"chal-00684","repo":"r2://affine-private-models/models/registrations/7d0afc5418c6ac42470128ce314cc381886daa2d9b68c8fa758385944c5508f9/","hotkey":"5DXneBViuM5W15GX21QVVq3BNTr852NHr2zDDstyxTV4esjd","uid":67,"duration_s":2578.0,"revision":"1263db471baf0f6ee7168f73693566bd71ef694d74e0658701161edb4951db98","accepted":false,"error_code":null,"error_detail":"","z":0.16749464021109245,"margin":0.004983463414105205,"se":0.029752972440339445,"n_paired_turns":990,"n_forfeit_turns":7,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":4479857479960154904,"n":1000,"digest":"af0dab30aeb971ed34dab59f92abe2127c96d3f57a957bc293a45133e69f2281","n_paired_turns":990,"n_forfeit_turns":7,"margin":0.004983463414105205,"se":0.029752972440339445,"z":0.16749464021109245,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.004983463414105205,"se":0.029752972440339445,"z":0.16749464021109245,"sd_diff":0.9361554226437203,"n_paired_turns":990,"n_forfeit_turns":7,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.02114115054333135,"A":8.153745396791452,"Mc":0.15842372093792076},"tool_call":{"R":0.008812390699732426,"A":5.2651404484974265,"Mc":0.1769363871933839},"text":{"R":0.0903399254579322,"A":17.188519886749475,"Mc":0.1462974499000135},"terminus_json":{"R":0.002084796250613733,"A":4.973934268611787,"Mc":0.11733945954367213},"boxed":{"R":0.05155274823734511,"A":4.828925861811939,"Mc":0.10976659775222841}},"challenger":{"mean":-0.6344885560722046,"mean_valid":-0.6017720228775228,"sd_valid":1.3272574783708355,"n_turns":995,"n_valid":984,"n_forfeits":6,"n_unscorable":5,"mean_z_R":0.15254123688107787,"mean_typ_c":0.7134819514689523,"mean_z_A":-0.09114956871999062,"bind_frac":{"R":0.3475609756097561,"Gc":0.14939024390243902,"A":0.5030487804878049},"n_leg_dropped":{"R":0,"Gc":53,"A":0},"mean_content_share":0.2798026877207035,"mean_R":0.01501471594334011,"mean_A":2.519240221409293,"mean_mc":-0.6419406243102407},"king":{"mean":-0.6394720194863097,"mean_valid":-0.6231786213692468,"sd_valid":1.2749597192306512,"n_turns":995,"n_valid":987,"n_forfeits":3,"n_unscorable":5,"mean_z_R":0.15020259697155852,"mean_typ_c":0.6609049756272422,"mean_z_A":-0.10056118456423987,"bind_frac":{"R":0.3262411347517731,"Gc":0.15602836879432624,"A":0.5177304964539007},"n_leg_dropped":{"R":0,"Gc":56,"A":0},"mean_content_share":0.2769783845185967,"mean_R":0.015526277691457938,"mean_A":2.2648339411997727,"mean_mc":-0.6711969830768484}},"rejection_reason":null,"reign_number":null,"score":0.002266916993458777,"score_king":0.0021204328666131443,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9137062,"blocks_since_crown":13752,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1408.4361666102268,"mean_len_y":677.0033863867253,"n_samples":3000,"think_close_rate":0.9696666666666667,"n_text_fallback":25,"by_dialect":{"bash":{"n_turns":279,"zero_ref_turns":2,"mean_refs":2.942652329749104,"ref_pair_agreement":0.20652173913043478,"ref_pair_n":276},"tool_call":{"n_turns":323,"zero_ref_turns":1,"mean_refs":2.9473684210526314,"ref_pair_agreement":0.18162393162393162,"ref_pair_n":312},"text":{"n_turns":350,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":35,"zero_ref_turns":2,"mean_refs":2.6285714285714286,"ref_pair_agreement":0.5666666666666667,"ref_pair_n":30},"terminus_json":{"n_turns":13,"zero_ref_turns":0,"mean_refs":2.923076923076923,"ref_pair_agreement":0.3333333333333333,"ref_pair_n":13}},"ref_pair_agreement":0.21394611727416799,"ref_pair_n":631},"duel_seconds":2110.412077980116,"challenger":{"reason":0.002266916993458777,"n_turns":995,"n_pairs":2936,"n_forfeits":6,"forfeit_rate":0.006030150753768844,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-28.325279190741615,"mean_len_z":983.4928474114441,"median_len_z":645.0,"mean_len_y":363.7568119891008,"mean_b":0.09049765593239727,"b_gate_pass_rate":0.5378065395095368,"mean_r_leg":0.01501471594334011,"mean_g_leg":0.05799367398954217,"g_bind_frac":0.20930232558139536,"a_match":0.14072327044025157,"a_match_n":636,"a_match_centered":-0.07268370607028754,"n_turns_cap_raised":43,"mean_cap_tokens":4141.020100502513,"max_cap_tokens":6042,"len_z_delta":-424.94331919878266,"len_y_delta":-313.2465743976245,"n_samples":998,"think_close_rate":0.9949899799599199,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":277,"n_valid":276,"parse_rate":0.9963898916967509,"reason":0.007917914962181296,"mean_b":0.11593426386349237,"b_gate_pass_rate":0.8863080684596577,"median_len_z":487.0,"mean_r_leg":0.01677239173759019,"mean_g_leg":0.05248143915508578,"g_bind_frac":0.2210144927536232,"a_match":0.15157004830917875,"a_match_n":276,"a_match_centered":-0.051515151515151514},"boxed":{"n_turns":33,"n_valid":31,"parse_rate":0.9393939393939394,"reason":-0.005450154749564306,"mean_b":0.7976873564249607,"b_gate_pass_rate":0.7471264367816092,"median_len_z":2285.0,"mean_r_leg":0.05087103829595133,"mean_g_leg":0.01452989280306456,"g_bind_frac":0.5161290322580645,"a_match":0.35,"a_match_n":30,"a_match_centered":-0.23214285714285715},"terminus_json":{"n_turns":13,"n_valid":13,"parse_rate":1.0,"reason":-0.007759087319471195,"mean_b":0.015616654008847703,"b_gate_pass_rate":0.3157894736842105,"median_len_z":583.0,"mean_r_leg":0.0010020460800707405,"mean_g_leg":0.02629674403415204,"g_bind_frac":0.23076923076923078,"a_match":0.38461538461538464,"a_match_n":13,"a_match_centered":0.05128205128205128},"text":{"n_turns":350,"n_valid":347,"parse_rate":0.9914285714285714,"reason":-0.0002897929718830059,"mean_b":0.07070924742148407,"b_gate_pass_rate":0.34870317002881845,"median_len_z":804.0,"mean_r_leg":0.01897474292788179,"mean_g_leg":0.05905884942895878,"g_bind_frac":0.19596541786743515,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":322,"n_valid":322,"parse_rate":1.0,"reason":0.0013803439317238001,"mean_b":0.02864110351902196,"b_gate_pass_rate":0.43487394957983194,"median_len_z":507.0,"mean_r_leg":0.006354376913658647,"mean_g_leg":0.06703466232194366,"g_bind_frac":0.18322981366459629,"a_match":0.10147213459516298,"a_match_n":317,"a_match_centered":-0.08225806451612903}}},"king":{"reason":0.0021204328666131443,"n_turns":995,"n_pairs":2945,"n_forfeits":3,"forfeit_rate":0.003015075376884422,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-26.410107024928333,"mean_len_z":976.70220713073,"median_len_z":654.0,"mean_len_y":338.93480475382006,"mean_b":0.08786805555993782,"b_gate_pass_rate":0.5429541595925297,"mean_r_leg":0.015526277691457938,"mean_g_leg":0.056829514405974516,"g_bind_frac":0.21875,"a_match":0.14054336468129572,"a_match_n":638,"a_match_centered":-0.07218683651804671,"n_turns_cap_raised":43,"mean_cap_tokens":4141.020100502513,"max_cap_tokens":6042,"len_z_delta":-431.7339594794968,"len_y_delta":-338.06858163290525,"n_samples":995,"think_close_rate":0.9989949748743718,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":277,"n_valid":276,"parse_rate":0.9963898916967509,"reason":0.007941911915621463,"mean_b":0.11512591979408641,"b_gate_pass_rate":0.8679706601466992,"median_len_z":491.0,"mean_r_leg":0.01699448587647568,"mean_g_leg":0.0520835075204381,"g_bind_frac":0.22826086956521738,"a_match":0.1431159420289855,"a_match_n":276,"a_match_centered":-0.06},"boxed":{"n_turns":33,"n_valid":33,"parse_rate":1.0,"reason":0.0030628179164317003,"mean_b":0.7774841424107791,"b_gate_pass_rate":0.6521739130434783,"median_len_z":2169.5,"mean_r_leg":0.06169637183156718,"mean_g_leg":0.018207585499512974,"g_bind_frac":0.5454545454545454,"a_match":0.36363636363636365,"a_match_n":33,"a_match_centered":-0.2},"terminus_json":{"n_turns":13,"n_valid":12,"parse_rate":0.9230769230769231,"reason":-0.011614633896825108,"mean_b":0.016458815819296955,"b_gate_pass_rate":0.4166666666666667,"median_len_z":607.5,"mean_r_leg":0.0007435209605940405,"mean_g_leg":0.03140588309635803,"g_bind_frac":0.16666666666666666,"a_match":0.4166666666666667,"a_match_n":12,"a_match_centered":0.05555555555555555},"text":{"n_turns":350,"n_valid":349,"parse_rate":0.9971428571428571,"reason":-0.0012124867778320514,"mean_b":0.060558250467008815,"b_gate_pass_rate":0.3839541547277937,"median_len_z":804.0,"mean_r_leg":0.019137089930429813,"mean_g_leg":0.05733358749541712,"g_bind_frac":0.22349570200573066,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":322,"n_valid":322,"parse_rate":1.0,"reason":0.00119319479289016,"mean_b":0.030538733741816784,"b_gate_pass_rate":0.4327731092436975,"median_len_z":551.0,"mean_r_leg":0.006173423789845144,"mean_g_leg":0.06525679273461182,"g_bind_frac":0.17391304347826086,"a_match":0.10462670872765509,"a_match_n":317,"a_match_centered":-0.07556270096463022}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T08:22:16.872967+00:00","challenge_id":"chal-00683","repo":"r2://affine-private-models/models/registrations/5db30c14846130eb848808b20b6adb4a2b94e6e524fdf00c778a9416f7072797/","hotkey":"5CfiSUsMeRktCeYpjCXfrXc9Qdj8PpaTa4Fy72stgcLQcmJC","uid":18,"duration_s":2505.4,"revision":"390f4f1a16e6628df1385cbc0d21b4490e28e0d3ef72b4bc51e0d24884f05d4b","accepted":false,"error_code":null,"error_detail":"","z":-0.16664917821981856,"margin":-0.004673160789684805,"se":0.02804190719452978,"n_paired_turns":988,"n_forfeit_turns":3,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":14719525623836906279,"n":1000,"digest":"8fd3f7adb6f00d5ca8ae744ad723aa03c275dc4df9b91eff821290c5d4a681f1","n_paired_turns":988,"n_forfeit_turns":3,"margin":-0.004673160789684805,"se":0.02804190719452978,"z":-0.16664917821981856,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.004673160789684805,"se":0.02804190719452978,"z":-0.16664917821981856,"sd_diff":0.8814263306694109,"n_paired_turns":988,"n_forfeit_turns":3,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"tool_call":{"R":0.006878430962574459,"A":4.870297019138384,"Mc":0.17313240628529028},"text":{"R":0.07119762585888302,"A":20.7656373613227,"Mc":0.15851602888873048},"bash":{"R":0.022534391463799534,"A":6.083218680548814,"Mc":0.14079082154099828},"boxed":{"R":0.09064355241917468,"A":7.908772521767273,"Mc":0.10526567747001976},"terminus_json":{"R":0.0029107667104477865,"A":12.24118518960847,"Mc":0.13314725167534264}},"challenger":{"mean":-0.6386250860548099,"mean_valid":-0.6331930952605392,"sd_valid":1.3006941004852572,"n_turns":993,"n_valid":987,"n_forfeits":1,"n_unscorable":5,"mean_z_R":0.2647255450700719,"mean_typ_c":0.6622175791134065,"mean_z_A":-0.09243025357747119,"bind_frac":{"R":0.3282674772036474,"Gc":0.1661600810536981,"A":0.5055724417426545},"n_leg_dropped":{"R":0,"Gc":45,"A":0},"mean_content_share":0.2816119913046592,"mean_R":0.019192031307568653,"mean_A":2.521446788913276,"mean_mc":-0.6274625168828637},"king":{"mean":-0.6339519252651251,"mean_valid":-0.617608631636491,"sd_valid":1.2707478317634036,"n_turns":993,"n_valid":985,"n_forfeits":3,"n_unscorable":5,"mean_z_R":0.2368109022361459,"mean_typ_c":0.6170744678050318,"mean_z_A":-0.08408653732659838,"bind_frac":{"R":0.3197969543147208,"Gc":0.18274111675126903,"A":0.49746192893401014},"n_leg_dropped":{"R":0,"Gc":44,"A":0},"mean_content_share":0.2773206976224974,"mean_R":0.017096673263180706,"mean_A":2.5145332890450094,"mean_mc":-0.657318070138846}},"rejection_reason":null,"reign_number":null,"score":0.003987579366712384,"score_king":0.0034086032194628555,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9136090,"blocks_since_crown":12780,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1532.9068027210885,"mean_len_y":700.6853741496599,"n_samples":3000,"think_close_rate":0.9573333333333334,"n_text_fallback":12,"by_dialect":{"tool_call":{"n_turns":281,"zero_ref_turns":2,"mean_refs":2.9395017793594307,"ref_pair_agreement":0.14303030303030304,"ref_pair_n":275},"bash":{"n_turns":289,"zero_ref_turns":1,"mean_refs":2.9480968858131487,"ref_pair_agreement":0.19230769230769232,"ref_pair_n":286},"boxed":{"n_turns":55,"zero_ref_turns":4,"mean_refs":2.5454545454545454,"ref_pair_agreement":0.5185185185185185,"ref_pair_n":45},"text":{"n_turns":359,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":16,"zero_ref_turns":0,"mean_refs":2.8125,"ref_pair_agreement":0.3333333333333333,"ref_pair_n":16}},"ref_pair_agreement":0.1977491961414791,"ref_pair_n":622},"duel_seconds":2027.3253892376088,"challenger":{"reason":0.003987579366712384,"n_turns":993,"n_pairs":2937,"n_forfeits":1,"forfeit_rate":0.0010070493454179255,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.1700038912991806,"mean_len_z":993.8675519237318,"median_len_z":636.0,"mean_len_y":365.76881171263193,"mean_b":0.11962096502467057,"b_gate_pass_rate":0.5594143684031324,"mean_r_leg":0.019192031307568653,"mean_g_leg":0.057899906273528166,"g_bind_frac":0.2399193548387097,"a_match":0.15122470713525027,"a_match_n":626,"a_match_centered":-0.04878048780487805,"n_turns_cap_raised":60,"mean_cap_tokens":4159.221550855992,"max_cap_tokens":6068,"len_z_delta":-539.0392507973568,"len_y_delta":-334.91656243702795,"n_samples":996,"think_close_rate":0.998995983935743,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":288,"n_valid":288,"parse_rate":1.0,"reason":0.010063085180108722,"mean_b":0.12091750031818801,"b_gate_pass_rate":0.9096244131455399,"median_len_z":466.0,"mean_r_leg":0.018448321969629172,"mean_g_leg":0.0480874406754865,"g_bind_frac":0.2847222222222222,"a_match":0.15046296296296297,"a_match_n":288,"a_match_centered":-0.04079254079254079},"boxed":{"n_turns":51,"n_valid":51,"parse_rate":1.0,"reason":0.0057256782330589815,"mean_b":0.974922835017254,"b_gate_pass_rate":0.7071428571428572,"median_len_z":3019.0,"mean_r_leg":0.07769081845325476,"mean_g_leg":0.01431480575656574,"g_bind_frac":0.6862745098039216,"a_match":0.45185185185185184,"a_match_n":45,"a_match_centered":-0.11666666666666667},"terminus_json":{"n_turns":16,"n_valid":16,"parse_rate":1.0,"reason":-0.004313785472762082,"mean_b":0.026978604582741508,"b_gate_pass_rate":0.6888888888888889,"median_len_z":768.0,"mean_r_leg":0.001636422736006138,"mean_g_leg":0.030207625810940265,"g_bind_frac":0.25,"a_match":0.3541666666666667,"a_match_n":16,"a_match_centered":0.02083333333333333},"text":{"n_turns":359,"n_valid":358,"parse_rate":0.9972144846796658,"reason":0.0002493218880884539,"mean_b":0.08098566555016073,"b_gate_pass_rate":0.3547486033519553,"median_len_z":758.0,"mean_r_leg":0.02166659785848987,"mean_g_leg":0.059692569108648966,"g_bind_frac":0.21508379888268156,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":279,"n_valid":279,"parse_rate":1.0,"reason":0.0026845956958011317,"mean_b":0.028599546122094095,"b_gate_pass_rate":0.4322033898305085,"median_len_z":488.0,"mean_r_leg":0.007097927568542794,"mean_g_leg":0.0752838969940631,"g_bind_frac":0.14336917562724014,"a_match":0.0914560770156438,"a_match_n":277,"a_match_centered":-0.05128205128205128}}},"king":{"reason":0.0034086032194628555,"n_turns":993,"n_pairs":2931,"n_forfeits":3,"forfeit_rate":0.0030211480362537764,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-2.293587830924767,"mean_len_z":951.4261344251108,"median_len_z":657.0,"mean_len_y":334.54759467758447,"mean_b":0.11879161825654776,"b_gate_pass_rate":0.5841009894234049,"mean_r_leg":0.017096673263180706,"mean_g_leg":0.057946290166512794,"g_bind_frac":0.24141414141414141,"a_match":0.1520700636942675,"a_match_n":628,"a_match_centered":-0.04781199351701783,"n_turns_cap_raised":60,"mean_cap_tokens":4159.221550855992,"max_cap_tokens":6068,"len_z_delta":-581.4806682959777,"len_y_delta":-366.1377794720754,"n_samples":993,"think_close_rate":0.9979859013091642,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":288,"n_valid":288,"parse_rate":1.0,"reason":0.009348234994378493,"mean_b":0.12174965075961451,"b_gate_pass_rate":0.8931924882629108,"median_len_z":461.0,"mean_r_leg":0.01996371758813299,"mean_g_leg":0.046011033164074566,"g_bind_frac":0.2708333333333333,"a_match":0.14699074074074076,"a_match_n":288,"a_match_centered":-0.04428904428904429},"boxed":{"n_turns":51,"n_valid":50,"parse_rate":0.9803921568627451,"reason":0.005094462349025229,"mean_b":1.0021663016244489,"b_gate_pass_rate":0.7883211678832117,"median_len_z":2316.0,"mean_r_leg":0.0731540055587661,"mean_g_leg":0.014479296131235705,"g_bind_frac":0.6,"a_match":0.45035460992907805,"a_match_n":47,"a_match_centered":-0.09920634920634921},"terminus_json":{"n_turns":16,"n_valid":16,"parse_rate":1.0,"reason":-0.009507544834940106,"mean_b":0.024700053986852814,"b_gate_pass_rate":0.5555555555555556,"median_len_z":707.0,"mean_r_leg":0.0012993115534507705,"mean_g_leg":0.02320675421829376,"g_bind_frac":0.3125,"a_match":0.3125,"a_match_n":16,"a_match_centered":-0.020833333333333336},"text":{"n_turns":359,"n_valid":357,"parse_rate":0.9944289693593314,"reason":0.00031249790308516016,"mean_b":0.07573231289137523,"b_gate_pass_rate":0.41456582633053224,"median_len_z":813.0,"mean_r_leg":0.015702592722138396,"mean_g_leg":0.06035557784309188,"g_bind_frac":0.22969187675070027,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":279,"n_valid":279,"parse_rate":1.0,"reason":0.0016937910713146667,"mean_b":0.03018152276528956,"b_gate_pass_rate":0.45278450363196127,"median_len_z":533.0,"mean_r_leg":0.006780792116737178,"mean_g_leg":0.07696571881561255,"g_bind_frac":0.15770609318996415,"a_match":0.09747292418772563,"a_match_n":277,"a_match_centered":-0.045177045177045176}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T05:00:12.796111+00:00","challenge_id":"chal-00682","repo":"r2://affine-private-models/models/registrations/c58b098b93cadcd1a90eb812b8c630324553df09f135c1c7c3b8b85d281dc04f/","hotkey":"5CyjqiGUU6erDpJ1oky4eWfUxtFJrE6By3WvEErFK74GPUrU","uid":14,"duration_s":2568.9,"revision":"dea6da9317f023b695423ec2cc4d3c13f01222e272cbae51db15c06d2e5c798e","accepted":false,"error_code":null,"error_detail":"","z":1.3234369551420972,"margin":0.04723204236528492,"se":0.03568892509897732,"n_paired_turns":990,"n_forfeit_turns":10,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":4220953849699191278,"n":1000,"digest":"797078aeb8b94066effe05bd16232dff1e4a5d7cbdd8e12b24259a21006c0156","n_paired_turns":990,"n_forfeit_turns":10,"margin":0.04723204236528492,"se":0.03568892509897732,"z":1.3234369551420972,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.04723204236528492,"se":0.03568892509897732,"z":1.3234369551420972,"sd_diff":1.1229258127646766,"n_paired_turns":990,"n_forfeit_turns":10,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"text":{"R":0.04924005526902264,"A":12.285460876472065,"Mc":0.15359150814381348},"bash":{"R":0.022903829226466728,"A":6.026512360024215,"Mc":0.14824512929832528},"tool_call":{"R":0.0078064155163276505,"A":6.441198269768981,"Mc":0.18167054269741262},"terminus_json":{"R":0.003172091328914339,"A":9.617033405693578,"Mc":0.14166642109509867},"boxed":{"R":0.12660303882984927,"A":6.07578600967651,"Mc":0.10558839453796733}},"challenger":{"mean":-0.7532019109146358,"mean_valid":-0.7051151667173158,"sd_valid":1.5794379330188042,"n_turns":997,"n_valid":982,"n_forfeits":9,"n_unscorable":6,"mean_z_R":0.19858515061180504,"mean_typ_c":0.6634916411940264,"mean_z_A":-0.05493593454290818,"bind_frac":{"R":0.3665987780040733,"Gc":0.15376782077393075,"A":0.47963340122199594},"n_leg_dropped":{"R":0,"Gc":36,"A":0},"mean_content_share":0.2796733328886479,"mean_R":0.01746451198386981,"mean_A":3.293603158538496,"mean_mc":-0.6240583087423702},"king":{"mean":-0.7951341572303395,"mean_valid":-0.7687135184345545,"sd_valid":1.5044487105237316,"n_turns":997,"n_valid":985,"n_forfeits":5,"n_unscorable":7,"mean_z_R":0.19743599961507696,"mean_typ_c":0.6505612522800774,"mean_z_A":-0.15588282929173283,"bind_frac":{"R":0.3461928934010152,"Gc":0.15736040609137056,"A":0.4964467005076142},"n_leg_dropped":{"R":0,"Gc":36,"A":0},"mean_content_share":0.27607982962199845,"mean_R":0.01804559734715753,"mean_A":2.4246517057745627,"mean_mc":-0.6731908281262694}},"rejection_reason":null,"reign_number":null,"score":0.0030830373108676136,"score_king":0.0021620062796979963,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9135075,"blocks_since_crown":11765,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1446.0689422102062,"mean_len_y":714.6279148360933,"n_samples":3000,"think_close_rate":0.9686666666666667,"n_text_fallback":7,"by_dialect":{"text":{"n_turns":367,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":290,"zero_ref_turns":0,"mean_refs":2.962068965517241,"ref_pair_agreement":0.16724336793540948,"ref_pair_n":289},"tool_call":{"n_turns":286,"zero_ref_turns":2,"mean_refs":2.9475524475524475,"ref_pair_agreement":0.16904761904761906,"ref_pair_n":280},"terminus_json":{"n_turns":16,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.2708333333333333,"ref_pair_n":16},"boxed":{"n_turns":41,"zero_ref_turns":1,"mean_refs":2.6341463414634148,"ref_pair_agreement":0.48484848484848486,"ref_pair_n":33}},"ref_pair_agreement":0.18770226537216828,"ref_pair_n":618},"duel_seconds":2109.1140045849606,"challenger":{"reason":0.0030830373108676136,"n_turns":997,"n_pairs":2934,"n_forfeits":9,"forfeit_rate":0.009027081243731194,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.8297208963737952,"mean_len_z":1056.4720518064075,"median_len_z":674.5,"mean_len_y":400.43353783231083,"mean_b":0.09401307784800017,"b_gate_pass_rate":0.5613496932515337,"mean_r_leg":0.01746451198386981,"mean_g_leg":0.06139515759109219,"g_bind_frac":0.18927125506072875,"a_match":0.1594551282051282,"a_match_n":624,"a_match_centered":-0.026785714285714284,"n_turns_cap_raised":39,"mean_cap_tokens":4133.644934804413,"max_cap_tokens":6062,"len_z_delta":-389.5968904037986,"len_y_delta":-314.19437700378245,"n_samples":1000,"think_close_rate":0.991,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":290,"n_valid":290,"parse_rate":1.0,"reason":0.007931608228777993,"mean_b":0.11943444605933953,"b_gate_pass_rate":0.9010477299185099,"median_len_z":521.0,"mean_r_leg":0.017666244556379877,"mean_g_leg":0.05246979040244701,"g_bind_frac":0.22758620689655173,"a_match":0.15804597701149425,"a_match_n":290,"a_match_centered":-0.00865051903114187},"boxed":{"n_turns":40,"n_valid":38,"parse_rate":0.95,"reason":0.004628602868723401,"mean_b":0.901389928291995,"b_gate_pass_rate":0.7019230769230769,"median_len_z":2047.0,"mean_r_leg":0.10407188098983826,"mean_g_leg":0.019479689774930205,"g_bind_frac":0.631578947368421,"a_match":0.3333333333333333,"a_match_n":36,"a_match_centered":-0.125},"terminus_json":{"n_turns":16,"n_valid":16,"parse_rate":1.0,"reason":0.0015594816071529101,"mean_b":0.02245642778057716,"b_gate_pass_rate":0.3125,"median_len_z":524.0,"mean_r_leg":0.0015594816071529101,"mean_g_leg":0.06263837884594967,"g_bind_frac":0.0,"a_match":0.35416666666666663,"a_match_n":16,"a_match_centered":0.08333333333333333},"text":{"n_turns":367,"n_valid":360,"parse_rate":0.9809264305177112,"reason":-0.0011840309441172468,"mean_b":0.049996933773667956,"b_gate_pass_rate":0.36944444444444446,"median_len_z":837.0,"mean_r_leg":0.017742962845655266,"mean_g_leg":0.06445713084394004,"g_bind_frac":0.175,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.003514314607806479,"mean_b":0.028969195361403625,"b_gate_pass_rate":0.4578884934756821,"median_len_z":561.0,"mean_r_leg":0.006213299686440182,"mean_g_leg":0.07216608136087495,"g_bind_frac":0.11971830985915492,"a_match":0.1276595744680851,"a_match_n":282,"a_match_centered":-0.040621266427718045}}},"king":{"reason":0.0021620062796979963,"n_turns":997,"n_pairs":2944,"n_forfeits":5,"forfeit_rate":0.0050150451354062184,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.2246356893958428,"mean_len_z":981.7367527173913,"median_len_z":679.0,"mean_len_y":351.01222826086956,"mean_b":0.10183618689001653,"b_gate_pass_rate":0.5798233695652174,"mean_r_leg":0.01804559734715753,"mean_g_leg":0.05977935683152477,"g_bind_frac":0.2217741935483871,"a_match":0.14699627857522596,"a_match_n":627,"a_match_centered":-0.03862776877363587,"n_turns_cap_raised":39,"mean_cap_tokens":4133.644934804413,"max_cap_tokens":6062,"len_z_delta":-464.3321894928149,"len_y_delta":-363.6156865752237,"n_samples":997,"think_close_rate":0.9949849548645938,"n_text_fallback":0,"by_dialect":{"bash":{"n_turns":290,"n_valid":290,"parse_rate":1.0,"reason":0.008266842267650001,"mean_b":0.12219139770239465,"b_gate_pass_rate":0.8859138533178114,"median_len_z":499.0,"mean_r_leg":0.019272647699885643,"mean_g_leg":0.05123933881104268,"g_bind_frac":0.25862068965517243,"a_match":0.14195402298850573,"a_match_n":290,"a_match_centered":-0.024798154555940023},"boxed":{"n_turns":40,"n_valid":40,"parse_rate":1.0,"reason":0.009504173681474434,"mean_b":0.9331500701501825,"b_gate_pass_rate":0.6944444444444444,"median_len_z":1800.5,"mean_r_leg":0.10728708875823428,"mean_g_leg":0.018927104587528963,"g_bind_frac":0.75,"a_match":0.3333333333333333,"a_match_n":38,"a_match_centered":-0.10416666666666667},"terminus_json":{"n_turns":16,"n_valid":16,"parse_rate":1.0,"reason":-0.00012103754964528618,"mean_b":0.023510675705123874,"b_gate_pass_rate":0.375,"median_len_z":448.5,"mean_r_leg":0.0009077987526091901,"mean_g_leg":0.05989703111324077,"g_bind_frac":0.0625,"a_match":0.3333333333333333,"a_match_n":16,"a_match_centered":0.0625},"text":{"n_turns":367,"n_valid":362,"parse_rate":0.9863760217983651,"reason":-0.0026170099351935008,"mean_b":0.06290817051126311,"b_gate_pass_rate":0.4143646408839779,"median_len_z":825.5,"mean_r_leg":0.017631897650503967,"mean_g_leg":0.061588234349222636,"g_bind_frac":0.19060773480662985,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.0011984095175766347,"mean_b":0.02920086642058629,"b_gate_pass_rate":0.47805456702253857,"median_len_z":570.0,"mean_r_leg":0.005716230477323514,"mean_g_leg":0.07194132466879787,"g_bind_frac":0.15845070422535212,"a_match":0.1166077738515901,"a_match_n":283,"a_match_centered":-0.051190476190476196}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-24T04:16:16.357365+00:00","challenge_id":"chal-00681","repo":"r2://affine-private-models/models/registrations/bb5379c53ac03486290a4a9e440cc875cc387f8ab661f5e8344f82ba64a72513/","hotkey":"5GSxzP9kFd8RMqFCZeFNL7vhZ5hhB8NekFxt4T2k5K4TRoDL","uid":238,"duration_s":2576.4,"revision":"95bc24909d5ffef1cf55f41bd5cdaad415c87e3a22a240ed7d3c815e5123806b","accepted":false,"error_code":null,"error_detail":"","z":-2.569858583380747,"margin":-0.09013088524517729,"se":0.03507231325025157,"n_paired_turns":990,"n_forfeit_turns":2,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":3308010583351980985,"n":1000,"digest":"99f12fb5ea03fbfe0f6665b700103e4b940e92c63a984255e95827405cb52de7","n_paired_turns":990,"n_forfeit_turns":2,"margin":-0.09013088524517729,"se":0.03507231325025157,"z":-2.569858583380747,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":1},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.09013088524517729,"se":0.03507231325025157,"z":-2.569858583380747,"sd_diff":1.1035245738797728,"n_paired_turns":990,"n_forfeit_turns":2,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.02276004051738787,"A":5.819817443232314,"Mc":0.14477992606968937},"tool_call":{"R":0.00693186263760767,"A":5.8473678200663075,"Mc":0.15633163880352918},"text":{"R":0.0762853211346077,"A":15.029030800367417,"Mc":0.15090234917819106},"boxed":{"R":0.11357482561535627,"A":5.441368091941412,"Mc":0.11022934970714855},"terminus_json":{"R":0.0019393004040753478,"A":14.326862030019589,"Mc":0.10048783308651651}},"challenger":{"mean":-0.8387276455681638,"mean_valid":-0.8282797258223504,"sd_valid":1.5948847671623991,"n_turns":995,"n_valid":988,"n_forfeits":2,"n_unscorable":5,"mean_z_R":0.2974141171197937,"mean_typ_c":0.4095810548133718,"mean_z_A":-0.20344467432112495,"bind_frac":{"R":0.305668016194332,"Gc":0.20040485829959515,"A":0.4939271255060729},"n_leg_dropped":{"R":0,"Gc":45,"A":0},"mean_content_share":0.25755532031610817,"mean_R":0.023412079327073416,"mean_A":2.0087702867880632,"mean_mc":-0.6970111572706758},"king":{"mean":-0.7485967603229865,"mean_valid":-0.7379663893924663,"sd_valid":1.5236518832556596,"n_turns":995,"n_valid":988,"n_forfeits":2,"n_unscorable":5,"mean_z_R":0.2792653537245763,"mean_typ_c":0.5185698179872635,"mean_z_A":-0.1394474796979129,"bind_frac":{"R":0.3410931174089069,"Gc":0.17307692307692307,"A":0.48582995951417},"n_leg_dropped":{"R":0,"Gc":45,"A":0},"mean_content_share":0.2798368908704896,"mean_R":0.02185971281087099,"mean_A":2.6663622800626947,"mean_mc":-0.6602042784227303}},"rejection_reason":null,"reign_number":null,"score":0.0034028075659564417,"score_king":0.002953585191198188,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9134854,"blocks_since_crown":11544,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1362.9827644474485,"mean_len_y":823.2281176072997,"n_samples":3000,"think_close_rate":0.965,"n_text_fallback":15,"by_dialect":{"tool_call":{"n_turns":257,"zero_ref_turns":3,"mean_refs":2.914396887159533,"ref_pair_agreement":0.2056451612903226,"ref_pair_n":248},"text":{"n_turns":395,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":295,"zero_ref_turns":0,"mean_refs":2.976271186440678,"ref_pair_agreement":0.19340159271899884,"ref_pair_n":293},"boxed":{"n_turns":36,"zero_ref_turns":1,"mean_refs":2.8055555555555554,"ref_pair_agreement":0.48484848484848486,"ref_pair_n":33},"terminus_json":{"n_turns":17,"zero_ref_turns":1,"mean_refs":2.7058823529411766,"ref_pair_agreement":0.20833333333333331,"ref_pair_n":16}},"ref_pair_agreement":0.21525423728813559,"ref_pair_n":590},"duel_seconds":2114.5504808970727,"challenger":{"reason":0.0034028075659564417,"n_turns":995,"n_pairs":2953,"n_forfeits":2,"forfeit_rate":0.0020100502512562816,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-8.54677677791326,"mean_len_z":1051.7846258042669,"median_len_z":837.0,"mean_len_y":429.5577378936675,"mean_b":0.11689225432022478,"b_gate_pass_rate":0.49779884862851337,"mean_r_leg":0.023412079327073416,"mean_g_leg":0.05120329639345553,"g_bind_frac":0.27492447129909364,"a_match":0.1455160744500846,"a_match_n":591,"a_match_centered":-0.06655290102389079,"n_turns_cap_raised":42,"mean_cap_tokens":4135.642211055277,"max_cap_tokens":6058,"len_z_delta":-311.19813864318166,"len_y_delta":-393.67037971363226,"n_samples":998,"think_close_rate":0.9979959919839679,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":295,"n_valid":295,"parse_rate":1.0,"reason":0.010520079346450804,"mean_b":0.12723309147935116,"b_gate_pass_rate":0.8405466970387244,"median_len_z":603.0,"mean_r_leg":0.02264004953554748,"mean_g_leg":0.04504602376836258,"g_bind_frac":0.29491525423728815,"a_match":0.11864406779661017,"a_match_n":295,"a_match_centered":-0.0739476678043231},"boxed":{"n_turns":35,"n_valid":35,"parse_rate":1.0,"reason":0.007469656997129956,"mean_b":0.8940989411444634,"b_gate_pass_rate":0.8910891089108911,"median_len_z":1609.0,"mean_r_leg":0.07761848291112824,"mean_g_leg":0.019429582893173886,"g_bind_frac":0.6,"a_match":0.3541666666666667,"a_match_n":32,"a_match_centered":-0.11827956989247311},"terminus_json":{"n_turns":16,"n_valid":16,"parse_rate":1.0,"reason":-0.014847486827768104,"mean_b":0.02856994469585021,"b_gate_pass_rate":0.5,"median_len_z":1040.5,"mean_r_leg":0.0018604493687199735,"mean_g_leg":0.004691284636964744,"g_bind_frac":0.4375,"a_match":0.20833333333333331,"a_match_n":16,"a_match_centered":0.0},"text":{"n_turns":395,"n_valid":393,"parse_rate":0.9949367088607595,"reason":0.00045035169514244375,"mean_b":0.10318909897152566,"b_gate_pass_rate":0.2366412213740458,"median_len_z":966.0,"mean_r_leg":0.031119570527084743,"mean_g_leg":0.0527801778071449,"g_bind_frac":0.26208651399491095,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":254,"n_valid":254,"parse_rate":1.0,"reason":0.00031733462868955924,"mean_b":0.026961301054372167,"b_gate_pass_rate":0.4539385847797063,"median_len_z":781.0,"mean_r_leg":0.006271554527023948,"mean_g_leg":0.06322279713926739,"g_bind_frac":0.21653543307086615,"a_match":0.14650537634408603,"a_match_n":248,"a_match_centered":-0.05555555555555555}}},"king":{"reason":0.002953585191198188,"n_turns":995,"n_pairs":2953,"n_forfeits":2,"forfeit_rate":0.0020100502512562816,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-8.706991561753343,"mean_len_z":949.753809685066,"median_len_z":692.0,"mean_len_y":361.82492380629867,"mean_b":0.10506617431698205,"b_gate_pass_rate":0.5800880460548594,"mean_r_leg":0.02185971281087099,"mean_g_leg":0.05232205937886381,"g_bind_frac":0.23967774420946628,"a_match":0.16835585585585586,"a_match_n":592,"a_match_centered":-0.04656445201590005,"n_turns_cap_raised":42,"mean_cap_tokens":4135.642211055277,"max_cap_tokens":6058,"len_z_delta":-413.2289547623825,"len_y_delta":-461.40319380100107,"n_samples":995,"think_close_rate":0.9979899497487437,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":295,"n_valid":295,"parse_rate":1.0,"reason":0.009328773251003935,"mean_b":0.13023896678796018,"b_gate_pass_rate":0.8667425968109339,"median_len_z":496.0,"mean_r_leg":0.021018756363349374,"mean_g_leg":0.045104908563324914,"g_bind_frac":0.28135593220338984,"a_match":0.14463276836158193,"a_match_n":295,"a_match_centered":-0.051194539249146756},"boxed":{"n_turns":35,"n_valid":35,"parse_rate":1.0,"reason":0.007968244124192957,"mean_b":0.8851626914753049,"b_gate_pass_rate":0.7821782178217822,"median_len_z":1707.0,"mean_r_leg":0.07364658244829693,"mean_g_leg":0.025521270629616913,"g_bind_frac":0.6,"a_match":0.3434343434343434,"a_match_n":33,"a_match_centered":-0.11458333333333334},"terminus_json":{"n_turns":16,"n_valid":16,"parse_rate":1.0,"reason":-0.008482554110794167,"mean_b":0.026025859906551645,"b_gate_pass_rate":0.6304347826086957,"median_len_z":849.5,"mean_r_leg":0.0023349089318728975,"mean_g_leg":0.012599456795340287,"g_bind_frac":0.375,"a_match":0.20833333333333331,"a_match_n":16,"a_match_centered":0.0},"text":{"n_turns":395,"n_valid":393,"parse_rate":0.9949367088607595,"reason":-3.0033778548283712e-05,"mean_b":0.07054205523226402,"b_gate_pass_rate":0.40966921119592875,"median_len_z":826.0,"mean_r_leg":0.028503999087098324,"mean_g_leg":0.054283276106135245,"g_bind_frac":0.19338422391857507,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":254,"n_valid":254,"parse_rate":1.0,"reason":0.000218601654128194,"mean_b":0.029563278243888526,"b_gate_pass_rate":0.4819759679572764,"median_len_z":580.0,"mean_r_leg":0.006650004425893014,"mean_g_leg":0.063864935616369,"g_bind_frac":0.2047244094488189,"a_match":0.1706989247311828,"a_match_n":248,"a_match_centered":-0.03523035230352303}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T23:04:18.125911+00:00","challenge_id":"chal-00680","repo":"r2://affine-private-models/models/registrations/a9027b7431a07dfb1007ad1d49387583cc5f3b69430e04e6057f2f4184bb2445/","hotkey":"5EK1zZSNvxUHMKXCVB7yfVoY1N6nx6ARbpJNUVANVKVZqpkd","uid":230,"duration_s":2567.1,"revision":"2712922b11bf10ac13c665a7069d821d26a8dec0b3fe61f3fb1773aaf179c113","accepted":false,"error_code":null,"error_detail":"","z":-2.1219006948405577,"margin":-0.07780361482884098,"se":0.036666944413573155,"n_paired_turns":993,"n_forfeit_turns":3,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":5046160175723833043,"n":1000,"digest":"b47fdcb2a5932765226a002c83a4c07e6e64aa7b504607cf9f2f2207e930e0d6","n_paired_turns":993,"n_forfeit_turns":3,"margin":-0.07780361482884098,"se":0.036666944413573155,"z":-2.1219006948405577,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.07780361482884098,"se":0.036666944413573155,"z":-2.1219006948405577,"sd_diff":1.1554451778166142,"n_paired_turns":993,"n_forfeit_turns":3,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.021006195257468184,"A":5.3794543421967855,"Mc":0.149947242267268},"text":{"R":0.04552856718091404,"A":42.17434116066389,"Mc":0.14714771774910698},"tool_call":{"R":0.007774860895845887,"A":5.021238139127047,"Mc":0.17777971779182927},"terminus_json":{"R":0.001037693005507406,"A":5.557019084738828,"Mc":0.09725752430244695},"boxed":{"R":0.07627291027054774,"A":5.542361677419374,"Mc":0.11497444762251606}},"challenger":{"mean":-0.7649030632661631,"mean_valid":-0.759625747805746,"sd_valid":1.4883102899899145,"n_turns":1000,"n_valid":992,"n_forfeits":1,"n_unscorable":7,"mean_z_R":0.33801321839017995,"mean_typ_c":0.4169369197923831,"mean_z_A":-0.1582672458230189,"bind_frac":{"R":0.2762096774193548,"Gc":0.2086693548387097,"A":0.5151209677419355},"n_leg_dropped":{"R":0,"Gc":44,"A":0},"mean_content_share":0.25778316995368517,"mean_R":0.018491726028774604,"mean_A":2.1502696562198196,"mean_mc":-0.7060952260378756},"king":{"mean":-0.6870994484373222,"mean_valid":-0.6709997497962231,"sd_valid":1.388439691976629,"n_turns":1000,"n_valid":990,"n_forfeits":3,"n_unscorable":7,"mean_z_R":0.24750183362317402,"mean_typ_c":0.610741338726373,"mean_z_A":-0.13941827522778308,"bind_frac":{"R":0.31414141414141417,"Gc":0.17474747474747473,"A":0.5111111111111111},"n_leg_dropped":{"R":0,"Gc":42,"A":0},"mean_content_share":0.2796564499269112,"mean_R":0.015399843936916681,"mean_A":2.5793214333330985,"mean_mc":-0.665648903750674}},"rejection_reason":null,"reign_number":null,"score":0.0023913175058839415,"score_king":0.0036398274187887493,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9133295,"blocks_since_crown":9985,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1420.5111561866127,"mean_len_y":727.1913455037187,"n_samples":3000,"think_close_rate":0.9643333333333334,"n_text_fallback":12,"by_dialect":{"bash":{"n_turns":316,"zero_ref_turns":0,"mean_refs":2.9462025316455698,"ref_pair_agreement":0.1891025641025641,"ref_pair_n":312},"text":{"n_turns":349,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":284,"zero_ref_turns":0,"mean_refs":2.954225352112676,"ref_pair_agreement":0.1756919374247894,"ref_pair_n":277},"boxed":{"n_turns":39,"zero_ref_turns":0,"mean_refs":2.717948717948718,"ref_pair_agreement":0.5980392156862745,"ref_pair_n":34},"terminus_json":{"n_turns":12,"zero_ref_turns":0,"mean_refs":2.9166666666666665,"ref_pair_agreement":0.5833333333333334,"ref_pair_n":12}},"ref_pair_agreement":0.2125984251968504,"ref_pair_n":635},"duel_seconds":2185.580823269207,"challenger":{"reason":0.0023913175058839415,"n_turns":1000,"n_pairs":2955,"n_forfeits":1,"forfeit_rate":0.001,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":21.50042679568038,"mean_len_z":1080.785448392555,"median_len_z":743.0,"mean_len_y":293.54483925549914,"mean_b":0.11358255482970299,"b_gate_pass_rate":0.6040609137055838,"mean_r_leg":0.018491726028774604,"mean_g_leg":0.053425629039245484,"g_bind_frac":0.25125125125125125,"a_match":0.14631633178773829,"a_match_n":647,"a_match_centered":-0.06509186351706037,"n_turns_cap_raised":46,"mean_cap_tokens":4151.113,"max_cap_tokens":6070,"len_z_delta":-339.7257077940576,"len_y_delta":-433.64650624821957,"n_samples":1003,"think_close_rate":0.9990029910269193,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.009323588754661986,"mean_b":0.12754320205692887,"b_gate_pass_rate":0.8668098818474759,"median_len_z":552.0,"mean_r_leg":0.0190063167303505,"mean_g_leg":0.045681946114785835,"g_bind_frac":0.2689873417721519,"a_match":0.14135021097046413,"a_match_n":316,"a_match_centered":-0.045940170940170943},"boxed":{"n_turns":39,"n_valid":39,"parse_rate":1.0,"reason":4.094180104576604e-05,"mean_b":0.8700307443198887,"b_gate_pass_rate":0.6037735849056604,"median_len_z":2147.0,"mean_r_leg":0.04062414693059524,"mean_g_leg":0.012064822747943706,"g_bind_frac":0.6410256410256411,"a_match":0.23684210526315788,"a_match_n":38,"a_match_centered":-0.36274509803921573},"terminus_json":{"n_turns":12,"n_valid":12,"parse_rate":1.0,"reason":-0.005554382725849158,"mean_b":0.024230491642263055,"b_gate_pass_rate":0.5142857142857142,"median_len_z":1031.0,"mean_r_leg":0.0014967396246513896,"mean_g_leg":0.02959903377397497,"g_bind_frac":0.3333333333333333,"a_match":0.3888888888888889,"a_match_n":12,"a_match_centered":-0.19444444444444445},"text":{"n_turns":349,"n_valid":348,"parse_rate":0.997134670487106,"reason":-0.002423190853449223,"mean_b":0.09075416770400985,"b_gate_pass_rate":0.4367816091954023,"median_len_z":895.0,"mean_r_leg":0.0258258996212298,"mean_g_leg":0.059872474428585905,"g_bind_frac":0.22701149425287356,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.0012528624286406262,"mean_b":0.0346544114641214,"b_gate_pass_rate":0.5244338498212158,"median_len_z":663.0,"mean_r_leg":0.006610994866119966,"mean_g_leg":0.06082877057862154,"g_bind_frac":0.20422535211267606,"a_match":0.12930011862396204,"a_match_n":281,"a_match_centered":-0.044524669073405534}}},"king":{"reason":0.0036398274187887493,"n_turns":1000,"n_pairs":2949,"n_forfeits":3,"forfeit_rate":0.003,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":21.950807500907715,"mean_len_z":938.8463886063072,"median_len_z":651.0,"mean_len_y":335.25907087148187,"mean_b":0.10140565151948276,"b_gate_pass_rate":0.5920651068158698,"mean_r_leg":0.015399843936916681,"mean_g_leg":0.057339923265212686,"g_bind_frac":0.2226680040120361,"a_match":0.14699792960662528,"a_match_n":644,"a_match_centered":-0.06309148264984227,"n_turns_cap_raised":46,"mean_cap_tokens":4151.113,"max_cap_tokens":6070,"len_z_delta":-481.66476758030547,"len_y_delta":-391.93227463223684,"n_samples":1000,"think_close_rate":0.997,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.010388762626781805,"mean_b":0.12443741227392331,"b_gate_pass_rate":0.8657357679914071,"median_len_z":510.0,"mean_r_leg":0.020183499120380744,"mean_g_leg":0.0477579494783082,"g_bind_frac":0.25316455696202533,"a_match":0.14240506329113925,"a_match_n":316,"a_match_centered":-0.04487179487179487},"boxed":{"n_turns":39,"n_valid":39,"parse_rate":1.0,"reason":0.00230855548288817,"mean_b":0.9535287273295824,"b_gate_pass_rate":0.6792452830188679,"median_len_z":2117.0,"mean_r_leg":0.06965227427263763,"mean_g_leg":0.01676919890828563,"g_bind_frac":0.5384615384615384,"a_match":0.25438596491228066,"a_match_n":38,"a_match_centered":-0.3137254901960784},"terminus_json":{"n_turns":12,"n_valid":12,"parse_rate":1.0,"reason":-0.0011895129715585517,"mean_b":0.016767259212738427,"b_gate_pass_rate":0.2571428571428571,"median_len_z":817.0,"mean_r_leg":0.0013015797472484653,"mean_g_leg":0.035915425335611685,"g_bind_frac":0.16666666666666666,"a_match":0.638888888888889,"a_match_n":12,"a_match_centered":0.05555555555555555},"text":{"n_turns":349,"n_valid":346,"parse_rate":0.9914040114613181,"reason":0.0004106422903136945,"mean_b":0.0538734016622105,"b_gate_pass_rate":0.42485549132947975,"median_len_z":829.0,"mean_r_leg":0.013135559445983009,"mean_g_leg":0.06691683007921215,"g_bind_frac":0.1791907514450867,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.0004855801451840963,"mean_b":0.030527467710579233,"b_gate_pass_rate":0.49821215733015495,"median_len_z":558.0,"mean_r_leg":0.005981329088576216,"mean_g_leg":0.06281050842047105,"g_bind_frac":0.2007042253521127,"a_match":0.11630695443645085,"a_match_n":278,"a_match_centered":-0.057971014492753624}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T22:20:25.425811+00:00","challenge_id":"chal-00679","repo":"r2://affine-private-models/models/registrations/3b173d100c4eb9cbbf6720c6ca12a9573afda25057ddc6d9cb37698e7139a06f/","hotkey":"5D9wmdDFPzCs9GQSzMxXaybcsT74tkHXGEG3bWLyYx54y3LC","uid":211,"duration_s":2682.0,"revision":"6bc164a58171aafb04d7b249d61afbd52f1f41fdd7dc3c05defa03654f40c6b9","accepted":false,"error_code":null,"error_detail":"","z":-2.5102825309085652,"margin":-0.07422254829856927,"se":0.029567408203930477,"n_paired_turns":987,"n_forfeit_turns":3,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2819074483755259884,"n":1000,"digest":"da6487a372c87311044259295aae41bcaf071005f1f8825713234783d776f64b","n_paired_turns":987,"n_forfeit_turns":3,"margin":-0.07422254829856927,"se":0.029567408203930477,"z":-2.5102825309085652,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.07422254829856927,"se":0.029567408203930477,"z":-2.5102825309085652,"sd_diff":0.9289061398952981,"n_paired_turns":987,"n_forfeit_turns":3,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2},"sigma_by_dialect":{"bash":{"R":0.02966694272171953,"A":6.479757511985462,"Mc":0.16373578359490112},"text":{"R":0.06590756413270205,"A":16.525087391129382,"Mc":0.16010916923471719},"tool_call":{"R":0.008263304195901653,"A":5.297346193099593,"Mc":0.165886650044362},"terminus_json":{"R":0.0027645880433097695,"A":7.070207377167512,"Mc":0.11515935243292702},"boxed":{"R":0.1308558063594707,"A":4.78454710965637,"Mc":0.14375369179511732}},"challenger":{"mean":-0.699476814057239,"mean_valid":-0.6887143304309594,"sd_valid":1.2448668544283765,"n_turns":993,"n_valid":985,"n_forfeits":2,"n_unscorable":6,"mean_z_R":0.28900942973639226,"mean_typ_c":0.5921558357372032,"mean_z_A":-0.19211313531874052,"bind_frac":{"R":0.28223350253807106,"Gc":0.17563451776649747,"A":0.5421319796954315},"n_leg_dropped":{"R":0,"Gc":43,"A":0},"mean_content_share":0.2523715027217617,"mean_R":0.023007539407538986,"mean_A":2.212009994497677,"mean_mc":-0.6878465233556117},"king":{"mean":-0.6252542657586698,"mean_valid":-0.6143410764505656,"sd_valid":1.210976703545234,"n_turns":993,"n_valid":985,"n_forfeits":2,"n_unscorable":6,"mean_z_R":0.22541390756109483,"mean_typ_c":0.7028772132347595,"mean_z_A":-0.1414935251763289,"bind_frac":{"R":0.34213197969543147,"Gc":0.13096446700507614,"A":0.5269035532994923},"n_leg_dropped":{"R":0,"Gc":41,"A":0},"mean_content_share":0.2774536833341084,"mean_R":0.021941078838492698,"mean_A":2.6964773292814344,"mean_mc":-0.6560265133297585}},"rejection_reason":null,"reign_number":null,"score":0.0036208479086815696,"score_king":0.004546359426142424,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9133066,"blocks_since_crown":9756,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max","ref_min_content":10,"typ_min_refs":2}},"teacher":{"mean_len_z":1364.554122836783,"mean_len_y":672.825924669155,"n_samples":3000,"think_close_rate":0.964,"n_text_fallback":10,"by_dialect":{"text":{"n_turns":363,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":290,"zero_ref_turns":2,"mean_refs":2.9310344827586206,"ref_pair_agreement":0.1879432624113475,"ref_pair_n":282},"bash":{"n_turns":287,"zero_ref_turns":2,"mean_refs":2.9442508710801394,"ref_pair_agreement":0.19434628975265017,"ref_pair_n":283},"boxed":{"n_turns":39,"zero_ref_turns":3,"mean_refs":2.58974358974359,"ref_pair_agreement":0.4270833333333333,"ref_pair_n":32},"terminus_json":{"n_turns":21,"zero_ref_turns":0,"mean_refs":2.9523809523809526,"ref_pair_agreement":0.4126984126984127,"ref_pair_n":21}},"ref_pair_agreement":0.21089536138079829,"ref_pair_n":618},"duel_seconds":2270.75218845997,"challenger":{"reason":0.0036208479086815696,"n_turns":993,"n_pairs":2941,"n_forfeits":2,"forfeit_rate":0.002014098690835851,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":2.0778707744487916,"mean_len_z":1125.1142468548112,"median_len_z":764.0,"mean_len_y":326.00918055083304,"mean_b":0.10021969971065771,"b_gate_pass_rate":0.6004760285617137,"mean_r_leg":0.023007539407538986,"mean_g_leg":0.05435571937855832,"g_bind_frac":0.26437941473259335,"a_match":0.1626730564430245,"a_match_n":626,"a_match_centered":-0.047271745002701246,"n_turns_cap_raised":48,"mean_cap_tokens":4152.590130916415,"max_cap_tokens":6043,"len_z_delta":-239.4398759819719,"len_y_delta":-346.816744118322,"n_samples":996,"think_close_rate":0.9979919678714859,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":285,"n_valid":285,"parse_rate":1.0,"reason":0.010634412924511694,"mean_b":0.12818635245529914,"b_gate_pass_rate":0.8816568047337278,"median_len_z":595.0,"mean_r_leg":0.024255635080193377,"mean_g_leg":0.05267929950044463,"g_bind_frac":0.2982456140350877,"a_match":0.14210526315789473,"a_match_n":285,"a_match_centered":-0.05123674911660778},"boxed":{"n_turns":36,"n_valid":36,"parse_rate":1.0,"reason":0.0013720679247534514,"mean_b":0.9124694177062586,"b_gate_pass_rate":0.7326732673267327,"median_len_z":2185.0,"mean_r_leg":0.12488069832386617,"mean_g_leg":0.006211718961928964,"g_bind_frac":0.6666666666666666,"a_match":0.35714285714285715,"a_match_n":35,"a_match_centered":-0.06770833333333334},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":0.0002336347097036326,"mean_b":0.025799295406144288,"b_gate_pass_rate":0.46774193548387094,"median_len_z":663.0,"mean_r_leg":0.0027275442070651312,"mean_g_leg":0.05361365949441055,"g_bind_frac":0.19047619047619047,"a_match":0.4920634920634921,"a_match_n":21,"a_match_centered":0.07936507936507936},"text":{"n_turns":363,"n_valid":362,"parse_rate":0.9972451790633609,"reason":0.00023282142081336023,"mean_b":0.05952375345841797,"b_gate_pass_rate":0.4447513812154696,"median_len_z":887.0,"mean_r_leg":0.025324970349612043,"mean_g_leg":0.05279203486522955,"g_bind_frac":0.2513812154696133,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":288,"n_valid":287,"parse_rate":0.9965277777777778,"reason":0.0014787477079333876,"mean_b":0.033089616605621715,"b_gate_pass_rate":0.51357733175915,"median_len_z":725.0,"mean_r_leg":0.007550497283794121,"mean_g_leg":0.06408603551672269,"g_bind_frac":0.20209059233449478,"a_match":0.13508771929824562,"a_match_n":285,"a_match_centered":-0.05041518386714116}}},"king":{"reason":0.004546359426142424,"n_turns":993,"n_pairs":2941,"n_forfeits":2,"forfeit_rate":0.002014098690835851,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-9.91489057373722,"mean_len_z":950.8728323699422,"median_len_z":671.0,"mean_len_y":340.15334920095205,"mean_b":0.09422430069320972,"b_gate_pass_rate":0.5746344780686842,"mean_r_leg":0.021941078838492698,"mean_g_leg":0.055860879853082225,"g_bind_frac":0.2341069626639758,"a_match":0.1621477937267411,"a_match_n":627,"a_match_centered":-0.04800431499460626,"n_turns_cap_raised":48,"mean_cap_tokens":4152.590130916415,"max_cap_tokens":6043,"len_z_delta":-413.6812904668409,"len_y_delta":-332.672575468203,"n_samples":993,"think_close_rate":0.9979859013091642,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":285,"n_valid":285,"parse_rate":1.0,"reason":0.010773808728060828,"mean_b":0.12913252859653754,"b_gate_pass_rate":0.8875739644970414,"median_len_z":533.0,"mean_r_leg":0.024007526052310053,"mean_g_leg":0.053784497953972527,"g_bind_frac":0.256140350877193,"a_match":0.14269005847953214,"a_match_n":285,"a_match_centered":-0.050647820965842166},"boxed":{"n_turns":36,"n_valid":36,"parse_rate":1.0,"reason":0.0063416112912843495,"mean_b":0.8625734039384604,"b_gate_pass_rate":0.9108910891089109,"median_len_z":2055.0,"mean_r_leg":0.1149970765897133,"mean_g_leg":0.012430555459544123,"g_bind_frac":0.6666666666666666,"a_match":0.4142857142857143,"a_match_n":35,"a_match_centered":-0.005208333333333336},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":-0.0003086576158913299,"mean_b":0.021876134089433872,"b_gate_pass_rate":0.2903225806451613,"median_len_z":582.0,"mean_r_leg":0.0020121205960947895,"mean_g_leg":0.052647107169963285,"g_bind_frac":0.19047619047619047,"a_match":0.4603174603174603,"a_match_n":21,"a_match_centered":0.047619047619047616},"text":{"n_turns":363,"n_valid":361,"parse_rate":0.9944903581267218,"reason":0.001608677461851385,"mean_b":0.04999692953661474,"b_gate_pass_rate":0.40166204986149584,"median_len_z":819.0,"mean_r_leg":0.024743770947707796,"mean_g_leg":0.05450522773045077,"g_bind_frac":0.2299168975069252,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":288,"n_valid":288,"parse_rate":1.0,"reason":0.0022160878731163876,"mean_b":0.029851497500202825,"b_gate_pass_rate":0.4647058823529412,"median_len_z":567.0,"mean_r_leg":0.006204213896415683,"mean_g_leg":0.065278033193461,"g_bind_frac":0.16666666666666666,"a_match":0.12878787878787878,"a_match_n":286,"a_match_centered":-0.05732860520094563}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T21:31:54.435349+00:00","challenge_id":"chal-00678","repo":"r2://affine-private-models/models/registrations/c213e8744d4e40817ac53a4a87053aed5381a4ec657a4afa5988052ecc4c9b81/","hotkey":"5FS8xd54ymdTEAsiUmRx1ZtDkiwMzXCyD9JG4DY52jdvSAei","uid":101,"duration_s":2703.5,"revision":"514e2e7681ca426c8a4fca52535655f441f8e9b86cc7dc6aa40930057cc3f51c","accepted":false,"error_code":null,"error_detail":"","z":-2.0615106859898966,"margin":-0.05482812659516114,"se":0.02659609138471856,"n_paired_turns":982,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":505418649326495698,"n":1000,"digest":"b2165ae986c1dbbb1c40cd14b22373646c1ad2c8dd7e46ed1872eb6d0045d830","n_paired_turns":982,"n_forfeit_turns":5,"margin":-0.05482812659516114,"se":0.02659609138471856,"z":-2.0615106859898966,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.05482812659516114,"se":0.02659609138471856,"z":-2.0615106859898966,"sd_diff":0.8334385037657568,"n_paired_turns":982,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"tool_call":{"R":0.00735253904544508,"A":5.966894760302096,"Mc":0.18409950341677567},"text":{"R":0.11982373092521831,"A":23.35770318306542,"Mc":0.17974075806289255},"bash":{"R":0.03006198947897848,"A":6.047541520731026,"Mc":0.15377434392795927},"terminus_json":{"R":0.0012111263588662953,"A":9.802131265525851,"Mc":0.13451155853852304},"boxed":{"R":0.05088524465398252,"A":6.222662682453475,"Mc":0.11793948903599547}},"challenger":{"mean":-0.631893945703256,"mean_valid":-0.6099385017184021,"sd_valid":1.2630914655540442,"n_turns":989,"n_valid":978,"n_forfeits":4,"n_unscorable":7,"mean_z_R":0.20474596976440596,"mean_typ_c":0.6893067850657674,"mean_z_A":-0.08032434256702269,"bind_frac":{"R":0.310838445807771,"Gc":0.15337423312883436,"A":0.5357873210633947},"n_leg_dropped":{"R":0,"Gc":8,"A":0},"mean_content_share":0.2636289968416335,"mean_R":0.021167416627077423,"mean_A":2.1276978399308493,"mean_mc":-0.6665506615611609},"king":{"mean":-0.5770658191080947,"mean_valid":-0.5548861292066964,"sd_valid":1.1927122800131515,"n_turns":989,"n_valid":978,"n_forfeits":4,"n_unscorable":7,"mean_z_R":0.18409573456887418,"mean_typ_c":0.741823922149173,"mean_z_A":-0.027868954741730574,"bind_frac":{"R":0.3619631901840491,"Gc":0.15337423312883436,"A":0.48466257668711654},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.28363980671737404,"mean_R":0.020234701494061334,"mean_A":2.4926109145304265,"mean_mc":-0.6568698964434356}},"rejection_reason":null,"reign_number":null,"score":0.003959494733024062,"score_king":0.0031167869702403237,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9132822,"blocks_since_crown":9512,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-6.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1394.7780047667688,"mean_len_y":698.943820224719,"n_samples":3000,"think_close_rate":0.9616666666666667,"n_text_fallback":19,"by_dialect":{"text":{"n_turns":369,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":283,"zero_ref_turns":4,"mean_refs":2.9257950530035335,"ref_pair_agreement":0.13788968824940048,"ref_pair_n":278},"tool_call":{"n_turns":285,"zero_ref_turns":1,"mean_refs":2.9368421052631577,"ref_pair_agreement":0.16484848484848486,"ref_pair_n":275},"terminus_json":{"n_turns":21,"zero_ref_turns":0,"mean_refs":2.9523809523809526,"ref_pair_agreement":0.47619047619047616,"ref_pair_n":21},"boxed":{"n_turns":42,"zero_ref_turns":6,"mean_refs":2.4523809523809526,"ref_pair_agreement":0.4444444444444445,"ref_pair_n":30}},"ref_pair_agreement":0.1771523178807947,"ref_pair_n":604},"duel_seconds":2142.829817323014,"challenger":{"reason":0.003959494733024062,"n_turns":989,"n_pairs":2925,"n_forfeits":4,"forfeit_rate":0.004044489383215369,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":3.4069160879380136,"mean_len_z":1060.8929914529915,"median_len_z":737.0,"mean_len_y":335.48820512820515,"mean_b":0.09173561807272555,"b_gate_pass_rate":0.5931623931623932,"mean_r_leg":0.021167416627077423,"mean_g_leg":0.05532121655421668,"g_bind_frac":0.2517766497461929,"a_match":0.13725490196078433,"a_match_n":612,"a_match_centered":-0.03814262023217247,"n_turns_cap_raised":49,"mean_cap_tokens":4151.0404448938325,"max_cap_tokens":6031,"len_z_delta":-333.88501331377734,"len_y_delta":-363.4556150965139,"n_samples":992,"think_close_rate":0.9959677419354839,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":279,"n_valid":279,"parse_rate":1.0,"reason":0.010638501673655675,"mean_b":0.11817218632066454,"b_gate_pass_rate":0.8671497584541062,"median_len_z":573.0,"mean_r_leg":0.0235439480895366,"mean_g_leg":0.04729847845473563,"g_bind_frac":0.2903225806451613,"a_match":0.1135005973715651,"a_match_n":279,"a_match_centered":-0.023980815347721823},"boxed":{"n_turns":36,"n_valid":36,"parse_rate":1.0,"reason":0.0048468156685526325,"mean_b":0.7499953073294797,"b_gate_pass_rate":0.6990291262135923,"median_len_z":2564.0,"mean_r_leg":0.054809324344995664,"mean_g_leg":0.01541459138058691,"g_bind_frac":0.7222222222222222,"a_match":0.18627450980392157,"a_match_n":34,"a_match_centered":-0.23333333333333334},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":-0.004851714375408483,"mean_b":0.022633045649759417,"b_gate_pass_rate":0.3709677419354839,"median_len_z":910.0,"mean_r_leg":0.0010890525373632835,"mean_g_leg":0.048942004806708045,"g_bind_frac":0.38095238095238093,"a_match":0.5555555555555556,"a_match_n":21,"a_match_centered":0.07936507936507936},"text":{"n_turns":369,"n_valid":366,"parse_rate":0.991869918699187,"reason":0.0007261799091216642,"mean_b":0.05886815414780314,"b_gate_pass_rate":0.4453551912568306,"median_len_z":899.0,"mean_r_leg":0.028255396675707294,"mean_g_leg":0.058605433942121525,"g_bind_frac":0.20218579234972678,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":283,"parse_rate":0.9964788732394366,"reason":0.0021381639977487783,"mean_b":0.03260205497566268,"b_gate_pass_rate":0.5191846522781774,"median_len_z":668.5,"mean_r_leg":0.006868066776244551,"mean_g_leg":0.06453295619637354,"g_bind_frac":0.20848056537102475,"a_match":0.1235011990407674,"a_match_n":278,"a_match_centered":-0.040145985401459854}}},"king":{"reason":0.0031167869702403237,"n_turns":989,"n_pairs":2925,"n_forfeits":4,"forfeit_rate":0.004044489383215369,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":3.65951234035506,"mean_len_z":937.3452991452991,"median_len_z":677.0,"mean_len_y":339.72991452991454,"mean_b":0.08801098975970437,"b_gate_pass_rate":0.5692307692307692,"mean_r_leg":0.020234701494061334,"mean_g_leg":0.05600431043783882,"g_bind_frac":0.2436548223350254,"a_match":0.14896514161220045,"a_match_n":612,"a_match_centered":-0.02621412803532009,"n_turns_cap_raised":49,"mean_cap_tokens":4151.0404448938325,"max_cap_tokens":6031,"len_z_delta":-457.4327056214697,"len_y_delta":-359.2139056948045,"n_samples":989,"think_close_rate":0.9959555106167847,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":279,"n_valid":279,"parse_rate":1.0,"reason":0.00978891118997083,"mean_b":0.11408989426666663,"b_gate_pass_rate":0.8671497584541062,"median_len_z":515.0,"mean_r_leg":0.023181157331817887,"mean_g_leg":0.04658242326184605,"g_bind_frac":0.2974910394265233,"a_match":0.11589008363201912,"a_match_n":279,"a_match_centered":-0.02158273381294964},"boxed":{"n_turns":36,"n_valid":36,"parse_rate":1.0,"reason":0.006797738595179939,"mean_b":0.715214631551463,"b_gate_pass_rate":0.7766990291262136,"median_len_z":2405.0,"mean_r_leg":0.0702360979101978,"mean_g_leg":0.017625368446756617,"g_bind_frac":0.7222222222222222,"a_match":0.25252525252525254,"a_match_n":33,"a_match_centered":-0.16666666666666666},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":-0.0003414095734078486,"mean_b":0.021573053714869592,"b_gate_pass_rate":0.4838709677419355,"median_len_z":761.0,"mean_r_leg":0.0016435341816486064,"mean_g_leg":0.05362444456946387,"g_bind_frac":0.23809523809523808,"a_match":0.5238095238095238,"a_match_n":21,"a_match_centered":0.047619047619047616},"text":{"n_turns":369,"n_valid":365,"parse_rate":0.989159891598916,"reason":-0.000276515414005879,"mean_b":0.05794332086443919,"b_gate_pass_rate":0.40821917808219177,"median_len_z":829.0,"mean_r_leg":0.025050911102406207,"mean_g_leg":0.05905165774037444,"g_bind_frac":0.2,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.0007601453906657565,"mean_b":0.029286905457170595,"b_gate_pass_rate":0.4659498207885305,"median_len_z":576.0,"mean_r_leg":0.006186766834905694,"mean_g_leg":0.06638474653499134,"g_bind_frac":0.18661971830985916,"a_match":0.14157706093189965,"a_match_n":279,"a_match_centered":-0.02121212121212121}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T20:42:53.165531+00:00","challenge_id":"chal-00677","repo":"r2://affine-private-models/models/registrations/2aa732d3d2e408af8c8d6cfd6c980e146a2c5bc5a3ba2ea665441d3105445a41/","hotkey":"5HJC3Wf3EYy3ZBeD7Xu7aJUvxdzhngV3VuAtN6gwF7Y8dmoe","uid":182,"duration_s":2472.9,"revision":"c8ff6675975527e144776c29e7b1a5ba49f00f849aca230cfb9c08ed07bff998","accepted":false,"error_code":null,"error_detail":"","z":1.215941336729996,"margin":0.054402854008833705,"se":0.04474134760081279,"n_paired_turns":989,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":13598404653717610294,"n":1000,"digest":"6467a275e90c6faf052126316efd002e18c490390e14c8f2da63dd37cfad086a","n_paired_turns":989,"n_forfeit_turns":8,"margin":0.054402854008833705,"se":0.04474134760081279,"z":1.215941336729996,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.054402854008833705,"se":0.04474134760081279,"z":1.215941336729996,"sd_diff":1.4070424709653409,"n_paired_turns":989,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"bash":{"R":0.020038034500981093,"A":6.365762514829944,"Mc":0.1464102517218237},"tool_call":{"R":0.008582067211037757,"A":5.397053675460901,"Mc":0.20153448141554048},"text":{"R":0.0542451073902258,"A":29.56570989551035,"Mc":0.1758584029228683},"boxed":{"R":0.11505596468387363,"A":8.014717990535035,"Mc":0.12151119859265205},"terminus_json":{"R":0.002295535166900653,"A":10.671409758671006,"Mc":0.11232439836098394}},"challenger":{"mean":-0.6896269436456951,"mean_valid":-0.6321555358390167,"sd_valid":1.7493379247188723,"n_turns":994,"n_valid":984,"n_forfeits":5,"n_unscorable":5,"mean_z_R":0.26199820641247007,"mean_typ_c":0.6788813577532459,"mean_z_A":-0.06621270442847063,"bind_frac":{"R":0.2936991869918699,"Gc":0.16056910569105692,"A":0.5457317073170732},"n_leg_dropped":{"R":0,"Gc":9,"A":0},"mean_content_share":0.2644724549683863,"mean_R":0.017424825968926198,"mean_A":2.5595689038795113,"mean_mc":-0.6638191571929725},"king":{"mean":-0.7440297976545288,"mean_valid":-0.6753260120857874,"sd_valid":1.8859633473471307,"n_turns":994,"n_valid":983,"n_forfeits":6,"n_unscorable":5,"mean_z_R":0.28307715393165755,"mean_typ_c":0.6193065511127624,"mean_z_A":-0.06626810874889978,"bind_frac":{"R":0.3123092573753815,"Gc":0.16276703967446593,"A":0.5249237029501526},"n_leg_dropped":{"R":0,"Gc":9,"A":0},"mean_content_share":0.2794349040888935,"mean_R":0.01854661732834895,"mean_A":2.491143229697508,"mean_mc":-0.6582596694392212}},"rejection_reason":null,"reign_number":null,"score":0.0025737745738034783,"score_king":0.002780789766443083,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9132596,"blocks_since_crown":9286,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1232.5773265651437,"mean_len_y":724.3678510998308,"n_samples":3000,"think_close_rate":0.966,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":294,"zero_ref_turns":1,"mean_refs":2.95578231292517,"ref_pair_agreement":0.20229885057471264,"ref_pair_n":290},"tool_call":{"n_turns":287,"zero_ref_turns":1,"mean_refs":2.947735191637631,"ref_pair_agreement":0.17018779342723006,"ref_pair_n":284},"text":{"n_turns":368,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":38,"zero_ref_turns":4,"mean_refs":2.6052631578947367,"ref_pair_agreement":0.4838709677419355,"ref_pair_n":31},"terminus_json":{"n_turns":13,"zero_ref_turns":0,"mean_refs":2.8461538461538463,"ref_pair_agreement":0.5128205128205129,"ref_pair_n":13}},"ref_pair_agreement":0.2081984897518878,"ref_pair_n":618},"duel_seconds":1984.9722872469574,"challenger":{"reason":0.0025737745738034783,"n_turns":994,"n_pairs":2940,"n_forfeits":5,"forfeit_rate":0.005030181086519115,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.8559734817878482,"mean_len_z":1028.6942176870748,"median_len_z":729.0,"mean_len_y":340.7081632653061,"mean_b":0.10770480336929202,"b_gate_pass_rate":0.5840136054421768,"mean_r_leg":0.017424825968926198,"mean_g_leg":0.05740590335773896,"g_bind_frac":0.25075834175935285,"a_match":0.15253333333333333,"a_match_n":625,"a_match_centered":-0.05393743257820928,"n_turns_cap_raised":38,"mean_cap_tokens":4135.090543259557,"max_cap_tokens":6016,"len_z_delta":-203.88310887806892,"len_y_delta":-383.6596878345247,"n_samples":997,"think_close_rate":0.9949849548645938,"n_text_fallback":0,"by_dialect":{"bash":{"n_turns":293,"n_valid":293,"parse_rate":1.0,"reason":0.008237338980366849,"mean_b":0.12492120732087729,"b_gate_pass_rate":0.8584579976985041,"median_len_z":503.0,"mean_r_leg":0.0217229030904066,"mean_g_leg":0.043351279983975866,"g_bind_frac":0.3447098976109215,"a_match":0.15642775881683732,"a_match_n":293,"a_match_centered":-0.044252873563218394},"boxed":{"n_turns":34,"n_valid":34,"parse_rate":1.0,"reason":0.011110261623474005,"mean_b":0.9641604954267977,"b_gate_pass_rate":0.7272727272727273,"median_len_z":2324.0,"mean_r_leg":0.11867216560811167,"mean_g_leg":0.021872755590063776,"g_bind_frac":0.6470588235294118,"a_match":0.4090909090909091,"a_match_n":33,"a_match_centered":-0.048387096774193554},"terminus_json":{"n_turns":13,"n_valid":13,"parse_rate":1.0,"reason":-0.005716479977826158,"mean_b":0.024741966911825446,"b_gate_pass_rate":0.5135135135135135,"median_len_z":735.0,"mean_r_leg":0.0009359085127311578,"mean_g_leg":0.03031921274095009,"g_bind_frac":0.46153846153846156,"a_match":0.46153846153846156,"a_match_n":13,"a_match_centered":-0.05128205128205128},"text":{"n_turns":368,"n_valid":363,"parse_rate":0.9864130434782609,"reason":-0.002796795877355838,"mean_b":0.07560657193451649,"b_gate_pass_rate":0.3856749311294766,"median_len_z":879.0,"mean_r_leg":0.013024075017467206,"mean_g_leg":0.06265271992139569,"g_bind_frac":0.18457300275482094,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":286,"n_valid":286,"parse_rate":1.0,"reason":0.0030439784352928084,"mean_b":0.03474313721536307,"b_gate_pass_rate":0.5437352245862884,"median_len_z":671.0,"mean_r_leg":0.007320218898940486,"mean_g_leg":0.07060053356062149,"g_bind_frac":0.18181818181818182,"a_match":0.1048951048951049,"a_match_n":286,"a_match_centered":-0.06455399061032864}}},"king":{"reason":0.002780789766443083,"n_turns":994,"n_pairs":2937,"n_forfeits":6,"forfeit_rate":0.006036217303822937,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":1.4455963824752964,"mean_len_z":950.5522642151856,"median_len_z":675.0,"mean_len_y":341.99761661559415,"mean_b":0.10506296504759143,"b_gate_pass_rate":0.6026557711950971,"mean_r_leg":0.01854661732834895,"mean_g_leg":0.057686351342755134,"g_bind_frac":0.2408906882591093,"a_match":0.14469453376205788,"a_match_n":622,"a_match_centered":-0.061788617886178863,"n_turns_cap_raised":38,"mean_cap_tokens":4135.090543259557,"max_cap_tokens":6016,"len_z_delta":-282.02506234995815,"len_y_delta":-382.3702344842366,"n_samples":994,"think_close_rate":0.9949698189134809,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":293,"n_valid":293,"parse_rate":1.0,"reason":0.009148967071145628,"mean_b":0.12787589707981623,"b_gate_pass_rate":0.8860759493670886,"median_len_z":462.0,"mean_r_leg":0.022259100397091038,"mean_g_leg":0.04416608723395434,"g_bind_frac":0.3651877133105802,"a_match":0.15073947667804322,"a_match_n":293,"a_match_centered":-0.05},"boxed":{"n_turns":34,"n_valid":33,"parse_rate":0.9705882352941176,"reason":0.008010909049905162,"mean_b":0.976578836259926,"b_gate_pass_rate":0.8229166666666666,"median_len_z":2216.0,"mean_r_leg":0.12052196535336226,"mean_g_leg":0.02456123012332856,"g_bind_frac":0.6363636363636364,"a_match":0.2849462365591398,"a_match_n":31,"a_match_centered":-0.2011494252873563},"terminus_json":{"n_turns":13,"n_valid":13,"parse_rate":1.0,"reason":-0.006926341822919883,"mean_b":0.027611293984822614,"b_gate_pass_rate":0.5945945945945946,"median_len_z":732.0,"mean_r_leg":0.0007252206570849228,"mean_g_leg":0.033345396058866376,"g_bind_frac":0.23076923076923078,"a_match":0.5128205128205129,"a_match_n":13,"a_match_centered":0.0},"text":{"n_turns":368,"n_valid":363,"parse_rate":0.9864130434782609,"reason":-0.0017855916163741772,"mean_b":0.06848551908441229,"b_gate_pass_rate":0.40771349862258954,"median_len_z":842.0,"mean_r_leg":0.0159027820677063,"mean_g_leg":0.06369482996402852,"g_bind_frac":0.15977961432506887,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":286,"n_valid":286,"parse_rate":1.0,"reason":0.0019518424014882368,"mean_b":0.03320550513132316,"b_gate_pass_rate":0.5378250591016549,"median_len_z":597.0,"mean_r_leg":0.007142583525456788,"mean_g_leg":0.06883992149411185,"g_bind_frac":0.17132867132867133,"a_match":0.1064327485380117,"a_match_n":285,"a_match_centered":-0.062426383981154306}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T19:45:28.616814+00:00","challenge_id":"chal-00676","repo":"r2://affine-private-models/models/registrations/94071ef39b0cadb49c63310b122f4078c4e9c253702e843dd720aa570ec55507/","hotkey":"5Cf9rmpd7tnEc2Md911Ca9azpWEd45ESpzp7GbMNQgj79xH7","uid":39,"duration_s":2742.6,"revision":"1157c8376afd31ecd88ccc01e5424eaf224e8e334c6e9e0eddbfc9e49a7b17eb","accepted":false,"error_code":null,"error_detail":"","z":-4.179820654563985,"margin":-0.2900820937191772,"se":0.06940060775153926,"n_paired_turns":993,"n_forfeit_turns":21,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":4386202043161429074,"n":1000,"digest":"f94117925c73ecbb45e36a46d0806fe3dc9fbff72c010da9c90da1507e3ac35e","n_paired_turns":993,"n_forfeit_turns":21,"margin":-0.2900820937191772,"se":0.06940060775153926,"z":-4.179820654563985,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":0.9,"n":20,"by_reason":{"no_think_close":2},"by_prompt":{"assistant_bash":{"ok":false,"reasons":["no_think_close"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.2900820937191772,"se":0.06940060775153926,"z":-4.179820654563985,"sd_diff":2.186945185821773,"n_paired_turns":993,"n_forfeit_turns":21,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"bash":{"R":0.029772049219021723,"A":5.873809639525771,"Mc":0.15627393092105316},"text":{"R":0.03673274588800081,"A":13.242697748673542,"Mc":0.17631448795820986},"tool_call":{"R":0.010480119549039817,"A":6.987054693743729,"Mc":0.19774953816224203},"terminus_json":{"R":0.0017670032532697345,"A":8.234320745130105,"Mc":0.14280462197114707},"boxed":{"R":0.1356424722008577,"A":4.887481475756015,"Mc":0.10907611967652037}},"challenger":{"mean":-1.1886886067412687,"mean_valid":-0.9328653947608667,"sd_valid":2.525284852566011,"n_turns":1000,"n_valid":972,"n_forfeits":23,"n_unscorable":5,"mean_z_R":0.13472297701531433,"mean_typ_c":0.3988111240483112,"mean_z_A":-0.022896922798631043,"bind_frac":{"R":0.3991769547325103,"Gc":0.14814814814814814,"A":0.45267489711934156},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.30059850344221806,"mean_R":0.016616770110978712,"mean_A":3.490597175632749,"mean_mc":-0.6277308878656959},"king":{"mean":-0.8768314648987104,"mean_valid":-0.8431248935802217,"sd_valid":2.1578898478449204,"n_turns":1000,"n_valid":990,"n_forfeits":3,"n_unscorable":7,"mean_z_R":0.13658265109708723,"mean_typ_c":0.5211832275264295,"mean_z_A":-0.1011546902429448,"bind_frac":{"R":0.36363636363636365,"Gc":0.14646464646464646,"A":0.4898989898989899},"n_leg_dropped":{"R":0,"Gc":8,"A":0},"mean_content_share":0.28108581292445267,"mean_R":0.01689967588095477,"mean_A":2.3308638250568467,"mean_mc":-0.6664398780211055}},"rejection_reason":null,"reign_number":null,"score":0.0023480388765645243,"score_king":0.003338341074449479,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9132287,"blocks_since_crown":8977,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1503.016846361186,"mean_len_y":727.4002695417789,"n_samples":3000,"think_close_rate":0.973,"n_text_fallback":6,"by_dialect":{"text":{"n_turns":404,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":276,"zero_ref_turns":0,"mean_refs":2.9456521739130435,"ref_pair_agreement":0.16544117647058823,"ref_pair_n":272},"tool_call":{"n_turns":262,"zero_ref_turns":0,"mean_refs":2.9770992366412212,"ref_pair_agreement":0.17752234993614305,"ref_pair_n":261},"terminus_json":{"n_turns":23,"zero_ref_turns":0,"mean_refs":2.9130434782608696,"ref_pair_agreement":0.45454545454545453,"ref_pair_n":22},"boxed":{"n_turns":35,"zero_ref_turns":0,"mean_refs":2.742857142857143,"ref_pair_agreement":0.4946236559139785,"ref_pair_n":31}},"ref_pair_agreement":0.19908987485779295,"ref_pair_n":586},"duel_seconds":2212.9483417826705,"challenger":{"reason":0.0023480388765645243,"n_turns":1000,"n_pairs":2908,"n_forfeits":23,"forfeit_rate":0.023,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-0.6441452292552096,"mean_len_z":1382.3830811554333,"median_len_z":560.0,"mean_len_y":533.1076341127923,"mean_b":0.09260592907604515,"b_gate_pass_rate":0.46011004126547456,"mean_r_leg":0.016616770110978712,"mean_g_leg":0.05929013159310783,"g_bind_frac":0.2128966223132037,"a_match":0.1764199655765921,"a_match_n":581,"a_match_centered":-0.025217391304347827,"n_turns_cap_raised":50,"mean_cap_tokens":4148.894,"max_cap_tokens":5996,"len_z_delta":-120.63376520575275,"len_y_delta":-194.2926354289866,"n_samples":1003,"think_close_rate":0.9770687936191426,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":276,"n_valid":271,"parse_rate":0.9818840579710145,"reason":0.004022969372214635,"mean_b":0.11180958192803148,"b_gate_pass_rate":0.8169364881693649,"median_len_z":369.0,"mean_r_leg":0.016975001975364706,"mean_g_leg":0.0459315082195386,"g_bind_frac":0.24354243542435425,"a_match":0.13653136531365315,"a_match_n":271,"a_match_centered":-0.02973977695167286},"boxed":{"n_turns":35,"n_valid":33,"parse_rate":0.9428571428571428,"reason":0.0047954432054861116,"mean_b":0.9198102281675324,"b_gate_pass_rate":0.23076923076923078,"median_len_z":4520.0,"mean_r_leg":0.11551425838471409,"mean_g_leg":0.026203786232623448,"g_bind_frac":0.696969696969697,"a_match":0.5572916666666666,"a_match_n":32,"a_match_centered":0.0632183908045977},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.003968297124739121,"mean_b":0.024516574787953313,"b_gate_pass_rate":0.373134328358209,"median_len_z":673.0,"mean_r_leg":0.0012678003358532245,"mean_g_leg":0.039744058063410755,"g_bind_frac":0.17391304347826086,"a_match":0.4782608695652174,"a_match_n":23,"a_match_centered":0.045454545454545456},"text":{"n_turns":404,"n_valid":392,"parse_rate":0.9702970297029703,"reason":0.002413234713574216,"mean_b":0.06427047780019379,"b_gate_pass_rate":0.3163265306122449,"median_len_z":755.0,"mean_r_leg":0.015418245657749923,"mean_g_leg":0.06492414838301858,"g_bind_frac":0.17091836734693877,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":262,"n_valid":258,"parse_rate":0.9847328244274809,"reason":0.0007106214779629288,"mean_b":0.0241083324226508,"b_gate_pass_rate":0.3424124513618677,"median_len_z":362.0,"mean_r_leg":0.006780141980016303,"mean_g_leg":0.07073610616935305,"g_bind_frac":0.18604651162790697,"a_match":0.1437908496732026,"a_match_n":255,"a_match_centered":-0.036601307189542485}}},"king":{"reason":0.003338341074449479,"n_turns":1000,"n_pairs":2959,"n_forfeits":3,"forfeit_rate":0.003,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":8.056134642389408,"mean_len_z":956.2274417032781,"median_len_z":672.0,"mean_len_y":363.9425481581615,"mean_b":0.09808958684086569,"b_gate_pass_rate":0.5782358905035485,"mean_r_leg":0.01689967588095477,"mean_g_leg":0.05808143203813712,"g_bind_frac":0.238716148445336,"a_match":0.14867903316469927,"a_match_n":593,"a_match_centered":-0.05156695156695157,"n_turns_cap_raised":50,"mean_cap_tokens":4148.894,"max_cap_tokens":5996,"len_z_delta":-546.7894046579079,"len_y_delta":-363.4577213836174,"n_samples":1000,"think_close_rate":0.997,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":276,"n_valid":276,"parse_rate":1.0,"reason":0.006942262221245594,"mean_b":0.11827741345412583,"b_gate_pass_rate":0.8917589175891759,"median_len_z":485.0,"mean_r_leg":0.018411938060907324,"mean_g_leg":0.04605894681953939,"g_bind_frac":0.3007246376811594,"a_match":0.125,"a_match_n":276,"a_match_centered":-0.03860294117647059},"boxed":{"n_turns":35,"n_valid":35,"parse_rate":1.0,"reason":0.01164695835860162,"mean_b":1.0330001165083837,"b_gate_pass_rate":0.84375,"median_len_z":2357.0,"mean_r_leg":0.12985304321211888,"mean_g_leg":0.023614224580551166,"g_bind_frac":0.7428571428571429,"a_match":0.4509803921568627,"a_match_n":34,"a_match_centered":-0.06451612903225806},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.004691196241275892,"mean_b":0.022069671649362237,"b_gate_pass_rate":0.23880597014925373,"median_len_z":626.0,"mean_r_leg":0.0017276559135444075,"mean_g_leg":0.04063324947918854,"g_bind_frac":0.34782608695652173,"a_match":0.44927536231884063,"a_match_n":23,"a_match_centered":0.01515151515151515},"text":{"n_turns":404,"n_valid":401,"parse_rate":0.9925742574257426,"reason":0.001512888956437361,"mean_b":0.05805187925014374,"b_gate_pass_rate":0.428927680798005,"median_len_z":829.0,"mean_r_leg":0.013408876572667703,"mean_g_leg":0.06053015106673234,"g_bind_frac":0.16957605985037408,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":262,"n_valid":262,"parse_rate":1.0,"reason":0.0019516165419209545,"mean_b":0.030262128718823358,"b_gate_pass_rate":0.4782051282051282,"median_len_z":520.0,"mean_r_leg":0.006892098642847527,"mean_g_leg":0.07313460016690666,"g_bind_frac":0.20229007633587787,"a_match":0.1076923076923077,"a_match_n":260,"a_match_centered":-0.06923076923076923}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T17:40:55.529906+00:00","challenge_id":"chal-00675","repo":"r2://affine-private-models/models/registrations/f25f14926592dd134ef751002c2b6dcb0f2abba07f037abdd71c5e6b23b8cca5/","hotkey":"5D6ELpSDETPFFiFba5mpTgDwwhBAGCaA5feYvi5fCMWFecN6","uid":46,"duration_s":2656.2,"revision":"c5bc111156f483120fef5ba06f778a238f1d95198d983d99f8a959f9b0d3f755","accepted":false,"error_code":null,"error_detail":"","z":-1.2913727552635543,"margin":-0.03813774196382697,"se":0.029532713779487702,"n_paired_turns":985,"n_forfeit_turns":3,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":17326459703168804711,"n":1000,"digest":"3d08e10985415307c3a0d2538d5337a907db70cc805755cfe46e5a9979aac156","n_paired_turns":985,"n_forfeit_turns":3,"margin":-0.03813774196382697,"se":0.029532713779487702,"z":-1.2913727552635543,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.03813774196382697,"se":0.029532713779487702,"z":-1.2913727552635543,"sd_diff":0.9268756472329098,"n_paired_turns":985,"n_forfeit_turns":3,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"tool_call":{"R":0.007899943408803593,"A":5.391929572609217,"Mc":0.19045165659178095},"text":{"R":0.1429707814861649,"A":18.376920434345212,"Mc":0.1780455692813279},"bash":{"R":0.024934666042118435,"A":5.638763712897709,"Mc":0.14738641639348116},"terminus_json":{"R":0.001441066992240026,"A":6.0312043378167735,"Mc":0.10967658222780885},"boxed":{"R":0.1452654766863721,"A":7.435584369346286,"Mc":0.1010335295823565}},"challenger":{"mean":-0.7852734445752604,"mean_valid":-0.751012569151356,"sd_valid":1.800916220148468,"n_turns":994,"n_valid":982,"n_forfeits":3,"n_unscorable":9,"mean_z_R":0.22066589512357832,"mean_typ_c":0.6008767230272708,"mean_z_A":-0.11553555234560554,"bind_frac":{"R":0.335030549898167,"Gc":0.1670061099796334,"A":0.4979633401221996},"n_leg_dropped":{"R":0,"Gc":9,"A":0},"mean_content_share":0.26290421691538646,"mean_R":0.020917526430506834,"mean_A":2.3190706062020747,"mean_mc":-0.6797677588553934},"king":{"mean":-0.7471357026114335,"mean_valid":-0.7242407599921281,"sd_valid":1.7320051853986613,"n_turns":994,"n_valid":983,"n_forfeits":2,"n_unscorable":9,"mean_z_R":0.2040471027187507,"mean_typ_c":0.6164578134539581,"mean_z_A":-0.11519432158409793,"bind_frac":{"R":0.3306205493387589,"Gc":0.17090539165818922,"A":0.49847405900305186},"n_leg_dropped":{"R":0,"Gc":10,"A":0},"mean_content_share":0.27723695287685574,"mean_R":0.020740284779139213,"mean_A":2.303728914600344,"mean_mc":-0.6671332056821506}},"rejection_reason":null,"reign_number":null,"score":0.0042185964532027165,"score_king":0.0036925067044084334,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9131671,"blocks_since_crown":8361,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1315.3434309053778,"mean_len_y":692.6535057862492,"n_samples":3000,"think_close_rate":0.9596666666666667,"n_text_fallback":11,"by_dialect":{"bash":{"n_turns":300,"zero_ref_turns":0,"mean_refs":2.9566666666666666,"ref_pair_agreement":0.12709030100334448,"ref_pair_n":299},"terminus_json":{"n_turns":16,"zero_ref_turns":0,"mean_refs":2.9375,"ref_pair_agreement":0.5625,"ref_pair_n":16},"text":{"n_turns":361,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":285,"zero_ref_turns":1,"mean_refs":2.9263157894736844,"ref_pair_agreement":0.15942028985507245,"ref_pair_n":276},"boxed":{"n_turns":38,"zero_ref_turns":5,"mean_refs":2.289473684210526,"ref_pair_agreement":0.41666666666666663,"ref_pair_n":28}},"ref_pair_agreement":0.16585891222401722,"ref_pair_n":619},"duel_seconds":2130.0109830801375,"challenger":{"reason":0.0042185964532027165,"n_turns":994,"n_pairs":2931,"n_forfeits":3,"forfeit_rate":0.0030181086519114686,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":5.251282616465784,"mean_len_z":1011.8713749573525,"median_len_z":716.0,"mean_len_y":339.79495052882976,"mean_b":0.09502393887298367,"b_gate_pass_rate":0.5834186284544524,"mean_r_leg":0.020917526430506834,"mean_g_leg":0.0564856973850313,"g_bind_frac":0.2391523713420787,"a_match":0.1265923566878981,"a_match_n":628,"a_match_centered":-0.04072276159654801,"n_turns_cap_raised":44,"mean_cap_tokens":4144.028169014085,"max_cap_tokens":6012,"len_z_delta":-303.4720559480253,"len_y_delta":-352.8585552574194,"n_samples":997,"think_close_rate":0.9969909729187563,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":300,"n_valid":300,"parse_rate":1.0,"reason":0.010395158965898085,"mean_b":0.1239342772000636,"b_gate_pass_rate":0.8850056369785795,"median_len_z":559.0,"mean_r_leg":0.022308365754738643,"mean_g_leg":0.050819946057135704,"g_bind_frac":0.31333333333333335,"a_match":0.07333333333333333,"a_match_n":300,"a_match_centered":-0.05351170568561873},"boxed":{"n_turns":33,"n_valid":32,"parse_rate":0.9696969696969697,"reason":0.0043228206232830664,"mean_b":0.7939791937901327,"b_gate_pass_rate":0.686046511627907,"median_len_z":1970.0,"mean_r_leg":0.07027810653989004,"mean_g_leg":0.016665483738722946,"g_bind_frac":0.65625,"a_match":0.36666666666666664,"a_match_n":30,"a_match_centered":-0.09876543209876544},"terminus_json":{"n_turns":16,"n_valid":16,"parse_rate":1.0,"reason":-0.0037302563908983622,"mean_b":0.02050534469816864,"b_gate_pass_rate":0.3191489361702128,"median_len_z":593.0,"mean_r_leg":0.0021855711980131795,"mean_g_leg":0.024460880488596876,"g_bind_frac":0.3125,"a_match":0.5208333333333334,"a_match_n":16,"a_match_centered":-0.04166666666666667},"text":{"n_turns":361,"n_valid":359,"parse_rate":0.9944598337950139,"reason":0.0009330589562294405,"mean_b":0.06843577272808885,"b_gate_pass_rate":0.39275766016713093,"median_len_z":913.0,"mean_r_leg":0.027156680548179633,"mean_g_leg":0.05871002143486047,"g_bind_frac":0.17827298050139276,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.0023061053633847864,"mean_b":0.030736417104726278,"b_gate_pass_rate":0.513189448441247,"median_len_z":585.0,"mean_r_leg":0.00705507782031514,"mean_g_leg":0.06594991207342857,"g_bind_frac":0.18661971830985916,"a_match":0.13534278959810875,"a_match_n":282,"a_match_centered":-0.021135265700483092}}},"king":{"reason":0.0036925067044084334,"n_turns":994,"n_pairs":2934,"n_forfeits":2,"forfeit_rate":0.002012072434607646,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":9.867577414623147,"mean_len_z":959.0109066121336,"median_len_z":643.0,"mean_len_y":334.5068166325835,"mean_b":0.09678323133975644,"b_gate_pass_rate":0.5961145194274029,"mean_r_leg":0.020740284779139213,"mean_g_leg":0.055873335095237335,"g_bind_frac":0.23286290322580644,"a_match":0.12798092209856915,"a_match_n":629,"a_match_centered":-0.04072276159654801,"n_turns_cap_raised":44,"mean_cap_tokens":4144.028169014085,"max_cap_tokens":6012,"len_z_delta":-356.3325242932442,"len_y_delta":-358.1466891536657,"n_samples":994,"think_close_rate":0.9979879275653923,"n_text_fallback":0,"by_dialect":{"bash":{"n_turns":300,"n_valid":300,"parse_rate":1.0,"reason":0.010254758403833499,"mean_b":0.12424292975145679,"b_gate_pass_rate":0.8962795941375423,"median_len_z":487.0,"mean_r_leg":0.02095705404079562,"mean_g_leg":0.052826759145618254,"g_bind_frac":0.2833333333333333,"a_match":0.08444444444444445,"a_match_n":300,"a_match_centered":-0.04236343366778149},"boxed":{"n_turns":33,"n_valid":32,"parse_rate":0.9696969696969697,"reason":0.0027740638122255895,"mean_b":0.8299070868726209,"b_gate_pass_rate":0.7325581395348837,"median_len_z":1926.0,"mean_r_leg":0.08607247856269373,"mean_g_leg":0.011582033655597668,"g_bind_frac":0.75,"a_match":0.3111111111111111,"a_match_n":30,"a_match_centered":-0.16049382716049382},"terminus_json":{"n_turns":16,"n_valid":16,"parse_rate":1.0,"reason":-0.004142684848031568,"mean_b":0.021351542970736513,"b_gate_pass_rate":0.2978723404255319,"median_len_z":562.0,"mean_r_leg":0.0015410399519844803,"mean_g_leg":0.022467016046859824,"g_bind_frac":0.1875,"a_match":0.4791666666666667,"a_match_n":16,"a_match_centered":-0.08333333333333333},"text":{"n_turns":361,"n_valid":360,"parse_rate":0.997229916897507,"reason":-0.0007047537360360918,"mean_b":0.07043208091659942,"b_gate_pass_rate":0.4111111111111111,"median_len_z":885.5,"mean_r_leg":0.026273284623674703,"mean_g_leg":0.057142662794200515,"g_bind_frac":0.18611111111111112,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.0028981658222043062,"mean_b":0.030355326955282785,"b_gate_pass_rate":0.5191846522781774,"median_len_z":546.0,"mean_r_leg":0.007217915038403418,"mean_g_leg":0.0643551575040454,"g_bind_frac":0.18309859154929578,"a_match":0.1348645465253239,"a_match_n":283,"a_match_centered":-0.024758454106280192}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T16:55:41.169327+00:00","challenge_id":"chal-00673","repo":"r2://affine-private-models/models/registrations/d2b7d722230efb8cd3537e252e2211cc47494e260e8416c1f72b431b4f0d6828/","hotkey":"5DJcD5xMeqSNdQgjPRbL3UweWVtREUnjSJXkAMAShTeJowJQ","uid":218,"duration_s":2527.8,"revision":"2ec6461ab549316eaeed200a7338e160441ccb6711f3d6c09f429033b564529c","accepted":false,"error_code":null,"error_detail":"","z":-3.626345171818314,"margin":-0.13930567430110322,"se":0.03841489645930558,"n_paired_turns":990,"n_forfeit_turns":7,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":636420924284954949,"n":1000,"digest":"2a14c721f38833fefc7a7e17d01294f940ce10c2b15030d50314b8e276b896bc","n_paired_turns":990,"n_forfeit_turns":7,"margin":-0.13930567430110322,"se":0.03841489645930558,"z":-3.626345171818314,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.13930567430110322,"se":0.03841489645930558,"z":-3.626345171818314,"sd_diff":1.2086964992417975,"n_paired_turns":990,"n_forfeit_turns":7,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"bash":{"R":0.023445840867335765,"A":5.913049232898737,"Mc":0.1543648220186488},"text":{"R":0.08285030094354134,"A":12.912582417225314,"Mc":0.17894749340894664},"tool_call":{"R":0.008328875190260984,"A":5.943739204881916,"Mc":0.18210621583117198},"boxed":{"R":0.08442748775953351,"A":7.151895526561757,"Mc":0.08688125728272418},"terminus_json":{"R":0.0012821728663544253,"A":6.382601493353937,"Mc":0.10209717952760067}},"challenger":{"mean":-1.0777995695281126,"mean_valid":-0.9890011920446014,"sd_valid":2.143523422976716,"n_turns":997,"n_valid":984,"n_forfeits":8,"n_unscorable":5,"mean_z_R":0.1908067049121062,"mean_typ_c":0.3876152862616961,"mean_z_A":-0.2120376337768326,"bind_frac":{"R":0.32621951219512196,"Gc":0.18800813008130082,"A":0.48577235772357724},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.28552494715960103,"mean_R":0.01937894159783365,"mean_A":1.5157485891349933,"mean_mc":-0.6943392743442864},"king":{"mean":-0.9164288438523188,"mean_valid":-0.8714650663425919,"sd_valid":2.1013666920805596,"n_turns":997,"n_valid":986,"n_forfeits":4,"n_unscorable":7,"mean_z_R":0.19499734939363444,"mean_typ_c":0.48997792901615156,"mean_z_A":-0.1271976564842474,"bind_frac":{"R":0.36004056795131845,"Gc":0.16328600405679514,"A":0.4766734279918864},"n_leg_dropped":{"R":0,"Gc":8,"A":0},"mean_content_share":0.2775954756746438,"mean_R":0.019430784102689506,"mean_A":2.3281177694628608,"mean_mc":-0.6735819510169239}},"rejection_reason":null,"reign_number":null,"score":0.0032676180849895197,"score_king":0.0040092580846218095,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9131455,"blocks_since_crown":8145,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1480.0582458516762,"mean_len_y":638.0545208262783,"n_samples":3000,"think_close_rate":0.9673333333333334,"n_text_fallback":13,"by_dialect":{"text":{"n_turns":360,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":289,"zero_ref_turns":2,"mean_refs":2.916955017301038,"ref_pair_agreement":0.14671361502347416,"ref_pair_n":284},"tool_call":{"n_turns":295,"zero_ref_turns":0,"mean_refs":2.9627118644067796,"ref_pair_agreement":0.16666666666666669,"ref_pair_n":290},"boxed":{"n_turns":36,"zero_ref_turns":1,"mean_refs":2.7222222222222223,"ref_pair_agreement":0.3958333333333333,"ref_pair_n":32},"terminus_json":{"n_turns":20,"zero_ref_turns":0,"mean_refs":2.9,"ref_pair_agreement":0.5789473684210527,"ref_pair_n":19}},"ref_pair_agreement":0.18186666666666668,"ref_pair_n":625},"duel_seconds":2081.691283084918,"challenger":{"reason":0.0032676180849895197,"n_turns":997,"n_pairs":2934,"n_forfeits":8,"forfeit_rate":0.00802407221664995,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-98.29053720776109,"mean_len_z":948.2805044308112,"median_len_z":607.0,"mean_len_y":425.36059986366735,"mean_b":0.09927653260938371,"b_gate_pass_rate":0.49693251533742333,"mean_r_leg":0.01937894159783365,"mean_g_leg":0.05961145918566563,"g_bind_frac":0.21840242669362994,"a_match":0.13804981452040274,"a_match_n":629,"a_match_centered":-0.04421221864951769,"n_turns_cap_raised":49,"mean_cap_tokens":4154.21664994985,"max_cap_tokens":6008,"len_z_delta":-531.777741420865,"len_y_delta":-212.693920962611,"n_samples":1000,"think_close_rate":0.994,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":287,"n_valid":286,"parse_rate":0.9965156794425087,"reason":0.009629865139400434,"mean_b":0.11652144778360642,"b_gate_pass_rate":0.8836104513064132,"median_len_z":499.5,"mean_r_leg":0.021530772543400713,"mean_g_leg":0.053772180719498054,"g_bind_frac":0.26223776223776224,"a_match":0.11480186480186481,"a_match_n":286,"a_match_centered":-0.031103286384976527},"boxed":{"n_turns":35,"n_valid":33,"parse_rate":0.9428571428571428,"reason":0.0029152514969527322,"mean_b":0.8761922750545793,"b_gate_pass_rate":0.5894736842105263,"median_len_z":2380.0,"mean_r_leg":0.09160813182642359,"mean_g_leg":0.018397295883593043,"g_bind_frac":0.6666666666666666,"a_match":0.3709677419354839,"a_match_n":31,"a_match_centered":-0.06111111111111111},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0013915719572043545,"mean_b":0.016084593415683086,"b_gate_pass_rate":0.25862068965517243,"median_len_z":479.0,"mean_r_leg":0.00046928181756097817,"mean_g_leg":0.031607845452498534,"g_bind_frac":0.2,"a_match":0.5833333333333333,"a_match_n":20,"a_match_centered":0.03508771929824561},"text":{"n_turns":360,"n_valid":355,"parse_rate":0.9861111111111112,"reason":-8.222785020959615e-05,"mean_b":0.07883260121849138,"b_gate_pass_rate":0.28732394366197184,"median_len_z":751.0,"mean_r_leg":0.023187718879202523,"mean_g_leg":0.06060175750060945,"g_bind_frac":0.18591549295774648,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":295,"n_valid":295,"parse_rate":1.0,"reason":0.001523537622212959,"mean_b":0.028648048965843522,"b_gate_pass_rate":0.38558352402745993,"median_len_z":516.5,"mean_r_leg":0.005911451200355199,"mean_g_leg":0.07058982326414226,"g_bind_frac":0.16610169491525423,"a_match":0.10559360730593607,"a_match_n":292,"a_match_centered":-0.06055363321799308}}},"king":{"reason":0.0040092580846218095,"n_turns":997,"n_pairs":2941,"n_forfeits":4,"forfeit_rate":0.004012036108324975,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-98.56935475947058,"mean_len_z":962.5936756205373,"median_len_z":671.0,"mean_len_y":325.46480788847333,"mean_b":0.10507574558704459,"b_gate_pass_rate":0.5688541312478749,"mean_r_leg":0.019430784102689506,"mean_g_leg":0.05949283441722857,"g_bind_frac":0.23363544813695872,"a_match":0.1300684570826751,"a_match_n":633,"a_match_centered":-0.05181623931623932,"n_turns_cap_raised":49,"mean_cap_tokens":4154.21664994985,"max_cap_tokens":6008,"len_z_delta":-517.464570231139,"len_y_delta":-312.589712937805,"n_samples":997,"think_close_rate":0.995987963891675,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":287,"n_valid":287,"parse_rate":1.0,"reason":0.009921429069964495,"mean_b":0.12220153166637109,"b_gate_pass_rate":0.8813760379596679,"median_len_z":532.0,"mean_r_leg":0.020745228884069933,"mean_g_leg":0.05277030151767558,"g_bind_frac":0.29965156794425085,"a_match":0.10859465737514518,"a_match_n":287,"a_match_centered":-0.03697183098591549},"boxed":{"n_turns":35,"n_valid":35,"parse_rate":1.0,"reason":0.007857587786102306,"mean_b":0.9109449360206373,"b_gate_pass_rate":0.7448979591836735,"median_len_z":2312.0,"mean_r_leg":0.0754585246428633,"mean_g_leg":0.019255355131502033,"g_bind_frac":0.6,"a_match":0.2828282828282829,"a_match_n":33,"a_match_centered":-0.13978494623655913},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.003443618666946326,"mean_b":0.017831943274726595,"b_gate_pass_rate":0.25862068965517243,"median_len_z":529.0,"mean_r_leg":0.0006641403226727943,"mean_g_leg":0.026827996114677583,"g_bind_frac":0.2,"a_match":0.5833333333333333,"a_match_n":20,"a_match_centered":0.03508771929824561},"text":{"n_turns":360,"n_valid":356,"parse_rate":0.9888888888888889,"reason":0.0010401180163424968,"mean_b":0.08234981639282271,"b_gate_pass_rate":0.4353932584269663,"median_len_z":811.5,"mean_r_leg":0.024962994221773185,"mean_g_leg":0.061870415160198144,"g_bind_frac":0.19662921348314608,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":295,"n_valid":295,"parse_rate":1.0,"reason":0.0019294728211192564,"mean_b":0.03175676914102528,"b_gate_pass_rate":0.43135011441647597,"median_len_z":594.0,"mean_r_leg":0.006100782414704011,"mean_g_leg":0.07015234878579124,"g_bind_frac":0.17288135593220338,"a_match":0.10295790671217292,"a_match_n":293,"a_match_centered":-0.06264367816091955}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"failed","at":"2026-09-23T16:32:40.353612+00:00","challenge_id":"chal-00674","repo":"r2://affine-private-models/models/registrations/8a319af76285303ea266af3b27f931dcc3853db189de7f903ef433dcec6e56d7/","hotkey":"5FZuzNMY76qejzbQ4xQnQSHT1xTFYsQQqbh9sT8gQ1XEmDDB","uid":null,"duration_s":null,"revision":"2ec6461ab549316eaeed200a7338e160441ccb6711f3d6c09f429033b564529c","accepted":null,"error_code":"revision_already_submitted","error_detail":"revision 2ec6461ab549 was already submitted before","z":null,"margin":null,"se":null,"n_paired_turns":null,"n_forfeit_turns":null,"near_miss":null,"protocol_probe":null,"sd_meter":null,"rejection_reason":null,"reign_number":null,"score":null,"score_king":null,"gates":null,"duel_params":null,"teacher":null,"duel_seconds":null,"challenger":null,"king":null,"challenger_wins":null,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T13:44:52.722932+00:00","challenge_id":"chal-00672","repo":"r2://affine-private-models/models/registrations/33e74f23fcb13fe28e3aa2cd125e65871eed71cb3c990b3e0aef41809e3b54e6/","hotkey":"5EgHmsfuDuLpAvjtQtsHfSTMYr7XJaaXyH2TnPZVi2cf8A4S","uid":33,"duration_s":2576.8,"revision":"3eb078b4c742633c699ac7462bd2e13319b12cd86b138d8d97341d4391fa4f6d","accepted":false,"error_code":null,"error_detail":"","z":0.681448692500633,"margin":0.024333928707224745,"se":0.035709113503364955,"n_paired_turns":991,"n_forfeit_turns":2,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":11623733435146984783,"n":1000,"digest":"afbd4630b403d82c3ead07a4a52e6a2511fef8cadf455c172da60719d6f0f9d8","n_paired_turns":991,"n_forfeit_turns":2,"margin":0.024333928707224745,"se":0.035709113503364955,"z":0.681448692500633,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.024333928707224745,"se":0.035709113503364955,"z":0.681448692500633,"sd_diff":1.1241283379185116,"n_paired_turns":991,"n_forfeit_turns":2,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"tool_call":{"R":0.008851412671435183,"A":6.5218194809038765,"Mc":0.19149975736896743},"bash":{"R":0.01995657997139642,"A":6.6936404017482065,"Mc":0.15334265900422028},"text":{"R":0.07023428525284872,"A":34.2799935068191,"Mc":0.17233504012100137},"boxed":{"R":0.08208313719636806,"A":5.219161341443334,"Mc":0.11242908798304294},"terminus_json":{"R":0.0026261318792689665,"A":7.881103623626622,"Mc":0.09619281319947569}},"challenger":{"mean":-0.7832397061915821,"mean_valid":-0.7605566722303923,"sd_valid":2.052683522695578,"n_turns":998,"n_valid":989,"n_forfeits":2,"n_unscorable":7,"mean_z_R":0.25115651127936844,"mean_typ_c":0.55946589848772,"mean_z_A":-0.10946049283082801,"bind_frac":{"R":0.339737108190091,"Gc":0.1557128412537917,"A":0.5045500505561172},"n_leg_dropped":{"R":0,"Gc":9,"A":0},"mean_content_share":0.2804970438517674,"mean_R":0.01790864798238315,"mean_A":2.180095649739681,"mean_mc":-0.6416946186622647},"king":{"mean":-0.8188563227668525,"mean_valid":-0.7849398100957712,"sd_valid":2.078204134175766,"n_turns":998,"n_valid":989,"n_forfeits":3,"n_unscorable":6,"mean_z_R":0.3018147375750424,"mean_typ_c":0.4681844220547585,"mean_z_A":-0.09336126603565408,"bind_frac":{"R":0.3306370070778564,"Gc":0.1597573306370071,"A":0.5096056622851365},"n_leg_dropped":{"R":0,"Gc":9,"A":0},"mean_content_share":0.27692929880794037,"mean_R":0.018283650088312765,"mean_A":2.383639977787814,"mean_mc":-0.662412138857895}},"rejection_reason":null,"reign_number":null,"score":0.0037194313612396216,"score_king":0.003711168478826567,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9130497,"blocks_since_crown":7187,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1431.296584376057,"mean_len_y":690.0148799458912,"n_samples":3000,"think_close_rate":0.9666666666666667,"n_text_fallback":4,"by_dialect":{"tool_call":{"n_turns":295,"zero_ref_turns":1,"mean_refs":2.9457627118644067,"ref_pair_agreement":0.16608996539792387,"ref_pair_n":289},"text":{"n_turns":372,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":47,"zero_ref_turns":1,"mean_refs":2.617021276595745,"ref_pair_agreement":0.5793650793650793,"ref_pair_n":42},"bash":{"n_turns":263,"zero_ref_turns":0,"mean_refs":2.96958174904943,"ref_pair_agreement":0.16793893129770993,"ref_pair_n":262},"terminus_json":{"n_turns":23,"zero_ref_turns":0,"mean_refs":2.9565217391304346,"ref_pair_agreement":0.5217391304347826,"ref_pair_n":23}},"ref_pair_agreement":0.20833333333333334,"ref_pair_n":616},"duel_seconds":2098.4087321888655,"challenger":{"reason":0.0037194313612396216,"n_turns":998,"n_pairs":2951,"n_forfeits":2,"forfeit_rate":0.002004008016032064,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":18.42257535647319,"mean_len_z":962.0118603863098,"median_len_z":626.0,"mean_len_y":374.4147746526601,"mean_b":0.10412978063767676,"b_gate_pass_rate":0.5391392748220942,"mean_r_leg":0.01790864798238315,"mean_g_leg":0.058515269145778925,"g_bind_frac":0.21084337349397592,"a_match":0.1623725174449812,"a_match_n":621,"a_match_centered":-0.042755991285403055,"n_turns_cap_raised":43,"mean_cap_tokens":4138.23246492986,"max_cap_tokens":6042,"len_z_delta":-469.28472398974714,"len_y_delta":-315.600105293231,"n_samples":1001,"think_close_rate":0.998001998001998,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":263,"n_valid":263,"parse_rate":1.0,"reason":0.007302144540000295,"mean_b":0.11472236801365755,"b_gate_pass_rate":0.8553137003841229,"median_len_z":426.0,"mean_r_leg":0.018814762798856285,"mean_g_leg":0.04891952842521319,"g_bind_frac":0.2737642585551331,"a_match":0.14068441064638784,"a_match_n":263,"a_match_centered":-0.026717557251908396},"boxed":{"n_turns":46,"n_valid":46,"parse_rate":1.0,"reason":0.012855361958546047,"mean_b":0.9145658302760403,"b_gate_pass_rate":0.8048780487804879,"median_len_z":2028.0,"mean_r_leg":0.09191834488464717,"mean_g_leg":0.022372231334728324,"g_bind_frac":0.5652173913043478,"a_match":0.4108527131782946,"a_match_n":43,"a_match_centered":-0.16666666666666669},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0005025990264621128,"mean_b":0.018939321778380574,"b_gate_pass_rate":0.3382352941176471,"median_len_z":719.0,"mean_r_leg":0.001970894932719681,"mean_g_leg":0.03393939195101246,"g_bind_frac":0.17391304347826086,"a_match":0.5289855072463768,"a_match_n":23,"a_match_centered":0.007246376811594201},"text":{"n_turns":372,"n_valid":370,"parse_rate":0.9946236559139785,"reason":0.0008893331656033291,"mean_b":0.07161421464397687,"b_gate_pass_rate":0.3864864864864865,"median_len_z":771.0,"mean_r_leg":0.017366859175461696,"mean_g_leg":0.061385967426158435,"g_bind_frac":0.16216216216216217,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":294,"n_valid":294,"parse_rate":1.0,"reason":0.002996291409551484,"mean_b":0.028098462581611514,"b_gate_pass_rate":0.428078250863061,"median_len_z":534.0,"mean_r_leg":0.007447001466963479,"mean_g_leg":0.07106406629052835,"g_bind_frac":0.16326530612244897,"a_match":0.11643835616438356,"a_match_n":292,"a_match_centered":-0.04413472706155633}}},"king":{"reason":0.003711168478826567,"n_turns":998,"n_pairs":2950,"n_forfeits":3,"forfeit_rate":0.003006012024048096,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":16.982924547794223,"mean_len_z":973.3566101694915,"median_len_z":645.0,"mean_len_y":342.99389830508477,"mean_b":0.10345327534311058,"b_gate_pass_rate":0.5498305084745763,"mean_r_leg":0.018283650088312765,"mean_g_leg":0.058128780696028726,"g_bind_frac":0.23316582914572864,"a_match":0.16102150537634408,"a_match_n":620,"a_match_centered":-0.044389978213507625,"n_turns_cap_raised":43,"mean_cap_tokens":4138.23246492986,"max_cap_tokens":6042,"len_z_delta":-457.93997420656535,"len_y_delta":-347.0209816408064,"n_samples":998,"think_close_rate":0.996993987975952,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":263,"n_valid":263,"parse_rate":1.0,"reason":0.007784925762785209,"mean_b":0.11677703664188066,"b_gate_pass_rate":0.8629961587708067,"median_len_z":428.0,"mean_r_leg":0.02088265268603941,"mean_g_leg":0.048296847400409244,"g_bind_frac":0.2889733840304182,"a_match":0.14195183776932827,"a_match_n":263,"a_match_centered":-0.025445292620865142},"boxed":{"n_turns":46,"n_valid":45,"parse_rate":0.9782608695652174,"reason":0.0057658186787263735,"mean_b":0.9147320799848109,"b_gate_pass_rate":0.7704918032786885,"median_len_z":2398.0,"mean_r_leg":0.09264123360576869,"mean_g_leg":0.020708728019912706,"g_bind_frac":0.6,"a_match":0.4603174603174603,"a_match_n":42,"a_match_centered":-0.125},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":0.00014766791988182269,"mean_b":0.018585791909232426,"b_gate_pass_rate":0.22058823529411764,"median_len_z":752.0,"mean_r_leg":0.002176237055075914,"mean_g_leg":0.03593206049893776,"g_bind_frac":0.17391304347826086,"a_match":0.4855072463768116,"a_match_n":23,"a_match_centered":-0.036231884057971016},"text":{"n_turns":372,"n_valid":370,"parse_rate":0.9946236559139785,"reason":0.0007393984688589713,"mean_b":0.06799699108139756,"b_gate_pass_rate":0.4486486486486487,"median_len_z":874.5,"mean_r_leg":0.016356551291185253,"mean_g_leg":0.06103548030235227,"g_bind_frac":0.20540540540540542,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":294,"n_valid":294,"parse_rate":1.0,"reason":0.0037844571920482013,"mean_b":0.02951264549659539,"b_gate_pass_rate":0.3924050632911392,"median_len_z":541.0,"mean_r_leg":0.008262793330537267,"mean_g_leg":0.07072995939455431,"g_bind_frac":0.16666666666666666,"a_match":0.1095890410958904,"a_match_n":292,"a_match_centered":-0.051103368176538905}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T07:01:52.553197+00:00","challenge_id":"chal-00671","repo":"r2://affine-private-models/models/registrations/e7c5d7c6ca5e67105a7c5aee2a2e6ad0c262e6696b939442baf19b6672875203/","hotkey":"5Ex95sLQaKEfuTyLcLfW5FmizknQ6MhvrQ62TMoc3v24njk1","uid":45,"duration_s":2577.5,"revision":"b4eae600646f70c0213b3e62aa47144d4c7e4a5d057a6fb109cbde030cac1fd3","accepted":false,"error_code":null,"error_detail":"","z":-0.037061726096159535,"margin":-0.0011979475516954083,"se":0.03232303721060482,"n_paired_turns":992,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":9435684226885414172,"n":1000,"digest":"83367bb7693247c0e55ab7af71709cd5fef0612491031dcc238f301bba432981","n_paired_turns":992,"n_forfeit_turns":4,"margin":-0.0011979475516954083,"se":0.03232303721060482,"z":-0.037061726096159535,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.0011979475516954083,"se":0.03232303721060482,"z":-0.037061726096159535,"sd_diff":1.0180473980331164,"n_paired_turns":992,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"bash":{"R":0.026116455551059632,"A":5.988214196745242,"Mc":0.15524754715774278},"tool_call":{"R":0.007631475845883283,"A":5.714437980588473,"Mc":0.2029452830439507},"text":{"R":0.15129194696001716,"A":21.949642954550193,"Mc":0.16986472371405462},"terminus_json":{"R":0.0018940490141700927,"A":9.63977037969586,"Mc":0.12581679231841736},"boxed":{"R":0.19471269207914488,"A":4.866336519697978,"Mc":0.1357290165886114}},"challenger":{"mean":-0.7122564120616347,"mean_valid":-0.678016542735229,"sd_valid":1.7300477776815006,"n_turns":995,"n_valid":989,"n_forfeits":3,"n_unscorable":3,"mean_z_R":0.17630801668682583,"mean_typ_c":0.7175639845391691,"mean_z_A":-0.11417315044440976,"bind_frac":{"R":0.3528816986855409,"Gc":0.14256825075834176,"A":0.5045500505561172},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.28765511460669446,"mean_R":0.022239199447822048,"mean_A":1.74651094562564,"mean_mc":-0.6551979198119128},"king":{"mean":-0.7110584645099393,"mean_valid":-0.6768149613689178,"sd_valid":1.6729035493533329,"n_turns":995,"n_valid":989,"n_forfeits":3,"n_unscorable":3,"mean_z_R":0.15819294649725696,"mean_typ_c":0.7488313375797646,"mean_z_A":-0.15084183601008863,"bind_frac":{"R":0.34277047522750254,"Gc":0.1263902932254803,"A":0.5308392315470172},"n_leg_dropped":{"R":0,"Gc":6,"A":0},"mean_content_share":0.2835843880024613,"mean_R":0.02102425524170566,"mean_A":1.5795272924147512,"mean_mc":-0.6563224067583415}},"rejection_reason":null,"reign_number":null,"score":0.003992490754848213,"score_king":0.003917406037439372,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9128488,"blocks_since_crown":5178,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1202.8134504900304,"mean_len_y":684.6272389320717,"n_samples":3000,"think_close_rate":0.9753333333333334,"n_text_fallback":19,"by_dialect":{"text":{"n_turns":370,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":316,"zero_ref_turns":2,"mean_refs":2.949367088607595,"ref_pair_agreement":0.17891373801916932,"ref_pair_n":313},"tool_call":{"n_turns":289,"zero_ref_turns":3,"mean_refs":2.934256055363322,"ref_pair_agreement":0.1553973902728351,"ref_pair_n":281},"boxed":{"n_turns":6,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.8666666666666666,"ref_pair_n":5},"terminus_json":{"n_turns":19,"zero_ref_turns":0,"mean_refs":2.6842105263157894,"ref_pair_agreement":0.3137254901960784,"ref_pair_n":17}},"ref_pair_agreement":0.17748917748917747,"ref_pair_n":616},"duel_seconds":2126.1047955057584,"challenger":{"reason":0.003992490754848213,"n_turns":995,"n_pairs":2950,"n_forfeits":3,"forfeit_rate":0.003015075376884422,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-6.431334934090883,"mean_len_z":834.9257627118644,"median_len_z":598.5,"mean_len_y":368.76745762711863,"mean_b":0.07784160968415983,"b_gate_pass_rate":0.5572881355932203,"mean_r_leg":0.022239199447822048,"mean_g_leg":0.05929768228536156,"g_bind_frac":0.20665322580645162,"a_match":0.13548387096774195,"a_match_n":620,"a_match_centered":-0.04112554112554112,"n_turns_cap_raised":36,"mean_cap_tokens":4128.627135678392,"max_cap_tokens":6027,"len_z_delta":-367.88768777816597,"len_y_delta":-315.85978130495306,"n_samples":998,"think_close_rate":0.996993987975952,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":314,"n_valid":314,"parse_rate":1.0,"reason":0.00958748064638566,"mean_b":0.11634657873559087,"b_gate_pass_rate":0.8465665236051502,"median_len_z":469.0,"mean_r_leg":0.02298066682880067,"mean_g_leg":0.04456504446344124,"g_bind_frac":0.2961783439490446,"a_match":0.11358811040339702,"a_match_n":314,"a_match_centered":-0.06496272630457933},"boxed":{"n_turns":6,"n_valid":6,"parse_rate":1.0,"reason":0.02271763520304542,"mean_b":1.5724679668893684,"b_gate_pass_rate":0.6666666666666666,"median_len_z":2050.5,"mean_r_leg":0.10366992897843202,"mean_g_leg":0.052257915681837505,"g_bind_frac":0.16666666666666666,"a_match":0.9333333333333333,"a_match_n":5,"a_match_centered":0.06666666666666667},"terminus_json":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":-0.0004919124083440599,"mean_b":0.01907907774546959,"b_gate_pass_rate":0.27450980392156865,"median_len_z":767.0,"mean_r_leg":0.001170560389038753,"mean_g_leg":0.04762167914738016,"g_bind_frac":0.15789473684210525,"a_match":0.3333333333333333,"a_match_n":19,"a_match_centered":0.058823529411764705},"text":{"n_turns":370,"n_valid":367,"parse_rate":0.9918918918918919,"reason":0.0005658487690279047,"mean_b":0.06372011889220668,"b_gate_pass_rate":0.4223433242506812,"median_len_z":782.0,"mean_r_leg":0.03440455690883978,"mean_g_leg":0.05973014831475749,"g_bind_frac":0.17983651226158037,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":286,"n_valid":286,"parse_rate":1.0,"reason":0.002187887615765087,"mean_b":0.025665601317634037,"b_gate_pass_rate":0.42924528301886794,"median_len_z":524.5,"mean_r_leg":0.005505677836327037,"mean_g_leg":0.07584109453199604,"g_bind_frac":0.14685314685314685,"a_match":0.13238770685579196,"a_match_n":282,"a_match_centered":-0.022538552787663108}}},"king":{"reason":0.003917406037439372,"n_turns":995,"n_pairs":2950,"n_forfeits":3,"forfeit_rate":0.003015075376884422,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.8446577552171368,"mean_len_z":867.291186440678,"median_len_z":620.0,"mean_len_y":346.3857627118644,"mean_b":0.07582866627268484,"b_gate_pass_rate":0.5677966101694916,"mean_r_leg":0.02102425524170566,"mean_g_leg":0.059754824073868125,"g_bind_frac":0.22379032258064516,"a_match":0.12708669897684438,"a_match_n":619,"a_match_centered":-0.04986449864498645,"n_turns_cap_raised":36,"mean_cap_tokens":4128.627135678392,"max_cap_tokens":6027,"len_z_delta":-335.52226404935243,"len_y_delta":-338.2414762202073,"n_samples":995,"think_close_rate":0.9979899497487437,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":314,"n_valid":313,"parse_rate":0.9968152866242038,"reason":0.008762566208081116,"mean_b":0.11289597331260137,"b_gate_pass_rate":0.8557588805166846,"median_len_z":492.0,"mean_r_leg":0.021685681340695904,"mean_g_leg":0.045338216764736546,"g_bind_frac":0.329073482428115,"a_match":0.11395101171458998,"a_match_n":313,"a_match_centered":-0.06517094017094016},"boxed":{"n_turns":6,"n_valid":6,"parse_rate":1.0,"reason":0.029726424617444402,"mean_b":1.4885019065154974,"b_gate_pass_rate":0.8333333333333334,"median_len_z":2166.0,"mean_r_leg":0.10733364363649081,"mean_g_leg":0.05179766748279571,"g_bind_frac":0.16666666666666666,"a_match":0.9333333333333333,"a_match_n":5,"a_match_centered":0.06666666666666667},"terminus_json":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":-0.0022989466798038235,"mean_b":0.019887372057813546,"b_gate_pass_rate":0.43137254901960786,"median_len_z":791.0,"mean_r_leg":0.0013975562118888217,"mean_g_leg":0.045356741944607384,"g_bind_frac":0.15789473684210525,"a_match":0.2631578947368421,"a_match_n":19,"a_match_centered":-0.019607843137254905},"text":{"n_turns":370,"n_valid":368,"parse_rate":0.9945945945945946,"reason":0.001191334931465623,"mean_b":0.06007304091126057,"b_gate_pass_rate":0.4157608695652174,"median_len_z":791.5,"mean_r_leg":0.032102745427313874,"mean_g_leg":0.060614979722322576,"g_bind_frac":0.1956521739130435,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":286,"n_valid":286,"parse_rate":1.0,"reason":0.00199615640728682,"mean_b":0.029111177875889738,"b_gate_pass_rate":0.4528301886792453,"median_len_z":526.0,"mean_r_leg":0.005538731444188323,"mean_g_leg":0.07554911536453014,"g_bind_frac":0.15034965034965034,"a_match":0.1182033096926714,"a_match_n":282,"a_match_centered":-0.036773428232502965}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-23T03:01:45.811587+00:00","challenge_id":"chal-00670","repo":"r2://affine-private-models/models/registrations/c6396a70532fbfda96c51407ca12d76cbfd9abf9b7929f031e751127cd84703a/","hotkey":"5DbVqSQQVunYDdFEB6ckHV3srFCXBNmXmxpQMkdqrGg3dmGy","uid":25,"duration_s":2713.2,"revision":"1e448cceff8b7a49299659d60ad75fa054ed62ee450e36b6ab808c7dedddcfb8","accepted":false,"error_code":null,"error_detail":"","z":-1.831393832308969,"margin":-0.10745249790307689,"se":0.05867252363059662,"n_paired_turns":987,"n_forfeit_turns":16,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":5186341975023086174,"n":1000,"digest":"488d762fbd140000d6843c06a5b9f5b8b50c12f9a1b1272f9d14ef0031585472","n_paired_turns":987,"n_forfeit_turns":16,"margin":-0.10745249790307689,"se":0.05867252363059662,"z":-1.831393832308969,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.10745249790307689,"se":0.05867252363059662,"z":-1.831393832308969,"sd_diff":1.843288632798331,"n_paired_turns":987,"n_forfeit_turns":16,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"tool_call":{"R":0.07105579639258425,"A":6.81179926491943,"Mc":0.1877720127977705},"bash":{"R":0.02578964600925011,"A":6.065651566672042,"Mc":0.16119262064650403},"text":{"R":0.06040148237598574,"A":20.339945465894854,"Mc":0.16720887056426942},"terminus_json":{"R":0.00987367431165655,"A":18.616424156492204,"Mc":0.11903265818571603},"boxed":{"R":0.039880209262117446,"A":4.117908503882086,"Mc":0.12106398403414072}},"challenger":{"mean":-0.8761749339713678,"mean_valid":-0.7046873944128587,"sd_valid":1.8702339010641964,"n_turns":993,"n_valid":973,"n_forfeits":15,"n_unscorable":5,"mean_z_R":0.07613265640159626,"mean_typ_c":0.5425302499504399,"mean_z_A":-0.09862664710937571,"bind_frac":{"R":0.3648509763617677,"Gc":0.15827338129496402,"A":0.47687564234326824},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.2892630487159079,"mean_R":0.01546461512753937,"mean_A":2.1546518990174874,"mean_mc":-0.6743702891459475},"king":{"mean":-0.7574520965890319,"mean_valid":-0.7002089809912164,"sd_valid":1.8059419011639901,"n_turns":993,"n_valid":982,"n_forfeits":5,"n_unscorable":6,"mean_z_R":0.06768150383961664,"mean_typ_c":0.5918324043477767,"mean_z_A":-0.10752513827053552,"bind_frac":{"R":0.34623217922606925,"Gc":0.1629327902240326,"A":0.4908350305498982},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.2872570584423305,"mean_R":0.015156041165052004,"mean_A":1.8850041283815056,"mean_mc":-0.6763128444194657}},"rejection_reason":null,"reign_number":null,"score":0.002761539332042979,"score_king":0.002863384559154848,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9127276,"blocks_since_crown":3966,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1258.447948457104,"mean_len_y":690.7361817565277,"n_samples":3000,"think_close_rate":0.972,"n_text_fallback":24,"by_dialect":{"text":{"n_turns":358,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":282,"zero_ref_turns":3,"mean_refs":2.9397163120567376,"ref_pair_agreement":0.15808823529411764,"ref_pair_n":272},"bash":{"n_turns":332,"zero_ref_turns":4,"mean_refs":2.897590361445783,"ref_pair_agreement":0.2006172839506173,"ref_pair_n":324},"terminus_json":{"n_turns":20,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.38333333333333336,"ref_pair_n":20},"boxed":{"n_turns":8,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.8333333333333334,"ref_pair_n":8}},"ref_pair_agreement":0.19604700854700854,"ref_pair_n":624},"duel_seconds":2227.43909852067,"challenger":{"reason":0.002761539332042979,"n_turns":993,"n_pairs":2907,"n_forfeits":15,"forfeit_rate":0.015105740181268883,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":45.16555343375531,"mean_len_z":1078.6818025455796,"median_len_z":557.0,"mean_len_y":515.6934984520124,"mean_b":0.07405396320629007,"b_gate_pass_rate":0.47678018575851394,"mean_r_leg":0.01546461512753937,"mean_g_leg":0.05878161994598787,"g_bind_frac":0.21779141104294478,"a_match":0.159967845659164,"a_match_n":622,"a_match_centered":-0.035443722943722944,"n_turns_cap_raised":40,"mean_cap_tokens":4132.719033232628,"max_cap_tokens":6075,"len_z_delta":-179.76614591152452,"len_y_delta":-175.04268330451532,"n_samples":996,"think_close_rate":0.9869477911646586,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":328,"n_valid":326,"parse_rate":0.9939024390243902,"reason":0.007792345404511272,"mean_b":0.12096954096268343,"b_gate_pass_rate":0.8133472367049009,"median_len_z":433.0,"mean_r_leg":0.018911491573492676,"mean_g_leg":0.05044474538192302,"g_bind_frac":0.29141104294478526,"a_match":0.15593047034764826,"a_match_n":326,"a_match_centered":-0.043859649122807015},"boxed":{"n_turns":8,"n_valid":8,"parse_rate":1.0,"reason":0.009612227335829749,"mean_b":1.3082348886151587,"b_gate_pass_rate":0.375,"median_len_z":3049.5,"mean_r_leg":0.08041703489637847,"mean_g_leg":0.028090687481458113,"g_bind_frac":0.25,"a_match":0.875,"a_match_n":8,"a_match_centered":0.041666666666666664},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.00019350566198021501,"mean_b":0.025618233509055385,"b_gate_pass_rate":0.35,"median_len_z":536.5,"mean_r_leg":0.0023689230760628914,"mean_g_leg":0.039262847312250805,"g_bind_frac":0.1,"a_match":0.45,"a_match_n":20,"a_match_centered":0.06666666666666667},"text":{"n_turns":358,"n_valid":346,"parse_rate":0.9664804469273743,"reason":-0.0007170052799784928,"mean_b":0.04497412094132973,"b_gate_pass_rate":0.2630057803468208,"median_len_z":761.5,"mean_r_leg":0.012101256491347563,"mean_g_leg":0.06191321861121222,"g_bind_frac":0.1907514450867052,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":279,"n_valid":278,"parse_rate":0.996415770609319,"reason":0.0013260912144238265,"mean_b":0.023785971408068318,"b_gate_pass_rate":0.3668280871670702,"median_len_z":497.5,"mean_r_leg":0.014681646960706294,"mean_g_leg":0.06694777419817671,"g_bind_frac":0.17266187050359713,"a_match":0.12189054726368158,"a_match_n":268,"a_match_centered":-0.03522012578616352}}},"king":{"reason":0.002863384559154848,"n_turns":993,"n_pairs":2934,"n_forfeits":5,"forfeit_rate":0.005035246727089627,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":39.838124382710255,"mean_len_z":863.4505794137696,"median_len_z":607.0,"mean_len_y":350.939672801636,"mean_b":0.08286743986530214,"b_gate_pass_rate":0.5783912747102932,"mean_r_leg":0.015156041165052004,"mean_g_leg":0.057891189298203964,"g_bind_frac":0.2236842105263158,"a_match":0.1388004246284501,"a_match_n":628,"a_match_centered":-0.05501878690284487,"n_turns_cap_raised":40,"mean_cap_tokens":4132.719033232628,"max_cap_tokens":6075,"len_z_delta":-394.9973690433345,"len_y_delta":-339.7965089548917,"n_samples":993,"think_close_rate":0.9949647532729103,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":328,"n_valid":328,"parse_rate":1.0,"reason":0.0075402971019601995,"mean_b":0.12415796494654133,"b_gate_pass_rate":0.8492723492723493,"median_len_z":460.0,"mean_r_leg":0.019605692591372716,"mean_g_leg":0.04894290728930711,"g_bind_frac":0.2865853658536585,"a_match":0.13160569105691056,"a_match_n":328,"a_match_centered":-0.06738683127572016},"boxed":{"n_turns":8,"n_valid":8,"parse_rate":1.0,"reason":0.0076118522550158154,"mean_b":1.4180109319322425,"b_gate_pass_rate":0.75,"median_len_z":2123.5,"mean_r_leg":0.0220509472894012,"mean_g_leg":0.03259491424512681,"g_bind_frac":0.25,"a_match":0.7916666666666666,"a_match_n":8,"a_match_centered":-0.04166666666666667},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.005966386223419723,"mean_b":0.020936453784367502,"b_gate_pass_rate":0.5,"median_len_z":525.5,"mean_r_leg":0.0023491881338046066,"mean_g_leg":0.031093924726285777,"g_bind_frac":0.25,"a_match":0.38333333333333336,"a_match_n":20,"a_match_centered":0.0},"text":{"n_turns":358,"n_valid":353,"parse_rate":0.9860335195530726,"reason":-0.0002766042692131271,"mean_b":0.06033533844589625,"b_gate_pass_rate":0.4164305949008499,"median_len_z":788.0,"mean_r_leg":0.01186288326463771,"mean_g_leg":0.061089123918699535,"g_bind_frac":0.18413597733711048,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":279,"n_valid":279,"parse_rate":1.0,"reason":0.0018909700810193042,"mean_b":0.02956517886439532,"b_gate_pass_rate":0.47165259348612787,"median_len_z":581.0,"mean_r_leg":0.01481187228563697,"mean_g_leg":0.06701119313241978,"g_bind_frac":0.1971326164874552,"a_match":0.11029411764705882,"a_match_n":272,"a_match_centered":-0.04460966542750929}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T19:09:16.879903+00:00","challenge_id":"chal-00669","repo":"r2://affine-private-models/models/registrations/fe8aa638ecf9e4fe1f1b5b7d19fb7df62b77e4e56629e0e7c6d77a6f4dc09b1f/","hotkey":"5GTN8JTQbHgbG4gEWg2XgqrmNn49rzRsVgJzqNUHysovMLPw","uid":155,"duration_s":2766.0,"revision":"0f224c741ce0ddd5dd9ebe13b76efe191662cc58b55dbe7ef3f4a04eb590edbd","accepted":false,"error_code":null,"error_detail":"","z":0.28031607838012457,"margin":0.007943365540688105,"se":0.028337174187762604,"n_paired_turns":989,"n_forfeit_turns":2,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2283444187207133531,"n":1000,"digest":"70e429743c0f33148cef8972fbfeb257af710b4ad263c42a0f949c928f450cbc","n_paired_turns":989,"n_forfeit_turns":2,"margin":0.007943365540688105,"se":0.028337174187762604,"z":0.28031607838012457,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.007943365540688105,"se":0.028337174187762604,"z":0.28031607838012457,"sd_diff":0.8911579495786229,"n_paired_turns":989,"n_forfeit_turns":2,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"},"sigma_by_dialect":{"bash":{"R":0.023902288356662877,"A":7.336219168531229,"Mc":0.16359863330678798},"tool_call":{"R":0.009929530790056621,"A":7.772286121830186,"Mc":0.17397551829914196},"text":{"R":0.02128423982589192,"A":17.881249920874897,"Mc":0.1879989642216649},"terminus_json":{"R":0.0017093284326065666,"A":7.76679300627834,"Mc":0.1629414556642408},"boxed":{"R":0.215794271507872,"A":5.3044686630137825,"Mc":0.11820880769689875}},"challenger":{"mean":-0.7560018544095809,"mean_valid":-0.7446212894848943,"sd_valid":1.979935968824617,"n_turns":996,"n_valid":988,"n_forfeits":1,"n_unscorable":7,"mean_z_R":0.18044689875785144,"mean_typ_c":0.5749557421139094,"mean_z_A":-0.08813061136246213,"bind_frac":{"R":0.3360323886639676,"Gc":0.14068825910931174,"A":0.5232793522267206},"n_leg_dropped":{"R":0,"Gc":6,"A":0},"mean_content_share":0.2885582274142742,"mean_R":0.013031439158078492,"mean_A":1.6881282302151885,"mean_mc":-0.6741418885283613},"king":{"mean":-0.763945219950269,"mean_valid":-0.7411771251578683,"sd_valid":1.9785514282617893,"n_turns":996,"n_valid":987,"n_forfeits":2,"n_unscorable":7,"mean_z_R":0.2456642035664653,"mean_typ_c":0.5579265287538641,"mean_z_A":-0.08406266249063114,"bind_frac":{"R":0.3262411347517731,"Gc":0.15602836879432624,"A":0.5177304964539007},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.2848214559566324,"mean_R":0.014591720857966868,"mean_A":1.7465673494600318,"mean_mc":-0.6814950072839092}},"rejection_reason":null,"reign_number":null,"score":0.0037649245997733913,"score_king":0.0043322153379960465,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":4096,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4864,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9124910,"blocks_since_crown":1600,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true,"content_prefix":"refs_max"}},"teacher":{"mean_len_z":1274.7677966101694,"mean_len_y":679.2159322033898,"n_samples":3000,"think_close_rate":0.976,"n_text_fallback":25,"by_dialect":{"tool_call":{"n_turns":286,"zero_ref_turns":1,"mean_refs":2.9265734265734267,"ref_pair_agreement":0.1733821733821734,"ref_pair_n":273},"bash":{"n_turns":300,"zero_ref_turns":2,"mean_refs":2.9133333333333336,"ref_pair_agreement":0.16780045351473924,"ref_pair_n":294},"text":{"n_turns":371,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":24,"zero_ref_turns":1,"mean_refs":2.875,"ref_pair_agreement":0.34782608695652173,"ref_pair_n":23},"boxed":{"n_turns":19,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.7368421052631579,"ref_pair_n":19}},"ref_pair_agreement":0.19485495347564316,"ref_pair_n":609},"duel_seconds":2216.5583606660366,"challenger":{"reason":0.0037649245997733913,"n_turns":996,"n_pairs":2947,"n_forfeits":1,"forfeit_rate":0.001004016064257028,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-36.88451046018151,"mean_len_z":849.5748218527316,"median_len_z":580.0,"mean_len_y":402.2701051917204,"mean_b":0.09045125921409376,"b_gate_pass_rate":0.5748218527315915,"mean_r_leg":0.013031439158078492,"mean_g_leg":0.059713384435431206,"g_bind_frac":0.20301507537688443,"a_match":0.14324178782983307,"a_match_n":619,"a_match_centered":-0.05098684210526316,"n_turns_cap_raised":32,"mean_cap_tokens":4124.29718875502,"max_cap_tokens":5893,"len_z_delta":-425.1929747574378,"len_y_delta":-276.9458270116694,"n_samples":999,"think_close_rate":0.998998998998999,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":298,"n_valid":298,"parse_rate":1.0,"reason":0.00866148879798377,"mean_b":0.12094758718808539,"b_gate_pass_rate":0.8409610983981693,"median_len_z":510.0,"mean_r_leg":0.0168133602833887,"mean_g_leg":0.04797667509979453,"g_bind_frac":0.2651006711409396,"a_match":0.12080536912751678,"a_match_n":298,"a_match_centered":-0.048752834467120185},"boxed":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":0.0007277392041034651,"mean_b":1.541830336199836,"b_gate_pass_rate":0.8421052631578947,"median_len_z":1924.0,"mean_r_leg":0.10248039868776988,"mean_g_leg":0.020866371108334468,"g_bind_frac":0.47368421052631576,"a_match":0.6491228070175439,"a_match_n":19,"a_match_centered":-0.08771929824561404},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0004021522356608335,"mean_b":0.022818031432060272,"b_gate_pass_rate":0.43478260869565216,"median_len_z":531.0,"mean_r_leg":0.0010190542020659897,"mean_g_leg":0.05946566447918913,"g_bind_frac":0.13043478260869565,"a_match":0.36231884057971014,"a_match_n":23,"a_match_centered":0.014492753623188404},"text":{"n_turns":371,"n_valid":370,"parse_rate":0.9973045822102425,"reason":0.0016933760403545282,"mean_b":0.04273079383988261,"b_gate_pass_rate":0.44054054054054054,"median_len_z":696.0,"mean_r_leg":0.011169340567339751,"mean_g_leg":0.0634108662456972,"g_bind_frac":0.16486486486486487,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":285,"n_valid":285,"parse_rate":1.0,"reason":0.0018804252110380263,"mean_b":0.028628094632108924,"b_gate_pass_rate":0.46833930704898447,"median_len_z":513.0,"mean_r_leg":0.006500627249850569,"mean_g_leg":0.06979500522290391,"g_bind_frac":0.17543859649122806,"a_match":0.11469534050179211,"a_match_n":279,"a_match_centered":-0.056372549019607844}}},"king":{"reason":0.0043322153379960465,"n_turns":996,"n_pairs":2944,"n_forfeits":2,"forfeit_rate":0.002008032128514056,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-31.569176479551718,"mean_len_z":840.5866168478261,"median_len_z":607.0,"mean_len_y":385.9052309782609,"mean_b":0.09613562797598427,"b_gate_pass_rate":0.5699728260869565,"mean_r_leg":0.014591720857966868,"mean_g_leg":0.06017772481691447,"g_bind_frac":0.21026156941649898,"a_match":0.14135702746365106,"a_match_n":619,"a_match_centered":-0.051176792556102906,"n_turns_cap_raised":32,"mean_cap_tokens":4124.29718875502,"max_cap_tokens":5893,"len_z_delta":-434.1811797623433,"len_y_delta":-293.3107012251289,"n_samples":996,"think_close_rate":0.9979919678714859,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":298,"n_valid":298,"parse_rate":1.0,"reason":0.009855619740386685,"mean_b":0.1205212823623525,"b_gate_pass_rate":0.8558352402745996,"median_len_z":513.0,"mean_r_leg":0.019002496964638283,"mean_g_leg":0.04905402006739414,"g_bind_frac":0.2751677852348993,"a_match":0.11912751677852348,"a_match_n":298,"a_match_centered":-0.04705215419501134},"boxed":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":0.0028564041941683826,"mean_b":1.5304829259608916,"b_gate_pass_rate":0.7368421052631579,"median_len_z":1652.0,"mean_r_leg":0.11420768023313457,"mean_g_leg":0.023098539543666446,"g_bind_frac":0.47368421052631576,"a_match":0.631578947368421,"a_match_n":19,"a_match_centered":-0.10526315789473684},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":0.0002540607713829756,"mean_b":0.02379003315237845,"b_gate_pass_rate":0.4782608695652174,"median_len_z":552.0,"mean_r_leg":0.0015270927937686154,"mean_g_leg":0.06045977945984054,"g_bind_frac":0.043478260869565216,"a_match":0.391304347826087,"a_match_n":23,"a_match_centered":0.043478260869565216},"text":{"n_turns":371,"n_valid":369,"parse_rate":0.9946091644204852,"reason":0.0023279809145070186,"mean_b":0.05820269048199123,"b_gate_pass_rate":0.4173441734417344,"median_len_z":711.0,"mean_r_leg":0.013042558993535739,"mean_g_leg":0.06487983230635333,"g_bind_frac":0.16802168021680217,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":285,"n_valid":285,"parse_rate":1.0,"reason":0.0015933887624411155,"mean_b":0.02912577126135288,"b_gate_pass_rate":0.46953405017921146,"median_len_z":521.0,"mean_r_leg":0.006398782842301531,"mean_g_leg":0.06817001820343563,"g_bind_frac":0.19298245614035087,"a_match":0.1111111111111111,"a_match_n":279,"a_match_centered":-0.059829059829059825}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T16:58:08.335351+00:00","challenge_id":"chal-00668","repo":"r2://affine-private-models/models/registrations/d29b20a7f909c6f75287db58838703351101ae4e9be3154605805d340c2e66d4/","hotkey":"5DLyWJP3RiyuCZaojFt8k4zaCZBEQA9NXKcp5ddUVwhperU3","uid":234,"duration_s":2450.8,"revision":"0e139cc70d3e880f074c9234c717fac73b0e17389c1179b57c26d9aec2624b40","accepted":false,"error_code":null,"error_detail":"","z":-0.6223849659264188,"margin":-0.024552706834047523,"se":0.03944938933012443,"n_paired_turns":991,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":14063967453144554067,"n":1000,"digest":"2171e326f6e1f57233159230b8b42c1e5a3cb0e11927ec8f2ef2fce8051f8e60","n_paired_turns":991,"n_forfeit_turns":5,"margin":-0.024552706834047523,"se":0.03944938933012443,"z":-0.6223849659264188,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.024552706834047523,"se":0.03944938933012443,"z":-0.6223849659264188,"sd_diff":1.2418727912524123,"n_paired_turns":991,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.023220789632109756,"A":6.428198382248953,"Mc":0.14954475774232917},"text":{"R":0.03418357305958104,"A":13.864441194978838,"Mc":0.17050121153349881},"tool_call":{"R":0.007568564811400789,"A":5.599090229453157,"Mc":0.1944431479602131},"boxed":{"R":0.11967570492583172,"A":2.696556261353484,"Mc":0.1266979779473989},"terminus_json":{"R":0.001645625346969926,"A":7.905955949236349,"Mc":0.10309549969160786}},"challenger":{"mean":-0.6426400395330117,"mean_valid":-0.5966122382747868,"sd_valid":1.2310213475311824,"n_turns":997,"n_valid":987,"n_forfeits":4,"n_unscorable":6,"mean_z_R":0.14719306343837638,"mean_typ_c":0.7766887212854805,"mean_z_A":-0.11352010315340998,"bind_frac":{"R":0.3525835866261398,"Gc":0.1408308004052685,"A":0.5065856129685917},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.326052524805996,"mean_R":0.013524034257819815,"mean_A":2.539220320212966,"mean_mc":-0.6700422315028489},"king":{"mean":-0.6180873326989642,"mean_valid":-0.5950703202271724,"sd_valid":1.3363998269554949,"n_turns":997,"n_valid":989,"n_forfeits":2,"n_unscorable":6,"mean_z_R":0.16410295773672748,"mean_typ_c":0.7420007432900785,"mean_z_A":-0.10854219564838562,"bind_frac":{"R":0.3488372093023256,"Gc":0.13953488372093023,"A":0.5116279069767442},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.3267813881125712,"mean_R":0.013648856156216709,"mean_A":2.5526958663471344,"mean_mc":-0.6827021808684447}},"rejection_reason":null,"reign_number":null,"score":0.0023197888254242152,"score_king":0.002895813002649018,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9124280,"blocks_since_crown":970,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1210.4033955857385,"mean_len_y":608.3018675721562,"n_samples":3000,"think_close_rate":0.9753333333333334,"n_text_fallback":12,"by_dialect":{"terminus_json":{"n_turns":25,"zero_ref_turns":1,"mean_refs":2.84,"ref_pair_agreement":0.5555555555555556,"ref_pair_n":24},"bash":{"n_turns":307,"zero_ref_turns":0,"mean_refs":2.9283387622149837,"ref_pair_agreement":0.22549019607843138,"ref_pair_n":306},"text":{"n_turns":349,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":293,"zero_ref_turns":2,"mean_refs":2.9146757679180886,"ref_pair_agreement":0.18374558303886926,"ref_pair_n":283},"boxed":{"n_turns":26,"zero_ref_turns":0,"mean_refs":2.8461538461538463,"ref_pair_agreement":0.84,"ref_pair_n":25}},"ref_pair_agreement":0.24346917450365727,"ref_pair_n":638},"duel_seconds":2087.0324899498373,"challenger":{"reason":0.0023197888254242152,"n_turns":997,"n_pairs":2933,"n_forfeits":4,"forfeit_rate":0.004012036108324975,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":1.4235652669163767,"mean_len_z":867.2836685987044,"median_len_z":599.0,"mean_len_y":357.6580293215138,"mean_b":0.10267042021592379,"b_gate_pass_rate":0.6092737811114899,"mean_r_leg":0.013524034257819815,"mean_g_leg":0.0556283929040023,"g_bind_frac":0.21450151057401812,"a_match":0.1891124871001032,"a_match_n":646,"a_match_centered":-0.05355276907001045,"n_turns_cap_raised":107,"mean_cap_tokens":2186.703109327984,"max_cap_tokens":5085,"len_z_delta":-343.11972698703414,"len_y_delta":-250.64383825064237,"n_samples":1000,"think_close_rate":0.996,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":307,"n_valid":307,"parse_rate":1.0,"reason":0.008745876119387685,"mean_b":0.12507564110427014,"b_gate_pass_rate":0.8954393770856507,"median_len_z":459.0,"mean_r_leg":0.020921316951002463,"mean_g_leg":0.04470253992714634,"g_bind_frac":0.2768729641693811,"a_match":0.15689467969598261,"a_match_n":307,"a_match_centered":-0.06808278867102396},"boxed":{"n_turns":26,"n_valid":26,"parse_rate":1.0,"reason":0.001125148827444575,"mean_b":1.5576150745815638,"b_gate_pass_rate":0.7972972972972973,"median_len_z":2120.0,"mean_r_leg":0.08518434427951169,"mean_g_leg":0.0294808670045446,"g_bind_frac":0.38461538461538464,"a_match":0.7692307692307693,"a_match_n":26,"a_match_centered":-0.08},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.0013783888072205243,"mean_b":0.021002023862146967,"b_gate_pass_rate":0.36619718309859156,"median_len_z":623.0,"mean_r_leg":0.001420907082234701,"mean_g_leg":0.03569207793890162,"g_bind_frac":0.16666666666666666,"a_match":0.5416666666666666,"a_match_n":24,"a_match_centered":-0.01388888888888889},"text":{"n_turns":349,"n_valid":345,"parse_rate":0.9885386819484241,"reason":-0.0006579136888287658,"mean_b":0.045594643402546764,"b_gate_pass_rate":0.4318840579710145,"median_len_z":725.0,"mean_r_leg":0.009865675754609188,"mean_g_leg":0.0600085129028234,"g_bind_frac":0.19130434782608696,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":291,"n_valid":291,"parse_rate":1.0,"reason":-0.00047668443451238365,"mean_b":0.028974503519533436,"b_gate_pass_rate":0.5269320843091335,"median_len_z":551.0,"mean_r_leg":0.004652813943217227,"mean_g_leg":0.06594249151860648,"g_bind_frac":0.16494845360824742,"a_match":0.14186851211072665,"a_match_n":289,"a_match_centered":-0.038869257950530034}}},"king":{"reason":0.002895813002649018,"n_turns":997,"n_pairs":2939,"n_forfeits":2,"forfeit_rate":0.0020060180541624875,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":0.7172942387368018,"mean_len_z":856.256890098673,"median_len_z":602.0,"mean_len_y":357.2749234433481,"mean_b":0.10316557283571297,"b_gate_pass_rate":0.5940796189179993,"mean_r_leg":0.013648856156216709,"mean_g_leg":0.055917209344358274,"g_bind_frac":0.23417085427135678,"a_match":0.18814699792960662,"a_match_n":644,"a_match_centered":-0.05476939203354298,"n_turns_cap_raised":107,"mean_cap_tokens":2186.703109327984,"max_cap_tokens":5085,"len_z_delta":-354.1465054870655,"len_y_delta":-251.0269441288081,"n_samples":997,"think_close_rate":0.9979939819458375,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":307,"n_valid":307,"parse_rate":1.0,"reason":0.009797559136984352,"mean_b":0.12847447640978982,"b_gate_pass_rate":0.8854282536151279,"median_len_z":479.0,"mean_r_leg":0.022783949285693165,"mean_g_leg":0.04474325033930639,"g_bind_frac":0.30293159609120524,"a_match":0.16123778501628663,"a_match_n":307,"a_match_centered":-0.06372549019607843},"boxed":{"n_turns":26,"n_valid":25,"parse_rate":0.9615384615384616,"reason":-0.0005344391301522152,"mean_b":1.5029274919371944,"b_gate_pass_rate":0.7605633802816901,"median_len_z":1885.0,"mean_r_leg":0.07489322170804012,"mean_g_leg":0.03270629596272532,"g_bind_frac":0.32,"a_match":0.6933333333333332,"a_match_n":25,"a_match_centered":-0.18055555555555555},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.00032270670684386043,"mean_b":0.01920418705146747,"b_gate_pass_rate":0.323943661971831,"median_len_z":666.0,"mean_r_leg":0.0014756419889376386,"mean_g_leg":0.04113596173736567,"g_bind_frac":0.08333333333333333,"a_match":0.513888888888889,"a_match_n":24,"a_match_centered":-0.041666666666666664},"text":{"n_turns":349,"n_valid":348,"parse_rate":0.997134670487106,"reason":8.863241032030158e-05,"mean_b":0.053160732899775756,"b_gate_pass_rate":0.4482758620689655,"median_len_z":731.0,"mean_r_leg":0.009760705693205717,"mean_g_leg":0.05905651326548652,"g_bind_frac":0.20689655172413793,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":291,"n_valid":291,"parse_rate":1.0,"reason":-0.00044679527239415795,"mean_b":0.028259847677047433,"b_gate_pass_rate":0.47423887587822017,"median_len_z":571.0,"mean_r_leg":0.004403669804318653,"mean_g_leg":0.06716446167118625,"g_bind_frac":0.19931271477663232,"a_match":0.14583333333333334,"a_match_n":288,"a_match_centered":-0.03546099290780142}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T16:16:05.523393+00:00","challenge_id":"chal-00667","repo":"r2://affine-private-models/models/registrations/440248512e0479964dd17b2a714d124f40cf402b1783874a7ae564ae6470ef4d/","hotkey":"5CcSWMojo1ejkFsNPKjcABXmftyMij1hw6i8FZrLfsuDkWXr","uid":237,"duration_s":2482.8,"revision":"70a5f1d051215834859163d1ef77e677338a6056493652068f831d260fcdb925","accepted":false,"error_code":null,"error_detail":"","z":0.4110133855701404,"margin":0.013489576802067426,"se":0.032820285848732776,"n_paired_turns":993,"n_forfeit_turns":3,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2117691191747533392,"n":1000,"digest":"f384c74d74ec22dcba11590dbd0bef7a0d27b2d0239ab91f6ed898b5de42d1ef","n_paired_turns":993,"n_forfeit_turns":3,"margin":0.013489576802067426,"se":0.032820285848732776,"z":0.4110133855701404,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.013489576802067426,"se":0.032820285848732776,"z":0.4110133855701404,"sd_diff":1.034229648119885,"n_paired_turns":993,"n_forfeit_turns":3,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.026767718568062593,"A":5.492303705650983,"Mc":0.1488246358213658},"tool_call":{"R":0.009228194363181199,"A":5.580558117803879,"Mc":0.1937908964152708},"text":{"R":0.018010466383614785,"A":9.628570433864596,"Mc":0.1793470798039081},"boxed":{"R":0.10361127239657536,"A":2.4200008595158478,"Mc":0.13028529497748562},"terminus_json":{"R":0.0013271780227958742,"A":8.542351156769884,"Mc":0.10265911005129612}},"challenger":{"mean":-0.6778882942917015,"mean_valid":-0.6435788648804642,"sd_valid":1.3457873836401348,"n_turns":998,"n_valid":990,"n_forfeits":3,"n_unscorable":5,"mean_z_R":0.18580760728673865,"mean_typ_c":0.8062540860403564,"mean_z_A":-0.17439471757859631,"bind_frac":{"R":0.3393939393939394,"Gc":0.14444444444444443,"A":0.5161616161616162},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.3332811753579539,"mean_R":0.012481272548897918,"mean_A":2.709798723616957,"mean_mc":-0.6778090199418844},"king":{"mean":-0.6913778710937689,"mean_valid":-0.6685552230031407,"sd_valid":1.439564662268166,"n_turns":998,"n_valid":991,"n_forfeits":2,"n_unscorable":5,"mean_z_R":0.22719171615116235,"mean_typ_c":0.7943661127599987,"mean_z_A":-0.2095518930635996,"bind_frac":{"R":0.31987891019172554,"Gc":0.14026236125126135,"A":0.5398587285570131},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.32682310091194955,"mean_R":0.013677523572717846,"mean_A":2.4805598472220978,"mean_mc":-0.6723148164808396}},"rejection_reason":null,"reign_number":null,"score":0.0031964280337684297,"score_king":0.0037497332429368966,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9124067,"blocks_since_crown":757,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1098.482456140351,"mean_len_y":606.4534412955466,"n_samples":3000,"think_close_rate":0.9826666666666667,"n_text_fallback":20,"by_dialect":{"bash":{"n_turns":325,"zero_ref_turns":1,"mean_refs":2.9353846153846153,"ref_pair_agreement":0.19791666666666666,"ref_pair_n":320},"text":{"n_turns":348,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":272,"zero_ref_turns":1,"mean_refs":2.952205882352941,"ref_pair_agreement":0.17870722433460076,"ref_pair_n":263},"boxed":{"n_turns":24,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.7083333333333334,"ref_pair_n":24},"terminus_json":{"n_turns":31,"zero_ref_turns":0,"mean_refs":2.935483870967742,"ref_pair_agreement":0.5053763440860215,"ref_pair_n":31}},"ref_pair_agreement":0.22413793103448276,"ref_pair_n":638},"duel_seconds":2107.906416437123,"challenger":{"reason":0.0031964280337684297,"n_turns":998,"n_pairs":2955,"n_forfeits":3,"forfeit_rate":0.003006012024048096,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-8.361053675927504,"mean_len_z":782.0839255499154,"median_len_z":581.0,"mean_len_y":354.7763113367174,"mean_b":0.08666754350471642,"b_gate_pass_rate":0.5918781725888325,"mean_r_leg":0.012481272548897918,"mean_g_leg":0.05862396992993221,"g_bind_frac":0.2201005025125628,"a_match":0.17701863354037267,"a_match_n":644,"a_match_centered":-0.04559748427672956,"n_turns_cap_raised":83,"mean_cap_tokens":2139.9158316633266,"max_cap_tokens":5077,"len_z_delta":-316.3985305904355,"len_y_delta":-251.67712995882914,"n_samples":1001,"think_close_rate":0.997002997002997,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":324,"n_valid":324,"parse_rate":1.0,"reason":0.00796434365052849,"mean_b":0.12074963727090848,"b_gate_pass_rate":0.8867924528301887,"median_len_z":440.0,"mean_r_leg":0.02161356965451451,"mean_g_leg":0.044738925628478005,"g_bind_frac":0.2839506172839506,"a_match":0.14609053497942387,"a_match_n":324,"a_match_centered":-0.05},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":0.011081448031798785,"mean_b":1.0989977549894459,"b_gate_pass_rate":0.7916666666666666,"median_len_z":1380.0,"mean_r_leg":0.056786409530518965,"mean_g_leg":0.030882267392615115,"g_bind_frac":0.375,"a_match":0.5833333333333334,"a_match_n":24,"a_match_centered":-0.125},"terminus_json":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":-0.005278057002158693,"mean_b":0.01979760253330407,"b_gate_pass_rate":0.32967032967032966,"median_len_z":557.0,"mean_r_leg":0.0008517133262496439,"mean_g_leg":0.016596805927498945,"g_bind_frac":0.22580645161290322,"a_match":0.5591397849462365,"a_match_n":31,"a_match_centered":0.05376344086021505},"text":{"n_turns":348,"n_valid":345,"parse_rate":0.9913793103448276,"reason":-0.0009660872963936389,"mean_b":0.035785439652077075,"b_gate_pass_rate":0.42028985507246375,"median_len_z":715.0,"mean_r_leg":0.006092146349153148,"mean_g_leg":0.06451880829117541,"g_bind_frac":0.2028985507246377,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":271,"n_valid":271,"parse_rate":1.0,"reason":0.0031123661563778504,"mean_b":0.028567978667895146,"b_gate_pass_rate":0.47447073474470736,"median_len_z":540.0,"mean_r_leg":0.007103329098843898,"mean_g_leg":0.07498440559049788,"g_bind_frac":0.15129151291512916,"a_match":0.13333333333333333,"a_match_n":265,"a_match_centered":-0.04469987228607918}}},"king":{"reason":0.0037497332429368966,"n_turns":998,"n_pairs":2958,"n_forfeits":2,"forfeit_rate":0.002004008016032064,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-7.613822217222376,"mean_len_z":841.4519945909399,"median_len_z":603.0,"mean_len_y":352.0446247464503,"mean_b":0.09027343593447558,"b_gate_pass_rate":0.5835023664638269,"mean_r_leg":0.013677523572717846,"mean_g_leg":0.05892429583440594,"g_bind_frac":0.22289156626506024,"a_match":0.1772609819121447,"a_match_n":645,"a_match_centered":-0.04500261643118786,"n_turns_cap_raised":83,"mean_cap_tokens":2139.9158316633266,"max_cap_tokens":5077,"len_z_delta":-257.03046154941103,"len_y_delta":-254.40881654909623,"n_samples":998,"think_close_rate":0.9979959919839679,"n_text_fallback":1,"by_dialect":{"bash":{"n_turns":324,"n_valid":324,"parse_rate":1.0,"reason":0.00963138133569635,"mean_b":0.1244913313023861,"b_gate_pass_rate":0.9014675052410901,"median_len_z":458.0,"mean_r_leg":0.024291456737946176,"mean_g_leg":0.044556531638803513,"g_bind_frac":0.32098765432098764,"a_match":0.14969135802469136,"a_match_n":324,"a_match_centered":-0.04635416666666667},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":0.009359900756922229,"mean_b":1.13653741139164,"b_gate_pass_rate":0.8333333333333334,"median_len_z":1323.0,"mean_r_leg":0.06698942863912899,"mean_g_leg":0.02878697852470408,"g_bind_frac":0.4166666666666667,"a_match":0.5416666666666666,"a_match_n":24,"a_match_centered":-0.16666666666666666},"terminus_json":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":-0.005852995482593761,"mean_b":0.015854922362058797,"b_gate_pass_rate":0.16483516483516483,"median_len_z":575.0,"mean_r_leg":0.0007315522739355351,"mean_g_leg":0.017451203453421518,"g_bind_frac":0.25806451612903225,"a_match":0.5268817204301075,"a_match_n":31,"a_match_centered":0.02150537634408602},"text":{"n_turns":348,"n_valid":346,"parse_rate":0.9942528735632183,"reason":-0.0007524882252027374,"mean_b":0.04090391643076402,"b_gate_pass_rate":0.43352601156069365,"median_len_z":786.0,"mean_r_leg":0.006133887784723369,"mean_g_leg":0.06491906721417462,"g_bind_frac":0.17341040462427745,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":271,"n_valid":271,"parse_rate":1.0,"reason":0.0031008758961263124,"mean_b":0.028060195045359844,"b_gate_pass_rate":0.4246575342465753,"median_len_z":546.0,"mean_r_leg":0.007378715549767639,"mean_g_leg":0.0758612928130723,"g_bind_frac":0.14760147601476015,"a_match":0.13721804511278196,"a_match_n":266,"a_match_centered":-0.04007633587786259}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T15:33:30.574673+00:00","challenge_id":"chal-00665","repo":"r2://affine-private-models/models/registrations/a942b8ba115b0963909d22c41f311120f835eda2764a3a420a8a07fc44f83d56/","hotkey":"5CXhEmqwS325AqiLtkwCCqaNL66Jo3EzEqZHRsPfeQyvoVMM","uid":235,"duration_s":2495.5,"revision":"cc55fbd50c2b447ae01caada503328188bffe3640e2f791276ede7b51f7af2e2","accepted":false,"error_code":null,"error_detail":"","z":0.011310832502898395,"margin":0.00046774110748686054,"se":0.04135337583391869,"n_paired_turns":984,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":6967746141415979581,"n":1000,"digest":"ffe0d1d4da2115565d1304104a8e8ba22007e014f5e4b40bd4d0d82ae71aa828","n_paired_turns":984,"n_forfeit_turns":5,"margin":0.00046774110748686054,"se":0.04135337583391869,"z":0.011310832502898395,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.00046774110748686054,"se":0.04135337583391869,"z":0.011310832502898395,"sd_diff":1.297204712362528,"n_paired_turns":984,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.024143922485760763,"A":6.301561650640585,"Mc":0.15492535126258689},"tool_call":{"R":0.008537255716823969,"A":5.420264715000507,"Mc":0.1916848486323716},"text":{"R":0.015978102442230184,"A":25.67320655105145,"Mc":0.1862491240225833},"boxed":{"R":0.06924032303066467,"A":3.7524505786345395,"Mc":0.12334975007801972},"terminus_json":{"R":0.0011746470776936645,"A":7.4544410608487555,"Mc":0.12730267383456723}},"challenger":{"mean":-0.5430788690220064,"mean_valid":-0.5080424129639697,"sd_valid":1.1748288430126923,"n_turns":997,"n_valid":981,"n_forfeits":3,"n_unscorable":13,"mean_z_R":0.3815504561455481,"mean_typ_c":0.8286679352917031,"mean_z_A":-0.07145282539306741,"bind_frac":{"R":0.3384301732925586,"Gc":0.14475025484199797,"A":0.5168195718654435},"n_leg_dropped":{"R":0,"Gc":6,"A":0},"mean_content_share":0.30612643165688574,"mean_R":0.015553301125945643,"mean_A":2.531573303307588,"mean_mc":-0.6969758229396948},"king":{"mean":-0.5435466101294932,"mean_valid":-0.5085115844723969,"sd_valid":1.077950890192446,"n_turns":997,"n_valid":981,"n_forfeits":3,"n_unscorable":13,"mean_z_R":0.35543695492463867,"mean_typ_c":0.8524724911818007,"mean_z_A":-0.08832165116971503,"bind_frac":{"R":0.3363914373088685,"Gc":0.13557594291539246,"A":0.528032619775739},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.3237413505973408,"mean_R":0.015113800328696806,"mean_A":2.657912093711324,"mean_mc":-0.6909411896415861}},"rejection_reason":null,"reign_number":null,"score":0.0028655518402114755,"score_king":0.0022490340611930225,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9123853,"blocks_since_crown":543,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1306.642954390742,"mean_len_y":631.1136827773996,"n_samples":3000,"think_close_rate":0.9706666666666667,"n_text_fallback":16,"by_dialect":{"tool_call":{"n_turns":292,"zero_ref_turns":0,"mean_refs":2.910958904109589,"ref_pair_agreement":0.18996415770609318,"ref_pair_n":279},"text":{"n_turns":331,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":314,"zero_ref_turns":2,"mean_refs":2.910828025477707,"ref_pair_agreement":0.16450216450216448,"ref_pair_n":308},"boxed":{"n_turns":35,"zero_ref_turns":0,"mean_refs":2.8857142857142857,"ref_pair_agreement":0.75,"ref_pair_n":32},"terminus_json":{"n_turns":28,"zero_ref_turns":1,"mean_refs":2.857142857142857,"ref_pair_agreement":0.5925925925925926,"ref_pair_n":27}},"ref_pair_agreement":0.22239422084623323,"ref_pair_n":646},"duel_seconds":2098.26951626502,"challenger":{"reason":0.0028655518402114755,"n_turns":997,"n_pairs":2929,"n_forfeits":3,"forfeit_rate":0.003009027081243731,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-0.6485667922446042,"mean_len_z":1039.839194264254,"median_len_z":726.0,"mean_len_y":377.8695800614544,"mean_b":0.10790636120977937,"b_gate_pass_rate":0.5609423011266644,"mean_r_leg":0.015553301125945643,"mean_g_leg":0.05845368866762544,"g_bind_frac":0.22334004024144868,"a_match":0.19191919191919193,"a_match_n":660,"a_match_centered":-0.02635658914728682,"n_turns_cap_raised":106,"mean_cap_tokens":2201.848545636911,"max_cap_tokens":5096,"len_z_delta":-266.803760126488,"len_y_delta":-253.2441027159452,"n_samples":1000,"think_close_rate":0.998,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":312,"n_valid":312,"parse_rate":1.0,"reason":0.009489052680349507,"mean_b":0.12005946591422097,"b_gate_pass_rate":0.8829321663019694,"median_len_z":595.0,"mean_r_leg":0.02344474380225293,"mean_g_leg":0.04668359134581036,"g_bind_frac":0.2948717948717949,"a_match":0.13408119658119658,"a_match_n":312,"a_match_centered":-0.02867965367965368},"boxed":{"n_turns":35,"n_valid":35,"parse_rate":1.0,"reason":0.0015694007784943914,"mean_b":1.3506510657621957,"b_gate_pass_rate":0.7227722772277227,"median_len_z":2161.0,"mean_r_leg":0.06551116748230684,"mean_g_leg":0.02195653277009516,"g_bind_frac":0.37142857142857144,"a_match":0.6666666666666666,"a_match_n":32,"a_match_centered":-0.08333333333333333},"terminus_json":{"n_turns":27,"n_valid":26,"parse_rate":0.9629629629629629,"reason":-0.006713297573941935,"mean_b":0.019173487007532835,"b_gate_pass_rate":0.2727272727272727,"median_len_z":1088.0,"mean_r_leg":0.0009909709199656534,"mean_g_leg":0.033255952011080336,"g_bind_frac":0.23076923076923078,"a_match":0.6025641025641025,"a_match_n":26,"a_match_centered":-0.012820512820512822},"text":{"n_turns":331,"n_valid":329,"parse_rate":0.9939577039274925,"reason":-0.0016572752089348936,"mean_b":0.04356682079165653,"b_gate_pass_rate":0.3252279635258359,"median_len_z":840.0,"mean_r_leg":0.011570958212886217,"mean_g_leg":0.06647986069385574,"g_bind_frac":0.1580547112462006,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":292,"n_valid":292,"parse_rate":1.0,"reason":0.0019563659240697724,"mean_b":0.02991860220578704,"b_gate_pass_rate":0.49529411764705883,"median_len_z":654.0,"mean_r_leg":0.006916848955642611,"mean_g_leg":0.0686050632472839,"g_bind_frac":0.20205479452054795,"a_match":0.1649425287356322,"a_match_n":290,"a_match_centered":-0.01851851851851852}}},"king":{"reason":0.0022490340611930225,"n_turns":997,"n_pairs":2929,"n_forfeits":3,"forfeit_rate":0.003009027081243731,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-6.333872192735983,"mean_len_z":875.4383748719699,"median_len_z":621.0,"mean_len_y":328.0314100375555,"mean_b":0.10863805990747047,"b_gate_pass_rate":0.5701604643222943,"mean_r_leg":0.015113800328696806,"mean_g_leg":0.057811203328194706,"g_bind_frac":0.2193158953722334,"a_match":0.18914141414141414,"a_match_n":660,"a_match_centered":-0.02915376676986584,"n_turns_cap_raised":106,"mean_cap_tokens":2201.848545636911,"max_cap_tokens":5096,"len_z_delta":-431.2045795187721,"len_y_delta":-303.08227273984414,"n_samples":997,"think_close_rate":0.9969909729187563,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":312,"n_valid":312,"parse_rate":1.0,"reason":0.009114458854369132,"mean_b":0.1274143836066535,"b_gate_pass_rate":0.8960612691466083,"median_len_z":522.0,"mean_r_leg":0.021962296105000376,"mean_g_leg":0.04692717330887149,"g_bind_frac":0.28525641025641024,"a_match":0.12927350427350429,"a_match_n":312,"a_match_centered":-0.03354978354978355},"boxed":{"n_turns":35,"n_valid":35,"parse_rate":1.0,"reason":0.0015881738402511406,"mean_b":1.3077484222562712,"b_gate_pass_rate":0.8415841584158416,"median_len_z":2070.0,"mean_r_leg":0.06318920747267692,"mean_g_leg":0.023072909930994142,"g_bind_frac":0.34285714285714286,"a_match":0.65625,"a_match_n":32,"a_match_centered":-0.09375},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.006047171136520034,"mean_b":0.018911727729038205,"b_gate_pass_rate":0.3,"median_len_z":863.0,"mean_r_leg":0.0007748809331869212,"mean_g_leg":0.03018536362039184,"g_bind_frac":0.2222222222222222,"a_match":0.5925925925925926,"a_match_n":27,"a_match_centered":-2.05596856412066e-18},"text":{"n_turns":331,"n_valid":328,"parse_rate":0.9909365558912386,"reason":-0.00166113139918729,"mean_b":0.046691964581167575,"b_gate_pass_rate":0.38109756097560976,"median_len_z":728.0,"mean_r_leg":0.012295063181576232,"mean_g_leg":0.06595983675414446,"g_bind_frac":0.16158536585365854,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":292,"n_valid":292,"parse_rate":1.0,"reason":0.0001921158419675296,"mean_b":0.02612201039814635,"b_gate_pass_rate":0.43176470588235294,"median_len_z":549.0,"mean_r_leg":0.006525877985163575,"mean_g_leg":0.06700573601083176,"g_bind_frac":0.19863013698630136,"a_match":0.1643598615916955,"a_match_n":289,"a_match_centered":-0.01971326164874552}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T14:51:01.228334+00:00","challenge_id":"chal-00664","repo":"r2://affine-private-models/models/registrations/2bc7cd0fb4407be8f999c2bd99fc2f9073678ff9ce95a2d54b91b2ebe39ddb8c/","hotkey":"5E3aWNSupF382FQSMD49dcGGi9vUrp6TWF79EtvX5YrQnhqM","uid":73,"duration_s":2395.1,"revision":"7cd766b511bc0c9a0778ae787a7991da15117634bd7c3dd9e528ce3558dff5b9","accepted":false,"error_code":null,"error_detail":"","z":-4.744557122472927,"margin":-0.23735337772786486,"se":0.05002645591590076,"n_paired_turns":986,"n_forfeit_turns":7,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":15073769636263664913,"n":1000,"digest":"469944b5bd481d9f540a96b9ae8e803a9d9b359b0235fc84f960a3a8062130e3","n_paired_turns":986,"n_forfeit_turns":7,"margin":-0.23735337772786486,"se":0.05002645591590076,"z":-4.744557122472927,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.23735337772786486,"se":0.05002645591590076,"z":-4.744557122472927,"sd_diff":1.5708625794207731,"n_paired_turns":986,"n_forfeit_turns":7,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.025907516541391715,"A":6.95784426801025,"Mc":0.15465205567377874},"tool_call":{"R":0.009703416167379644,"A":6.618690372572983,"Mc":0.19176326099471314},"text":{"R":0.04146617585992528,"A":7.778405987059881,"Mc":0.16587852924750898},"boxed":{"R":0.10269278247492677,"A":2.9558552937476343,"Mc":0.13504320169583395},"terminus_json":{"R":0.004606437463832871,"A":12.494988596580555,"Mc":0.12600436126574444}},"challenger":{"mean":-0.9027159105412254,"mean_valid":-0.8120333030686306,"sd_valid":1.5198275578428302,"n_turns":993,"n_valid":979,"n_forfeits":8,"n_unscorable":6,"mean_z_R":0.11790101384535588,"mean_typ_c":0.5472033359319088,"mean_z_A":-0.26128749080551944,"bind_frac":{"R":0.3289070480081716,"Gc":0.1930541368743616,"A":0.4780388151174668},"n_leg_dropped":{"R":0,"Gc":2,"A":0},"mean_content_share":0.324974050652875,"mean_R":0.014331084479879679,"mean_A":1.792376717915999,"mean_mc":-0.7037770600647189},"king":{"mean":-0.6541076807956538,"mean_valid":-0.6194813563219885,"sd_valid":1.1993856974171149,"n_turns":993,"n_valid":983,"n_forfeits":3,"n_unscorable":7,"mean_z_R":0.17662207919393683,"mean_typ_c":0.8331347881700442,"mean_z_A":-0.1802580721501962,"bind_frac":{"R":0.36012207527975587,"Gc":0.12614445574771108,"A":0.513733468972533},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3264110500744189,"mean_R":0.015353206927645848,"mean_A":2.48684280844707,"mean_mc":-0.6611405626927563}},"rejection_reason":null,"reign_number":null,"score":0.0020253857071432864,"score_king":0.0032767887087032715,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9123650,"blocks_since_crown":340,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1214.9932042133878,"mean_len_y":569.0818892286782,"n_samples":3000,"think_close_rate":0.9756666666666667,"n_text_fallback":18,"by_dialect":{"bash":{"n_turns":297,"zero_ref_turns":5,"mean_refs":2.8855218855218854,"ref_pair_agreement":0.1522491349480969,"ref_pair_n":289},"text":{"n_turns":348,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":300,"zero_ref_turns":2,"mean_refs":2.93,"ref_pair_agreement":0.20114942528735633,"ref_pair_n":290},"boxed":{"n_turns":31,"zero_ref_turns":0,"mean_refs":2.935483870967742,"ref_pair_agreement":0.7777777777777778,"ref_pair_n":30},"terminus_json":{"n_turns":24,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.5,"ref_pair_n":24}},"ref_pair_agreement":0.21748288572933122,"ref_pair_n":633},"duel_seconds":2041.1920887329616,"challenger":{"reason":0.0020253857071432864,"n_turns":993,"n_pairs":2923,"n_forfeits":8,"forfeit_rate":0.008056394763343404,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":5.098010774834952,"mean_len_z":827.3417721518987,"median_len_z":568.0,"mean_len_y":428.8515224084844,"mean_b":0.09761313686228879,"b_gate_pass_rate":0.5183031132398221,"mean_r_leg":0.014331084479879679,"mean_g_leg":0.05439703981584169,"g_bind_frac":0.24873096446700507,"a_match":0.18881856540084388,"a_match_n":632,"a_match_centered":-0.03253333333333333,"n_turns_cap_raised":98,"mean_cap_tokens":2171.965760322256,"max_cap_tokens":5060,"len_z_delta":-387.6514320614891,"len_y_delta":-140.23036682019375,"n_samples":996,"think_close_rate":0.9949799196787149,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":292,"n_valid":288,"parse_rate":0.9863013698630136,"reason":0.006541483826957478,"mean_b":0.12060398455134082,"b_gate_pass_rate":0.8457008244994111,"median_len_z":433.0,"mean_r_leg":0.021829969317440325,"mean_g_leg":0.044193322725857256,"g_bind_frac":0.3263888888888889,"a_match":0.12384259259259259,"a_match_n":288,"a_match_centered":-0.02913752913752914},"boxed":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":0.009103629056469597,"mean_b":1.3326253541874586,"b_gate_pass_rate":0.6263736263736264,"median_len_z":1446.0,"mean_r_leg":0.05020911027072801,"mean_g_leg":0.031799714648916295,"g_bind_frac":0.3548387096774194,"a_match":0.7634408602150538,"a_match_n":31,"a_match_centered":-0.022222222222222223},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.0016095965546893255,"mean_b":0.022300623920057404,"b_gate_pass_rate":0.4583333333333333,"median_len_z":569.5,"mean_r_leg":0.0033575021957335882,"mean_g_leg":0.037794298333752946,"g_bind_frac":0.2916666666666667,"a_match":0.5694444444444444,"a_match_n":24,"a_match_centered":0.06944444444444443},"text":{"n_turns":348,"n_valid":344,"parse_rate":0.9885057471264368,"reason":-0.0008446214284612364,"mean_b":0.03513524981728726,"b_gate_pass_rate":0.3313953488372093,"median_len_z":720.5,"mean_r_leg":0.013440620260719046,"mean_g_leg":0.05838277599176135,"g_bind_frac":0.22093023255813954,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":298,"n_valid":298,"parse_rate":1.0,"reason":0.0005081906153966331,"mean_b":0.027071997951807095,"b_gate_pass_rate":0.4152445961319681,"median_len_z":430.0,"mean_r_leg":0.005263259088862899,"mean_g_leg":0.06334522824921072,"g_bind_frac":0.1912751677852349,"a_match":0.16032295271049596,"a_match_n":289,"a_match_centered":-0.0456140350877193}}},"king":{"reason":0.0032767887087032715,"n_turns":993,"n_pairs":2934,"n_forfeits":3,"forfeit_rate":0.0030211480362537764,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-4.613450209633549,"mean_len_z":806.3653715064758,"median_len_z":608.5,"mean_len_y":327.52590320381734,"mean_b":0.10458989854208887,"b_gate_pass_rate":0.6111111111111112,"mean_r_leg":0.015353206927645848,"mean_g_leg":0.05673925149342663,"g_bind_frac":0.23434343434343435,"a_match":0.17135416666666667,"a_match_n":640,"a_match_centered":-0.0490506329113924,"n_turns_cap_raised":98,"mean_cap_tokens":2171.965760322256,"max_cap_tokens":5060,"len_z_delta":-408.62783270691205,"len_y_delta":-241.55598602486083,"n_samples":993,"think_close_rate":0.9969788519637462,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":292,"n_valid":292,"parse_rate":1.0,"reason":0.007294567103299506,"mean_b":0.1267715448799017,"b_gate_pass_rate":0.868144690781797,"median_len_z":469.0,"mean_r_leg":0.02144925095932391,"mean_g_leg":0.0446691498487519,"g_bind_frac":0.3253424657534247,"a_match":0.1175799086757991,"a_match_n":292,"a_match_centered":-0.040369088811995385},"boxed":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":0.010352344343092451,"mean_b":1.345191458003107,"b_gate_pass_rate":0.8681318681318682,"median_len_z":1410.0,"mean_r_leg":0.04424180130169257,"mean_g_leg":0.03760557284039697,"g_bind_frac":0.3548387096774194,"a_match":0.7096774193548387,"a_match_n":31,"a_match_centered":-0.07777777777777778},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.0003578818213919914,"mean_b":0.022444049874853784,"b_gate_pass_rate":0.4166666666666667,"median_len_z":717.5,"mean_r_leg":0.002703247723827261,"mean_g_leg":0.04304867720154963,"g_bind_frac":0.20833333333333334,"a_match":0.5972222222222222,"a_match_n":24,"a_match_centered":0.09722222222222221},"text":{"n_turns":348,"n_valid":345,"parse_rate":0.9913793103448276,"reason":0.001228449551152977,"mean_b":0.043432940547254315,"b_gate_pass_rate":0.463768115942029,"median_len_z":735.0,"mean_r_leg":0.01598964421758125,"mean_g_leg":0.0640216022837579,"g_bind_frac":0.16521739130434782,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":298,"n_valid":298,"parse_rate":1.0,"reason":0.0012886028149503316,"mean_b":0.03326741823064004,"b_gate_pass_rate":0.5233219567690558,"median_len_z":525.0,"mean_r_leg":0.006656686367305214,"mean_g_leg":0.06322843430829139,"g_bind_frac":0.21476510067114093,"a_match":0.13310580204778158,"a_match_n":293,"a_match_centered":-0.06689734717416378}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T14:10:14.314335+00:00","challenge_id":"chal-00663","repo":"r2://affine-private-models/models/registrations/0b6a1869d070772869256710fc9596cbe76a058a44cc15165697debf47b88c24/","hotkey":"5HqMwrfSiccunLqoPJv8sY8b7ECjc5vevLgGAX4yexyexzTX","uid":11,"duration_s":2575.8,"revision":"91724e5f8dd1b721d52ea44ddb4cf933e3632222e142219626abab6b9e0cde92","accepted":false,"error_code":null,"error_detail":"","z":-1.1914309923226498,"margin":-0.051479270210208074,"se":0.04320793276482692,"n_paired_turns":981,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":4381254342577429494,"n":1000,"digest":"ab70740ffb3875e1d6f2ce14e7d2b951827207dba76bd376879f0ac3e0d18f14","n_paired_turns":981,"n_forfeit_turns":5,"margin":-0.051479270210208074,"se":0.04320793276482692,"z":-1.1914309923226498,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.051479270210208074,"se":0.04320793276482692,"z":-1.1914309923226498,"sd_diff":1.3533121850435759,"n_paired_turns":981,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02907617875156159,"A":6.195294125985177,"Mc":0.14509594064793305},"text":{"R":0.052510456901052924,"A":11.793747274252206,"Mc":0.17466947614970238},"tool_call":{"R":0.0069995862354107485,"A":5.060304617247927,"Mc":0.174160884009572},"terminus_json":{"R":0.001720927030192254,"A":7.537643253416873,"Mc":0.15529725610794914},"boxed":{"R":0.18208767158082376,"A":4.5435330611008355,"Mc":0.14810322562680237}},"challenger":{"mean":-0.6633992964268275,"mean_valid":-0.6402397444276994,"sd_valid":1.3883010474878679,"n_turns":994,"n_valid":979,"n_forfeits":2,"n_unscorable":13,"mean_z_R":0.1831133171389219,"mean_typ_c":0.7317073853081584,"mean_z_A":-0.11871204304167096,"bind_frac":{"R":0.3564862104187947,"Gc":0.1317671092951992,"A":0.5117466802860061},"n_leg_dropped":{"R":0,"Gc":10,"A":0},"mean_content_share":0.3194409165684547,"mean_R":0.017279660410005518,"mean_A":2.2597905366815234,"mean_mc":-0.6816036881699465},"king":{"mean":-0.6119200262166193,"mean_valid":-0.5769872655608421,"sd_valid":1.270833093701979,"n_turns":994,"n_valid":978,"n_forfeits":3,"n_unscorable":13,"mean_z_R":0.1933212043969266,"mean_typ_c":0.8191601988089088,"mean_z_A":-0.11107239613645614,"bind_frac":{"R":0.36809815950920244,"Gc":0.13496932515337423,"A":0.49693251533742333},"n_leg_dropped":{"R":0,"Gc":10,"A":0},"mean_content_share":0.3212006674447493,"mean_R":0.018360152884281437,"mean_A":2.293754317773973,"mean_mc":-0.6800268252612234}},"rejection_reason":null,"reign_number":null,"score":0.0031104971291363486,"score_king":0.002962159156273321,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9123310,"crown_block_source":"king","decision_block":9123431,"blocks_since_crown":121,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1354.6298191743433,"mean_len_y":663.0402592971682,"n_samples":3000,"think_close_rate":0.964,"n_text_fallback":11,"by_dialect":{"text":{"n_turns":340,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":284,"zero_ref_turns":3,"mean_refs":2.897887323943662,"ref_pair_agreement":0.2258852258852259,"ref_pair_n":273},"bash":{"n_turns":315,"zero_ref_turns":2,"mean_refs":2.9174603174603173,"ref_pair_agreement":0.16021505376344086,"ref_pair_n":310},"boxed":{"n_turns":31,"zero_ref_turns":1,"mean_refs":2.903225806451613,"ref_pair_agreement":0.6436781609195402,"ref_pair_n":29},"terminus_json":{"n_turns":30,"zero_ref_turns":0,"mean_refs":2.6333333333333333,"ref_pair_agreement":0.4230769230769231,"ref_pair_n":26}},"ref_pair_agreement":0.22100313479623823,"ref_pair_n":638},"duel_seconds":2162.1260362402536,"challenger":{"reason":0.0031104971291363486,"n_turns":994,"n_pairs":2925,"n_forfeits":2,"forfeit_rate":0.002012072434607646,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":5.6699791440867875,"mean_len_z":898.9531623931624,"median_len_z":637.0,"mean_len_y":359.8088888888889,"mean_b":0.10374035834721387,"b_gate_pass_rate":0.6047863247863248,"mean_r_leg":0.017279660410005518,"mean_g_leg":0.055036078198204566,"g_bind_frac":0.23084677419354838,"a_match":0.18865030674846625,"a_match_n":652,"a_match_centered":-0.029780564263322883,"n_turns_cap_raised":112,"mean_cap_tokens":2190.258551307847,"max_cap_tokens":5078,"len_z_delta":-455.6766567811809,"len_y_delta":-303.2313704082793,"n_samples":997,"think_close_rate":0.9979939819458375,"n_text_fallback":0,"by_dialect":{"bash":{"n_turns":313,"n_valid":313,"parse_rate":1.0,"reason":0.009422380718132329,"mean_b":0.12311424110945926,"b_gate_pass_rate":0.8759521218715995,"median_len_z":519.0,"mean_r_leg":0.023722638596549054,"mean_g_leg":0.04950541235069136,"g_bind_frac":0.26198083067092653,"a_match":0.14802981895633655,"a_match_n":313,"a_match_centered":-0.010752688172043012},"boxed":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":0.005130292779611687,"mean_b":1.209354616372776,"b_gate_pass_rate":0.7666666666666667,"median_len_z":1971.0,"mean_r_leg":0.09473103345258423,"mean_g_leg":0.023082962321379123,"g_bind_frac":0.43333333333333335,"a_match":0.5977011494252873,"a_match_n":29,"a_match_centered":-0.04597701149425288},"terminus_json":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":-0.00439944944170705,"mean_b":0.021590346119182296,"b_gate_pass_rate":0.31645569620253167,"median_len_z":725.0,"mean_r_leg":0.0011775708878369586,"mean_g_leg":0.03875733790873743,"g_bind_frac":0.3,"a_match":0.4222222222222222,"a_match_n":30,"a_match_centered":0.0641025641025641},"text":{"n_turns":340,"n_valid":338,"parse_rate":0.9941176470588236,"reason":0.0007651493869212517,"mean_b":0.05481209910771354,"b_gate_pass_rate":0.47928994082840237,"median_len_z":790.0,"mean_r_leg":0.015591375134219683,"mean_g_leg":0.06261725127657414,"g_bind_frac":0.19230769230769232,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":281,"n_valid":281,"parse_rate":1.0,"reason":-0.0004962530608692286,"mean_b":0.029370035569648532,"b_gate_pass_rate":0.4665856622114216,"median_len_z":556.0,"mean_r_leg":0.005583965553120044,"mean_g_leg":0.05722688814401059,"g_bind_frac":0.21352313167259787,"a_match":0.16666666666666666,"a_match_n":280,"a_match_centered":-0.05860805860805861}}},"king":{"reason":0.002962159156273321,"n_turns":994,"n_pairs":2922,"n_forfeits":3,"forfeit_rate":0.0030181086519114686,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":10.095886018196648,"mean_len_z":920.5653661875427,"median_len_z":647.0,"mean_len_y":358.46030116358656,"mean_b":0.10299284542716475,"b_gate_pass_rate":0.6146475017111568,"mean_r_leg":0.018360152884281437,"mean_g_leg":0.054296960860309905,"g_bind_frac":0.22906155398587286,"a_match":0.1894871794871795,"a_match_n":650,"a_match_centered":-0.028039832285115304,"n_turns_cap_raised":112,"mean_cap_tokens":2190.258551307847,"max_cap_tokens":5078,"len_z_delta":-434.0644529868006,"len_y_delta":-304.5799581335816,"n_samples":994,"think_close_rate":0.9969818913480886,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":313,"n_valid":313,"parse_rate":1.0,"reason":0.00955682944100073,"mean_b":0.1158850190420398,"b_gate_pass_rate":0.8694232861806311,"median_len_z":532.0,"mean_r_leg":0.024686410837138902,"mean_g_leg":0.04880861435642299,"g_bind_frac":0.26198083067092653,"a_match":0.1496272630457934,"a_match_n":313,"a_match_centered":-0.009139784946236561},"boxed":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":0.002730296264718241,"mean_b":1.2141037828122214,"b_gate_pass_rate":0.7333333333333333,"median_len_z":2013.5,"mean_r_leg":0.12494969149963443,"mean_g_leg":0.02050775056486795,"g_bind_frac":0.5333333333333333,"a_match":0.5632183908045977,"a_match_n":29,"a_match_centered":-0.08045977011494253},"terminus_json":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":-0.003649409233824378,"mean_b":0.02220950647141249,"b_gate_pass_rate":0.4177215189873418,"median_len_z":759.0,"mean_r_leg":0.0009997846671766935,"mean_g_leg":0.040106870309299804,"g_bind_frac":0.23333333333333334,"a_match":0.4222222222222222,"a_match_n":30,"a_match_centered":0.0641025641025641},"text":{"n_turns":340,"n_valid":337,"parse_rate":0.9911764705882353,"reason":0.0002922762678143805,"mean_b":0.05731565284623253,"b_gate_pass_rate":0.49554896142433236,"median_len_z":818.0,"mean_r_leg":0.0152480189092954,"mean_g_leg":0.06120345238397455,"g_bind_frac":0.18694362017804153,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":281,"n_valid":281,"parse_rate":1.0,"reason":-0.0004224268885453841,"mean_b":0.03095594817333928,"b_gate_pass_rate":0.4823815309842041,"median_len_z":546.0,"mean_r_leg":0.005519566757514389,"mean_g_leg":0.05724978590527496,"g_bind_frac":0.2099644128113879,"a_match":0.17026378896882494,"a_match_n":278,"a_match_centered":-0.05289052890528906}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"crowned","at":"2026-09-22T13:03:08.856670+00:00","challenge_id":"chal-00662","repo":"r2://affine-private-models/models/registrations/9c670e726a7d5f78e91075d29de04c59d4e719111b8b7740e9d9d48bd4d8c1f5/","hotkey":"5GUYP8io4jChxGgVe1GvtXJBYFGe3eshCdEU3aXv45JRkzc4","uid":36,"duration_s":2390.3,"revision":"1c520d6f1cfad05d707d662324b03783defaab98f6284347cda5cf41443de18b","accepted":true,"error_code":null,"error_detail":"","z":4.929443348380554,"margin":0.22882941538787493,"se":0.04642094435734841,"n_paired_turns":989,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":5012233538161709781,"n":1000,"digest":"ab6acfc9de25c176c70ee143d62a1d2fd789f377205904982b78506a78b2af4b","n_paired_turns":989,"n_forfeit_turns":4,"margin":0.22882941538787493,"se":0.04642094435734841,"z":4.929443348380554,"challenger_wins":true}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.22882941538787493,"se":0.04642094435734841,"z":4.929443348380554,"sd_diff":1.459863051865732,"n_paired_turns":989,"n_forfeit_turns":4,"would_crown":true,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.028901101457535574,"A":5.848272497220176,"Mc":0.15399122245417624},"text":{"R":0.05695767349500189,"A":19.218326053123825,"Mc":0.1757008662720929},"tool_call":{"R":0.007571779986275213,"A":5.004501170736548,"Mc":0.19245522494494718},"terminus_json":{"R":0.0012483059948890732,"A":7.7600457911180385,"Mc":0.13399655225962032},"boxed":{"R":0.09591821510341643,"A":2.6986687290216316,"Mc":0.12271356449163508}},"challenger":{"mean":-0.6095693948700251,"mean_valid":-0.5864884817897213,"sd_valid":1.2865188461768262,"n_turns":999,"n_valid":987,"n_forfeits":2,"n_unscorable":10,"mean_z_R":0.14735108262334787,"mean_typ_c":0.7961317324156323,"mean_z_A":-0.12294718443324716,"bind_frac":{"R":0.3495440729483283,"Gc":0.1458966565349544,"A":0.5045592705167173},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.3186824287434216,"mean_R":0.012945731616886596,"mean_A":2.506169286790714,"mean_mc":-0.690317446089015},"king":{"mean":-0.8609247460595997,"mean_valid":-0.7930725110102165,"sd_valid":1.693077089997344,"n_turns":999,"n_valid":985,"n_forfeits":6,"n_unscorable":8,"mean_z_R":0.10577033769254514,"mean_typ_c":0.6284300691615975,"mean_z_A":-0.2520290730331582,"bind_frac":{"R":0.29035532994923857,"Gc":0.17868020304568527,"A":0.5309644670050762},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.31842571660641494,"mean_R":0.012048661907152739,"mean_A":1.2389800587703126,"mean_mc":-0.7302715376482335}},"rejection_reason":null,"reign_number":21,"score":0.003651623102984356,"score_king":0.002648023727371667,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9123111,"blocks_since_crown":19882,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1210.7763513513514,"mean_len_y":598.535472972973,"n_samples":3000,"think_close_rate":0.9806666666666667,"n_text_fallback":8,"by_dialect":{"tool_call":{"n_turns":292,"zero_ref_turns":0,"mean_refs":2.958904109589041,"ref_pair_agreement":0.18118466898954705,"ref_pair_n":287},"bash":{"n_turns":300,"zero_ref_turns":1,"mean_refs":2.9133333333333336,"ref_pair_agreement":0.17754868270332186,"ref_pair_n":291},"text":{"n_turns":361,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":19,"zero_ref_turns":0,"mean_refs":2.8947368421052633,"ref_pair_agreement":0.45614035087719296,"ref_pair_n":19},"boxed":{"n_turns":28,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.75,"ref_pair_n":28}},"ref_pair_agreement":0.21333333333333335,"ref_pair_n":625},"duel_seconds":2020.353769202251,"challenger":{"reason":0.003651623102984356,"n_turns":999,"n_pairs":2954,"n_forfeits":2,"forfeit_rate":0.002002002002002002,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-28.817678597748294,"mean_len_z":870.555856465809,"median_len_z":661.0,"mean_len_y":367.2241029113067,"mean_b":0.10399689795276562,"b_gate_pass_rate":0.5744752877454299,"mean_r_leg":0.012945731616886596,"mean_g_leg":0.05959160243670844,"g_bind_frac":0.21965897693079237,"a_match":0.15850447604002105,"a_match_n":633,"a_match_centered":-0.05466237942122187,"n_turns_cap_raised":94,"mean_cap_tokens":2169.871871871872,"max_cap_tokens":5105,"len_z_delta":-340.2204948855424,"len_y_delta":-231.3113700616663,"n_samples":1002,"think_close_rate":0.998003992015968,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":299,"n_valid":299,"parse_rate":1.0,"reason":0.009093960726582022,"mean_b":0.124046296667728,"b_gate_pass_rate":0.8546910755148741,"median_len_z":595.0,"mean_r_leg":0.022478106998548745,"mean_g_leg":0.048052312683385355,"g_bind_frac":0.27424749163879597,"a_match":0.14715719063545152,"a_match_n":299,"a_match_centered":-0.029782359679266894},"boxed":{"n_turns":28,"n_valid":28,"parse_rate":1.0,"reason":0.012199314801296044,"mean_b":1.310455791662232,"b_gate_pass_rate":0.7857142857142857,"median_len_z":1464.0,"mean_r_leg":0.042251557357693016,"mean_g_leg":0.03296021119635861,"g_bind_frac":0.32142857142857145,"a_match":0.5679012345679012,"a_match_n":27,"a_match_centered":-0.17283950617283952},"terminus_json":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":-0.005440425689283848,"mean_b":0.020740114395091425,"b_gate_pass_rate":0.3090909090909091,"median_len_z":707.0,"mean_r_leg":0.0012249539896041078,"mean_g_leg":0.029410640773270647,"g_bind_frac":0.2631578947368421,"a_match":0.42105263157894735,"a_match_n":19,"a_match_centered":-0.03508771929824562},"text":{"n_turns":361,"n_valid":359,"parse_rate":0.9944598337950139,"reason":0.001196329653697368,"mean_b":0.05410482397424636,"b_gate_pass_rate":0.4178272980501393,"median_len_z":751.0,"mean_r_leg":0.008933365382014447,"mean_g_leg":0.0645725557934804,"g_bind_frac":0.20334261838440112,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":292,"n_valid":292,"parse_rate":1.0,"reason":0.0008862653811941825,"mean_b":0.03391259844126683,"b_gate_pass_rate":0.4826388888888889,"median_len_z":584.0,"mean_r_leg":0.0060703579640712085,"mean_g_leg":0.06980120040759058,"g_bind_frac":0.17123287671232876,"a_match":0.11458333333333333,"a_match_n":288,"a_match_centered":-0.07017543859649122}}},"king":{"reason":0.002648023727371667,"n_turns":999,"n_pairs":2947,"n_forfeits":6,"forfeit_rate":0.006006006006006006,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-22.93800092251873,"mean_len_z":910.1720393620631,"median_len_z":600.0,"mean_len_y":473.956226671191,"mean_b":0.09885572522293966,"b_gate_pass_rate":0.498133695283339,"mean_r_leg":0.012048661907152739,"mean_g_leg":0.05848946427125669,"g_bind_frac":0.2175226586102719,"a_match":0.16852737905369486,"a_match_n":627,"a_match_centered":-0.04146472805600431,"n_turns_cap_raised":94,"mean_cap_tokens":2169.871871871872,"max_cap_tokens":5105,"len_z_delta":-300.60431198928836,"len_y_delta":-124.579246301782,"n_samples":999,"think_close_rate":0.996996996996997,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":299,"n_valid":296,"parse_rate":0.9899665551839465,"reason":0.008006068457369985,"mean_b":0.12537187429712662,"b_gate_pass_rate":0.825287356321839,"median_len_z":539.0,"mean_r_leg":0.022194993759549166,"mean_g_leg":0.04658647591837555,"g_bind_frac":0.2702702702702703,"a_match":0.14864864864864866,"a_match_n":296,"a_match_centered":-0.022988505747126436},"boxed":{"n_turns":28,"n_valid":28,"parse_rate":1.0,"reason":0.014335764307526795,"mean_b":1.2793109414907327,"b_gate_pass_rate":0.5,"median_len_z":1467.0,"mean_r_leg":0.04842301075448322,"mean_g_leg":0.033658147856845205,"g_bind_frac":0.39285714285714285,"a_match":0.7283950617283951,"a_match_n":27,"a_match_centered":-0.01234567901234568},"terminus_json":{"n_turns":19,"n_valid":19,"parse_rate":1.0,"reason":-0.00859277332475054,"mean_b":0.02296409209572506,"b_gate_pass_rate":0.45454545454545453,"median_len_z":593.0,"mean_r_leg":0.001222606612120336,"mean_g_leg":0.026852010995856324,"g_bind_frac":0.2631578947368421,"a_match":0.4035087719298246,"a_match_n":19,"a_match_centered":-0.05263157894736842},"text":{"n_turns":361,"n_valid":358,"parse_rate":0.9916897506925207,"reason":-0.00044717673851033603,"mean_b":0.04468072789415371,"b_gate_pass_rate":0.3016759776536313,"median_len_z":698.0,"mean_r_leg":0.00677411323601525,"mean_g_leg":0.06187813382499646,"g_bind_frac":0.19273743016759776,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":292,"n_valid":292,"parse_rate":1.0,"reason":0.0005988127741520925,"mean_b":0.029562552875804973,"b_gate_pass_rate":0.41550925925925924,"median_len_z":492.0,"mean_r_leg":0.0054465642319412345,"mean_g_leg":0.0708405920933461,"g_bind_frac":0.17465753424657535,"a_match":0.12046783625730995,"a_match_n":285,"a_match_centered":-0.062426383981154306}}},"challenger_wins":true,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T12:22:08.788867+00:00","challenge_id":"chal-00661","repo":"r2://affine-private-models/models/registrations/c13444aadaf0114d187f185ea97caea36523a7a306e367e8c5c0b2152d7757e4/","hotkey":"5GNtXyGVNTZavqEPtBTm3V4BEK8mbu6K7MvKnCTi3bjGfw8h","uid":4,"duration_s":2468.2,"revision":"bb958ba89c26c0e6cbee553871342f34393a04001ad8a43ef0fe5172d12c867e","accepted":false,"error_code":null,"error_detail":"","z":-0.33077285250353894,"margin":-0.022861382922888612,"se":0.06911505206626356,"n_paired_turns":991,"n_forfeit_turns":16,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2312655849395225656,"n":1000,"digest":"35f028fab6757b0c61a157ccb46b954a811518aa162075e8348569cbf2b14b82","n_paired_turns":991,"n_forfeit_turns":16,"margin":-0.022861382922888612,"se":0.06911505206626356,"z":-0.33077285250353894,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.022861382922888612,"se":0.06911505206626356,"z":-0.33077285250353894,"sd_diff":2.175752377529029,"n_paired_turns":991,"n_forfeit_turns":16,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"tool_call":{"R":0.008363261419272705,"A":5.8396158948996755,"Mc":0.185367934250197},"text":{"R":0.049451275135837774,"A":9.55056439955923,"Mc":0.16513300932643737},"bash":{"R":0.021735228377757737,"A":4.8224037520318825,"Mc":0.14771234659149896},"boxed":{"R":0.14748277835734563,"A":4.958895776262898,"Mc":0.12123586004016416},"terminus_json":{"R":0.007134360361776161,"A":16.62966823799657,"Mc":0.12388779273700577}},"challenger":{"mean":-1.0206737592494177,"mean_valid":-0.8294354948101145,"sd_valid":1.8265779719226107,"n_turns":996,"n_valid":976,"n_forfeits":17,"n_unscorable":3,"mean_z_R":0.1254685786931092,"mean_typ_c":0.5380540708309919,"mean_z_A":-0.11271431638446915,"bind_frac":{"R":0.3524590163934426,"Gc":0.17725409836065573,"A":0.4702868852459016},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.3358349928729092,"mean_R":0.011383099021401537,"mean_A":2.745489004182213,"mean_mc":-0.6677002434726338},"king":{"mean":-0.9756543011686065,"mean_valid":-0.8972290777013101,"sd_valid":1.858284069895664,"n_turns":996,"n_valid":984,"n_forfeits":7,"n_unscorable":5,"mean_z_R":0.16786874310021604,"mean_typ_c":0.48742052039611233,"mean_z_A":-0.23700845778393428,"bind_frac":{"R":0.29776422764227645,"Gc":0.19004065040650406,"A":0.5121951219512195},"n_leg_dropped":{"R":0,"Gc":6,"A":0},"mean_content_share":0.32848644503594465,"mean_R":0.012586022087294434,"mean_A":1.621990538258006,"mean_mc":-0.7042922763645646}},"rejection_reason":null,"reign_number":null,"score":0.0022556333392232996,"score_king":0.0030145376810096214,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9122900,"blocks_since_crown":19671,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1138.6293279022402,"mean_len_y":643.9613034623218,"n_samples":3000,"think_close_rate":0.9733333333333334,"n_text_fallback":20,"by_dialect":{"text":{"n_turns":355,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":287,"zero_ref_turns":0,"mean_refs":2.9303135888501743,"ref_pair_agreement":0.2210144927536232,"ref_pair_n":276},"boxed":{"n_turns":24,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.6818181818181818,"ref_pair_n":22},"bash":{"n_turns":304,"zero_ref_turns":3,"mean_refs":2.901315789473684,"ref_pair_agreement":0.19286510590858416,"ref_pair_n":299},"terminus_json":{"n_turns":30,"zero_ref_turns":1,"mean_refs":2.8666666666666667,"ref_pair_agreement":0.45977011494252873,"ref_pair_n":29}},"ref_pair_agreement":0.23482428115015974,"ref_pair_n":626},"duel_seconds":2115.037971680984,"challenger":{"reason":0.0022556333392232996,"n_turns":996,"n_pairs":2901,"n_forfeits":17,"forfeit_rate":0.01706827309236948,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":0.10996277541204107,"mean_len_z":949.4822475008617,"median_len_z":490.0,"mean_len_y":498.51120303343674,"mean_b":0.08644996676942175,"b_gate_pass_rate":0.4812133746983799,"mean_r_leg":0.011383099021401537,"mean_g_leg":0.056505860371702125,"g_bind_frac":0.21450459652706844,"a_match":0.19791666666666666,"a_match_n":624,"a_match_centered":-0.036043360433604336,"n_turns_cap_raised":82,"mean_cap_tokens":2158.855421686747,"max_cap_tokens":5103,"len_z_delta":-189.1470804013785,"len_y_delta":-145.45010042888504,"n_samples":999,"think_close_rate":0.985985985985986,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":301,"n_valid":297,"parse_rate":0.9867109634551495,"reason":0.006932261560957972,"mean_b":0.11892023632114922,"b_gate_pass_rate":0.8363844393592678,"median_len_z":411.0,"mean_r_leg":0.017906226782727568,"mean_g_leg":0.04420735379466328,"g_bind_frac":0.29292929292929293,"a_match":0.17789001122334455,"a_match_n":297,"a_match_centered":-0.016328828828828832},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":0.0066238583027968135,"mean_b":1.1551082457785218,"b_gate_pass_rate":0.4583333333333333,"median_len_z":1589.5,"mean_r_leg":0.05538240198866526,"mean_g_leg":0.023614084029867526,"g_bind_frac":0.4583333333333333,"a_match":0.6515151515151515,"a_match_n":22,"a_match_centered":0.015873015873015872},"terminus_json":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":-0.002727078570401106,"mean_b":0.015295913890654487,"b_gate_pass_rate":0.26744186046511625,"median_len_z":454.0,"mean_r_leg":0.001416237166141618,"mean_g_leg":0.0444554982637804,"g_bind_frac":0.27586206896551724,"a_match":0.41379310344827586,"a_match_n":29,"a_match_centered":-0.04597701149425288},"text":{"n_turns":355,"n_valid":347,"parse_rate":0.9774647887323944,"reason":-0.00022289228619977317,"mean_b":0.038512418312355405,"b_gate_pass_rate":0.29394812680115273,"median_len_z":611.0,"mean_r_leg":0.007842798422984272,"mean_g_leg":0.058694043602534544,"g_bind_frac":0.16138328530259366,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":287,"n_valid":282,"parse_rate":0.9825783972125436,"reason":0.0005548415222769498,"mean_b":0.026908692390816728,"b_gate_pass_rate":0.36594202898550726,"median_len_z":424.0,"mean_r_leg":0.006149663153051073,"mean_g_leg":0.07080451287388456,"g_bind_frac":0.1702127659574468,"a_match":0.16062801932367152,"a_match_n":276,"a_match_centered":-0.06071871127633209}}},"king":{"reason":0.0030145376810096214,"n_turns":996,"n_pairs":2926,"n_forfeits":7,"forfeit_rate":0.007028112449799197,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":14.985743515822989,"mean_len_z":812.512987012987,"median_len_z":549.0,"mean_len_y":474.147983595352,"mean_b":0.08441834150297108,"b_gate_pass_rate":0.5034176349965823,"mean_r_leg":0.012586022087294434,"mean_g_leg":0.056781343541556326,"g_bind_frac":0.21739130434782608,"a_match":0.19404572036150983,"a_match_n":627,"a_match_centered":-0.03781739600216099,"n_turns_cap_raised":82,"mean_cap_tokens":2158.855421686747,"max_cap_tokens":5103,"len_z_delta":-326.11634088925325,"len_y_delta":-169.81331986696978,"n_samples":996,"think_close_rate":0.9949799196787149,"n_text_fallback":8,"by_dialect":{"bash":{"n_turns":301,"n_valid":299,"parse_rate":0.9933554817275747,"reason":0.007874215554546168,"mean_b":0.12128713563481056,"b_gate_pass_rate":0.8472063854047891,"median_len_z":452.0,"mean_r_leg":0.01804047285529501,"mean_g_leg":0.04326939888638189,"g_bind_frac":0.2842809364548495,"a_match":0.1794871794871795,"a_match_n":299,"a_match_centered":-0.01234567901234568},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":0.010088183122969522,"mean_b":1.114542917735478,"b_gate_pass_rate":0.625,"median_len_z":1696.0,"mean_r_leg":0.0391865319765892,"mean_g_leg":0.03290156881008608,"g_bind_frac":0.4166666666666667,"a_match":0.6363636363636364,"a_match_n":22,"a_match_centered":-0.047619047619047616},"terminus_json":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":-0.0023610780864618576,"mean_b":0.015972669928677744,"b_gate_pass_rate":0.313953488372093,"median_len_z":436.0,"mean_r_leg":0.002994677425974469,"mean_g_leg":0.048294856756195,"g_bind_frac":0.2413793103448276,"a_match":0.43678160919540227,"a_match_n":29,"a_match_centered":-0.02298850574712644},"text":{"n_turns":355,"n_valid":350,"parse_rate":0.9859154929577465,"reason":-0.0007632161167020494,"mean_b":0.03387024232583229,"b_gate_pass_rate":0.30857142857142855,"median_len_z":711.0,"mean_r_leg":0.012132713652963808,"mean_g_leg":0.05645162216436801,"g_bind_frac":0.2,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":287,"n_valid":287,"parse_rate":1.0,"reason":0.0025422900325872454,"mean_b":0.027889126222378047,"b_gate_pass_rate":0.3971462544589774,"median_len_z":488.0,"mean_r_leg":0.006201053203039213,"mean_g_leg":0.07411478132637803,"g_bind_frac":0.14982578397212543,"a_match":0.14921780986762936,"a_match_n":277,"a_match_centered":-0.06666666666666667}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T11:39:50.617548+00:00","challenge_id":"chal-00660","repo":"r2://affine-private-models/models/registrations/b7a5d22e68d4b6c6a520e12f6089ad9a085018efea2eac9c1ab5170e94aaeca6/","hotkey":"5DqmHs9geNARnaic2QQLMbnVaR3hzC4cwEGfe9GLFk1TMVuC","uid":230,"duration_s":2530.6,"revision":"d962f4c8387699ffe87595a68a3203e0118910708aafd46962fdd4b689f7d6b5","accepted":false,"error_code":null,"error_detail":"","z":-0.7095850239212026,"margin":-0.037111717897076964,"se":0.052300593510268494,"n_paired_turns":989,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":6264692232854917837,"n":1000,"digest":"0f86a927dcebb7a220e6f56123147501c8e58302c45209fab129158e548dfcbb","n_paired_turns":989,"n_forfeit_turns":8,"margin":-0.037111717897076964,"se":0.052300593510268494,"z":-0.7095850239212026,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.037111717897076964,"se":0.052300593510268494,"z":-0.7095850239212026,"sd_diff":1.6447684361725663,"n_paired_turns":989,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"text":{"R":0.047059342263429234,"A":27.8483591929111,"Mc":0.15783336564089248},"bash":{"R":0.024260185825812002,"A":5.853939031015749,"Mc":0.15995762131167288},"tool_call":{"R":0.008731567330824327,"A":5.955935138532981,"Mc":0.19855435516248382},"terminus_json":{"R":0.0008620781954722764,"A":10.646383245696827,"Mc":0.12372797827813603},"boxed":{"R":0.14603215812857157,"A":3.487385819867723,"Mc":0.12120583683700813}},"challenger":{"mean":-0.7670707988005611,"mean_valid":-0.6985076500648575,"sd_valid":1.4260702392348843,"n_turns":997,"n_valid":983,"n_forfeits":6,"n_unscorable":8,"mean_z_R":0.1828599305024682,"mean_typ_c":0.5378519153278047,"mean_z_A":-0.1307315162973465,"bind_frac":{"R":0.31841302136317395,"Gc":0.19837232960325535,"A":0.4832146490335707},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.32391330148682707,"mean_R":0.01621891249264868,"mean_A":1.5954688209788128,"mean_mc":-0.7370097142232547},"king":{"mean":-0.729959080903484,"mean_valid":-0.6726926128186441,"sd_valid":1.4043907780050413,"n_turns":997,"n_valid":984,"n_forfeits":5,"n_unscorable":8,"mean_z_R":0.1923684438287094,"mean_typ_c":0.5635691220897152,"mean_z_A":-0.1458629004959958,"bind_frac":{"R":0.29878048780487804,"Gc":0.17479674796747968,"A":0.5264227642276422},"n_leg_dropped":{"R":0,"Gc":6,"A":0},"mean_content_share":0.3220418753992183,"mean_R":0.01620002319019133,"mean_A":1.1771658435387655,"mean_mc":-0.7213172223683832}},"rejection_reason":null,"reign_number":null,"score":0.002728577186367166,"score_king":0.0030572856884369002,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9122683,"blocks_since_crown":19454,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1237.3063642518619,"mean_len_y":653.7728503723764,"n_samples":3000,"think_close_rate":0.974,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":320,"zero_ref_turns":2,"mean_refs":2.934375,"ref_pair_agreement":0.16878980891719744,"ref_pair_n":314},"tool_call":{"n_turns":269,"zero_ref_turns":1,"mean_refs":2.9182156133828996,"ref_pair_agreement":0.17496807151979565,"ref_pair_n":261},"text":{"n_turns":357,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":32,"zero_ref_turns":0,"mean_refs":2.9375,"ref_pair_agreement":0.46875,"ref_pair_n":32},"boxed":{"n_turns":22,"zero_ref_turns":0,"mean_refs":2.9545454545454546,"ref_pair_agreement":0.6818181818181818,"ref_pair_n":22}},"ref_pair_agreement":0.20455749867514572,"ref_pair_n":629},"duel_seconds":2160.854945359286,"challenger":{"reason":0.002728577186367166,"n_turns":997,"n_pairs":2936,"n_forfeits":6,"forfeit_rate":0.006018054162487462,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":13.12019450649873,"mean_len_z":874.8756811989101,"median_len_z":590.0,"mean_len_y":470.72275204359676,"mean_b":0.09368309006669713,"b_gate_pass_rate":0.5221389645776566,"mean_r_leg":0.01621891249264868,"mean_g_leg":0.059245492711539366,"g_bind_frac":0.24318869828456105,"a_match":0.1513227513227513,"a_match_n":630,"a_match_centered":-0.053763440860215055,"n_turns_cap_raised":94,"mean_cap_tokens":2180.132397191575,"max_cap_tokens":5106,"len_z_delta":-362.43068305295174,"len_y_delta":-183.05009832877965,"n_samples":1000,"think_close_rate":0.994,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.008955218902295368,"mean_b":0.11901421326533648,"b_gate_pass_rate":0.8306709265175719,"median_len_z":429.0,"mean_r_leg":0.02253378610509311,"mean_g_leg":0.05085997893365875,"g_bind_frac":0.29559748427672955,"a_match":0.11949685534591195,"a_match_n":318,"a_match_centered":-0.050955414012738856},"boxed":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":0.004114820344172937,"mean_b":1.4104500060362195,"b_gate_pass_rate":0.6307692307692307,"median_len_z":2532.0,"mean_r_leg":0.09672321166404457,"mean_g_leg":0.023150571056412838,"g_bind_frac":0.3181818181818182,"a_match":0.6439393939393939,"a_match_n":22,"a_match_centered":-0.03787878787878787},"terminus_json":{"n_turns":32,"n_valid":32,"parse_rate":1.0,"reason":-0.0027142724529364837,"mean_b":0.014863735717369238,"b_gate_pass_rate":0.23404255319148937,"median_len_z":561.5,"mean_r_leg":0.001117558349930569,"mean_g_leg":0.048401678168492876,"g_bind_frac":0.125,"a_match":0.484375,"a_match_n":32,"a_match_centered":0.015624999999999998},"text":{"n_turns":357,"n_valid":351,"parse_rate":0.9831932773109243,"reason":-0.00037729004011101755,"mean_b":0.045946968561036625,"b_gate_pass_rate":0.3475783475783476,"median_len_z":675.0,"mean_r_leg":0.01485429605829884,"mean_g_leg":0.056572727483617066,"g_bind_frac":0.23646723646723647,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":268,"n_valid":268,"parse_rate":1.0,"reason":1.363828029825842e-05,"mean_b":0.027822428961927718,"b_gate_pass_rate":0.41273885350318473,"median_len_z":581.0,"mean_r_leg":0.005707715890020832,"mean_g_leg":0.07695379240615516,"g_bind_frac":0.19776119402985073,"a_match":0.10723514211886305,"a_match_n":258,"a_match_centered":-0.06746031746031746}}},"king":{"reason":0.0030572856884369002,"n_turns":997,"n_pairs":2939,"n_forfeits":5,"forfeit_rate":0.0050150451354062184,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.6627291060645604,"mean_len_z":893.5464443688329,"median_len_z":577.0,"mean_len_y":464.3661109220823,"mean_b":0.09292905040784774,"b_gate_pass_rate":0.5205852330724736,"mean_r_leg":0.01620002319019133,"mean_g_leg":0.05963350061884928,"g_bind_frac":0.2318548387096774,"a_match":0.15060558188520273,"a_match_n":633,"a_match_centered":-0.05037513397642015,"n_turns_cap_raised":94,"mean_cap_tokens":2180.132397191575,"max_cap_tokens":5106,"len_z_delta":-343.75991988302894,"len_y_delta":-189.40673945029408,"n_samples":997,"think_close_rate":0.995987963891675,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":318,"n_valid":318,"parse_rate":1.0,"reason":0.009623245238746019,"mean_b":0.12450947699036291,"b_gate_pass_rate":0.8477103301384451,"median_len_z":435.0,"mean_r_leg":0.02220106010427973,"mean_g_leg":0.052127413433308935,"g_bind_frac":0.2610062893081761,"a_match":0.12054507337526206,"a_match_n":318,"a_match_centered":-0.04989384288747346},"boxed":{"n_turns":22,"n_valid":21,"parse_rate":0.9545454545454546,"reason":0.005800471689220159,"mean_b":1.3784752703657985,"b_gate_pass_rate":0.532258064516129,"median_len_z":2393.0,"mean_r_leg":0.07952788579025426,"mean_g_leg":0.0273606036984885,"g_bind_frac":0.38095238095238093,"a_match":0.6587301587301587,"a_match_n":21,"a_match_centered":-0.007936507936507938},"terminus_json":{"n_turns":32,"n_valid":32,"parse_rate":1.0,"reason":-0.002380886819462742,"mean_b":0.014534575908430646,"b_gate_pass_rate":0.22340425531914893,"median_len_z":552.5,"mean_r_leg":0.000985426231323603,"mean_g_leg":0.045407579527223726,"g_bind_frac":0.1875,"a_match":0.4947916666666667,"a_match_n":32,"a_match_centered":0.026041666666666664},"text":{"n_turns":357,"n_valid":353,"parse_rate":0.988795518207283,"reason":-0.0007104654454136592,"mean_b":0.0435959632456966,"b_gate_pass_rate":0.3371104815864023,"median_len_z":716.0,"mean_r_leg":0.016070077443257905,"mean_g_leg":0.05531543325544485,"g_bind_frac":0.22662889518413598,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":268,"n_valid":268,"parse_rate":1.0,"reason":0.0007094627258320741,"mean_b":0.02955953920948925,"b_gate_pass_rate":0.41146496815286626,"median_len_z":546.0,"mean_r_leg":0.006104960123287718,"mean_g_leg":0.07845504470296567,"g_bind_frac":0.19776119402985073,"a_match":0.10432569974554706,"a_match_n":262,"a_match_centered":-0.06405228758169934}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T10:56:47.185977+00:00","challenge_id":"chal-00659","repo":"r2://affine-private-models/models/registrations/5cf67ee37113da65c01acc7a8aeebee454f47d37fb2d25edc890a04e1a93daec/","hotkey":"5DsffDVJ3UGpqrQ678ei9DY7MX8KAJcwGjb6dyLXBJLXja3d","uid":213,"duration_s":2550.7,"revision":"1f5c29382cc4041197db12c3373babf49eed11b199fef787f1c09da7e04bfb83","accepted":false,"error_code":null,"error_detail":"","z":-5.0127692094068586,"margin":-0.3069544594147281,"se":0.06123450863022054,"n_paired_turns":991,"n_forfeit_turns":20,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":11710832233054762604,"n":1000,"digest":"a4d9db7964bd8dcde1816e51105a3e9e216e9d64a886d5aa5ca5dc7f0300c070","n_paired_turns":991,"n_forfeit_turns":20,"margin":-0.3069544594147281,"se":0.06123450863022054,"z":-5.0127692094068586,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.3069544594147281,"se":0.06123450863022054,"z":-5.0127692094068586,"sd_diff":1.9276716685576651,"n_paired_turns":991,"n_forfeit_turns":20,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02334369317062676,"A":6.329714167701138,"Mc":0.15842712214435126},"tool_call":{"R":0.008545479292048583,"A":5.623001780756833,"Mc":0.1885399161253632},"text":{"R":0.04566443943665383,"A":21.827041757696477,"Mc":0.17516389082039246},"boxed":{"R":0.11234101449918085,"A":3.6282480035000413,"Mc":0.13190386524271916},"terminus_json":{"R":0.0029429927480146127,"A":6.1680144240843156,"Mc":0.09739876265181208}},"challenger":{"mean":-1.0212726688064195,"mean_valid":-0.8183803772648545,"sd_valid":1.44482783327131,"n_turns":995,"n_valid":974,"n_forfeits":18,"n_unscorable":3,"mean_z_R":0.17269934435457804,"mean_typ_c":0.34129744329601336,"mean_z_A":-0.2187541585472,"bind_frac":{"R":0.2546201232032854,"Gc":0.24435318275154005,"A":0.5010266940451745},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.3141669441387464,"mean_R":0.01481222931923795,"mean_A":0.9637863574708605,"mean_mc":-0.8116185414206989},"king":{"mean":-0.7032397761614256,"mean_valid":-0.6113027651841025,"sd_valid":1.3424851956231323,"n_turns":995,"n_valid":983,"n_forfeits":8,"n_unscorable":4,"mean_z_R":0.2105635513677208,"mean_typ_c":0.7157832807044857,"mean_z_A":-0.14263690624762781,"bind_frac":{"R":0.31536113936927773,"Gc":0.16581892166836215,"A":0.5188199389623601},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.3174575029562366,"mean_R":0.015630553302384623,"mean_A":1.8564233398130163,"mean_mc":-0.7143367164537663}},"rejection_reason":null,"reign_number":null,"score":-2.789893761743561e-06,"score_king":0.003628714780157328,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9122466,"blocks_since_crown":19237,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1317.4857627118645,"mean_len_y":652.0003389830508,"n_samples":3000,"think_close_rate":0.9713333333333334,"n_text_fallback":20,"by_dialect":{"text":{"n_turns":355,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":316,"zero_ref_turns":1,"mean_refs":2.9588607594936707,"ref_pair_agreement":0.1624203821656051,"ref_pair_n":314},"tool_call":{"n_turns":281,"zero_ref_turns":2,"mean_refs":2.903914590747331,"ref_pair_agreement":0.15498154981549817,"ref_pair_n":271},"boxed":{"n_turns":28,"zero_ref_turns":0,"mean_refs":2.9285714285714284,"ref_pair_agreement":0.8024691358024691,"ref_pair_n":27},"terminus_json":{"n_turns":20,"zero_ref_turns":2,"mean_refs":2.6,"ref_pair_agreement":0.6274509803921569,"ref_pair_n":17}},"ref_pair_agreement":0.1992580816110228,"ref_pair_n":629},"duel_seconds":2198.849753261078,"challenger":{"reason":-2.789893761743561e-06,"n_turns":995,"n_pairs":2900,"n_forfeits":18,"forfeit_rate":0.018090452261306532,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-439.8040131158214,"mean_len_z":1006.8041379310345,"median_len_z":593.0,"mean_len_y":484.1313793103448,"mean_b":0.0923109300790907,"b_gate_pass_rate":0.5193103448275862,"mean_r_leg":0.01481222931923795,"mean_g_leg":0.05351272838706215,"g_bind_frac":0.25895598771750256,"a_match":0.16210413311862587,"a_match_n":621,"a_match_centered":-0.032467532467532464,"n_turns_cap_raised":122,"mean_cap_tokens":2207.4090452261307,"max_cap_tokens":5082,"len_z_delta":-310.68162478083,"len_y_delta":-167.868959672706,"n_samples":998,"think_close_rate":0.9929859719438878,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":315,"n_valid":305,"parse_rate":0.9682539682539683,"reason":0.004375335463276867,"mean_b":0.11614851049934578,"b_gate_pass_rate":0.8281938325991189,"median_len_z":442.5,"mean_r_leg":0.019619507354819,"mean_g_leg":0.04694996401210126,"g_bind_frac":0.2983606557377049,"a_match":0.12021857923497267,"a_match_n":305,"a_match_centered":-0.034972677595628415},"boxed":{"n_turns":28,"n_valid":27,"parse_rate":0.9642857142857143,"reason":0.003369316656994522,"mean_b":1.3052567417164551,"b_gate_pass_rate":0.3375,"median_len_z":2760.0,"mean_r_leg":0.07268019713879421,"mean_g_leg":0.037262897613582584,"g_bind_frac":0.25925925925925924,"a_match":0.7564102564102565,"a_match_n":26,"a_match_centered":-0.07692307692307693},"terminus_json":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":-0.010702636078488821,"mean_b":0.031415363312361874,"b_gate_pass_rate":0.5961538461538461,"median_len_z":925.0,"mean_r_leg":0.0008264368698644502,"mean_g_leg":0.020388197759094524,"g_bind_frac":0.2222222222222222,"a_match":0.6111111111111112,"a_match_n":18,"a_match_centered":0.0196078431372549},"text":{"n_turns":355,"n_valid":348,"parse_rate":0.9802816901408451,"reason":-0.0031193537606333784,"mean_b":0.02983100210452911,"b_gate_pass_rate":0.3333333333333333,"median_len_z":671.5,"mean_r_leg":0.013807481486362362,"mean_g_leg":0.05118480276461272,"g_bind_frac":0.25,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":279,"n_valid":279,"parse_rate":1.0,"reason":-0.0006284209576464027,"mean_b":0.030687678026065517,"b_gate_pass_rate":0.4264705882352941,"median_len_z":569.0,"mean_r_leg":0.00611237834414544,"mean_g_leg":0.0673003564629146,"g_bind_frac":0.22939068100358423,"a_match":0.12254901960784315,"a_match_n":272,"a_match_centered":-0.028606965174129355}}},"king":{"reason":0.003628714780157328,"n_turns":995,"n_pairs":2926,"n_forfeits":8,"forfeit_rate":0.008040201005025126,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-419.20165115493717,"mean_len_z":890.6120984278879,"median_len_z":600.0,"mean_len_y":472.62816131237184,"mean_b":0.09390899943125641,"b_gate_pass_rate":0.518796992481203,"mean_r_leg":0.015630553302384623,"mean_g_leg":0.05859602962939526,"g_bind_frac":0.22695035460992907,"a_match":0.1724960254372019,"a_match_n":629,"a_match_centered":-0.028044871794871796,"n_turns_cap_raised":122,"mean_cap_tokens":2207.4090452261307,"max_cap_tokens":5082,"len_z_delta":-426.8736642839766,"len_y_delta":-179.37217767067898,"n_samples":995,"think_close_rate":0.9949748743718593,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":315,"n_valid":312,"parse_rate":0.9904761904761905,"reason":0.007522385024392547,"mean_b":0.11604834347896952,"b_gate_pass_rate":0.8358531317494601,"median_len_z":510.0,"mean_r_leg":0.01920298113110474,"mean_g_leg":0.04607628386420302,"g_bind_frac":0.2948717948717949,"a_match":0.16185897435897437,"a_match_n":312,"a_match_centered":-0.0048231511254019305},"boxed":{"n_turns":28,"n_valid":28,"parse_rate":1.0,"reason":0.007296998413076399,"mean_b":1.3110454155830735,"b_gate_pass_rate":0.6951219512195121,"median_len_z":2647.0,"mean_r_leg":0.08283099850280261,"mean_g_leg":0.0354950847579629,"g_bind_frac":0.39285714285714285,"a_match":0.7037037037037037,"a_match_n":27,"a_match_centered":-0.09876543209876543},"terminus_json":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":-0.010230455329274796,"mean_b":0.018407655452065047,"b_gate_pass_rate":0.3076923076923077,"median_len_z":509.0,"mean_r_leg":0.0007729044636059424,"mean_g_leg":0.024562919954639897,"g_bind_frac":0.16666666666666666,"a_match":0.5555555555555556,"a_match_n":18,"a_match_centered":-0.03921568627450981},"text":{"n_turns":355,"n_valid":350,"parse_rate":0.9859154929577465,"reason":0.0014298687206550367,"mean_b":0.03381300704719164,"b_gate_pass_rate":0.3028571428571429,"median_len_z":714.5,"mean_r_leg":0.014669775661282584,"mean_g_leg":0.060612047468955876,"g_bind_frac":0.19714285714285715,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":279,"n_valid":279,"parse_rate":1.0,"reason":0.002556447197495189,"mean_b":0.028615669991985136,"b_gate_pass_rate":0.4325980392156863,"median_len_z":530.5,"mean_r_leg":0.007055284145794485,"mean_g_leg":0.07458160979226072,"g_bind_frac":0.17562724014336917,"a_match":0.10661764705882353,"a_match_n":272,"a_match_centered":-0.04708798017348203}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T10:11:11.803327+00:00","challenge_id":"chal-00658","repo":"r2://affine-private-models/models/registrations/dbc643d28013e7406c2924834ae1fa867403870c25514164138ce7708b4e8dcb/","hotkey":"5FaeWFkGo1rJrWGW4647LfdmSiMNrGXobmJLRdTjY2t2EyMS","uid":148,"duration_s":2357.5,"revision":"eb9c090c9036bca7616e7958758574449741c0309930569b944a88bc990a626e","accepted":false,"error_code":null,"error_detail":"","z":0.5642314560731265,"margin":0.032325812307386896,"se":0.05729175847862929,"n_paired_turns":986,"n_forfeit_turns":12,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":15649297456082261167,"n":1000,"digest":"15b88c3d30e0526c4a39fa14161c5d8ddc7c80f6acc6b12b4e6a79bf6831e98e","n_paired_turns":986,"n_forfeit_turns":12,"margin":0.032325812307386896,"se":0.05729175847862929,"z":0.5642314560731265,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.032325812307386896,"se":0.05729175847862929,"z":0.5642314560731265,"sd_diff":1.7989977074247652,"n_paired_turns":986,"n_forfeit_turns":12,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"text":{"R":0.011943485237315653,"A":16.473447211972328,"Mc":0.17521065500630278},"bash":{"R":0.024191839328585204,"A":5.883245645556097,"Mc":0.15363747232960154},"tool_call":{"R":0.013831024369276615,"A":5.63044112814412,"Mc":0.19997848593845532},"terminus_json":{"R":0.001118155617754325,"A":6.420177766568471,"Mc":0.11666405655203707},"boxed":{"R":0.087234932740182,"A":3.742061822654816,"Mc":0.12553686607535797}},"challenger":{"mean":-0.92924519591702,"mean_valid":-0.8500876028336892,"sd_valid":1.9139468556431214,"n_turns":993,"n_valid":979,"n_forfeits":7,"n_unscorable":7,"mean_z_R":0.2261129627650247,"mean_typ_c":0.5359842462540974,"mean_z_A":-0.1839753957505624,"bind_frac":{"R":0.32175689479060265,"Gc":0.17466802860061287,"A":0.5035750766087844},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.3288626423027515,"mean_R":0.012218599078841983,"mean_A":1.7038765651978005,"mean_mc":-0.7061985885144273},"king":{"mean":-0.9615710082244069,"mean_valid":-0.8255739364571512,"sd_valid":1.7540456769661015,"n_turns":993,"n_valid":974,"n_forfeits":12,"n_unscorable":7,"mean_z_R":0.21718262913398825,"mean_typ_c":0.5822385932694623,"mean_z_A":-0.20609088638685588,"bind_frac":{"R":0.31211498973305957,"Gc":0.1806981519507187,"A":0.5071868583162218},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.31923729006982005,"mean_R":0.011635023784126782,"mean_A":1.649738786103372,"mean_mc":-0.720285142856081}},"rejection_reason":null,"reign_number":null,"score":0.0014117809349776884,"score_king":0.0011179112540056681,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9122254,"blocks_since_crown":19025,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1267.0565202587675,"mean_len_y":684.6353421859039,"n_samples":3000,"think_close_rate":0.9663333333333334,"n_text_fallback":21,"by_dialect":{"tool_call":{"n_turns":282,"zero_ref_turns":5,"mean_refs":2.879432624113475,"ref_pair_agreement":0.15920398009950248,"ref_pair_n":268},"text":{"n_turns":349,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":320,"zero_ref_turns":1,"mean_refs":2.946875,"ref_pair_agreement":0.17827004219409284,"ref_pair_n":316},"terminus_json":{"n_turns":25,"zero_ref_turns":1,"mean_refs":2.64,"ref_pair_agreement":0.5454545454545454,"ref_pair_n":22},"boxed":{"n_turns":24,"zero_ref_turns":0,"mean_refs":2.875,"ref_pair_agreement":0.6805555555555555,"ref_pair_n":24}},"ref_pair_agreement":0.2021164021164021,"ref_pair_n":630},"duel_seconds":2004.7764188051224,"challenger":{"reason":0.0014117809349776884,"n_turns":993,"n_pairs":2918,"n_forfeits":7,"forfeit_rate":0.007049345417925478,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-9.632336422667386,"mean_len_z":833.4472241261137,"median_len_z":545.5,"mean_len_y":416.66895133653185,"mean_b":0.08907174906083369,"b_gate_pass_rate":0.5236463331048663,"mean_r_leg":0.012218599078841983,"mean_g_leg":0.05758394650858157,"g_bind_frac":0.23529411764705882,"a_match":0.16588050314465408,"a_match_n":636,"a_match_centered":-0.03647497337593184,"n_turns_cap_raised":98,"mean_cap_tokens":2182.682779456193,"max_cap_tokens":5110,"len_z_delta":-433.60929613265375,"len_y_delta":-267.9663908493721,"n_samples":996,"think_close_rate":0.9949799196787149,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":319,"n_valid":318,"parse_rate":0.9968652037617555,"reason":0.006939411256864793,"mean_b":0.12071400128883006,"b_gate_pass_rate":0.8563829787234043,"median_len_z":438.0,"mean_r_leg":0.018096061706283802,"mean_g_leg":0.04640689003024523,"g_bind_frac":0.27672955974842767,"a_match":0.1530398322851153,"a_match_n":318,"a_match_centered":-0.02433862433862434},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":0.009658816475261303,"mean_b":1.1498069940496807,"b_gate_pass_rate":0.42028985507246375,"median_len_z":2080.0,"mean_r_leg":0.05360904626246862,"mean_g_leg":0.02667073693677853,"g_bind_frac":0.4166666666666667,"a_match":0.6376811594202898,"a_match_n":23,"a_match_centered":-0.07246376811594203},"terminus_json":{"n_turns":24,"n_valid":23,"parse_rate":0.9583333333333334,"reason":-0.005259308356622888,"mean_b":0.013410937112431104,"b_gate_pass_rate":0.18461538461538463,"median_len_z":568.0,"mean_r_leg":0.0007273213929394754,"mean_g_leg":0.04468029073788436,"g_bind_frac":0.08695652173913043,"a_match":0.5217391304347826,"a_match_n":23,"a_match_centered":0.0},"text":{"n_turns":349,"n_valid":344,"parse_rate":0.9856733524355301,"reason":-0.0032009787199536077,"mean_b":0.04319034714875148,"b_gate_pass_rate":0.32558139534883723,"median_len_z":721.5,"mean_r_leg":0.008622044807442003,"mean_g_leg":0.056700851339847085,"g_bind_frac":0.22093023255813954,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":277,"n_valid":277,"parse_rate":1.0,"reason":0.0007212261946190002,"mean_b":0.02667410195660706,"b_gate_pass_rate":0.42610837438423643,"median_len_z":460.5,"mean_r_leg":0.0073056395416716356,"mean_g_leg":0.075261888063112,"g_bind_frac":0.20216606498194944,"a_match":0.11090686274509803,"a_match_n":272,"a_match_centered":-0.05075187969924812}}},"king":{"reason":0.0011179112540056681,"n_turns":993,"n_pairs":2903,"n_forfeits":12,"forfeit_rate":0.012084592145015106,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.4242019133530095,"mean_len_z":877.4205993799518,"median_len_z":593.0,"mean_len_y":424.0134343782294,"mean_b":0.09096831189959453,"b_gate_pass_rate":0.537030657940062,"mean_r_leg":0.011635023784126782,"mean_g_leg":0.05735376552096488,"g_bind_frac":0.2344546381243629,"a_match":0.16534810126582278,"a_match_n":632,"a_match_centered":-0.036115569823434994,"n_turns_cap_raised":98,"mean_cap_tokens":2182.682779456193,"max_cap_tokens":5110,"len_z_delta":-389.6359208788157,"len_y_delta":-260.6219078076745,"n_samples":993,"think_close_rate":0.9909365558912386,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":319,"n_valid":317,"parse_rate":0.9937304075235109,"reason":0.006566547036925816,"mean_b":0.12070769502930732,"b_gate_pass_rate":0.8495197438633938,"median_len_z":508.0,"mean_r_leg":0.017511610267735747,"mean_g_leg":0.04636637426757675,"g_bind_frac":0.27129337539432175,"a_match":0.14826498422712933,"a_match_n":317,"a_match_centered":-0.02653927813163482},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":0.006267688049254742,"mean_b":1.1789206398362462,"b_gate_pass_rate":0.5942028985507246,"median_len_z":1913.0,"mean_r_leg":0.03862836321422736,"mean_g_leg":0.020706520211564577,"g_bind_frac":0.5,"a_match":0.611111111111111,"a_match_n":24,"a_match_centered":-0.06944444444444445},"terminus_json":{"n_turns":24,"n_valid":23,"parse_rate":0.9583333333333334,"reason":-0.00768254437773525,"mean_b":0.0130786026906896,"b_gate_pass_rate":0.18461538461538463,"median_len_z":629.0,"mean_r_leg":0.0007421128107800891,"mean_g_leg":0.04369105783789619,"g_bind_frac":0.21739130434782608,"a_match":0.5217391304347826,"a_match_n":23,"a_match_centered":0.0},"text":{"n_turns":349,"n_valid":340,"parse_rate":0.9742120343839542,"reason":-0.0031356847094778277,"mean_b":0.04510961036310114,"b_gate_pass_rate":0.36764705882352944,"median_len_z":735.5,"mean_r_leg":0.008643367078101977,"mean_g_leg":0.05735287625068195,"g_bind_frac":0.21176470588235294,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":277,"n_valid":277,"parse_rate":1.0,"reason":0.0005186566279407478,"mean_b":0.028042442497663776,"b_gate_pass_rate":0.4125615763546798,"median_len_z":477.5,"mean_r_leg":0.007147594797877509,"mean_g_leg":0.07423853643560901,"g_bind_frac":0.19855595667870035,"a_match":0.11504975124378108,"a_match_n":268,"a_match_centered":-0.04752851711026616}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T09:30:40.931438+00:00","challenge_id":"chal-00657","repo":"r2://affine-private-models/models/registrations/107434bb0c5ada8330d1ea19c84f749ada09735bc4fb22bb38a68a2ef9fa0b26/","hotkey":"5FLiDhwAxiZxQu8gzgGHPTMx9gtUfg1whiA7R8yoko3wJaHU","uid":201,"duration_s":2369.3,"revision":"208c6392eadbb1f16de5181f88b2e11df743db3b7666e753b7af78df410beb72","accepted":false,"error_code":null,"error_detail":"","z":-5.521217242306668,"margin":-0.39438672499136607,"se":0.0714311188426627,"n_paired_turns":982,"n_forfeit_turns":19,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":14669411791373494749,"n":1000,"digest":"b62234981b92a450982216a77ba78776d879fcdd0f5bbabe92acce9d777e8e6f","n_paired_turns":982,"n_forfeit_turns":19,"margin":-0.39438672499136607,"se":0.0714311188426627,"z":-5.521217242306668,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.39438672499136607,"se":0.0714311188426627,"z":-5.521217242306668,"sd_diff":2.238428344578075,"n_paired_turns":982,"n_forfeit_turns":19,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.029293292776266636,"A":5.4133550540429045,"Mc":0.15477554625554274},"tool_call":{"R":0.007797198219843503,"A":5.830072339543065,"Mc":0.19994144534511465},"text":{"R":0.043153650282948305,"A":12.884941804045576,"Mc":0.16706438621972391},"terminus_json":{"R":0.001224236345609592,"A":6.343237465983932,"Mc":0.15200349827378812},"boxed":{"R":0.07214421377494908,"A":3.736201522605502,"Mc":0.13064360594404453}},"challenger":{"mean":-1.2701891647341663,"mean_valid":-1.069839999760323,"sd_valid":1.99201386912106,"n_turns":993,"n_valid":964,"n_forfeits":18,"n_unscorable":11,"mean_z_R":0.224687021354458,"mean_typ_c":0.11513878806374964,"mean_z_A":-0.3410164522728582,"bind_frac":{"R":0.2717842323651452,"Gc":0.26141078838174275,"A":0.46680497925311204},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.314219868556994,"mean_R":0.01683367366839123,"mean_A":1.0114436328665153,"mean_mc":-0.823541034266864},"king":{"mean":-0.8758024397428004,"mean_valid":-0.818872053047523,"sd_valid":1.6608442292527041,"n_turns":993,"n_valid":977,"n_forfeits":5,"n_unscorable":11,"mean_z_R":0.23815159344838338,"mean_typ_c":0.6030551243712103,"mean_z_A":-0.26940668174929866,"bind_frac":{"R":0.2865916069600819,"Gc":0.17911975435005117,"A":0.534288638689867},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.318100499927237,"mean_R":0.016931038355807823,"mean_A":1.697304543856754,"mean_mc":-0.7193411173678582}},"rejection_reason":null,"reign_number":null,"score":-0.0010205506388552602,"score_king":0.003157176637970227,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9122052,"blocks_since_crown":18823,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1195.9374572795625,"mean_len_y":578.3844839371155,"n_samples":3000,"think_close_rate":0.9663333333333334,"n_text_fallback":17,"by_dialect":{"tool_call":{"n_turns":277,"zero_ref_turns":5,"mean_refs":2.8736462093862816,"ref_pair_agreement":0.1856060606060606,"ref_pair_n":264},"bash":{"n_turns":330,"zero_ref_turns":2,"mean_refs":2.9212121212121214,"ref_pair_agreement":0.2132505175983437,"ref_pair_n":322},"terminus_json":{"n_turns":24,"zero_ref_turns":0,"mean_refs":2.7083333333333335,"ref_pair_agreement":0.5757575757575757,"ref_pair_n":22},"text":{"n_turns":345,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":24,"zero_ref_turns":0,"mean_refs":2.75,"ref_pair_agreement":0.7936507936507937,"ref_pair_n":21}},"ref_pair_agreement":0.23370429252782193,"ref_pair_n":629},"duel_seconds":1927.4375971606933,"challenger":{"reason":-0.0010205506388552602,"n_turns":993,"n_pairs":2876,"n_forfeits":18,"forfeit_rate":0.01812688821752266,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-19.11581170258359,"mean_len_z":982.289290681502,"median_len_z":568.0,"mean_len_y":425.29937413073714,"mean_b":0.09051531263959692,"b_gate_pass_rate":0.5469401947148818,"mean_r_leg":0.01683367366839123,"mean_g_leg":0.05081178518180435,"g_bind_frac":0.28307692307692306,"a_match":0.16560170394036208,"a_match_n":626,"a_match_centered":-0.05853658536585366,"n_turns_cap_raised":94,"mean_cap_tokens":2171.315206445116,"max_cap_tokens":5098,"len_z_delta":-213.64816659806047,"len_y_delta":-153.0851098063784,"n_samples":996,"think_close_rate":0.9929718875502008,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":328,"n_valid":316,"parse_rate":0.9634146341463414,"reason":0.0031977096260165524,"mean_b":0.12434665213608548,"b_gate_pass_rate":0.9045064377682404,"median_len_z":443.0,"mean_r_leg":0.023416169037878593,"mean_g_leg":0.04745055868501557,"g_bind_frac":0.34177215189873417,"a_match":0.14082278481012658,"a_match_n":316,"a_match_centered":-0.05412647374062165},"boxed":{"n_turns":24,"n_valid":23,"parse_rate":0.9583333333333334,"reason":-0.015378284113393039,"mean_b":1.2489369119243245,"b_gate_pass_rate":0.47619047619047616,"median_len_z":2734.0,"mean_r_leg":0.031207963766865892,"mean_g_leg":0.014400307035836347,"g_bind_frac":0.43478260869565216,"a_match":0.7833333333333333,"a_match_n":20,"a_match_centered":0.0},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.0043894207020696,"mean_b":0.03346747228150665,"b_gate_pass_rate":0.6307692307692307,"median_len_z":739.0,"mean_r_leg":0.0015011400740438817,"mean_g_leg":0.030344982537574054,"g_bind_frac":0.25,"a_match":0.4861111111111111,"a_match_n":24,"a_match_centered":-0.09090909090909091},"text":{"n_turns":345,"n_valid":341,"parse_rate":0.9884057971014493,"reason":-0.0031078970138857603,"mean_b":0.03818378886302392,"b_gate_pass_rate":0.31671554252199413,"median_len_z":705.0,"mean_r_leg":0.01984539044077958,"mean_g_leg":0.04936008316513357,"g_bind_frac":0.2727272727272727,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":272,"n_valid":271,"parse_rate":0.9963235294117647,"reason":-0.00189561086895225,"mean_b":0.030908615642175574,"b_gate_pass_rate":0.4224464060529634,"median_len_z":483.0,"mean_r_leg":0.005506397571922549,"mean_g_leg":0.061460660537851514,"g_bind_frac":0.2177121771217712,"a_match":0.11967418546365914,"a_match_n":266,"a_match_centered":-0.06552162849872774}}},"king":{"reason":0.003157176637970227,"n_turns":993,"n_pairs":2913,"n_forfeits":5,"forfeit_rate":0.005035246727089627,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-18.446478770659073,"mean_len_z":844.3618262959149,"median_len_z":598.0,"mean_len_y":419.5090971507037,"mean_b":0.09646805914314105,"b_gate_pass_rate":0.5403364229316856,"mean_r_leg":0.016931038355807823,"mean_g_leg":0.05690518844869439,"g_bind_frac":0.24696356275303644,"a_match":0.19295478443743427,"a_match_n":634,"a_match_centered":-0.04113247863247863,"n_turns_cap_raised":94,"mean_cap_tokens":2171.315206445116,"max_cap_tokens":5098,"len_z_delta":-351.57563098364767,"len_y_delta":-158.8753867864118,"n_samples":993,"think_close_rate":0.9959718026183283,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":328,"n_valid":327,"parse_rate":0.9969512195121951,"reason":0.00887152161789656,"mean_b":0.13010549046012118,"b_gate_pass_rate":0.8836967808930426,"median_len_z":458.0,"mean_r_leg":0.024960927334853868,"mean_g_leg":0.05008458921971012,"g_bind_frac":0.3211009174311927,"a_match":0.16972477064220184,"a_match_n":327,"a_match_centered":-0.04399585921325051},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.00194554592774628,"mean_b":1.3054009448434973,"b_gate_pass_rate":0.3787878787878788,"median_len_z":2128.5,"mean_r_leg":0.033645447593883354,"mean_g_leg":0.024153747700756713,"g_bind_frac":0.2916666666666667,"a_match":0.746031746031746,"a_match_n":21,"a_match_centered":-0.047619047619047616},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.00462807082543227,"mean_b":0.019808792956952002,"b_gate_pass_rate":0.4307692307692308,"median_len_z":629.0,"mean_r_leg":0.0009760052927310769,"mean_g_leg":0.0397297044088337,"g_bind_frac":0.25,"a_match":0.5833333333333334,"a_match_n":24,"a_match_centered":0.015151515151515148},"text":{"n_turns":345,"n_valid":341,"parse_rate":0.9884057971014493,"reason":0.0007342102169221471,"mean_b":0.041952044819447434,"b_gate_pass_rate":0.3284457478005865,"median_len_z":684.0,"mean_r_leg":0.017981867560744044,"mean_g_leg":0.05805745973829439,"g_bind_frac":0.20821114369501467,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":272,"n_valid":272,"parse_rate":1.0,"reason":0.00047677054438421935,"mean_b":0.031857906053650444,"b_gate_pass_rate":0.41959798994974873,"median_len_z":522.0,"mean_r_leg":0.005893054961575179,"mean_g_leg":0.06806569445248636,"g_bind_frac":0.20220588235294118,"a_match":0.14185750636132313,"a_match_n":262,"a_match_centered":-0.04182754182754183}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T08:49:55.372209+00:00","challenge_id":"chal-00656","repo":"r2://affine-private-models/models/registrations/13c322c2f9c0ec690748217cff17f62f074bd0601178def4de76b27b2a8b9837/","hotkey":"5DdfuhKMn3KG8YAfZx4SdBvDtrAQQmM4BtGHoxBkR5tBXyiv","uid":191,"duration_s":2474.4,"revision":"8412cb52cbbeb412fa6d3c407bddbd8a92de7146da4fb24764d4f02018766332","accepted":false,"error_code":null,"error_detail":"","z":1.118777540638871,"margin":0.049935851057144626,"se":0.04463429881567793,"n_paired_turns":988,"n_forfeit_turns":11,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2050531481908975650,"n":1000,"digest":"c7e5a71e80beaa5313e9d2c35c37fa0072c515ad054f9ac64e33ebd7e6b6a659","n_paired_turns":988,"n_forfeit_turns":11,"margin":0.049935851057144626,"se":0.04463429881567793,"z":1.118777540638871,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.049935851057144626,"se":0.04463429881567793,"z":1.118777540638871,"sd_diff":1.4029661375806695,"n_paired_turns":988,"n_forfeit_turns":11,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.031246461896833444,"A":8.716158484674338,"Mc":0.15905948033540143},"tool_call":{"R":0.008231968836837225,"A":6.85729794515187,"Mc":0.1930686926617814},"text":{"R":0.016003725998007357,"A":14.636149108305059,"Mc":0.19155994214522173},"boxed":{"R":0.08198675210408307,"A":3.222562708999458,"Mc":0.1113543214288209},"terminus_json":{"R":0.0012198412244224556,"A":8.582610575153312,"Mc":0.12985128826046943}},"challenger":{"mean":-0.7722127049649975,"mean_valid":-0.6689950485244306,"sd_valid":1.484674939905222,"n_turns":998,"n_valid":979,"n_forfeits":9,"n_unscorable":10,"mean_z_R":0.1660245633158735,"mean_typ_c":0.6678986739626835,"mean_z_A":-0.16203626367296417,"bind_frac":{"R":0.34831460674157305,"Gc":0.1481103166496425,"A":0.5035750766087844},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.3221039465343524,"mean_R":0.012057801362093645,"mean_A":2.223757101368343,"mean_mc":-0.7102920648258669},"king":{"mean":-0.8221485560221422,"mean_valid":-0.7193899625637145,"sd_valid":1.6124000175839004,"n_turns":998,"n_valid":979,"n_forfeits":9,"n_unscorable":10,"mean_z_R":0.19274543597318325,"mean_typ_c":0.655249595685067,"mean_z_A":-0.22303174810747445,"bind_frac":{"R":0.31869254341164455,"Gc":0.14504596527068436,"A":0.5362614913176711},"n_leg_dropped":{"R":0,"Gc":8,"A":0},"mean_content_share":0.3194727164507587,"mean_R":0.012594790337671136,"mean_A":1.5358630959163284,"mean_mc":-0.7137797973501373}},"rejection_reason":null,"reign_number":null,"score":0.0024915617086238902,"score_king":0.0024912863571266534,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9121838,"blocks_since_crown":18609,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1217.581458759373,"mean_len_y":641.5088616223586,"n_samples":3000,"think_close_rate":0.97,"n_text_fallback":19,"by_dialect":{"text":{"n_turns":350,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":331,"zero_ref_turns":2,"mean_refs":2.903323262839879,"ref_pair_agreement":0.2006172839506173,"ref_pair_n":324},"terminus_json":{"n_turns":22,"zero_ref_turns":0,"mean_refs":2.772727272727273,"ref_pair_agreement":0.4,"ref_pair_n":20},"tool_call":{"n_turns":270,"zero_ref_turns":0,"mean_refs":2.9,"ref_pair_agreement":0.1492921492921493,"ref_pair_n":259},"boxed":{"n_turns":27,"zero_ref_turns":0,"mean_refs":2.925925925925926,"ref_pair_agreement":0.8395061728395062,"ref_pair_n":27}},"ref_pair_agreement":0.21322751322751324,"ref_pair_n":630},"duel_seconds":2110.66929866001,"challenger":{"reason":0.0024915617086238902,"n_turns":998,"n_pairs":2911,"n_forfeits":9,"forfeit_rate":0.009018036072144289,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1711.8351446152856,"mean_len_z":886.7921676399862,"median_len_z":594.0,"mean_len_y":468.5372724149777,"mean_b":0.09952044691944614,"b_gate_pass_rate":0.5400206114737204,"mean_r_leg":0.012057801362093645,"mean_g_leg":0.0609113849423699,"g_bind_frac":0.2275025278058645,"a_match":0.17137624280481423,"a_match_n":637,"a_match_centered":-0.03866666666666667,"n_turns_cap_raised":106,"mean_cap_tokens":2173.3567134268537,"max_cap_tokens":5061,"len_z_delta":-330.7892911193867,"len_y_delta":-172.97158920738093,"n_samples":1001,"think_close_rate":0.994005994005994,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":329,"n_valid":326,"parse_rate":0.9908814589665653,"reason":0.007547622084888577,"mean_b":0.12228959833803521,"b_gate_pass_rate":0.8430962343096234,"median_len_z":514.0,"mean_r_leg":0.019337759129437644,"mean_g_leg":0.05139185295952158,"g_bind_frac":0.26380368098159507,"a_match":0.15541922290388546,"a_match_n":326,"a_match_centered":-0.041407867494824016},"boxed":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.0008217488221397102,"mean_b":1.1901085560776796,"b_gate_pass_rate":0.4050632911392405,"median_len_z":2286.0,"mean_r_leg":0.022153687822004987,"mean_g_leg":0.021758117678864843,"g_bind_frac":0.4074074074074074,"a_match":0.7037037037037037,"a_match_n":27,"a_match_centered":-0.1358024691358025},"terminus_json":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":-0.0035450021789250994,"mean_b":0.019202522161343057,"b_gate_pass_rate":0.3114754098360656,"median_len_z":787.0,"mean_r_leg":0.0015789821074150947,"mean_g_leg":0.04504038611270063,"g_bind_frac":0.22727272727272727,"a_match":0.37878787878787884,"a_match_n":22,"a_match_centered":0.016666666666666663},"text":{"n_turns":350,"n_valid":345,"parse_rate":0.9857142857142858,"reason":0.0011311469607784123,"mean_b":0.05430126413697845,"b_gate_pass_rate":0.36231884057971014,"median_len_z":684.0,"mean_r_leg":0.009950948934902866,"mean_g_leg":0.06894431111864914,"g_bind_frac":0.18840579710144928,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":270,"n_valid":269,"parse_rate":0.9962962962962963,"reason":-0.0010826416698519247,"mean_b":0.027440290778967636,"b_gate_pass_rate":0.4358974358974359,"median_len_z":523.0,"mean_r_leg":0.005781009333885451,"mean_g_leg":0.06737349678608578,"g_bind_frac":0.21561338289962825,"a_match":0.11895674300254452,"a_match_n":262,"a_match_centered":-0.029296875}}},"king":{"reason":0.0024912863571266534,"n_turns":998,"n_pairs":2912,"n_forfeits":9,"forfeit_rate":0.009018036072144289,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1815.8557773833077,"mean_len_z":885.7833104395604,"median_len_z":596.0,"mean_len_y":443.63392857142856,"mean_b":0.0926751606304557,"b_gate_pass_rate":0.507554945054945,"mean_r_leg":0.012594790337671136,"mean_g_leg":0.05941695683358843,"g_bind_frac":0.23053589484327602,"a_match":0.16771488469601678,"a_match_n":636,"a_match_centered":-0.042666666666666665,"n_turns_cap_raised":106,"mean_cap_tokens":2173.3567134268537,"max_cap_tokens":5061,"len_z_delta":-331.7981483198125,"len_y_delta":-197.87493305093005,"n_samples":998,"think_close_rate":0.9959919839679359,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":329,"n_valid":324,"parse_rate":0.9848024316109423,"reason":0.00786989265050157,"mean_b":0.12120802373294093,"b_gate_pass_rate":0.8517350157728707,"median_len_z":478.0,"mean_r_leg":0.02058723029688208,"mean_g_leg":0.049822409305998024,"g_bind_frac":0.2808641975308642,"a_match":0.1574074074074074,"a_match_n":324,"a_match_centered":-0.0375},"boxed":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.0006524979092854189,"mean_b":1.1840661583100318,"b_gate_pass_rate":0.5822784810126582,"median_len_z":2045.0,"mean_r_leg":0.02198810048580509,"mean_g_leg":0.01918842441802461,"g_bind_frac":0.37037037037037035,"a_match":0.6296296296296297,"a_match_n":27,"a_match_centered":-0.20987654320987656},"terminus_json":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":-0.005550594041912259,"mean_b":0.020315818868050284,"b_gate_pass_rate":0.2459016393442623,"median_len_z":899.0,"mean_r_leg":0.001804228849866051,"mean_g_leg":0.04286043440010593,"g_bind_frac":0.18181818181818182,"a_match":0.4090909090909091,"a_match_n":22,"a_match_centered":0.05},"text":{"n_turns":350,"n_valid":346,"parse_rate":0.9885714285714285,"reason":7.156612217055347e-05,"mean_b":0.03411518710364948,"b_gate_pass_rate":0.2947976878612717,"median_len_z":681.0,"mean_r_leg":0.010379623136535584,"mean_g_leg":0.06724061501535944,"g_bind_frac":0.1994219653179191,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":270,"n_valid":270,"parse_rate":1.0,"reason":4.367211892765219e-05,"mean_b":0.03117392275201589,"b_gate_pass_rate":0.384418901660281,"median_len_z":498.0,"mean_r_leg":0.005782458054488361,"mean_g_leg":0.06627644400693421,"g_bind_frac":0.2,"a_match":0.11280101394169835,"a_match_n":263,"a_match_centered":-0.03875968992248062}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T08:07:42.412467+00:00","challenge_id":"chal-00655","repo":"r2://affine-private-models/models/registrations/504efa2095a1e0e2f0e84cb8796d3dceb304bbc428abfcf7f8f8904df06441ad/","hotkey":"5CqrM8RVbW59KHyc9F8UcsdvA3p2tGfRVaSWK4rjHkMK4JHn","uid":47,"duration_s":2471.0,"revision":"8006b3e7a0e38a8eda636590bd0e0d78e734a1db3fe29f64dceff76ca447357a","accepted":false,"error_code":null,"error_detail":"","z":2.4640548615870035,"margin":0.1115462144846334,"se":0.04526937132105522,"n_paired_turns":986,"n_forfeit_turns":6,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":13407698185930671368,"n":1000,"digest":"2f2f2dcf35b0da2822a182a1966bcf69d4fba4ae8889934c7f1d3d03270eca52","n_paired_turns":986,"n_forfeit_turns":6,"margin":0.1115462144846334,"se":0.04526937132105522,"z":2.4640548615870035,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.1115462144846334,"se":0.04526937132105522,"z":2.4640548615870035,"sd_diff":1.421487093183166,"n_paired_turns":986,"n_forfeit_turns":6,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.024358729035783892,"A":5.666601496158431,"Mc":0.16696522812969852},"text":{"R":0.09196254670454188,"A":14.70841198560944,"Mc":0.17649232401893541},"tool_call":{"R":0.00889140832308416,"A":5.733902839180682,"Mc":0.19954647978496537},"boxed":{"R":0.22491906120424987,"A":3.618394710399599,"Mc":0.1376782907629099},"terminus_json":{"R":0.002173735054082248,"A":9.799694894740707,"Mc":0.17634801426608782}},"challenger":{"mean":-0.5332757523647256,"mean_valid":-0.509969402267906,"sd_valid":1.048356175143163,"n_turns":996,"n_valid":984,"n_forfeits":2,"n_unscorable":10,"mean_z_R":0.19293559555638715,"mean_typ_c":0.8486871321033789,"mean_z_A":-0.0650325817418284,"bind_frac":{"R":0.3434959349593496,"Gc":0.1524390243902439,"A":0.5040650406504065},"n_leg_dropped":{"R":0,"Gc":8,"A":0},"mean_content_share":0.32583295411669505,"mean_R":0.018650440427476447,"mean_A":2.8543123018415266,"mean_mc":-0.7095246733643548},"king":{"mean":-0.644821966849359,"mean_valid":-0.5753004686872122,"sd_valid":1.2375201001562393,"n_turns":996,"n_valid":980,"n_forfeits":6,"n_unscorable":10,"mean_z_R":0.17865286634150357,"mean_typ_c":0.7450036012208575,"mean_z_A":-0.10644672137584223,"bind_frac":{"R":0.3306122448979592,"Gc":0.15510204081632653,"A":0.5142857142857142},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.322005118726199,"mean_R":0.01779939035743854,"mean_A":2.445426001445522,"mean_mc":-0.7193585727707337}},"rejection_reason":null,"reign_number":null,"score":0.0032911801475866164,"score_king":0.003037412519544235,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9121627,"blocks_since_crown":18398,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1201.0747790618627,"mean_len_y":616.9401767505099,"n_samples":3000,"think_close_rate":0.973,"n_text_fallback":15,"by_dialect":{"boxed":{"n_turns":18,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.6274509803921569,"ref_pair_n":17},"text":{"n_turns":333,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":292,"zero_ref_turns":0,"mean_refs":2.904109589041096,"ref_pair_agreement":0.24381625441696114,"ref_pair_n":283},"bash":{"n_turns":332,"zero_ref_turns":2,"mean_refs":2.933734939759036,"ref_pair_agreement":0.1946992864424057,"ref_pair_n":327},"terminus_json":{"n_turns":25,"zero_ref_turns":2,"mean_refs":2.68,"ref_pair_agreement":0.4057971014492754,"ref_pair_n":23}},"ref_pair_agreement":0.23487179487179485,"ref_pair_n":650},"duel_seconds":2012.583900400903,"challenger":{"reason":0.0032911801475866164,"n_turns":996,"n_pairs":2936,"n_forfeits":2,"forfeit_rate":0.002008032128514056,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-186.46541253616977,"mean_len_z":921.5275885558583,"median_len_z":662.0,"mean_len_y":410.76805177111714,"mean_b":0.09200629531375364,"b_gate_pass_rate":0.553133514986376,"mean_r_leg":0.018650440427476447,"mean_g_leg":0.0580901142996668,"g_bind_frac":0.23541247484909456,"a_match":0.17307692307692307,"a_match_n":650,"a_match_centered":-0.06110244409776391,"n_turns_cap_raised":97,"mean_cap_tokens":2170.6787148594376,"max_cap_tokens":5063,"len_z_delta":-279.5471905060044,"len_y_delta":-206.17212497939272,"n_samples":999,"think_close_rate":0.997997997997998,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":330,"n_valid":330,"parse_rate":1.0,"reason":0.00842172022271537,"mean_b":0.12665198357780796,"b_gate_pass_rate":0.8501026694045175,"median_len_z":527.0,"mean_r_leg":0.021863496188979828,"mean_g_leg":0.04916933908505151,"g_bind_frac":0.2878787878787879,"a_match":0.1383838383838384,"a_match_n":330,"a_match_centered":-0.05504587155963303},"boxed":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":0.016289701497202897,"mean_b":1.2888706601413968,"b_gate_pass_rate":0.8888888888888888,"median_len_z":1866.5,"mean_r_leg":0.17544828406586246,"mean_g_leg":0.030569895521995297,"g_bind_frac":0.5,"a_match":0.5882352941176471,"a_match_n":17,"a_match_centered":-0.03921568627450981},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0023397223857800752,"mean_b":0.020008576108279354,"b_gate_pass_rate":0.26865671641791045,"median_len_z":544.0,"mean_r_leg":0.0009309598139405701,"mean_g_leg":0.06006634788527359,"g_bind_frac":0.21739130434782608,"a_match":0.46376811594202894,"a_match_n":23,"a_match_centered":0.05797101449275362},"text":{"n_turns":333,"n_valid":331,"parse_rate":0.993993993993994,"reason":0.0012255164000063053,"mean_b":0.05113730931131854,"b_gate_pass_rate":0.3413897280966767,"median_len_z":739.0,"mean_r_leg":0.019176476092015754,"mean_g_leg":0.06148725569082744,"g_bind_frac":0.1661631419939577,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":292,"n_valid":292,"parse_rate":1.0,"reason":-0.0005090760951322325,"mean_b":0.029543057362460202,"b_gate_pass_rate":0.46108490566037735,"median_len_z":697.0,"mean_r_leg":0.006153045435564634,"mean_g_leg":0.06586173274445448,"g_bind_frac":0.23972602739726026,"a_match":0.16488095238095238,"a_match_n":280,"a_match_centered":-0.07968369829683698}}},"king":{"reason":0.003037412519544235,"n_turns":996,"n_pairs":2925,"n_forfeits":6,"forfeit_rate":0.006024096385542169,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-46.55615318595491,"mean_len_z":853.0724786324786,"median_len_z":579.0,"mean_len_y":424.38803418803417,"mean_b":0.08862326015652203,"b_gate_pass_rate":0.5152136752136752,"mean_r_leg":0.01779939035743854,"mean_g_leg":0.05851892935490083,"g_bind_frac":0.23939393939393938,"a_match":0.18509984639016897,"a_match_n":651,"a_match_centered":-0.04698857736240914,"n_turns_cap_raised":97,"mean_cap_tokens":2170.6787148594376,"max_cap_tokens":5063,"len_z_delta":-348.00230042938415,"len_y_delta":-192.5521425624757,"n_samples":996,"think_close_rate":0.9969879518072289,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":330,"n_valid":328,"parse_rate":0.9939393939393939,"reason":0.007577719249061197,"mean_b":0.12451567718477055,"b_gate_pass_rate":0.8223140495867769,"median_len_z":432.0,"mean_r_leg":0.02138893522616437,"mean_g_leg":0.04912633919670745,"g_bind_frac":0.29878048780487804,"a_match":0.17327235772357724,"a_match_n":328,"a_match_centered":-0.01794871794871795},"boxed":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":0.013169229620077223,"mean_b":1.1639923838614104,"b_gate_pass_rate":0.6111111111111112,"median_len_z":1738.5,"mean_r_leg":0.0985667659578706,"mean_g_leg":0.02877014697354056,"g_bind_frac":0.5,"a_match":0.6666666666666667,"a_match_n":17,"a_match_centered":0.0392156862745098},"terminus_json":{"n_turns":23,"n_valid":22,"parse_rate":0.9565217391304348,"reason":-0.007615977000046797,"mean_b":0.018806218933875678,"b_gate_pass_rate":0.23076923076923078,"median_len_z":529.0,"mean_r_leg":0.0012646873177403276,"mean_g_leg":0.05813614021595573,"g_bind_frac":0.2727272727272727,"a_match":0.36363636363636365,"a_match_n":22,"a_match_centered":-0.015151515151515155},"text":{"n_turns":333,"n_valid":330,"parse_rate":0.990990990990991,"reason":0.0014027930986905727,"mean_b":0.05078016826757558,"b_gate_pass_rate":0.3333333333333333,"median_len_z":633.0,"mean_r_leg":0.02160787078962052,"mean_g_leg":0.060628791951401174,"g_bind_frac":0.18787878787878787,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":292,"n_valid":292,"parse_rate":1.0,"reason":-1.5045365576750862e-05,"mean_b":0.028704600116569712,"b_gate_pass_rate":0.392688679245283,"median_len_z":580.0,"mean_r_leg":0.005730148735875036,"mean_g_leg":0.06854774565272136,"g_bind_frac":0.21232876712328766,"a_match":0.15610328638497653,"a_match_n":284,"a_match_centered":-0.08872901678657075}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T06:22:41.774639+00:00","challenge_id":"chal-00654","repo":"r2://affine-private-models/models/registrations/830653331d0ec96e0fab4e7296e1fd23882214f8c7d02b26952eddc985419306/","hotkey":"5HQbUcpq7Ymj8wdmv8pigjkaHjDPMMVX7U2hEoYPNfRq23p9","uid":22,"duration_s":2693.8,"revision":"851c7cecd88d85ff3e19f27cfe53dbaaf7b4e98d859e4801c6f6d94bcf8f2a92","accepted":false,"error_code":null,"error_detail":"","z":-0.34090645181633894,"margin":-0.0229111961202049,"se":0.06720669555573021,"n_paired_turns":984,"n_forfeit_turns":18,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2113585838041496821,"n":1000,"digest":"c4acfaac50cfd60f7179ae49e3dc9c356bb9f5e5e44599d8e3f9ffdfaa237d70","n_paired_turns":984,"n_forfeit_turns":18,"margin":-0.0229111961202049,"se":0.06720669555573021,"z":-0.34090645181633894,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.0229111961202049,"se":0.06720669555573021,"z":-0.34090645181633894,"sd_diff":2.10819166317493,"n_paired_turns":984,"n_forfeit_turns":18,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"tool_call":{"R":0.008398207119794176,"A":6.197599926579101,"Mc":0.19965877524787604},"bash":{"R":0.03000375560434994,"A":5.473159050853688,"Mc":0.16787194102569572},"text":{"R":0.24115559901972014,"A":7.847519213616178,"Mc":0.18016849364347265},"terminus_json":{"R":0.001743841532213698,"A":8.52708066858897,"Mc":0.16808231006685678},"boxed":{"R":0.15392795036947735,"A":3.4277149453225437,"Mc":0.12904280709786847}},"challenger":{"mean":-0.9563170317453372,"mean_valid":-0.7507469247871326,"sd_valid":1.8294562698763273,"n_turns":996,"n_valid":967,"n_forfeits":18,"n_unscorable":11,"mean_z_R":0.1572157105555948,"mean_typ_c":0.7353116474104867,"mean_z_A":-0.20358895433334812,"bind_frac":{"R":0.38055842812823165,"Gc":0.13650465356773525,"A":0.48293691830403307},"n_leg_dropped":{"R":0,"Gc":0,"A":0},"mean_content_share":0.3315304072427425,"mean_R":0.01986935132626044,"mean_A":2.5462514343359537,"mean_mc":-0.6589231971678091},"king":{"mean":-0.922182580576093,"mean_valid":-0.842812343180016,"sd_valid":1.6692166502944585,"n_turns":996,"n_valid":977,"n_forfeits":7,"n_unscorable":12,"mean_z_R":0.15030526227017554,"mean_typ_c":0.716696459106177,"mean_z_A":-0.32315505430877395,"bind_frac":{"R":0.3500511770726714,"Gc":0.14329580348004095,"A":0.5066530194472876},"n_leg_dropped":{"R":0,"Gc":2,"A":0},"mean_content_share":0.32472981739062756,"mean_R":0.01957146240121171,"mean_A":1.5766261265543282,"mean_mc":-0.6929312914698859}},"rejection_reason":null,"reign_number":null,"score":0.002756571925064132,"score_king":0.002847625376165318,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9121084,"blocks_since_crown":17855,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1156.8013651877134,"mean_len_y":648.5440273037543,"n_samples":3000,"think_close_rate":0.9666666666666667,"n_text_fallback":19,"by_dialect":{"text":{"n_turns":356,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":292,"zero_ref_turns":2,"mean_refs":2.8801369863013697,"ref_pair_agreement":0.19464720194647203,"ref_pair_n":274},"bash":{"n_turns":299,"zero_ref_turns":2,"mean_refs":2.8862876254180603,"ref_pair_agreement":0.18543799772468716,"ref_pair_n":293},"terminus_json":{"n_turns":21,"zero_ref_turns":0,"mean_refs":2.9523809523809526,"ref_pair_agreement":0.4920634920634921,"ref_pair_n":21},"boxed":{"n_turns":32,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.611111111111111,"ref_pair_n":30}},"ref_pair_agreement":0.22060409924487595,"ref_pair_n":618},"duel_seconds":2199.464577694889,"challenger":{"reason":0.002756571925064132,"n_turns":996,"n_pairs":2883,"n_forfeits":18,"forfeit_rate":0.018072289156626505,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-0.4437316245232129,"mean_len_z":944.1366631980576,"median_len_z":497.0,"mean_len_y":504.75754422476587,"mean_b":0.09485435776384155,"b_gate_pass_rate":0.4616718695802983,"mean_r_leg":0.01986935132626044,"mean_g_leg":0.06062211071274325,"g_bind_frac":0.23824130879345604,"a_match":0.19687162891046384,"a_match_n":618,"a_match_centered":-0.0165016501650165,"n_turns_cap_raised":91,"mean_cap_tokens":2171.4317269076305,"max_cap_tokens":5113,"len_z_delta":-212.66470198965578,"len_y_delta":-143.78648307898845,"n_samples":999,"think_close_rate":0.982982982982983,"n_text_fallback":8,"by_dialect":{"bash":{"n_turns":297,"n_valid":293,"parse_rate":0.9865319865319865,"reason":0.007688852636856598,"mean_b":0.11388495717780998,"b_gate_pass_rate":0.7883040935672515,"median_len_z":388.0,"mean_r_leg":0.02463480388221476,"mean_g_leg":0.05116872301407116,"g_bind_frac":0.3003412969283277,"a_match":0.18031854379977244,"a_match_n":293,"a_match_centered":0.0017241379310344823},"boxed":{"n_turns":32,"n_valid":31,"parse_rate":0.96875,"reason":0.013620462123886958,"mean_b":1.238219403034229,"b_gate_pass_rate":0.2903225806451613,"median_len_z":2209.0,"mean_r_leg":0.09783341574823189,"mean_g_leg":0.03500842159137857,"g_bind_frac":0.5161290322580645,"a_match":0.6091954022988506,"a_match_n":29,"a_match_centered":0.011494252873563215},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":-0.004610443693443167,"mean_b":0.022704928485679083,"b_gate_pass_rate":0.3870967741935484,"median_len_z":515.0,"mean_r_leg":0.0012974526254238767,"mean_g_leg":0.04913184574323454,"g_bind_frac":0.23809523809523808,"a_match":0.5,"a_match_n":21,"a_match_centered":0.007936507936507934},"text":{"n_turns":356,"n_valid":348,"parse_rate":0.9775280898876404,"reason":0.0011743188194979044,"mean_b":0.03650120261006059,"b_gate_pass_rate":0.27011494252873564,"median_len_z":670.5,"mean_r_leg":0.02149509064839601,"mean_g_leg":0.06547903039252052,"g_bind_frac":0.1867816091954023,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":290,"n_valid":285,"parse_rate":0.9827586206896551,"reason":-0.0010177122962960847,"mean_b":0.025843316613907125,"b_gate_pass_rate":0.390832328106152,"median_len_z":416.0,"mean_r_leg":0.0058731723530627495,"mean_g_leg":0.06804300360492017,"g_bind_frac":0.20701754385964913,"a_match":0.14787878787878786,"a_match_n":275,"a_match_centered":-0.041353383458646614}}},"king":{"reason":0.002847625376165318,"n_turns":996,"n_pairs":2911,"n_forfeits":7,"forfeit_rate":0.007028112449799197,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":2.4906073199619745,"mean_len_z":856.6942631398146,"median_len_z":592.0,"mean_len_y":476.63689453795945,"mean_b":0.09861143729381633,"b_gate_pass_rate":0.4994847131569907,"mean_r_leg":0.01957146240121171,"mean_g_leg":0.05976207030327656,"g_bind_frac":0.24974721941354905,"a_match":0.18786433492315843,"a_match_n":629,"a_match_centered":-0.028501628664495113,"n_turns_cap_raised":91,"mean_cap_tokens":2171.4317269076305,"max_cap_tokens":5113,"len_z_delta":-300.1071020478988,"len_y_delta":-171.90713276579487,"n_samples":996,"think_close_rate":0.9949799196787149,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":297,"n_valid":295,"parse_rate":0.9932659932659933,"reason":0.008952854167923963,"mean_b":0.11810481925710581,"b_gate_pass_rate":0.819557625145518,"median_len_z":475.0,"mean_r_leg":0.023588660696523767,"mean_g_leg":0.05139022928383768,"g_bind_frac":0.3389830508474576,"a_match":0.15480225988700563,"a_match_n":295,"a_match_centered":-0.02625570776255708},"boxed":{"n_turns":32,"n_valid":32,"parse_rate":1.0,"reason":0.016437336346127828,"mean_b":1.335735697420244,"b_gate_pass_rate":0.65625,"median_len_z":1710.5,"mean_r_leg":0.0672279951201629,"mean_g_leg":0.03469719020296944,"g_bind_frac":0.40625,"a_match":0.6666666666666666,"a_match_n":30,"a_match_centered":0.05555555555555555},"terminus_json":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":-0.010102973724901059,"mean_b":0.019699076743929053,"b_gate_pass_rate":0.3387096774193548,"median_len_z":531.0,"mean_r_leg":0.001693957200990492,"mean_g_leg":0.03841179814415361,"g_bind_frac":0.3333333333333333,"a_match":0.46825396825396826,"a_match_n":21,"a_match_centered":-0.023809523809523808},"text":{"n_turns":356,"n_valid":351,"parse_rate":0.9859550561797753,"reason":-0.0006081413605782742,"mean_b":0.031543819958207195,"b_gate_pass_rate":0.30484330484330485,"median_len_z":701.0,"mean_r_leg":0.024274137032942737,"mean_g_leg":0.06191583770189166,"g_bind_frac":0.19658119658119658,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":290,"n_valid":290,"parse_rate":1.0,"reason":0.0002755282631032316,"mean_b":0.027274960872754165,"b_gate_pass_rate":0.4102259215219976,"median_len_z":489.0,"mean_r_leg":0.0058290702265343325,"mean_g_leg":0.06998328624249028,"g_bind_frac":0.2,"a_match":0.15076560659599528,"a_match_n":283,"a_match_centered":-0.04059040590405904}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T05:09:45.336516+00:00","challenge_id":"chal-00653","repo":"r2://affine-private-models/models/registrations/1f1780d325e7d5ec07e20b4cd96339788c706c9ca64aa2a15c5a680cd2793865/","hotkey":"5FvkFNeTbmoGe7qDcMQKWhkjyqgiZT3S9Fu1YidLDTN1qcn7","uid":40,"duration_s":2456.7,"revision":"014501c727a412b093df182063dbdd91cbe368e2fd8dc78d13a16b5761e3ed72","accepted":false,"error_code":null,"error_detail":"","z":3.546785512335692,"margin":0.1855007852278121,"se":0.05230110041406277,"n_paired_turns":984,"n_forfeit_turns":10,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":7726417605947688779,"n":1000,"digest":"8f7ea42d09b9bab206ec2d027c84cdf200569e8dad6cd7d398aedd4ccf6193c7","n_paired_turns":984,"n_forfeit_turns":10,"margin":0.1855007852278121,"se":0.05230110041406277,"z":3.546785512335692,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.1855007852278121,"se":0.05230110041406277,"z":3.546785512335692,"sd_diff":1.6406214136264123,"n_paired_turns":984,"n_forfeit_turns":10,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.021408648816551235,"A":6.663679202643804,"Mc":0.15560019418940896},"text":{"R":0.04265748368321107,"A":18.645536716368806,"Mc":0.1741460869130407},"tool_call":{"R":0.007512038965943534,"A":5.865111251472678,"Mc":0.18483781631832558},"boxed":{"R":0.09260822614899201,"A":4.468802609975276,"Mc":0.12472922331766867},"terminus_json":{"R":0.0026017383441356897,"A":10.121577692407602,"Mc":0.14855215154952472}},"challenger":{"mean":-0.5766132916910475,"mean_valid":-0.5065311646462073,"sd_valid":1.116433048648557,"n_turns":995,"n_valid":978,"n_forfeits":6,"n_unscorable":11,"mean_z_R":0.2693930219775758,"mean_typ_c":0.8233635013747865,"mean_z_A":-0.06577268789140607,"bind_frac":{"R":0.3323108384458078,"Gc":0.13496932515337423,"A":0.532719836400818},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.3213313549649139,"mean_R":0.014989241061827112,"mean_A":2.1719343008567544,"mean_mc":-0.6674960250392297},"king":{"mean":-0.7621140769188596,"mean_valid":-0.6700002578772108,"sd_valid":1.3626218138796695,"n_turns":995,"n_valid":976,"n_forfeits":8,"n_unscorable":11,"mean_z_R":0.12873375875944995,"mean_typ_c":0.6687987207708642,"mean_z_A":-0.1517966748751787,"bind_frac":{"R":0.3237704918032787,"Gc":0.17008196721311475,"A":0.5061475409836066},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.3275922876558107,"mean_R":0.01138720767833195,"mean_A":1.511450420727325,"mean_mc":-0.6937430441794037}},"rejection_reason":null,"reign_number":null,"score":0.002973823596820846,"score_king":0.001040358526072027,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9120739,"blocks_since_crown":17510,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1153.5526046986722,"mean_len_y":648.2339121552604,"n_samples":3000,"think_close_rate":0.97,"n_text_fallback":30,"by_dialect":{"text":{"n_turns":350,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":312,"zero_ref_turns":3,"mean_refs":2.894230769230769,"ref_pair_agreement":0.17049180327868851,"ref_pair_n":305},"tool_call":{"n_turns":295,"zero_ref_turns":1,"mean_refs":2.91864406779661,"ref_pair_agreement":0.1956521739130435,"ref_pair_n":276},"terminus_json":{"n_turns":25,"zero_ref_turns":1,"mean_refs":2.76,"ref_pair_agreement":0.5072463768115941,"ref_pair_n":23},"boxed":{"n_turns":18,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.5882352941176471,"ref_pair_n":17}},"ref_pair_agreement":0.2055823939881911,"ref_pair_n":621},"duel_seconds":2005.4621375752613,"challenger":{"reason":0.002973823596820846,"n_turns":995,"n_pairs":2921,"n_forfeits":6,"forfeit_rate":0.006030150753768844,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":4.2383374267368366,"mean_len_z":932.7141389934953,"median_len_z":666.0,"mean_len_y":349.5302978432044,"mean_b":0.08494491984823781,"b_gate_pass_rate":0.5655597398151319,"mean_r_leg":0.014989241061827112,"mean_g_leg":0.060417319326567104,"g_bind_frac":0.21840242669362994,"a_match":0.14360587002096437,"a_match_n":636,"a_match_centered":-0.05967741935483871,"n_turns_cap_raised":90,"mean_cap_tokens":2164.5618090452263,"max_cap_tokens":5037,"len_z_delta":-220.83846570517687,"len_y_delta":-298.70361431205606,"n_samples":998,"think_close_rate":0.9949899799599199,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":309,"n_valid":308,"parse_rate":0.9967637540453075,"reason":0.009212306787967339,"mean_b":0.11575114738468724,"b_gate_pass_rate":0.8669623059866962,"median_len_z":539.0,"mean_r_leg":0.01919292698692682,"mean_g_leg":0.04990570903662276,"g_bind_frac":0.2727272727272727,"a_match":0.10606060606060605,"a_match_n":308,"a_match_centered":-0.0633879781420765},"boxed":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":0.007528802194217771,"mean_b":1.1721236181800614,"b_gate_pass_rate":0.7222222222222222,"median_len_z":1536.0,"mean_r_leg":0.05976498207334702,"mean_g_leg":0.03350577173560515,"g_bind_frac":0.3888888888888889,"a_match":0.6470588235294118,"a_match_n":17,"a_match_centered":0.058823529411764705},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.0051187632521463656,"mean_b":0.020372348875646495,"b_gate_pass_rate":0.17391304347826086,"median_len_z":886.0,"mean_r_leg":0.0010037408406960325,"mean_g_leg":0.047731695748913346,"g_bind_frac":0.3333333333333333,"a_match":0.3611111111111111,"a_match_n":24,"a_match_centered":-0.13043478260869565},"text":{"n_turns":350,"n_valid":345,"parse_rate":0.9857142857142858,"reason":-0.0006069916694066452,"mean_b":0.04997110488582693,"b_gate_pass_rate":0.37681159420289856,"median_len_z":792.0,"mean_r_leg":0.01680158091734189,"mean_g_leg":0.061704096754582195,"g_bind_frac":0.17391304347826086,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":294,"n_valid":294,"parse_rate":1.0,"reason":0.0010616688578324927,"mean_b":0.03170280479063988,"b_gate_pass_rate":0.49825783972125437,"median_len_z":563.0,"mean_r_leg":0.006858955864604249,"mean_g_leg":0.07260269544608636,"g_bind_frac":0.19387755102040816,"a_match":0.13588850174216027,"a_match_n":287,"a_match_centered":-0.05696969696969697}}},"king":{"reason":0.001040358526072027,"n_turns":995,"n_pairs":2915,"n_forfeits":8,"forfeit_rate":0.008040201005025126,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":9.526074022616498,"mean_len_z":827.6085763293311,"median_len_z":560.0,"mean_len_y":428.50394511149227,"mean_b":0.07831056755342472,"b_gate_pass_rate":0.4909090909090909,"mean_r_leg":0.01138720767833195,"mean_g_leg":0.059439606189820145,"g_bind_frac":0.2198581560283688,"a_match":0.17726550079491257,"a_match_n":629,"a_match_centered":-0.02404105888708806,"n_turns_cap_raised":90,"mean_cap_tokens":2164.5618090452263,"max_cap_tokens":5037,"len_z_delta":-325.94402836934114,"len_y_delta":-219.72996704376817,"n_samples":995,"think_close_rate":0.9939698492462311,"n_text_fallback":8,"by_dialect":{"bash":{"n_turns":309,"n_valid":307,"parse_rate":0.9935275080906149,"reason":0.00642382826608209,"mean_b":0.11626859599382776,"b_gate_pass_rate":0.8776418242491657,"median_len_z":448.0,"mean_r_leg":0.0170507056737478,"mean_g_leg":0.048268747417550426,"g_bind_frac":0.2899022801302932,"a_match":0.16558089033659065,"a_match_n":307,"a_match_centered":-0.003837719298245615},"boxed":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":0.007430527581458812,"mean_b":1.1304303509582798,"b_gate_pass_rate":0.7777777777777778,"median_len_z":1588.5,"mean_r_leg":0.05282622442848553,"mean_g_leg":0.0290709417039428,"g_bind_frac":0.3888888888888889,"a_match":0.6875,"a_match_n":16,"a_match_centered":0.0625},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.011397091134556763,"mean_b":0.016004405206200244,"b_gate_pass_rate":0.14492753623188406,"median_len_z":586.0,"mean_r_leg":0.0011821933944178786,"mean_g_leg":0.042301451913932184,"g_bind_frac":0.2916666666666667,"a_match":0.513888888888889,"a_match_n":24,"a_match_centered":0.028985507246376805},"text":{"n_turns":350,"n_valid":344,"parse_rate":0.9828571428571429,"reason":-0.001776913701988024,"mean_b":0.03765651517534506,"b_gate_pass_rate":0.25872093023255816,"median_len_z":689.5,"mean_r_leg":0.00998535689100889,"mean_g_leg":0.0605265302681486,"g_bind_frac":0.1686046511627907,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":294,"n_valid":294,"parse_rate":1.0,"reason":-0.0006398153548258053,"mean_b":0.026412044190303,"b_gate_pass_rate":0.37514518002322883,"median_len_z":497.0,"mean_r_leg":0.005409523418323919,"mean_g_leg":0.07309097837862599,"g_bind_frac":0.19047619047619047,"a_match":0.13238770685579196,"a_match_n":282,"a_match_centered":-0.0559610705596107}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T03:59:26.947857+00:00","challenge_id":"chal-00652","repo":"r2://affine-private-models/models/registrations/15844370ff97c4087f6e4cd65fd81fcd92f538c1871412504a0c2325654c4f07/","hotkey":"5DBinDGJogYTcQWtRthte3nbk7ddtTuCPyHJnY5Qd9smnvbR","uid":38,"duration_s":2449.5,"revision":"4bd01ad01813b6513666f16efe4250721bf653324110d6a0d2b3b624fb0cce16","accepted":false,"error_code":null,"error_detail":"","z":4.06850220224706,"margin":0.1739529276398668,"se":0.04275601167028778,"n_paired_turns":985,"n_forfeit_turns":6,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":18273617656338630578,"n":1000,"digest":"b579276ac02f99a1a368766f0af41fa6f58edacb7d05090a5bb2df24fefa3765","n_paired_turns":985,"n_forfeit_turns":6,"margin":0.1739529276398668,"se":0.04275601167028778,"z":4.06850220224706,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.1739529276398668,"se":0.04275601167028778,"z":4.06850220224706,"sd_diff":1.3418850121901422,"n_paired_turns":985,"n_forfeit_turns":6,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02312645583463491,"A":5.757368225396595,"Mc":0.15412141366980772},"text":{"R":0.033970547557445795,"A":13.060141325064984,"Mc":0.16997529451059418},"tool_call":{"R":0.006167887565735767,"A":5.82516910081772,"Mc":0.2006234631104481},"terminus_json":{"R":0.0019923073767705995,"A":7.5657096969491,"Mc":0.12806354130501105},"boxed":{"R":0.1324153956553314,"A":5.672067355397522,"Mc":0.09069282775465838}},"challenger":{"mean":-0.6413651354926859,"mean_valid":-0.5950506202449497,"sd_valid":1.3377805398132923,"n_turns":995,"n_valid":981,"n_forfeits":4,"n_unscorable":10,"mean_z_R":0.374175939650577,"mean_typ_c":0.7763571641528741,"mean_z_A":-0.16782789633824285,"bind_frac":{"R":0.308868501529052,"Gc":0.14780835881753313,"A":0.5433231396534148},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.32552769383675884,"mean_R":0.017172097118579106,"mean_A":2.1863573851947438,"mean_mc":-0.6731112497513971},"king":{"mean":-0.8153180631325527,"mean_valid":-0.758253359373025,"sd_valid":1.5885542734388476,"n_turns":995,"n_valid":980,"n_forfeits":5,"n_unscorable":10,"mean_z_R":0.2809421762394601,"mean_typ_c":0.5935950091431305,"mean_z_A":-0.22691303110623068,"bind_frac":{"R":0.28877551020408165,"Gc":0.16938775510204082,"A":0.5418367346938775},"n_leg_dropped":{"R":0,"Gc":2,"A":0},"mean_content_share":0.3168326441498131,"mean_R":0.015479907317088057,"mean_A":1.632792186367257,"mean_mc":-0.719339165894025}},"rejection_reason":null,"reign_number":null,"score":0.0035782114318192973,"score_king":0.0026203708283479986,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9120388,"blocks_since_crown":17159,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1211.9262155729343,"mean_len_y":612.8820129207752,"n_samples":3000,"think_close_rate":0.971,"n_text_fallback":20,"by_dialect":{"text":{"n_turns":337,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":328,"zero_ref_turns":2,"mean_refs":2.902439024390244,"ref_pair_agreement":0.165625,"ref_pair_n":320},"tool_call":{"n_turns":276,"zero_ref_turns":1,"mean_refs":2.931159420289855,"ref_pair_agreement":0.18434343434343434,"ref_pair_n":264},"boxed":{"n_turns":31,"zero_ref_turns":1,"mean_refs":2.870967741935484,"ref_pair_agreement":0.7444444444444444,"ref_pair_n":30},"terminus_json":{"n_turns":28,"zero_ref_turns":1,"mean_refs":2.857142857142857,"ref_pair_agreement":0.4938271604938272,"ref_pair_n":27}},"ref_pair_agreement":0.21424856994279773,"ref_pair_n":641},"duel_seconds":2050.0558684188873,"challenger":{"reason":0.0035782114318192973,"n_turns":995,"n_pairs":2930,"n_forfeits":4,"forfeit_rate":0.004020100502512563,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-21.587838290605706,"mean_len_z":797.822866894198,"median_len_z":587.0,"mean_len_y":336.30546075085323,"mean_b":0.10901246672490737,"b_gate_pass_rate":0.6040955631399317,"mean_r_leg":0.017172097118579106,"mean_g_leg":0.05749449652294253,"g_bind_frac":0.2330978809283552,"a_match":0.17024539877300612,"a_match_n":652,"a_match_centered":-0.042708333333333334,"n_turns_cap_raised":95,"mean_cap_tokens":2180.9477386934673,"max_cap_tokens":5110,"len_z_delta":-414.1033486787363,"len_y_delta":-276.57655216992197,"n_samples":998,"think_close_rate":0.996993987975952,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":326,"n_valid":326,"parse_rate":1.0,"reason":0.00971003653002863,"mean_b":0.12753553607257037,"b_gate_pass_rate":0.8613445378151261,"median_len_z":462.5,"mean_r_leg":0.02307577450273629,"mean_g_leg":0.050852679785429025,"g_bind_frac":0.29754601226993865,"a_match":0.12269938650306748,"a_match_n":326,"a_match_centered":-0.04375},"boxed":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":0.007551252907256033,"mean_b":1.378012008123372,"b_gate_pass_rate":0.8314606741573034,"median_len_z":1632.0,"mean_r_leg":0.0975319017136514,"mean_g_leg":0.024020520903056293,"g_bind_frac":0.4666666666666667,"a_match":0.5555555555555556,"a_match_n":30,"a_match_centered":-0.1888888888888889},"terminus_json":{"n_turns":27,"n_valid":26,"parse_rate":0.9629629629629629,"reason":-0.009681632719817776,"mean_b":0.018658528551279724,"b_gate_pass_rate":0.38461538461538464,"median_len_z":641.0,"mean_r_leg":0.0009978454713856783,"mean_g_leg":0.03338834942452001,"g_bind_frac":0.2692307692307692,"a_match":0.5,"a_match_n":26,"a_match_centered":-0.01282051282051282},"text":{"n_turns":337,"n_valid":334,"parse_rate":0.9910979228486647,"reason":0.0007451630090354906,"mean_b":0.0500468077469902,"b_gate_pass_rate":0.46706586826347307,"median_len_z":727.5,"mean_r_leg":0.013980128600606356,"mean_g_leg":0.0623189033635535,"g_bind_frac":0.17065868263473055,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":275,"n_valid":275,"parse_rate":1.0,"reason":0.0006494364656120206,"mean_b":0.029353970148859678,"b_gate_pass_rate":0.4672435105067985,"median_len_z":474.0,"mean_r_leg":0.0068130246194609825,"mean_g_leg":0.0654394400313822,"g_bind_frac":0.20363636363636364,"a_match":0.15308641975308643,"a_match_n":270,"a_match_centered":-0.02777777777777778}}},"king":{"reason":0.0026203708283479986,"n_turns":995,"n_pairs":2926,"n_forfeits":5,"forfeit_rate":0.005025125628140704,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-19.507844874104222,"mean_len_z":824.556049213944,"median_len_z":566.0,"mean_len_y":434.79904306220095,"mean_b":0.10285964391227839,"b_gate_pass_rate":0.5116199589883801,"mean_r_leg":0.015479907317088057,"mean_g_leg":0.05614398164074179,"g_bind_frac":0.23737373737373738,"a_match":0.18,"a_match_n":650,"a_match_centered":-0.033437826541274814,"n_turns_cap_raised":95,"mean_cap_tokens":2180.9477386934673,"max_cap_tokens":5110,"len_z_delta":-387.37016635899033,"len_y_delta":-178.08296985857424,"n_samples":995,"think_close_rate":0.9949748743718593,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":326,"n_valid":326,"parse_rate":1.0,"reason":0.008016657022705131,"mean_b":0.12197359984987181,"b_gate_pass_rate":0.8361344537815126,"median_len_z":437.0,"mean_r_leg":0.020355831439863768,"mean_g_leg":0.048984285516654,"g_bind_frac":0.29141104294478526,"a_match":0.14468302658486706,"a_match_n":326,"a_match_centered":-0.021354166666666667},"boxed":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":0.007936743152450371,"mean_b":1.3485168261562048,"b_gate_pass_rate":0.5393258426966292,"median_len_z":2045.0,"mean_r_leg":0.08738100717775907,"mean_g_leg":0.024975068945464786,"g_bind_frac":0.4666666666666667,"a_match":0.6333333333333333,"a_match_n":30,"a_match_centered":-0.11111111111111112},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.0037248955774842425,"mean_b":0.013324891663453456,"b_gate_pass_rate":0.225,"median_len_z":639.0,"mean_r_leg":0.0007416924696398089,"mean_g_leg":0.03646668704632166,"g_bind_frac":0.25925925925925924,"a_match":0.5,"a_match_n":27,"a_match_centered":0.00617283950617284},"text":{"n_turns":337,"n_valid":333,"parse_rate":0.9881305637982196,"reason":-0.0008466193914143489,"mean_b":0.040452809993279375,"b_gate_pass_rate":0.3303303303303303,"median_len_z":697.0,"mean_r_leg":0.013300415682158171,"mean_g_leg":0.059058498824226494,"g_bind_frac":0.21921921921921922,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":275,"n_valid":274,"parse_rate":0.9963636363636363,"reason":0.0005149796571984909,"mean_b":0.028972834970203483,"b_gate_pass_rate":0.3784119106699752,"median_len_z":465.0,"mean_r_leg":0.005907346205656461,"mean_g_leg":0.06647201466723765,"g_bind_frac":0.1678832116788321,"a_match":0.13982521847690388,"a_match_n":267,"a_match_centered":-0.04342273307790549}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T03:17:48.706911+00:00","challenge_id":"chal-00651","repo":"r2://affine-private-models/models/registrations/ce465847a9bd07d82efb3b20c7aa6af4b48d45e2cb2b9718a7ce1cb1c9ffd39e/","hotkey":"5HcsAAEwqBVUiAV6VB7S45r1xNNqLRjH8f9EBL4RP3NCLhAp","uid":37,"duration_s":2405.4,"revision":"38315427122df3a50a93326fc52627d3aace7eb6992d162213be32adb94dc7cf","accepted":false,"error_code":null,"error_detail":"","z":3.4470808207102,"margin":0.1657237560688134,"se":0.04807655076525576,"n_paired_turns":993,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":16513594182857841481,"n":1000,"digest":"080f58550b9a056812f1a5d9f8ec73454f60132bbbcad129ad75351b3c3bcb18","n_paired_turns":993,"n_forfeit_turns":5,"margin":0.1657237560688134,"se":0.04807655076525576,"z":3.4470808207102,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.1657237560688134,"se":0.04807655076525576,"z":3.4470808207102,"sd_diff":1.5149835808845666,"n_paired_turns":993,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"tool_call":{"R":0.008527042667131715,"A":5.463288428516139,"Mc":0.19087013120932136},"text":{"R":0.043378979006066,"A":11.132186236303797,"Mc":0.15980490809911133},"bash":{"R":0.021239913342705787,"A":5.715106990445496,"Mc":0.15779013861894473},"terminus_json":{"R":0.001498654371776795,"A":15.859859517116393,"Mc":0.15985597350329922},"boxed":{"R":0.16333001009610829,"A":4.67274615319273,"Mc":0.1282110513836484}},"challenger":{"mean":-0.6917872425082385,"mean_valid":-0.6803878344865735,"sd_valid":1.23516411559465,"n_turns":996,"n_valid":992,"n_forfeits":1,"n_unscorable":3,"mean_z_R":0.19391488473225463,"mean_typ_c":0.7894218508536484,"mean_z_A":-0.2662114342446702,"bind_frac":{"R":0.3084677419354839,"Gc":0.1381048387096774,"A":0.5534274193548387},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.3285897804436474,"mean_R":0.01536855705759659,"mean_A":2.348476816069104,"mean_mc":-0.6744951169837051},"king":{"mean":-0.8575109985770519,"mean_valid":-0.8011218841973812,"sd_valid":1.4083276700024028,"n_turns":996,"n_valid":988,"n_forfeits":5,"n_unscorable":3,"mean_z_R":0.21451878992439602,"mean_typ_c":0.6484862950097571,"mean_z_A":-0.3107222608441189,"bind_frac":{"R":0.3006072874493927,"Gc":0.14878542510121456,"A":0.5506072874493927},"n_leg_dropped":{"R":0,"Gc":6,"A":0},"mean_content_share":0.32304396503716304,"mean_R":0.016741379177557747,"mean_A":1.960154155016224,"mean_mc":-0.7001494158582997}},"rejection_reason":null,"reign_number":null,"score":0.0037433615478371903,"score_king":0.0024502849461363603,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9120183,"blocks_since_crown":16954,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1146.3025693035836,"mean_len_y":594.5331304935768,"n_samples":3000,"think_close_rate":0.978,"n_text_fallback":20,"by_dialect":{"tool_call":{"n_turns":276,"zero_ref_turns":1,"mean_refs":2.9456521739130435,"ref_pair_agreement":0.18476903870162298,"ref_pair_n":267},"text":{"n_turns":334,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":336,"zero_ref_turns":1,"mean_refs":2.9583333333333335,"ref_pair_agreement":0.1506986027944112,"ref_pair_n":334},"boxed":{"n_turns":30,"zero_ref_turns":0,"mean_refs":2.9,"ref_pair_agreement":0.6428571428571429,"ref_pair_n":28},"terminus_json":{"n_turns":24,"zero_ref_turns":2,"mean_refs":2.5833333333333335,"ref_pair_agreement":0.37878787878787884,"ref_pair_n":22}},"ref_pair_agreement":0.1935483870967742,"ref_pair_n":651},"duel_seconds":2052.9436979237944,"challenger":{"reason":0.0037433615478371903,"n_turns":996,"n_pairs":2955,"n_forfeits":1,"forfeit_rate":0.001004016064257028,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-2.644278406814892,"mean_len_z":776.6582064297801,"median_len_z":586.0,"mean_len_y":348.82030456852794,"mean_b":0.1064522419811563,"b_gate_pass_rate":0.6328257191201354,"mean_r_leg":0.01536855705759659,"mean_g_leg":0.05716685691857817,"g_bind_frac":0.21708542713567838,"a_match":0.15089058524173027,"a_match_n":655,"a_match_centered":-0.044802867383512544,"n_turns_cap_raised":90,"mean_cap_tokens":2162.2088353413656,"max_cap_tokens":4898,"len_z_delta":-369.6443628738035,"len_y_delta":-245.71282592504883,"n_samples":999,"think_close_rate":0.998998998998999,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":335,"n_valid":335,"parse_rate":1.0,"reason":0.00885448744454611,"mean_b":0.11640760728319739,"b_gate_pass_rate":0.8591549295774648,"median_len_z":462.0,"mean_r_leg":0.01940581382854116,"mean_g_leg":0.047692765716497956,"g_bind_frac":0.25671641791044775,"a_match":0.11144278606965174,"a_match_n":335,"a_match_centered":-0.038922155688622756},"boxed":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":0.00921657531761077,"mean_b":1.3890974796230804,"b_gate_pass_rate":0.7931034482758621,"median_len_z":1303.0,"mean_r_leg":0.10359493305123933,"mean_g_leg":0.022798923430153224,"g_bind_frac":0.4666666666666667,"a_match":0.6264367816091955,"a_match_n":29,"a_match_centered":-0.029761904761904764},"terminus_json":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":-0.0011230741446760452,"mean_b":0.01750477159624177,"b_gate_pass_rate":0.24193548387096775,"median_len_z":762.5,"mean_r_leg":0.002152134172991543,"mean_g_leg":0.0493644074343011,"g_bind_frac":0.13636363636363635,"a_match":0.45454545454545453,"a_match_n":22,"a_match_centered":0.07575757575757575},"text":{"n_turns":334,"n_valid":333,"parse_rate":0.9970059880239521,"reason":0.0006600903818082076,"mean_b":0.05209587986499144,"b_gate_pass_rate":0.5255255255255256,"median_len_z":734.0,"mean_r_leg":0.012155429920491862,"mean_g_leg":0.05883438464587142,"g_bind_frac":0.1891891891891892,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":275,"n_valid":275,"parse_rate":1.0,"reason":0.0010540908794672847,"mean_b":0.030598589008016246,"b_gate_pass_rate":0.5006150061500615,"median_len_z":506.0,"mean_r_leg":0.005773867392292855,"mean_g_leg":0.07106222314699658,"g_bind_frac":0.18181818181818182,"a_match":0.12391573729863693,"a_match_n":269,"a_match_centered":-0.06367041198501873}}},"king":{"reason":0.0024502849461363603,"n_turns":996,"n_pairs":2944,"n_forfeits":5,"forfeit_rate":0.0050200803212851405,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-2.692848111491771,"mean_len_z":823.1749320652174,"median_len_z":584.0,"mean_len_y":444.4711277173913,"mean_b":0.09793359902273976,"b_gate_pass_rate":0.5251358695652174,"mean_r_leg":0.016741379177557747,"mean_g_leg":0.056686002720581365,"g_bind_frac":0.23107971745711403,"a_match":0.15228556753980482,"a_match_n":649,"a_match_centered":-0.037409700722394225,"n_turns_cap_raised":90,"mean_cap_tokens":2162.2088353413656,"max_cap_tokens":4898,"len_z_delta":-323.1276372383662,"len_y_delta":-150.06200277618547,"n_samples":996,"think_close_rate":0.9969879518072289,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":335,"n_valid":333,"parse_rate":0.9940298507462687,"reason":0.007014492670929129,"mean_b":0.11209799688009323,"b_gate_pass_rate":0.8574317492416582,"median_len_z":459.0,"mean_r_leg":0.01878945654274863,"mean_g_leg":0.046846242398631055,"g_bind_frac":0.26126126126126126,"a_match":0.10910910910910909,"a_match_n":333,"a_match_centered":-0.03614457831325301},"boxed":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":0.009536987410194932,"mean_b":1.2781588377970374,"b_gate_pass_rate":0.6666666666666666,"median_len_z":1565.0,"mean_r_leg":0.14244960058612863,"mean_g_leg":0.02090759365344262,"g_bind_frac":0.5333333333333333,"a_match":0.5459770114942529,"a_match_n":29,"a_match_centered":-0.11309523809523811},"terminus_json":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":-0.0049859594184891365,"mean_b":0.018214350564893015,"b_gate_pass_rate":0.27419354838709675,"median_len_z":869.0,"mean_r_leg":0.002287192789403941,"mean_g_leg":0.04646630443577197,"g_bind_frac":0.18181818181818182,"a_match":0.45454545454545453,"a_match_n":22,"a_match_centered":0.07575757575757575},"text":{"n_turns":334,"n_valid":331,"parse_rate":0.9910179640718563,"reason":-0.00010212433822432169,"mean_b":0.04344920677364051,"b_gate_pass_rate":0.29607250755287007,"median_len_z":725.0,"mean_r_leg":0.013036797680653129,"mean_g_leg":0.05866370375952762,"g_bind_frac":0.19939577039274925,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":275,"n_valid":275,"parse_rate":1.0,"reason":-0.00018792808924220612,"mean_b":0.027032503885538767,"b_gate_pass_rate":0.4046740467404674,"median_len_z":521.0,"mean_r_leg":0.006163023436281831,"mean_g_leg":0.0709413000936658,"g_bind_frac":0.20363636363636364,"a_match":0.13836477987421383,"a_match_n":265,"a_match_centered":-0.0404040404040404}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T02:36:36.628114+00:00","challenge_id":"chal-00650","repo":"r2://affine-private-models/models/registrations/4a14fa2abd9b59f59210daa97ef42303748a4fabdbb3c8a91f83b10531e2e677/","hotkey":"5EfpEpkbbyyCnxvTBDUuUvyYKrgZLd4vU6vcyVme4XUDu6ob","uid":34,"duration_s":2508.0,"revision":"4713483f7f23432ab4545a9f2e4a471c64c0af59c920a2bb5351dd5afb3e3290","accepted":false,"error_code":null,"error_detail":"","z":1.2392852489847295,"margin":0.06106380276971937,"se":0.04927340402037804,"n_paired_turns":990,"n_forfeit_turns":7,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2221224492645736803,"n":1000,"digest":"2dc88d2195aa0256fd59b98936aa0c2db43a387b80027b3ee9dabd760ef5b180","n_paired_turns":990,"n_forfeit_turns":7,"margin":0.06106380276971937,"se":0.04927340402037804,"z":1.2392852489847295,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.06106380276971937,"se":0.04927340402037804,"z":1.2392852489847295,"sd_diff":1.5503514634810562,"n_paired_turns":990,"n_forfeit_turns":7,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"text":{"R":0.04037172697267578,"A":20.19933390874211,"Mc":0.1735393737361467},"bash":{"R":0.020260437978331203,"A":5.663866820214965,"Mc":0.16242118617246482},"tool_call":{"R":0.010854060577661176,"A":5.593280425176244,"Mc":0.18961083047794539},"boxed":{"R":0.17026466446879499,"A":3.6266316540660637,"Mc":0.1164279584192946},"terminus_json":{"R":0.002503993188273091,"A":7.547114834536342,"Mc":0.16901067623023253}},"challenger":{"mean":-0.7468198794601337,"mean_valid":-0.7011680331293432,"sd_valid":1.499491062801358,"n_turns":998,"n_valid":986,"n_forfeits":4,"n_unscorable":8,"mean_z_R":0.22239189044014607,"mean_typ_c":0.7125936292209717,"mean_z_A":-0.16440659963747467,"bind_frac":{"R":0.31947261663286003,"Gc":0.1643002028397566,"A":0.5162271805273834},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3214411693904122,"mean_R":0.01673080258805898,"mean_A":1.6118829632842553,"mean_mc":-0.7016211890597036},"king":{"mean":-0.8191774423890561,"mean_valid":-0.7396390705361326,"sd_valid":1.4668760806018448,"n_turns":998,"n_valid":984,"n_forfeits":7,"n_unscorable":7,"mean_z_R":0.1062331712475698,"mean_typ_c":0.6189024967470734,"mean_z_A":-0.18534517451755944,"bind_frac":{"R":0.3130081300813008,"Gc":0.17479674796747968,"A":0.5121951219512195},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.3207560418961043,"mean_R":0.014542456892701953,"mean_A":1.5550272261652875,"mean_mc":-0.7410629821073892}},"rejection_reason":null,"reign_number":null,"score":0.0028465840644792168,"score_king":0.0023624264776922884,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9119969,"blocks_since_crown":16740,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1230.0833333333333,"mean_len_y":596.5823170731708,"n_samples":3000,"think_close_rate":0.9733333333333334,"n_text_fallback":13,"by_dialect":{"bash":{"n_turns":322,"zero_ref_turns":0,"mean_refs":2.9347826086956523,"ref_pair_agreement":0.15723270440251572,"ref_pair_n":318},"text":{"n_turns":342,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":295,"zero_ref_turns":2,"mean_refs":2.911864406779661,"ref_pair_agreement":0.20730270906949352,"ref_pair_n":283},"boxed":{"n_turns":21,"zero_ref_turns":0,"mean_refs":2.9523809523809526,"ref_pair_agreement":0.6,"ref_pair_n":20},"terminus_json":{"n_turns":20,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.35,"ref_pair_n":20}},"ref_pair_agreement":0.19916796671866874,"ref_pair_n":641},"duel_seconds":2144.858307644725,"challenger":{"reason":0.0028465840644792168,"n_turns":998,"n_pairs":2941,"n_forfeits":4,"forfeit_rate":0.004008016032064128,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-0.23349982186495968,"mean_len_z":895.1788507310439,"median_len_z":632.0,"mean_len_y":372.6239374362462,"mean_b":0.09139206124471252,"b_gate_pass_rate":0.5708942536552193,"mean_r_leg":0.01673080258805898,"mean_g_leg":0.058583109776716796,"g_bind_frac":0.23138832997987926,"a_match":0.12333333333333334,"a_match_n":650,"a_match_centered":-0.07265625,"n_turns_cap_raised":101,"mean_cap_tokens":2182.4679358717435,"max_cap_tokens":5001,"len_z_delta":-334.90448260228936,"len_y_delta":-223.95837963692458,"n_samples":1001,"think_close_rate":0.996003996003996,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":322,"n_valid":322,"parse_rate":1.0,"reason":0.006990106718164285,"mean_b":0.11513205128667804,"b_gate_pass_rate":0.8677248677248677,"median_len_z":528.0,"mean_r_leg":0.02149341457416536,"mean_g_leg":0.0484536835133921,"g_bind_frac":0.30434782608695654,"a_match":0.07039337474120082,"a_match_n":322,"a_match_centered":-0.0859538784067086},"boxed":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":0.00769872589868273,"mean_b":1.3503271648897175,"b_gate_pass_rate":0.8548387096774194,"median_len_z":2002.0,"mean_r_leg":0.10598728713136495,"mean_g_leg":0.020608889163264428,"g_bind_frac":0.5714285714285714,"a_match":0.5583333333333333,"a_match_n":20,"a_match_centered":-0.04166666666666667},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0047255070096568555,"mean_b":0.025759482830620795,"b_gate_pass_rate":0.45,"median_len_z":737.5,"mean_r_leg":0.0009279436198043642,"mean_g_leg":0.047504063692616706,"g_bind_frac":0.2,"a_match":0.35,"a_match_n":20,"a_match_centered":-2.7755575615628915e-18},"text":{"n_turns":342,"n_valid":339,"parse_rate":0.9912280701754386,"reason":0.0013955341638839395,"mean_b":0.04616616099280082,"b_gate_pass_rate":0.35103244837758113,"median_len_z":781.0,"mean_r_leg":0.016891214394062597,"mean_g_leg":0.0638932756229732,"g_bind_frac":0.18584070796460178,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":293,"n_valid":292,"parse_rate":0.9965870307167235,"reason":0.00015577046202679536,"mean_b":0.03240072897562497,"b_gate_pass_rate":0.49241540256709454,"median_len_z":596.0,"mean_r_leg":0.005955906499682903,"mean_g_leg":0.06707820768587479,"g_bind_frac":0.1815068493150685,"a_match":0.13657407407407407,"a_match_n":288,"a_match_centered":-0.06501182033096926}}},"king":{"reason":0.0023624264776922884,"n_turns":998,"n_pairs":2934,"n_forfeits":7,"forfeit_rate":0.0070140280561122245,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-0.3446326680221714,"mean_len_z":873.0211315610088,"median_len_z":579.0,"mean_len_y":456.42808452624405,"mean_b":0.08560526421325852,"b_gate_pass_rate":0.521813224267212,"mean_r_leg":0.014542456892701953,"mean_g_leg":0.05797228286903412,"g_bind_frac":0.23208879919273462,"a_match":0.15505675954592363,"a_match_n":646,"a_match_centered":-0.040031397174254316,"n_turns_cap_raised":101,"mean_cap_tokens":2182.4679358717435,"max_cap_tokens":5001,"len_z_delta":-357.06220177232444,"len_y_delta":-140.15423254692672,"n_samples":998,"think_close_rate":0.9959919839679359,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":322,"n_valid":319,"parse_rate":0.9906832298136646,"reason":0.007168802237591399,"mean_b":0.11080587742917354,"b_gate_pass_rate":0.847547974413646,"median_len_z":470.0,"mean_r_leg":0.019548458686781248,"mean_g_leg":0.04972892066223486,"g_bind_frac":0.2852664576802508,"a_match":0.12643678160919541,"a_match_n":319,"a_match_centered":-0.02742616033755274},"boxed":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":0.004907664802074269,"mean_b":1.3432193837117403,"b_gate_pass_rate":0.3709677419354839,"median_len_z":2424.0,"mean_r_leg":0.18472862557582437,"mean_g_leg":0.013688245185541768,"g_bind_frac":0.7142857142857143,"a_match":0.5916666666666667,"a_match_n":20,"a_match_centered":-0.008333333333333337},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0009133451897237286,"mean_b":0.020901127577616092,"b_gate_pass_rate":0.5,"median_len_z":565.5,"mean_r_leg":0.0010122500199073949,"mean_g_leg":0.051766554094109636,"g_bind_frac":0.15,"a_match":0.4166666666666667,"a_match_n":20,"a_match_centered":0.06666666666666667},"text":{"n_turns":342,"n_valid":339,"parse_rate":0.9912280701754386,"reason":0.0003091970196424061,"mean_b":0.038541209189143256,"b_gate_pass_rate":0.3303834808259587,"median_len_z":720.0,"mean_r_leg":0.00807471503829719,"mean_g_leg":0.06074799252523753,"g_bind_frac":0.20943952802359883,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":293,"n_valid":292,"parse_rate":0.9965870307167235,"reason":-0.00048188441479288344,"mean_b":0.027421065324378265,"b_gate_pass_rate":0.4049008168028005,"median_len_z":499.0,"mean_r_leg":0.005269664123668531,"mean_g_leg":0.0673652497778281,"g_bind_frac":0.17123287671232876,"a_match":0.13821138211382114,"a_match_n":287,"a_match_centered":-0.06405693950177936}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T01:53:38.673554+00:00","challenge_id":"chal-00649","repo":"r2://affine-private-models/models/registrations/5c303ca7618e4d178420eea8a53acd306a28bd92fb9420490725cb4b287ef3f4/","hotkey":"5GvJNXdCgjScLaVHYfb5BuYUqyXPjrMfmKoSQjRMNBqchm72","uid":224,"duration_s":2520.7,"revision":"7cff4ba294dc22258e57ff2e5db3e2bbd946cde8d9b4876aa5c5c1cc6f6e130e","accepted":false,"error_code":null,"error_detail":"","z":3.1967332465393743,"margin":0.13549730343537966,"se":0.04238617769626614,"n_paired_turns":987,"n_forfeit_turns":5,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":1739105915911962811,"n":1000,"digest":"8f674ab060f4fc50ece7f399b1984431185ec67495757fe21b59472e97ad9d93","n_paired_turns":987,"n_forfeit_turns":5,"margin":0.13549730343537966,"se":0.04238617769626614,"z":3.1967332465393743,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.13549730343537966,"se":0.04238617769626614,"z":3.1967332465393743,"sd_diff":1.3316277313586393,"n_paired_turns":987,"n_forfeit_turns":5,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02406900372130817,"A":6.364467398496544,"Mc":0.15717447546651428},"tool_call":{"R":0.009086769070842595,"A":8.362310726446704,"Mc":0.21073675155877064},"text":{"R":0.023277012267769407,"A":23.94318261406258,"Mc":0.16468347526305904},"terminus_json":{"R":0.002285884879309578,"A":8.965004385640407,"Mc":0.10346461692350192},"boxed":{"R":0.04370207184992013,"A":2.609451541327416,"Mc":0.11246274853479048}},"challenger":{"mean":-0.531615932588833,"mean_valid":-0.48494905947627487,"sd_valid":1.0241441108396658,"n_turns":996,"n_valid":983,"n_forfeits":4,"n_unscorable":9,"mean_z_R":0.28666117913979067,"mean_typ_c":0.8268248272941301,"mean_z_A":-0.08850423682230396,"bind_frac":{"R":0.34587995930824006,"Gc":0.150559511698881,"A":0.503560528992879},"n_leg_dropped":{"R":0,"Gc":8,"A":0},"mean_content_share":0.3095019666978373,"mean_R":0.014135763524036152,"mean_A":2.300988948183779,"mean_mc":-0.6709635429366406},"king":{"mean":-0.6785837691861315,"mean_valid":-0.6325617519877011,"sd_valid":1.3567980043411303,"n_turns":996,"n_valid":984,"n_forfeits":4,"n_unscorable":8,"mean_z_R":0.2523274573709251,"mean_typ_c":0.6762511322889468,"mean_z_A":-0.1692789031464141,"bind_frac":{"R":0.3079268292682927,"Gc":0.16666666666666666,"A":0.5254065040650406},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.32716741892113754,"mean_R":0.012938112940286173,"mean_A":1.4561387512901365,"mean_mc":-0.7118187016735099}},"rejection_reason":null,"reign_number":null,"score":0.003969752553682696,"score_king":0.002792956599372232,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9119753,"blocks_since_crown":16524,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1227.7202441505594,"mean_len_y":697.1915903696168,"n_samples":3000,"think_close_rate":0.9686666666666667,"n_text_fallback":12,"by_dialect":{"tool_call":{"n_turns":260,"zero_ref_turns":0,"mean_refs":2.923076923076923,"ref_pair_agreement":0.15405046480743692,"ref_pair_n":251},"bash":{"n_turns":314,"zero_ref_turns":3,"mean_refs":2.917197452229299,"ref_pair_agreement":0.15960912052117263,"ref_pair_n":307},"text":{"n_turns":363,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":32,"zero_ref_turns":1,"mean_refs":2.875,"ref_pair_agreement":0.4623655913978495,"ref_pair_n":31},"boxed":{"n_turns":31,"zero_ref_turns":0,"mean_refs":2.967741935483871,"ref_pair_agreement":0.8,"ref_pair_n":30}},"ref_pair_agreement":0.20355411954765748,"ref_pair_n":619},"duel_seconds":2125.228327683173,"challenger":{"reason":0.003969752553682696,"n_turns":996,"n_pairs":2938,"n_forfeits":4,"forfeit_rate":0.004016064257028112,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-9.28942813607276,"mean_len_z":992.7481279782165,"median_len_z":754.5,"mean_len_y":398.21715452688903,"mean_b":0.1059381264686864,"b_gate_pass_rate":0.5650102110279102,"mean_r_leg":0.014135763524036152,"mean_g_leg":0.0581898796895346,"g_bind_frac":0.2086693548387097,"a_match":0.16136724960254373,"a_match_n":629,"a_match_centered":-0.03808752025931929,"n_turns_cap_raised":100,"mean_cap_tokens":2178.740963855422,"max_cap_tokens":5041,"len_z_delta":-234.9721161723429,"len_y_delta":-298.9744358427278,"n_samples":999,"think_close_rate":0.995995995995996,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":311,"n_valid":311,"parse_rate":1.0,"reason":0.009771164139080912,"mean_b":0.11523362539325874,"b_gate_pass_rate":0.8504366812227074,"median_len_z":571.0,"mean_r_leg":0.01939512425035183,"mean_g_leg":0.04908852504166017,"g_bind_frac":0.2540192926045016,"a_match":0.11736334405144695,"a_match_n":311,"a_match_centered":-0.04071661237785016},"boxed":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":0.0012993589640347902,"mean_b":1.2798764967584737,"b_gate_pass_rate":0.8695652173913043,"median_len_z":1677.0,"mean_r_leg":0.05411921006327266,"mean_g_leg":0.0301922767303247,"g_bind_frac":0.1935483870967742,"a_match":0.7444444444444444,"a_match_n":30,"a_match_centered":-0.05555555555555556},"terminus_json":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":-0.0026025947542655894,"mean_b":0.01746809587806189,"b_gate_pass_rate":0.22826086956521738,"median_len_z":957.0,"mean_r_leg":0.0011559550186473872,"mean_g_leg":0.030390311883242937,"g_bind_frac":0.2903225806451613,"a_match":0.5376344086021506,"a_match_n":31,"a_match_centered":0.07526881720430106},"text":{"n_turns":363,"n_valid":360,"parse_rate":0.9917355371900827,"reason":0.0003542783493719551,"mean_b":0.0570448895443014,"b_gate_pass_rate":0.4111111111111111,"median_len_z":858.5,"mean_r_leg":0.011299731722026198,"mean_g_leg":0.057497897199485386,"g_bind_frac":0.18888888888888888,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":260,"n_valid":259,"parse_rate":0.9961538461538462,"reason":0.0031801490957266794,"mean_b":0.03262273281579008,"b_gate_pass_rate":0.44327176781002636,"median_len_z":712.5,"mean_r_leg":0.008530348403534714,"mean_g_leg":0.07675878812828832,"g_bind_frac":0.17374517374517376,"a_match":0.10116731517509728,"a_match_n":257,"a_match_centered":-0.04685408299866131}}},"king":{"reason":0.002792956599372232,"n_turns":996,"n_pairs":2939,"n_forfeits":4,"forfeit_rate":0.004016064257028112,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":68.03086468286229,"mean_len_z":852.3831235113985,"median_len_z":575.0,"mean_len_y":473.8713848247703,"mean_b":0.10431292736099723,"b_gate_pass_rate":0.5188839741408643,"mean_r_leg":0.012938112940286173,"mean_g_leg":0.05600290940089599,"g_bind_frac":0.22580645161290322,"a_match":0.1696,"a_match_n":625,"a_match_centered":-0.02926829268292683,"n_turns_cap_raised":100,"mean_cap_tokens":2178.740963855422,"max_cap_tokens":5041,"len_z_delta":-375.33712063916096,"len_y_delta":-223.32020554484654,"n_samples":996,"think_close_rate":0.9969879518072289,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":311,"n_valid":310,"parse_rate":0.9967845659163987,"reason":0.008563498437457436,"mean_b":0.12239518677787418,"b_gate_pass_rate":0.8437158469945355,"median_len_z":479.0,"mean_r_leg":0.018867427344196244,"mean_g_leg":0.049530229011401715,"g_bind_frac":0.25483870967741934,"a_match":0.12795698924731183,"a_match_n":310,"a_match_centered":-0.030401737242128125},"boxed":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":0.0004598727178326446,"mean_b":1.2848140824329524,"b_gate_pass_rate":0.6847826086956522,"median_len_z":1751.0,"mean_r_leg":0.03852932181334867,"mean_g_leg":0.02816180488972296,"g_bind_frac":0.25806451612903225,"a_match":0.711111111111111,"a_match_n":30,"a_match_centered":-0.08888888888888888},"terminus_json":{"n_turns":31,"n_valid":31,"parse_rate":1.0,"reason":-0.0027171864755663674,"mean_b":0.015712747268231877,"b_gate_pass_rate":0.29347826086956524,"median_len_z":583.0,"mean_r_leg":0.0012259315310691721,"mean_g_leg":0.027118968016448315,"g_bind_frac":0.22580645161290322,"a_match":0.5806451612903226,"a_match_n":31,"a_match_centered":0.11827956989247311},"text":{"n_turns":363,"n_valid":360,"parse_rate":0.9917355371900827,"reason":-0.0014710165041440563,"mean_b":0.049594320080064334,"b_gate_pass_rate":0.3416666666666667,"median_len_z":670.5,"mean_r_leg":0.00956523370447697,"mean_g_leg":0.053772926936793614,"g_bind_frac":0.21388888888888888,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":260,"n_valid":260,"parse_rate":1.0,"reason":0.002778817216998148,"mean_b":0.028123373148996763,"b_gate_pass_rate":0.3868421052631579,"median_len_z":472.0,"mean_r_leg":0.008883879126055337,"mean_g_leg":0.07357137490314337,"g_bind_frac":0.20384615384615384,"a_match":0.1062992125984252,"a_match_n":254,"a_match_centered":-0.039136302294197026}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T01:10:31.131794+00:00","challenge_id":"chal-00648","repo":"r2://affine-private-models/models/registrations/1fc23bb8984e73ecb3a02cbb88d66d1f48d475e194f70f2585c88fb53713984f/","hotkey":"5FpSMb6iHkLwSytbGC2mg9yYJnnoRsoFD1oWmKDHUgZxQb4D","uid":10,"duration_s":2394.3,"revision":"47fc2f04846a9929b5f9bf5eeaaad654a5de3d35939b7878818066d9ed19f94e","accepted":false,"error_code":null,"error_detail":"","z":-2.9572395351432568,"margin":-0.1902400543266139,"se":0.06433028236835003,"n_paired_turns":986,"n_forfeit_turns":14,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":15137629059008291312,"n":1000,"digest":"a2635bf0f483959ed9d5d4d92711ef095e6bea30fb080d63b81118c14b3f0d50","n_paired_turns":986,"n_forfeit_turns":14,"margin":-0.1902400543266139,"se":0.06433028236835003,"z":-2.9572395351432568,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.1902400543266139,"se":0.06433028236835003,"z":-2.9572395351432568,"sd_diff":2.020011840652763,"n_paired_turns":986,"n_forfeit_turns":14,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02414407144790616,"A":6.750865923104619,"Mc":0.15682118707379597},"text":{"R":0.019334608997506785,"A":21.466321465814183,"Mc":0.1675696969319317},"tool_call":{"R":0.008032957130391748,"A":5.826426705193393,"Mc":0.19735237601196384},"boxed":{"R":0.10191874870908779,"A":2.239069406023152,"Mc":0.102202143187286},"terminus_json":{"R":0.0031694460709995537,"A":12.228471941359421,"Mc":0.11868589501967385}},"challenger":{"mean":-0.9192519398663632,"mean_valid":-0.771204946257178,"sd_valid":1.6917782476984298,"n_turns":990,"n_valid":973,"n_forfeits":13,"n_unscorable":4,"mean_z_R":0.200597508819572,"mean_typ_c":0.5371487659666574,"mean_z_A":-0.17023224851617788,"bind_frac":{"R":0.3062692702980473,"Gc":0.1747173689619733,"A":0.5190133607399794},"n_leg_dropped":{"R":0,"Gc":1,"A":0},"mean_content_share":0.32072119400781035,"mean_R":0.013344555823228669,"mean_A":1.3392895417052888,"mean_mc":-0.6938389182105528},"king":{"mean":-0.7290118855397494,"mean_valid":-0.6715654629380151,"sd_valid":1.250399032006141,"n_turns":990,"n_valid":981,"n_forfeits":5,"n_unscorable":4,"mean_z_R":0.16842963936364488,"mean_typ_c":0.6348324189806395,"mean_z_A":-0.13418377754153893,"bind_frac":{"R":0.3200815494393476,"Gc":0.1783893985728848,"A":0.5015290519877675},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.32224026419346014,"mean_R":0.012933541088485755,"mean_A":1.8139131701927902,"mean_mc":-0.7210421199066746}},"rejection_reason":null,"reign_number":null,"score":0.0020865351953037983,"score_king":0.0019407042836593483,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9119548,"blocks_since_crown":16319,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1292.6875638841568,"mean_len_y":638.049744463373,"n_samples":3000,"think_close_rate":0.9726666666666667,"n_text_fallback":16,"by_dialect":{"text":{"n_turns":360,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":313,"zero_ref_turns":5,"mean_refs":2.9041533546325877,"ref_pair_agreement":0.19001085776330076,"ref_pair_n":307},"boxed":{"n_turns":30,"zero_ref_turns":1,"mean_refs":2.7666666666666666,"ref_pair_agreement":0.7435897435897435,"ref_pair_n":26},"tool_call":{"n_turns":269,"zero_ref_turns":3,"mean_refs":2.9182156133828996,"ref_pair_agreement":0.17938931297709923,"ref_pair_n":262},"terminus_json":{"n_turns":28,"zero_ref_turns":1,"mean_refs":2.7857142857142856,"ref_pair_agreement":0.4743589743589744,"ref_pair_n":26}},"ref_pair_agreement":0.22061191626409019,"ref_pair_n":621},"duel_seconds":2034.3019979600795,"challenger":{"reason":0.0020865351953037983,"n_turns":990,"n_pairs":2896,"n_forfeits":13,"forfeit_rate":0.013131313131313131,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.8814862567182948,"mean_len_z":865.7144337016574,"median_len_z":541.0,"mean_len_y":425.11671270718233,"mean_b":0.09003102404676269,"b_gate_pass_rate":0.5359116022099447,"mean_r_leg":0.013344555823228669,"mean_g_leg":0.05556155007646394,"g_bind_frac":0.2292732855680655,"a_match":0.18655913978494623,"a_match_n":620,"a_match_centered":-0.034688346883468835,"n_turns_cap_raised":101,"mean_cap_tokens":2182.09797979798,"max_cap_tokens":5036,"len_z_delta":-426.9731301824994,"len_y_delta":-212.9330317561907,"n_samples":993,"think_close_rate":0.9869083585095669,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":308,"n_valid":307,"parse_rate":0.9967532467532467,"reason":0.00984229507703126,"mean_b":0.12269123671690645,"b_gate_pass_rate":0.8642384105960265,"median_len_z":405.0,"mean_r_leg":0.020741915257246998,"mean_g_leg":0.05000915304055566,"g_bind_frac":0.2768729641693811,"a_match":0.15798045602605862,"a_match_n":307,"a_match_centered":-0.03213507625272331},"boxed":{"n_turns":29,"n_valid":27,"parse_rate":0.9310344827586207,"reason":-0.005346519105996437,"mean_b":1.0345504156254013,"b_gate_pass_rate":0.5454545454545454,"median_len_z":1710.0,"mean_r_leg":0.06135781688787021,"mean_g_leg":0.019703850021229163,"g_bind_frac":0.4444444444444444,"a_match":0.717948717948718,"a_match_n":26,"a_match_centered":0.013888888888888886},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.0014216339712770324,"mean_b":0.017941443581983466,"b_gate_pass_rate":0.20512820512820512,"median_len_z":686.5,"mean_r_leg":0.0017352916748478806,"mean_g_leg":0.036687559400043375,"g_bind_frac":0.1111111111111111,"a_match":0.5617283950617283,"a_match_n":27,"a_match_centered":0.07051282051282051},"text":{"n_turns":360,"n_valid":351,"parse_rate":0.975,"reason":-0.0027150034487679687,"mean_b":0.04479603930734291,"b_gate_pass_rate":0.33618233618233617,"median_len_z":640.0,"mean_r_leg":0.009992118746969595,"mean_g_leg":0.056954185155229355,"g_bind_frac":0.19658119658119658,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":266,"n_valid":265,"parse_rate":0.9962406015037594,"reason":0.0007709675657142008,"mean_b":0.027290973376885987,"b_gate_pass_rate":0.45652173913043476,"median_len_z":478.0,"mean_r_leg":0.005506096014867415,"mean_g_leg":0.06572580149960311,"g_bind_frac":0.20754716981132076,"a_match":0.12820512820512822,"a_match_n":260,"a_match_centered":-0.05276705276705276}}},"king":{"reason":0.0019407042836593483,"n_turns":990,"n_pairs":2920,"n_forfeits":5,"forfeit_rate":0.005050505050505051,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.6847759739581971,"mean_len_z":870.1075342465754,"median_len_z":583.0,"mean_len_y":451.2722602739726,"mean_b":0.08987105284589086,"b_gate_pass_rate":0.510958904109589,"mean_r_leg":0.012933541088485755,"mean_g_leg":0.05465947473674557,"g_bind_frac":0.23248730964467004,"a_match":0.19162640901771336,"a_match_n":621,"a_match_centered":-0.032467532467532464,"n_turns_cap_raised":101,"mean_cap_tokens":2182.09797979798,"max_cap_tokens":5036,"len_z_delta":-422.58002963758145,"len_y_delta":-186.7774841894004,"n_samples":990,"think_close_rate":0.9959595959595959,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":308,"n_valid":307,"parse_rate":0.9967532467532467,"reason":0.010058419568419045,"mean_b":0.11705963538743253,"b_gate_pass_rate":0.8399558498896247,"median_len_z":460.0,"mean_r_leg":0.02169533833457533,"mean_g_leg":0.050939655330831723,"g_bind_frac":0.2671009771986971,"a_match":0.16178067318132464,"a_match_n":307,"a_match_centered":-0.02832244008714597},"boxed":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":0.00043627724045227853,"mean_b":1.0548917119540384,"b_gate_pass_rate":0.5180722891566265,"median_len_z":1846.0,"mean_r_leg":0.044430844039539015,"mean_g_leg":0.018610158550572003,"g_bind_frac":0.41379310344827586,"a_match":0.7142857142857143,"a_match_n":28,"a_match_centered":-0.012820512820512824},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.001481001635567719,"mean_b":0.014472596207742612,"b_gate_pass_rate":0.11538461538461539,"median_len_z":703.5,"mean_r_leg":0.0006590422546839406,"mean_g_leg":0.03791108938602457,"g_bind_frac":0.1111111111111111,"a_match":0.5185185185185185,"a_match_n":27,"a_match_centered":0.02564102564102564},"text":{"n_turns":360,"n_valid":356,"parse_rate":0.9888888888888889,"reason":-0.0031231437042600445,"mean_b":0.04295789527564204,"b_gate_pass_rate":0.3146067415730337,"median_len_z":693.5,"mean_r_leg":0.009774369092149569,"mean_g_leg":0.055110940478970284,"g_bind_frac":0.20786516853932585,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":266,"n_valid":266,"parse_rate":1.0,"reason":-9.409491928377028e-05,"mean_b":0.027775207513646684,"b_gate_pass_rate":0.4369426751592357,"median_len_z":547.0,"mean_r_leg":0.004861297325622173,"mean_g_leg":0.06397864513994878,"g_bind_frac":0.21804511278195488,"a_match":0.13642213642213644,"a_match_n":259,"a_match_centered":-0.04521963824289405}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-22T00:29:26.299895+00:00","challenge_id":"chal-00647","repo":"r2://affine-private-models/models/registrations/0ef59631de43dcc7db26097bd96279f97ee7b0a9338875871c1aad5ea24c27a9/","hotkey":"5HbUMSmXh7712JVf2DMdn92jkncJCvMKgL6uh1PK9tii2ViQ","uid":233,"duration_s":2405.4,"revision":"946a9c43439c19d425d2361005c8e095051f8012d4fa936ad8c058db3aa78298","accepted":false,"error_code":null,"error_detail":"","z":-4.198668517792272,"margin":-0.3209916521591568,"se":0.0764508202538312,"n_paired_turns":977,"n_forfeit_turns":16,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":17124378153978608655,"n":1000,"digest":"f65ed05f6a75a2867f4a251dbeadc3c3aa7eb40e8664600443744e8e037f7714","n_paired_turns":977,"n_forfeit_turns":16,"margin":-0.3209916521591568,"se":0.0764508202538312,"z":-4.198668517792272,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.3209916521591568,"se":0.0764508202538312,"z":-4.198668517792272,"sd_diff":2.389623228749981,"n_paired_turns":977,"n_forfeit_turns":16,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.024699588319546033,"A":5.772804543682651,"Mc":0.14660171279112472},"text":{"R":0.02903026312769704,"A":11.325395695116272,"Mc":0.1791310086169609},"tool_call":{"R":0.00675226252923865,"A":6.428360047196352,"Mc":0.18943153947443547},"terminus_json":{"R":0.0011018698591387906,"A":8.235946241627545,"Mc":0.12497822506240429},"boxed":{"R":0.20049905496268247,"A":3.1840839311139955,"Mc":0.12448428629741927}},"challenger":{"mean":-1.1727826596501791,"mean_valid":-0.9925168142333246,"sd_valid":1.8439163441407986,"n_turns":992,"n_valid":961,"n_forfeits":16,"n_unscorable":15,"mean_z_R":0.1500899204649823,"mean_typ_c":0.3649740103939315,"mean_z_A":-0.33880911284042275,"bind_frac":{"R":0.2809573361082206,"Gc":0.20187304890738814,"A":0.5171696149843913},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.3165808249961856,"mean_R":0.014849844083001013,"mean_A":0.130407489570111,"mean_mc":-0.7463333150884617},"king":{"mean":-0.8517910074910222,"mean_valid":-0.8174536081301116,"sd_valid":1.8460767530485704,"n_turns":992,"n_valid":974,"n_forfeits":3,"n_unscorable":15,"mean_z_R":0.2968700568073132,"mean_typ_c":0.5137968088002833,"mean_z_A":-0.19798862386054444,"bind_frac":{"R":0.31519507186858314,"Gc":0.17864476386036962,"A":0.5061601642710473},"n_leg_dropped":{"R":0,"Gc":9,"A":0},"mean_content_share":0.32343464245603637,"mean_R":0.01747446620607614,"mean_A":1.3199937126701689,"mean_mc":-0.7305035901935533}},"rejection_reason":null,"reign_number":null,"score":-0.0003254172165679283,"score_king":0.00201857110921115,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9119341,"blocks_since_crown":16112,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1139.7677530017152,"mean_len_y":688.2888507718696,"n_samples":3000,"think_close_rate":0.9596666666666667,"n_text_fallback":23,"by_dialect":{"text":{"n_turns":365,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":321,"zero_ref_turns":5,"mean_refs":2.869158878504673,"ref_pair_agreement":0.1995685005393743,"ref_pair_n":309},"tool_call":{"n_turns":274,"zero_ref_turns":1,"mean_refs":2.8795620437956204,"ref_pair_agreement":0.16020671834625325,"ref_pair_n":258},"boxed":{"n_turns":19,"zero_ref_turns":1,"mean_refs":2.736842105263158,"ref_pair_agreement":0.7407407407407408,"ref_pair_n":18},"terminus_json":{"n_turns":21,"zero_ref_turns":1,"mean_refs":2.761904761904762,"ref_pair_agreement":0.31666666666666665,"ref_pair_n":20}},"ref_pair_agreement":0.2027548209366391,"ref_pair_n":605},"duel_seconds":2033.4866737509146,"challenger":{"reason":-0.0003254172165679283,"n_turns":992,"n_pairs":2868,"n_forfeits":16,"forfeit_rate":0.016129032258064516,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":587.5490093068119,"mean_len_z":861.9058577405858,"median_len_z":513.5,"mean_len_y":433.5676429567643,"mean_b":0.08561161882581804,"b_gate_pass_rate":0.5397489539748954,"mean_r_leg":0.014849844083001013,"mean_g_leg":0.053389447854868266,"g_bind_frac":0.2489754098360656,"a_match":0.15959760739532353,"a_match_n":613,"a_match_centered":-0.03824678950307091,"n_turns_cap_raised":92,"mean_cap_tokens":2170.0826612903224,"max_cap_tokens":5073,"len_z_delta":-277.86189526112935,"len_y_delta":-254.72120781510534,"n_samples":995,"think_close_rate":0.9869346733668342,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":316,"n_valid":312,"parse_rate":0.9873417721518988,"reason":0.006334454554452103,"mean_b":0.12815070611447235,"b_gate_pass_rate":0.9020902090209021,"median_len_z":385.0,"mean_r_leg":0.01951808182255923,"mean_g_leg":0.0467174082674373,"g_bind_frac":0.3269230769230769,"a_match":0.15117521367521367,"a_match_n":312,"a_match_centered":-0.04426229508196721},"boxed":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":0.0029255414964340274,"mean_b":1.2544757662714783,"b_gate_pass_rate":0.5576923076923077,"median_len_z":1995.0,"mean_r_leg":0.19902799930593196,"mean_g_leg":0.013842002007989188,"g_bind_frac":0.4444444444444444,"a_match":0.6862745098039216,"a_match_n":17,"a_match_centered":-0.03921568627450981},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0003998881883888169,"mean_b":0.014415941192652404,"b_gate_pass_rate":0.2413793103448276,"median_len_z":873.0,"mean_r_leg":0.0010242322943414847,"mean_g_leg":0.035879636852515696,"g_bind_frac":0.25,"a_match":0.4,"a_match_n":20,"a_match_centered":0.08333333333333333},"text":{"n_turns":365,"n_valid":354,"parse_rate":0.9698630136986301,"reason":-0.005191850353522668,"mean_b":0.03888310344755911,"b_gate_pass_rate":0.3248587570621469,"median_len_z":630.0,"mean_r_leg":0.00983367109768431,"mean_g_leg":0.05267403117657891,"g_bind_frac":0.2231638418079096,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":273,"n_valid":272,"parse_rate":0.9963369963369964,"reason":-0.0017367696782949146,"mean_b":0.02755071237330658,"b_gate_pass_rate":0.4320203303684879,"median_len_z":408.0,"mean_r_leg":0.00485183122939948,"mean_g_leg":0.06587835998973506,"g_bind_frac":0.1801470588235294,"a_match":0.11742424242424243,"a_match_n":264,"a_match_centered":-0.040522875816993466}}},"king":{"reason":0.00201857110921115,"n_turns":992,"n_pairs":2906,"n_forfeits":3,"forfeit_rate":0.0030241935483870967,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":444.6903786759133,"mean_len_z":859.0223675154853,"median_len_z":578.0,"mean_len_y":452.78871300757055,"mean_b":0.08761322262324506,"b_gate_pass_rate":0.508602890571232,"mean_r_leg":0.01747446620607614,"mean_g_leg":0.05404202088626606,"g_bind_frac":0.2568250758341759,"a_match":0.1747835497835498,"a_match_n":616,"a_match_centered":-0.02329450915141431,"n_turns_cap_raised":92,"mean_cap_tokens":2170.0826612903224,"max_cap_tokens":5073,"len_z_delta":-280.7453854862299,"len_y_delta":-235.5001377642991,"n_samples":992,"think_close_rate":0.9969758064516129,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":316,"n_valid":316,"parse_rate":1.0,"reason":0.009313252682617507,"mean_b":0.1274154827634739,"b_gate_pass_rate":0.8436482084690554,"median_len_z":490.0,"mean_r_leg":0.023671706029433748,"mean_g_leg":0.04722116453267913,"g_bind_frac":0.3259493670886076,"a_match":0.16772151898734178,"a_match_n":316,"a_match_centered":-0.02804746494066882},"boxed":{"n_turns":18,"n_valid":18,"parse_rate":1.0,"reason":0.0031048365439379656,"mean_b":1.3444587410641589,"b_gate_pass_rate":0.7692307692307693,"median_len_z":1846.5,"mean_r_leg":0.19357267892889213,"mean_g_leg":0.01546777926498513,"g_bind_frac":0.6111111111111112,"a_match":0.7450980392156863,"a_match_n":17,"a_match_centered":0.019607843137254898},"terminus_json":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":-0.0019020799759403176,"mean_b":0.01857590364833014,"b_gate_pass_rate":0.29310344827586204,"median_len_z":681.0,"mean_r_leg":0.0013124930181814126,"mean_g_leg":0.0330763340984745,"g_bind_frac":0.2,"a_match":0.38333333333333336,"a_match_n":20,"a_match_centered":0.06666666666666667},"text":{"n_turns":365,"n_valid":362,"parse_rate":0.9917808219178083,"reason":-0.002678868669654741,"mean_b":0.04217182906695079,"b_gate_pass_rate":0.2900552486187845,"median_len_z":722.0,"mean_r_leg":0.012886135518560842,"mean_g_leg":0.05446826493246565,"g_bind_frac":0.23480662983425415,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":273,"n_valid":273,"parse_rate":1.0,"reason":7.097545341476811e-05,"mean_b":0.025939799752018638,"b_gate_pass_rate":0.41698352344740175,"median_len_z":440.0,"mean_r_leg":0.0059584206362839846,"mean_g_leg":0.06545132619010526,"g_bind_frac":0.18681318681318682,"a_match":0.1305449936628644,"a_match_n":263,"a_match_centered":-0.027450980392156862}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T23:48:14.296942+00:00","challenge_id":"chal-00646","repo":"r2://affine-private-models/models/registrations/0cfd240d65492ec2da66af631f2448a79e9415efbecb92d82b362ca85c00597a/","hotkey":"5GvhtPv914orD3J2MiZ5tvdisgwS8AiiVc6akkcWY2MJ3VdQ","uid":211,"duration_s":471.9,"revision":"e29260a88ae608de87a9c22700d0bdeca4ed21b3d6b1dfe4489a5ef2afd76ee4","accepted":false,"error_code":null,"error_detail":"","z":null,"margin":null,"se":null,"n_paired_turns":null,"n_forfeit_turns":null,"near_miss":null,"protocol_probe":{"mode":"enforce","passed":false,"pass_rate":0.75,"min_pass_rate":0.9,"think_close_rate":0.85,"n":20,"by_reason":{"no_think_close":3,"no_tool_call":2},"by_prompt":{"assistant_bash":{"ok":false,"reasons":["no_think_close"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":false,"reasons":["no_think_close"]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":false,"reasons":["no_tool_call"]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":null,"rejection_reason":"protocol:pass_rate=0.75<0.9;no_think_close=3,no_tool_call=2","reign_number":null,"score":null,"score_king":null,"gates":null,"duel_params":null,"teacher":null,"duel_seconds":null,"challenger":null,"king":null,"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T23:39:15.454686+00:00","challenge_id":"chal-00645","repo":"r2://affine-private-models/models/registrations/117efcd8460322cc719d42cfeaf2660c86db96d5712355ea92eb7a54a8f94fba/","hotkey":"5HX95rbPMqykKxShEAXWThZW4gnTH8yUi4G8h5i8YfELAbaF","uid":101,"duration_s":2692.9,"revision":"55b029e01d34322254ecfe0d927ee1d6c2741712d914b3a3d1b897065c46a2d6","accepted":false,"error_code":null,"error_detail":"","z":-0.6387277358570834,"margin":-0.025533531331639988,"se":0.03997561073088137,"n_paired_turns":984,"n_forfeit_turns":11,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":5437523214370560621,"n":1000,"digest":"1d550320c2919899f0e9ff2ac5079f3d4c9d826605b6b99e4303cb72eb6f93d3","n_paired_turns":984,"n_forfeit_turns":11,"margin":-0.025533531331639988,"se":0.03997561073088137,"z":-0.6387277358570834,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":1},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.025533531331639988,"se":0.03997561073088137,"z":-0.6387277358570834,"sd_diff":1.253985909830747,"n_paired_turns":984,"n_forfeit_turns":11,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"tool_call":{"R":0.010357126620215153,"A":6.3734345845370886,"Mc":0.1887216487122822},"text":{"R":0.0676606422187993,"A":23.871676243436326,"Mc":0.17891755753134145},"bash":{"R":0.025559995441490846,"A":5.726867090311676,"Mc":0.1503034552135191},"terminus_json":{"R":0.001192184207499121,"A":6.313974442530166,"Mc":0.10806515844092791},"boxed":{"R":0.121388709804935,"A":2.7320147787620326,"Mc":0.09590115573795222}},"challenger":{"mean":-0.7278606497814593,"mean_valid":-0.6121302663089896,"sd_valid":1.4054783793050494,"n_turns":993,"n_valid":974,"n_forfeits":10,"n_unscorable":9,"mean_z_R":0.1935273307742138,"mean_typ_c":0.6361845571338431,"mean_z_A":-0.12457847095644355,"bind_frac":{"R":0.3193018480492813,"Gc":0.162217659137577,"A":0.5184804928131417},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.32560122200384506,"mean_R":0.018539277376539653,"mean_A":2.2237785270643378,"mean_mc":-0.6966602292943551},"king":{"mean":-0.7137968371112915,"mean_valid":-0.6097232423715391,"sd_valid":1.4107665467203332,"n_turns":993,"n_valid":976,"n_forfeits":9,"n_unscorable":8,"mean_z_R":0.17978176941261392,"mean_typ_c":0.6714833175051629,"mean_z_A":-0.1095278737821387,"bind_frac":{"R":0.33709016393442626,"Gc":0.1557377049180328,"A":0.507172131147541},"n_leg_dropped":{"R":0,"Gc":6,"A":0},"mean_content_share":0.3255860884735551,"mean_R":0.017665432014194148,"mean_A":2.187581877352605,"mean_mc":-0.6974524659526131}},"rejection_reason":null,"reign_number":null,"score":0.002335591080465307,"score_king":0.002632679494977865,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9119067,"blocks_since_crown":15838,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1150.9561522773624,"mean_len_y":715.3677770224338,"n_samples":3000,"think_close_rate":0.9666666666666667,"n_text_fallback":24,"by_dialect":{"bash":{"n_turns":310,"zero_ref_turns":2,"mean_refs":2.9290322580645163,"ref_pair_agreement":0.2156215621562156,"ref_pair_n":303},"terminus_json":{"n_turns":25,"zero_ref_turns":0,"mean_refs":2.88,"ref_pair_agreement":0.7222222222222222,"ref_pair_n":24},"text":{"n_turns":367,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":271,"zero_ref_turns":3,"mean_refs":2.904059040590406,"ref_pair_agreement":0.17829457364341086,"ref_pair_n":258},"boxed":{"n_turns":27,"zero_ref_turns":2,"mean_refs":2.740740740740741,"ref_pair_agreement":0.8533333333333333,"ref_pair_n":25}},"ref_pair_agreement":0.2459016393442623,"ref_pair_n":610},"duel_seconds":2267.5832936060615,"challenger":{"reason":0.002335591080465307,"n_turns":993,"n_pairs":2915,"n_forfeits":10,"forfeit_rate":0.010070493454179255,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":4.028175200248074,"mean_len_z":867.9313893653516,"median_len_z":582.0,"mean_len_y":471.48576329331047,"mean_b":0.09405150191133041,"b_gate_pass_rate":0.4933104631217839,"mean_r_leg":0.018539277376539653,"mean_g_leg":0.058684557227572924,"g_bind_frac":0.21871820956256358,"a_match":0.19539295392953931,"a_match_n":615,"a_match_centered":-0.05206611570247934,"n_turns_cap_raised":92,"mean_cap_tokens":2169.5649546827794,"max_cap_tokens":5071,"len_z_delta":-283.02476291201083,"len_y_delta":-243.8820137291233,"n_samples":996,"think_close_rate":0.9929718875502008,"n_text_fallback":8,"by_dialect":{"bash":{"n_turns":308,"n_valid":306,"parse_rate":0.9935064935064936,"reason":0.006598211752630345,"mean_b":0.11845528129595506,"b_gate_pass_rate":0.850828729281768,"median_len_z":420.0,"mean_r_leg":0.019715520256643432,"mean_g_leg":0.045405685212839775,"g_bind_frac":0.31699346405228757,"a_match":0.16122004357298475,"a_match_n":306,"a_match_centered":-0.056291390728476824},"boxed":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":0.00459463616687391,"mean_b":1.4383888007093413,"b_gate_pass_rate":0.527027027027027,"median_len_z":2170.0,"mean_r_leg":0.03869466930604068,"mean_g_leg":0.02895959885364115,"g_bind_frac":0.24,"a_match":0.8533333333333333,"a_match_n":25,"a_match_centered":-2.220446049250313e-18},"terminus_json":{"n_turns":25,"n_valid":24,"parse_rate":0.96,"reason":-0.011017655957202747,"mean_b":0.01638790848539493,"b_gate_pass_rate":0.17391304347826086,"median_len_z":619.0,"mean_r_leg":0.0007801636894421531,"mean_g_leg":0.02872060777381328,"g_bind_frac":0.25,"a_match":0.6875,"a_match_n":24,"a_match_centered":-0.03623188405797101},"text":{"n_turns":367,"n_valid":360,"parse_rate":0.9809264305177112,"reason":0.00012854159088796071,"mean_b":0.033501675573804124,"b_gate_pass_rate":0.28055555555555556,"median_len_z":711.0,"mean_r_leg":0.026794982325049784,"mean_g_leg":0.0659302071191805,"g_bind_frac":0.16111111111111112,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":268,"n_valid":268,"parse_rate":1.0,"reason":0.0014940054253516528,"mean_b":0.029485072351965513,"b_gate_pass_rate":0.39898348157560354,"median_len_z":497.0,"mean_r_leg":0.005816702105932981,"mean_g_leg":0.06956948118939434,"g_bind_frac":0.1791044776119403,"a_match":0.12692307692307692,"a_match_n":260,"a_match_centered":-0.05359477124183006}}},"king":{"reason":0.002632679494977865,"n_turns":993,"n_pairs":2919,"n_forfeits":9,"forfeit_rate":0.00906344410876133,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":6.185392207895178,"mean_len_z":860.9842411784858,"median_len_z":564.0,"mean_len_y":478.8458376156218,"mean_b":0.09645014054622854,"b_gate_pass_rate":0.49297704693388145,"mean_r_leg":0.017665432014194148,"mean_g_leg":0.05870951837997377,"g_bind_frac":0.20121951219512196,"a_match":0.19281045751633988,"a_match_n":612,"a_match_centered":-0.05417357656163626,"n_turns_cap_raised":92,"mean_cap_tokens":2169.5649546827794,"max_cap_tokens":5071,"len_z_delta":-289.9719110988766,"len_y_delta":-236.52193940681195,"n_samples":993,"think_close_rate":0.9929506545820745,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":308,"n_valid":306,"parse_rate":0.9935064935064936,"reason":0.00774100465489184,"mean_b":0.11907788312217586,"b_gate_pass_rate":0.8598233995584988,"median_len_z":441.0,"mean_r_leg":0.020230332556317128,"mean_g_leg":0.04681653466519775,"g_bind_frac":0.27450980392156865,"a_match":0.16448801742919392,"a_match_n":306,"a_match_centered":-0.04950495049504951},"boxed":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":0.003541635882061535,"mean_b":1.4817449990205103,"b_gate_pass_rate":0.527027027027027,"median_len_z":1959.0,"mean_r_leg":0.036388351505988265,"mean_g_leg":0.028324538137602683,"g_bind_frac":0.28,"a_match":0.8133333333333332,"a_match_n":25,"a_match_centered":-0.04},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.00419156181081486,"mean_b":0.01589906763671982,"b_gate_pass_rate":0.20833333333333334,"median_len_z":477.0,"mean_r_leg":0.0006818467009212189,"mean_g_leg":0.027363756885689296,"g_bind_frac":0.28,"a_match":0.7133333333333333,"a_match_n":25,"a_match_centered":0.020833333333333332},"text":{"n_turns":367,"n_valid":360,"parse_rate":0.9809264305177112,"reason":0.0007186487224362968,"mean_b":0.03626679332579491,"b_gate_pass_rate":0.28888888888888886,"median_len_z":704.5,"mean_r_leg":0.02429725717675382,"mean_g_leg":0.06704620370602259,"g_bind_frac":0.1527777777777778,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":268,"n_valid":268,"parse_rate":1.0,"reason":-6.520383622744138e-05,"mean_b":0.030103428915539642,"b_gate_pass_rate":0.3735705209656925,"median_len_z":489.0,"mean_r_leg":0.00566617836167869,"mean_g_leg":0.06684875286788525,"g_bind_frac":0.16791044776119404,"a_match":0.115234375,"a_match_n":256,"a_match_centered":-0.06839309428950864}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T22:53:17.163363+00:00","challenge_id":"chal-00644","repo":"r2://affine-private-models/models/registrations/13b0281672ef0c5b9b54bd1851597b91f3dcee64f20e0e47dec1f97d68ef0fd0/","hotkey":"5Dy9Hk1rPWst6sPKDEGUYEcoztcP6K2yq6Abtaq1vNpsdFJ1","uid":253,"duration_s":2439.3,"revision":"7cf33e4f62da8916a7ed1035493b944fa21c524f3a4a5bfd5db74b78a16918ea","accepted":false,"error_code":null,"error_detail":"","z":-2.259549576108505,"margin":-0.14417138593988027,"se":0.0638053652215848,"n_paired_turns":985,"n_forfeit_turns":16,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":15789191605193046926,"n":1000,"digest":"bad25d119dcf53018f5a5386306957b9bed5038c6cdc0527b33d88f75053a42c","n_paired_turns":985,"n_forfeit_turns":16,"margin":-0.14417138593988027,"se":0.0638053652215848,"z":-2.259549576108505,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":0.95,"n":20,"by_reason":{"no_think_close":1},"by_prompt":{"assistant_bash":{"ok":false,"reasons":["no_think_close"]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.14417138593988027,"se":0.0638053652215848,"z":-2.259549576108505,"sd_diff":2.0025128617799,"n_paired_turns":985,"n_forfeit_turns":16,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.029264094787215946,"A":5.65491144790002,"Mc":0.15871615564137256},"terminus_json":{"R":0.0011492364381685148,"A":7.385302266783502,"Mc":0.12818042252503847},"text":{"R":0.0643279424437823,"A":20.02365323236543,"Mc":0.1753311813897372},"tool_call":{"R":0.007470081447452611,"A":5.639012268795104,"Mc":0.19106307434661388},"boxed":{"R":0.12533737498132627,"A":3.2220624379744454,"Mc":0.11229759174950416}},"challenger":{"mean":-0.8441289233851584,"mean_valid":-0.6832821725379825,"sd_valid":1.6050997703154033,"n_turns":995,"n_valid":971,"n_forfeits":14,"n_unscorable":10,"mean_z_R":0.1879474969671198,"mean_typ_c":0.7181198360972416,"mean_z_A":-0.16649537633851086,"bind_frac":{"R":0.325437693099897,"Gc":0.1462409886714727,"A":0.5283213182286303},"n_leg_dropped":{"R":0,"Gc":1,"A":0},"mean_content_share":0.33304286123267934,"mean_R":0.016319881163436727,"mean_A":2.161695741124243,"mean_mc":-0.6574633451646706},"king":{"mean":-0.711418026758214,"mean_valid":-0.642304259575101,"sd_valid":1.3996583743734698,"n_turns":995,"n_valid":980,"n_forfeits":6,"n_unscorable":9,"mean_z_R":0.2024235505969389,"mean_typ_c":0.6819171079629485,"mean_z_A":-0.1494193230531674,"bind_frac":{"R":0.3040816326530612,"Gc":0.17142857142857143,"A":0.5244897959183673},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3190613672913055,"mean_R":0.017786942358882733,"mean_A":1.7667039845716968,"mean_mc":-0.7050441327589849}},"rejection_reason":null,"reign_number":null,"score":0.0028939701522547245,"score_king":0.0032481750238515755,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9118858,"blocks_since_crown":15629,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1160.4351222826087,"mean_len_y":581.3699048913044,"n_samples":3000,"think_close_rate":0.975,"n_text_fallback":18,"by_dialect":{"text":{"n_turns":344,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":317,"zero_ref_turns":1,"mean_refs":2.9400630914826498,"ref_pair_agreement":0.16132478632478633,"ref_pair_n":312},"tool_call":{"n_turns":271,"zero_ref_turns":4,"mean_refs":2.885608856088561,"ref_pair_agreement":0.19010416666666666,"ref_pair_n":256},"terminus_json":{"n_turns":38,"zero_ref_turns":0,"mean_refs":2.9473684210526314,"ref_pair_agreement":0.6754385964912281,"ref_pair_n":38},"boxed":{"n_turns":30,"zero_ref_turns":0,"mean_refs":2.8666666666666667,"ref_pair_agreement":0.8024691358024691,"ref_pair_n":27}},"ref_pair_agreement":0.23117430226434968,"ref_pair_n":633},"duel_seconds":2078.876687502954,"challenger":{"reason":0.0028939701522547245,"n_turns":995,"n_pairs":2902,"n_forfeits":14,"forfeit_rate":0.01407035175879397,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-0.6197697276964714,"mean_len_z":942.5899379738112,"median_len_z":489.0,"mean_len_y":480.11647139903516,"mean_b":0.1025569556608169,"b_gate_pass_rate":0.5117160578911096,"mean_r_leg":0.016319881163436727,"mean_g_leg":0.057899848365869505,"g_bind_frac":0.20591233435270132,"a_match":0.21462264150943397,"a_match_n":636,"a_match_centered":-0.013643659711075442,"n_turns_cap_raised":84,"mean_cap_tokens":2157.5336683417086,"max_cap_tokens":5090,"len_z_delta":-217.84518430879757,"len_y_delta":-101.25343349226921,"n_samples":998,"think_close_rate":0.9859719438877755,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":316,"n_valid":313,"parse_rate":0.990506329113924,"reason":0.008486603361229797,"mean_b":0.11885188631052483,"b_gate_pass_rate":0.8624052004333694,"median_len_z":422.0,"mean_r_leg":0.02504612368975923,"mean_g_leg":0.048635725312884535,"g_bind_frac":0.2747603833865815,"a_match":0.14802981895633655,"a_match_n":313,"a_match_centered":-0.00970873786407767},"boxed":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":0.00297301250944059,"mean_b":1.4687712829468371,"b_gate_pass_rate":0.27906976744186046,"median_len_z":2898.0,"mean_r_leg":0.05206065616920561,"mean_g_leg":0.023328013846281092,"g_bind_frac":0.3333333333333333,"a_match":0.75,"a_match_n":28,"a_match_centered":-0.0617283950617284},"terminus_json":{"n_turns":38,"n_valid":37,"parse_rate":0.9736842105263158,"reason":-0.0031021687180769588,"mean_b":0.016711720850430285,"b_gate_pass_rate":0.1834862385321101,"median_len_z":606.0,"mean_r_leg":0.0017057284055127073,"mean_g_leg":0.04031429245883078,"g_bind_frac":0.10810810810810811,"a_match":0.7252252252252251,"a_match_n":37,"a_match_centered":0.05855855855855856},"text":{"n_turns":344,"n_valid":336,"parse_rate":0.9767441860465116,"reason":9.000031686777995e-06,"mean_b":0.038725420330311296,"b_gate_pass_rate":0.31845238095238093,"median_len_z":557.5,"mean_r_leg":0.015049783222723245,"mean_g_leg":0.06220178547400801,"g_bind_frac":0.1488095238095238,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":267,"n_valid":265,"parse_rate":0.9925093632958801,"reason":0.0008364406908175661,"mean_b":0.02673822508247106,"b_gate_pass_rate":0.4175257731958763,"median_len_z":436.0,"mean_r_leg":0.005617765688760911,"mean_g_leg":0.06975660403152173,"g_bind_frac":0.19622641509433963,"a_match":0.1640826873385013,"a_match_n":258,"a_match_centered":-0.024}}},"king":{"reason":0.0032481750238515755,"n_turns":995,"n_pairs":2928,"n_forfeits":6,"forfeit_rate":0.006030150753768844,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":20.562001693188837,"mean_len_z":862.4573087431694,"median_len_z":573.0,"mean_len_y":438.0648907103825,"mean_b":0.10788797002307363,"b_gate_pass_rate":0.5396174863387978,"mean_r_leg":0.017786942358882733,"mean_g_leg":0.05716109757322822,"g_bind_frac":0.23053589484327602,"a_match":0.20338541666666665,"a_match_n":640,"a_match_centered":-0.025743099787685776,"n_turns_cap_raised":84,"mean_cap_tokens":2157.5336683417086,"max_cap_tokens":5090,"len_z_delta":-297.97781353943935,"len_y_delta":-143.3050141809219,"n_samples":995,"think_close_rate":0.9949748743718593,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":316,"n_valid":315,"parse_rate":0.9968354430379747,"reason":0.009700862141347414,"mean_b":0.12169283008893736,"b_gate_pass_rate":0.8675995694294941,"median_len_z":438.0,"mean_r_leg":0.026899544806696953,"mean_g_leg":0.04840570684073856,"g_bind_frac":0.30793650793650795,"a_match":0.1513227513227513,"a_match_n":315,"a_match_centered":-0.008574490889603431},"boxed":{"n_turns":30,"n_valid":29,"parse_rate":0.9666666666666667,"reason":0.001632039170250854,"mean_b":1.3904981771801372,"b_gate_pass_rate":0.5647058823529412,"median_len_z":2347.0,"mean_r_leg":0.08702137354592046,"mean_g_leg":0.030254631919555068,"g_bind_frac":0.27586206896551724,"a_match":0.8148148148148148,"a_match_n":27,"a_match_centered":0.012345679012345677},"terminus_json":{"n_turns":38,"n_valid":38,"parse_rate":1.0,"reason":-0.004021878150497273,"mean_b":0.020835364057904295,"b_gate_pass_rate":0.3392857142857143,"median_len_z":675.0,"mean_r_leg":0.001337656882275462,"mean_g_leg":0.030674617361395425,"g_bind_frac":0.23684210526315788,"a_match":0.6359649122807017,"a_match_n":38,"a_match_centered":-0.039473684210526314},"text":{"n_turns":344,"n_valid":341,"parse_rate":0.9912790697674418,"reason":-0.0006147890341245148,"mean_b":0.05743213780124155,"b_gate_pass_rate":0.34017595307917886,"median_len_z":667.0,"mean_r_leg":0.014717228420756715,"mean_g_leg":0.05788034872071487,"g_bind_frac":0.19941348973607037,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":267,"n_valid":266,"parse_rate":0.9962546816479401,"reason":0.001804566795568311,"mean_b":0.030249492001886646,"b_gate_pass_rate":0.43645699614890887,"median_len_z":529.0,"mean_r_leg":0.005732720650335638,"mean_g_leg":0.07332447047340665,"g_bind_frac":0.17293233082706766,"a_match":0.13974358974358975,"a_match_n":260,"a_match_centered":-0.048941798941798946}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T22:10:49.732400+00:00","challenge_id":"chal-00643","repo":"r2://affine-private-models/models/registrations/ba3dc5aad445390740f15ae85ba1e0c7a6f6572631ba8c9f1410df0b7fab8939/","hotkey":"5ERkCPzawJ5SaMFHwY2uPPwBaMcyk6LRd2iXFYBSe7ZzoYEa","uid":29,"duration_s":2446.6,"revision":"818cd79e5f075026a74431dd7029b3dd70c0bf6c24812156b864dbd18194e428","accepted":false,"error_code":null,"error_detail":"","z":3.5642095091826214,"margin":0.15709741732778348,"se":0.044076370068327035,"n_paired_turns":987,"n_forfeit_turns":7,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":8973083408890875049,"n":1000,"digest":"a238cda971c6d805f2cb181c6abe57adb22ff7ba07ee72e3bebef60746df1b15","n_paired_turns":987,"n_forfeit_turns":7,"margin":0.15709741732778348,"se":0.044076370068327035,"z":3.5642095091826214,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.15709741732778348,"se":0.044076370068327035,"z":3.5642095091826214,"sd_diff":1.38472775491102,"n_paired_turns":987,"n_forfeit_turns":7,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.024646793411842127,"A":5.553104223908682,"Mc":0.15244702776942942},"tool_call":{"R":0.009811137877920595,"A":6.304459569943139,"Mc":0.20458211197992243},"text":{"R":0.04237587598485867,"A":23.550756451092127,"Mc":0.18231188266934345},"terminus_json":{"R":0.0019053571553641394,"A":8.240912427591676,"Mc":0.1700310657039225},"boxed":{"R":0.1254085535317292,"A":3.368693999563735,"Mc":0.12206070135784089}},"challenger":{"mean":-0.5511109289688008,"mean_valid":-0.4928171964279087,"sd_valid":1.0930844701500864,"n_turns":995,"n_valid":982,"n_forfeits":5,"n_unscorable":8,"mean_z_R":0.19797917986414348,"mean_typ_c":0.8664185914112992,"mean_z_A":-0.054259761428501765,"bind_frac":{"R":0.3910386965376782,"Gc":0.12729124236252545,"A":0.4816700610997963},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.327292844797547,"mean_R":0.015576362685486721,"mean_A":2.124138013756933,"mean_mc":-0.6820958826554424},"king":{"mean":-0.7082083462965842,"mean_valid":-0.6275526916272741,"sd_valid":1.326680436802477,"n_turns":995,"n_valid":980,"n_forfeits":7,"n_unscorable":8,"mean_z_R":0.1521600238238236,"mean_typ_c":0.6936180500519821,"mean_z_A":-0.13031304875147465,"bind_frac":{"R":0.3377551020408163,"Gc":0.1540816326530612,"A":0.5081632653061224},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.3244551671075939,"mean_R":0.014470292536763043,"mean_A":1.3530743793333626,"mean_mc":-0.7087654685123115}},"rejection_reason":null,"reign_number":null,"score":0.003126207818299911,"score_king":0.002660961941984209,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9118645,"blocks_since_crown":15416,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1202.4219122150391,"mean_len_y":656.6573664511739,"n_samples":3000,"think_close_rate":0.9676666666666667,"n_text_fallback":19,"by_dialect":{"tool_call":{"n_turns":285,"zero_ref_turns":1,"mean_refs":2.912280701754386,"ref_pair_agreement":0.16545893719806762,"ref_pair_n":276},"text":{"n_turns":349,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":36,"zero_ref_turns":0,"mean_refs":2.75,"ref_pair_agreement":0.5151515151515151,"ref_pair_n":33},"bash":{"n_turns":309,"zero_ref_turns":4,"mean_refs":2.9158576051779934,"ref_pair_agreement":0.19581958195819582,"ref_pair_n":303},"boxed":{"n_turns":21,"zero_ref_turns":0,"mean_refs":2.9523809523809526,"ref_pair_agreement":0.7777777777777777,"ref_pair_n":21}},"ref_pair_agreement":0.21853607161664035,"ref_pair_n":633},"duel_seconds":2086.4660371779464,"challenger":{"reason":0.003126207818299911,"n_turns":995,"n_pairs":2924,"n_forfeits":5,"forfeit_rate":0.005025125628140704,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-2.0700296722370637,"mean_len_z":905.437756497948,"median_len_z":646.0,"mean_len_y":417.3669630642955,"mean_b":0.08261588074721901,"b_gate_pass_rate":0.5430916552667578,"mean_r_leg":0.015576362685486721,"mean_g_leg":0.060455120211284796,"g_bind_frac":0.24242424242424243,"a_match":0.18055555555555555,"a_match_n":636,"a_match_centered":-0.037480063795853266,"n_turns_cap_raised":92,"mean_cap_tokens":2154.425125628141,"max_cap_tokens":5103,"len_z_delta":-296.9841557170911,"len_y_delta":-239.29040338687838,"n_samples":998,"think_close_rate":0.9949899799599199,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":305,"n_valid":305,"parse_rate":1.0,"reason":0.009782381915885706,"mean_b":0.11747251956982382,"b_gate_pass_rate":0.8745837957824639,"median_len_z":547.0,"mean_r_leg":0.02404815295601924,"mean_g_leg":0.0462849854632181,"g_bind_frac":0.3114754098360656,"a_match":0.14972677595628414,"a_match_n":305,"a_match_centered":-0.045104510451045104},"boxed":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":0.010880841020781363,"mean_b":1.2049744683546255,"b_gate_pass_rate":0.9032258064516129,"median_len_z":2295.0,"mean_r_leg":0.09876189406527228,"mean_g_leg":0.039740854556364114,"g_bind_frac":0.38095238095238093,"a_match":0.746031746031746,"a_match_n":21,"a_match_centered":-0.03174603174603175},"terminus_json":{"n_turns":36,"n_valid":36,"parse_rate":1.0,"reason":-0.0027289802035788957,"mean_b":0.01905010291848635,"b_gate_pass_rate":0.3838383838383838,"median_len_z":749.0,"mean_r_leg":0.0011928665299999963,"mean_g_leg":0.04869995149187075,"g_bind_frac":0.2777777777777778,"a_match":0.5324074074074074,"a_match_n":36,"a_match_centered":0.06565656565656565},"text":{"n_turns":349,"n_valid":344,"parse_rate":0.9856733524355301,"reason":-0.0001987995086474993,"mean_b":0.035274727226373426,"b_gate_pass_rate":0.29941860465116277,"median_len_z":694.0,"mean_r_leg":0.012269180278296743,"mean_g_leg":0.06718037625613196,"g_bind_frac":0.18023255813953487,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.00023266531434394444,"mean_b":0.027383372828822673,"b_gate_pass_rate":0.4783132530120482,"median_len_z":604.5,"mean_r_leg":0.0061562373973985535,"mean_g_leg":0.07054874229362691,"g_bind_frac":0.22887323943661972,"a_match":0.12530413625304138,"a_match_n":274,"a_match_centered":-0.04197530864197531}}},"king":{"reason":0.002660961941984209,"n_turns":995,"n_pairs":2918,"n_forfeits":7,"forfeit_rate":0.007035175879396985,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.279044506460988,"mean_len_z":835.8039753255655,"median_len_z":586.0,"mean_len_y":428.4955448937628,"mean_b":0.08145479715585718,"b_gate_pass_rate":0.5109664153529815,"mean_r_leg":0.014470292536763043,"mean_g_leg":0.06011448600790937,"g_bind_frac":0.2257085020242915,"a_match":0.1902145473574045,"a_match_n":637,"a_match_centered":-0.026762056173820877,"n_turns_cap_raised":92,"mean_cap_tokens":2154.425125628141,"max_cap_tokens":5103,"len_z_delta":-366.61793688947364,"len_y_delta":-228.16182155741103,"n_samples":995,"think_close_rate":0.9939698492462311,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":305,"n_valid":304,"parse_rate":0.9967213114754099,"reason":0.008627279824370579,"mean_b":0.11659922603566238,"b_gate_pass_rate":0.8853006681514477,"median_len_z":436.5,"mean_r_leg":0.020460681445596558,"mean_g_leg":0.04620725508268865,"g_bind_frac":0.27960526315789475,"a_match":0.15789473684210525,"a_match_n":304,"a_match_centered":-0.03752759381898455},"boxed":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":0.004774901472778341,"mean_b":1.1746016522668958,"b_gate_pass_rate":0.532258064516129,"median_len_z":2243.0,"mean_r_leg":0.09319019531781773,"mean_g_leg":0.033614767857005644,"g_bind_frac":0.42857142857142855,"a_match":0.7777777777777777,"a_match_n":21,"a_match_centered":0.0},"terminus_json":{"n_turns":36,"n_valid":36,"parse_rate":1.0,"reason":-0.003987113120598372,"mean_b":0.021469455287371975,"b_gate_pass_rate":0.23232323232323232,"median_len_z":774.0,"mean_r_leg":0.0011243577942703271,"mean_g_leg":0.048479281366135454,"g_bind_frac":0.19444444444444445,"a_match":0.5601851851851852,"a_match_n":36,"a_match_centered":0.09595959595959595},"text":{"n_turns":349,"n_valid":343,"parse_rate":0.9828080229226361,"reason":-0.0002028957152622023,"mean_b":0.03476800869759944,"b_gate_pass_rate":0.3032069970845481,"median_len_z":675.0,"mean_r_leg":0.01266121893209044,"mean_g_leg":0.06612743360041604,"g_bind_frac":0.18075801749271136,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":284,"n_valid":284,"parse_rate":1.0,"reason":0.0004591920136653729,"mean_b":0.02680955862281838,"b_gate_pass_rate":0.39518072289156625,"median_len_z":532.5,"mean_r_leg":0.006113847855231011,"mean_g_leg":0.07117335440688877,"g_bind_frac":0.2112676056338028,"a_match":0.1328502415458937,"a_match_n":276,"a_match_centered":-0.031746031746031744}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T21:28:52.806551+00:00","challenge_id":"chal-00642","repo":"r2://affine-private-models/models/registrations/a9e5af038298e45109ec155106caa01d0dea7619d7f204c41f0de6fdf9112661/","hotkey":"5CRNJTn9WCH6HgyMHwtwKiHePy9YiCJtrRrnu7rrz33drUMz","uid":215,"duration_s":2468.9,"revision":"eaf50acd281f7025d886a39c7325072ceeec3b802b251486e3ad460a9a8adbf2","accepted":false,"error_code":null,"error_detail":"","z":-0.9799382543689819,"margin":-0.043273532934732344,"se":0.04415944855892758,"n_paired_turns":979,"n_forfeit_turns":6,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2525009578698588789,"n":1000,"digest":"40d2e0fe72ff5f036b720526a272cabcbe1c6a100ac3aa7815aed1df0e0f49cc","n_paired_turns":979,"n_forfeit_turns":6,"margin":-0.043273532934732344,"se":0.04415944855892758,"z":-0.9799382543689819,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":1},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.043273532934732344,"se":0.04415944855892758,"z":-0.9799382543689819,"sd_diff":1.3817039126350374,"n_paired_turns":979,"n_forfeit_turns":6,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.025199133689154808,"A":7.8113910227308265,"Mc":0.1650354340479158},"text":{"R":0.04596549763013254,"A":18.890443717267928,"Mc":0.18576947816873712},"tool_call":{"R":0.010760150329247717,"A":6.714218721518045,"Mc":0.18370757298016188},"terminus_json":{"R":0.002378267247933987,"A":7.871137289832926,"Mc":0.1714358054494356},"boxed":{"R":0.0956622718298452,"A":3.3175932543415065,"Mc":0.14930474790405757}},"challenger":{"mean":-0.7045331854345451,"mean_valid":-0.6814104283934694,"sd_valid":1.54756780162267,"n_turns":991,"n_valid":977,"n_forfeits":2,"n_unscorable":12,"mean_z_R":0.17844585009238748,"mean_typ_c":0.6901267339461307,"mean_z_A":-0.15554116730888276,"bind_frac":{"R":0.3132036847492323,"Gc":0.15148413510747186,"A":0.5353121801432958},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.32527010984416954,"mean_R":0.01529673980755202,"mean_A":1.037360234432334,"mean_mc":-0.6910963930543584},"king":{"mean":-0.6612596524998128,"mean_valid":-0.6030525665270192,"sd_valid":1.4008001859311803,"n_turns":991,"n_valid":974,"n_forfeits":5,"n_unscorable":12,"mean_z_R":0.20415602889052692,"mean_typ_c":0.7501721975063875,"mean_z_A":-0.1478631046513086,"bind_frac":{"R":0.3049281314168378,"Gc":0.14168377823408623,"A":0.553388090349076},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3238131651326102,"mean_R":0.015137480656334974,"mean_A":1.10729752127657,"mean_mc":-0.7020336340136865}},"rejection_reason":null,"reign_number":null,"score":0.0031708624580696317,"score_king":0.0027524081809432513,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9118433,"blocks_since_crown":15204,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1184.8398224043715,"mean_len_y":607.0286885245902,"n_samples":3000,"think_close_rate":0.9706666666666667,"n_text_fallback":14,"by_dialect":{"tool_call":{"n_turns":282,"zero_ref_turns":6,"mean_refs":2.900709219858156,"ref_pair_agreement":0.17224287484510534,"ref_pair_n":269},"bash":{"n_turns":308,"zero_ref_turns":3,"mean_refs":2.8733766233766236,"ref_pair_agreement":0.17283950617283952,"ref_pair_n":297},"text":{"n_turns":365,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":20,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.7333333333333333,"ref_pair_n":20},"terminus_json":{"n_turns":25,"zero_ref_turns":0,"mean_refs":2.8,"ref_pair_agreement":0.36231884057971014,"ref_pair_n":23}},"ref_pair_agreement":0.19813902572523262,"ref_pair_n":609},"duel_seconds":2106.277362781111,"challenger":{"reason":0.0031708624580696317,"n_turns":991,"n_pairs":2922,"n_forfeits":2,"forfeit_rate":0.0020181634712411706,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":1.5166029764714635,"mean_len_z":807.1317590691307,"median_len_z":553.0,"mean_len_y":436.24743326488704,"mean_b":0.0848837981068102,"b_gate_pass_rate":0.5246406570841889,"mean_r_leg":0.01529673980755202,"mean_g_leg":0.060201667063048976,"g_bind_frac":0.22143579373104147,"a_match":0.16154261057173677,"a_match_n":618,"a_match_centered":-0.035044150110375274,"n_turns_cap_raised":81,"mean_cap_tokens":2166.1130171543896,"max_cap_tokens":5101,"len_z_delta":-377.7080633352408,"len_y_delta":-170.78125525970313,"n_samples":994,"think_close_rate":0.9989939637826962,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":305,"n_valid":304,"parse_rate":0.9967213114754099,"reason":0.006666937793547166,"mean_b":0.12195938826840785,"b_gate_pass_rate":0.8639455782312925,"median_len_z":437.0,"mean_r_leg":0.023148524809604335,"mean_g_leg":0.04787342411448491,"g_bind_frac":0.27960526315789475,"a_match":0.1419956140350877,"a_match_n":304,"a_match_centered":-0.02759009009009009},"boxed":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":0.003959462700630926,"mean_b":1.2298212362680674,"b_gate_pass_rate":0.7,"median_len_z":1929.5,"mean_r_leg":0.03512484130333969,"mean_g_leg":0.02277051916056341,"g_bind_frac":0.45,"a_match":0.7333333333333333,"a_match_n":20,"a_match_centered":-2.7755575615628915e-18},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.0023109230368991767,"mean_b":0.012354592473176124,"b_gate_pass_rate":0.15714285714285714,"median_len_z":317.0,"mean_r_leg":0.0011489773866261968,"mean_g_leg":0.037270828251310534,"g_bind_frac":0.24,"a_match":0.38666666666666666,"a_match_n":25,"a_match_centered":0.014492753623188404},"text":{"n_turns":365,"n_valid":364,"parse_rate":0.9972602739726028,"reason":0.0016186514368753864,"mean_b":0.03735299227302292,"b_gate_pass_rate":0.31868131868131866,"median_len_z":684.5,"mean_r_leg":0.014988282553808184,"mean_g_leg":0.06414481802802975,"g_bind_frac":0.20054945054945056,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":276,"n_valid":276,"parse_rate":1.0,"reason":0.0017995823056719715,"mean_b":0.030585225432782703,"b_gate_pass_rate":0.45232273838630804,"median_len_z":446.5,"mean_r_leg":0.006899884120400731,"mean_g_leg":0.0733696845755622,"g_bind_frac":0.16666666666666666,"a_match":0.12019826517967783,"a_match_n":269,"a_match_centered":-0.050314465408805034}}},"king":{"reason":0.0027524081809432513,"n_turns":991,"n_pairs":2914,"n_forfeits":5,"forfeit_rate":0.005045408678102927,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":1.713637930926674,"mean_len_z":836.1859986273164,"median_len_z":586.0,"mean_len_y":487.0370624571036,"mean_b":0.08146109234891394,"b_gate_pass_rate":0.514070006863418,"mean_r_leg":0.015137480656334974,"mean_g_leg":0.05997917985045122,"g_bind_frac":0.21805273833671399,"a_match":0.17073170731707318,"a_match_n":615,"a_match_centered":-0.026067665002773157,"n_turns_cap_raised":81,"mean_cap_tokens":2166.1130171543896,"max_cap_tokens":5101,"len_z_delta":-348.6538237770551,"len_y_delta":-119.99162606748655,"n_samples":991,"think_close_rate":0.9979818365287588,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":305,"n_valid":302,"parse_rate":0.9901639344262295,"reason":0.006644494435225404,"mean_b":0.11535287173458986,"b_gate_pass_rate":0.8586088939566705,"median_len_z":505.0,"mean_r_leg":0.021799478292152896,"mean_g_leg":0.04925673335937148,"g_bind_frac":0.27483443708609273,"a_match":0.14624724061810154,"a_match_n":302,"a_match_centered":-0.024376417233560092},"boxed":{"n_turns":20,"n_valid":19,"parse_rate":0.95,"reason":-0.0034307214748385264,"mean_b":1.2304420315536695,"b_gate_pass_rate":0.5263157894736842,"median_len_z":2099.0,"mean_r_leg":0.043818146289815556,"mean_g_leg":0.02148471034912687,"g_bind_frac":0.3157894736842105,"a_match":0.6491228070175439,"a_match_n":19,"a_match_centered":-0.07017543859649124},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-2.268318484379541e-06,"mean_b":0.01389390069639589,"b_gate_pass_rate":0.2857142857142857,"median_len_z":427.0,"mean_r_leg":0.003916292114124141,"mean_g_leg":0.03428542063075448,"g_bind_frac":0.2,"a_match":0.41333333333333333,"a_match_n":25,"a_match_centered":0.043478260869565216},"text":{"n_turns":365,"n_valid":364,"parse_rate":0.9972602739726028,"reason":0.00037758571450281504,"mean_b":0.03643712179483004,"b_gate_pass_rate":0.3159340659340659,"median_len_z":731.5,"mean_r_leg":0.014743229032930663,"mean_g_leg":0.06200592100759638,"g_bind_frac":0.18956043956043955,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":276,"n_valid":276,"parse_rate":1.0,"reason":0.0022895581747694434,"mean_b":0.030948714848702482,"b_gate_pass_rate":0.4278728606356968,"median_len_z":541.0,"mean_r_leg":0.00740987692960054,"mean_g_leg":0.07401607825669332,"g_bind_frac":0.18840579710144928,"a_match":0.14188351920693928,"a_match_n":269,"a_match_centered":-0.03081761006289308}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T20:46:45.118103+00:00","challenge_id":"chal-00641","repo":"r2://affine-private-models/models/registrations/d1073d691869e2cbb0d54ac583a4c0aac252f8e949178fbb7d0d9d4c7e7935b9/","hotkey":"5GAp5FDxnnfXu5FYbNhyjZdnaFufg4vvieXtDer13WEHVBzL","uid":40,"duration_s":2495.2,"revision":"a671946da12b7d58c0401281393b5d05cf88d2b72df83fb19cd86b7a62bbf509","accepted":false,"error_code":null,"error_detail":"","z":0.6954963574359095,"margin":0.029148315837991854,"se":0.04191009129861315,"n_paired_turns":990,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":1677269691076023251,"n":1000,"digest":"a707649a39404c65f54d037e63f449c80a9f738bc67f3d1b63620509fe23808e","n_paired_turns":990,"n_forfeit_turns":4,"margin":0.029148315837991854,"se":0.04191009129861315,"z":0.6954963574359095,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.029148315837991854,"se":0.04191009129861315,"z":0.6954963574359095,"sd_diff":1.3186702374481305,"n_paired_turns":990,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.03225260988814447,"A":5.722931731803299,"Mc":0.15183933682627557},"tool_call":{"R":0.007946108698859538,"A":5.984317230490682,"Mc":0.19365925290764213},"text":{"R":0.043474949197762514,"A":20.868351799128476,"Mc":0.1799817209963223},"terminus_json":{"R":0.002447142872245188,"A":9.683211007535348,"Mc":0.11840424804669088},"boxed":{"R":0.13987457309996046,"A":3.5590492080087857,"Mc":0.106867207679972}},"challenger":{"mean":-0.6909556319779725,"mean_valid":-0.6565816369383918,"sd_valid":1.3988131551110432,"n_turns":996,"n_valid":987,"n_forfeits":3,"n_unscorable":6,"mean_z_R":0.19064706422014802,"mean_typ_c":0.6770352010486106,"mean_z_A":-0.11772988327406536,"bind_frac":{"R":0.3110435663627153,"Gc":0.17426545086119555,"A":0.5146909827760892},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3165897459546114,"mean_R":0.01790210687781875,"mean_A":2.116782758684579,"mean_mc":-0.7077786904225833},"king":{"mean":-0.7201039478159643,"mean_valid":-0.6858185494810585,"sd_valid":1.4740769163519614,"n_turns":996,"n_valid":987,"n_forfeits":3,"n_unscorable":6,"mean_z_R":0.21287655371279127,"mean_typ_c":0.6611205561956124,"mean_z_A":-0.1537714262502703,"bind_frac":{"R":0.3161094224924012,"Gc":0.17831813576494426,"A":0.5055724417426545},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3176792183730883,"mean_R":0.018110782235921847,"mean_A":1.9924740882579013,"mean_mc":-0.7019141453411553}},"rejection_reason":null,"reign_number":null,"score":0.005284483921678632,"score_king":0.004968114608786455,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9118221,"blocks_since_crown":14992,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1338.8097179748556,"mean_len_y":554.7200135915732,"n_samples":3000,"think_close_rate":0.9736666666666667,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":348,"zero_ref_turns":3,"mean_refs":2.8994252873563218,"ref_pair_agreement":0.18963831867057676,"ref_pair_n":341},"tool_call":{"n_turns":267,"zero_ref_turns":1,"mean_refs":2.940074906367041,"ref_pair_agreement":0.14942528735632185,"ref_pair_n":261},"text":{"n_turns":325,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":34,"zero_ref_turns":0,"mean_refs":2.911764705882353,"ref_pair_agreement":0.7352941176470589,"ref_pair_n":34},"terminus_json":{"n_turns":26,"zero_ref_turns":0,"mean_refs":2.8846153846153846,"ref_pair_agreement":0.5512820512820513,"ref_pair_n":26}},"ref_pair_agreement":0.21601208459214502,"ref_pair_n":662},"duel_seconds":2141.3977113338187,"challenger":{"reason":0.005284483921678632,"n_turns":996,"n_pairs":2935,"n_forfeits":3,"forfeit_rate":0.0030120481927710845,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.626677442283446,"mean_len_z":891.6660988074957,"median_len_z":614.0,"mean_len_y":431.1747870528109,"mean_b":0.1074341593836314,"b_gate_pass_rate":0.5512776831345826,"mean_r_leg":0.01790210687781875,"mean_g_leg":0.056623974126946676,"g_bind_frac":0.2537764350453172,"a_match":0.16741854636591477,"a_match_n":665,"a_match_centered":-0.044579533941236066,"n_turns_cap_raised":109,"mean_cap_tokens":2183.9246987951806,"max_cap_tokens":5100,"len_z_delta":-447.14361916735993,"len_y_delta":-123.54522653876228,"n_samples":999,"think_close_rate":0.997997997997998,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":345,"n_valid":344,"parse_rate":0.9971014492753624,"reason":0.010211533145873792,"mean_b":0.12352644235030014,"b_gate_pass_rate":0.8599801390268124,"median_len_z":494.0,"mean_r_leg":0.026208820345461285,"mean_g_leg":0.04598451766839275,"g_bind_frac":0.34593023255813954,"a_match":0.13662790697674418,"a_match_n":344,"a_match_centered":-0.04901960784313726},"boxed":{"n_turns":34,"n_valid":34,"parse_rate":1.0,"reason":0.005076457605476649,"mean_b":1.2136541340237772,"b_gate_pass_rate":0.5757575757575758,"median_len_z":1527.0,"mean_r_leg":0.08644644205155008,"mean_g_leg":0.024293730877504017,"g_bind_frac":0.4117647058823529,"a_match":0.6274509803921569,"a_match_n":34,"a_match_centered":-0.10784313725490195},"terminus_json":{"n_turns":26,"n_valid":26,"parse_rate":1.0,"reason":-0.0010829168296674421,"mean_b":0.019116222059766586,"b_gate_pass_rate":0.26666666666666666,"median_len_z":640.0,"mean_r_leg":0.0024077926292036308,"mean_g_leg":0.039982451335731126,"g_bind_frac":0.19230769230769232,"a_match":0.5897435897435898,"a_match_n":26,"a_match_centered":0.038461538461538464},"text":{"n_turns":325,"n_valid":323,"parse_rate":0.9938461538461538,"reason":0.0030104608823550254,"mean_b":0.04891443949361292,"b_gate_pass_rate":0.34365325077399383,"median_len_z":708.0,"mean_r_leg":0.012221406790523373,"mean_g_leg":0.06366233834763678,"g_bind_frac":0.21052631578947367,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":266,"n_valid":266,"parse_rate":1.0,"reason":0.0023215170785158773,"mean_b":0.027954856754214746,"b_gate_pass_rate":0.4356687898089172,"median_len_z":544.0,"mean_r_leg":0.006810759020241687,"mean_g_leg":0.06759573819278239,"g_bind_frac":0.17293233082706766,"a_match":0.10600255427841634,"a_match_n":261,"a_match_centered":-0.03875968992248062}}},"king":{"reason":0.004968114608786455,"n_turns":996,"n_pairs":2934,"n_forfeits":3,"forfeit_rate":0.0030120481927710845,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-0.6563312629168125,"mean_len_z":888.525221540559,"median_len_z":615.0,"mean_len_y":416.05862304021815,"mean_b":0.11345664459934009,"b_gate_pass_rate":0.5160190865712339,"mean_r_leg":0.018110782235921847,"mean_g_leg":0.05611240571527682,"g_bind_frac":0.2648539778449144,"a_match":0.1646586345381526,"a_match_n":664,"a_match_centered":-0.04921359715880264,"n_turns_cap_raised":109,"mean_cap_tokens":2183.9246987951806,"max_cap_tokens":5100,"len_z_delta":-450.28449643429667,"len_y_delta":-138.66139055135505,"n_samples":996,"think_close_rate":0.9979919678714859,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":345,"n_valid":344,"parse_rate":0.9971014492753624,"reason":0.009515060322503275,"mean_b":0.13337702703220583,"b_gate_pass_rate":0.8578528827037774,"median_len_z":496.0,"mean_r_leg":0.02550578595067049,"mean_g_leg":0.04443118143357391,"g_bind_frac":0.3546511627906977,"a_match":0.14777131782945735,"a_match_n":344,"a_match_centered":-0.04068627450980392},"boxed":{"n_turns":34,"n_valid":34,"parse_rate":1.0,"reason":0.005082964601040517,"mean_b":1.276977390438551,"b_gate_pass_rate":0.5656565656565656,"median_len_z":1637.0,"mean_r_leg":0.07991954618781444,"mean_g_leg":0.022572288433459296,"g_bind_frac":0.4117647058823529,"a_match":0.5098039215686274,"a_match_n":34,"a_match_centered":-0.22549019607843138},"terminus_json":{"n_turns":26,"n_valid":26,"parse_rate":1.0,"reason":0.0005895152258648049,"mean_b":0.015818125386389333,"b_gate_pass_rate":0.2,"median_len_z":666.0,"mean_r_leg":0.003277459972139486,"mean_g_leg":0.03888597440655838,"g_bind_frac":0.23076923076923078,"a_match":0.5897435897435898,"a_match_n":26,"a_match_centered":0.038461538461538464},"text":{"n_turns":325,"n_valid":323,"parse_rate":0.9938461538461538,"reason":0.0030329956033090626,"mean_b":0.050015722460492094,"b_gate_pass_rate":0.29721362229102166,"median_len_z":714.0,"mean_r_leg":0.014021852433040442,"mean_g_leg":0.06298942987261663,"g_bind_frac":0.21362229102167182,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":266,"n_valid":266,"parse_rate":1.0,"reason":0.0018484006605427518,"mean_b":0.028830764252805313,"b_gate_pass_rate":0.3719745222929936,"median_len_z":553.0,"mean_r_leg":0.00706195311167806,"mean_g_leg":0.06883914839081635,"g_bind_frac":0.19548872180451127,"a_match":0.09935897435897435,"a_match_n":260,"a_match_centered":-0.046044098573281456}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T20:03:59.519421+00:00","challenge_id":"chal-00640","repo":"r2://affine-private-models/models/registrations/4e865e4d865acbccc18e87df04e488aaef1b12730eb58a9ac75f7327471a5a13/","hotkey":"5CDcaPTheF2tvyCx2dXmXeKVZRRzT2aHgckyyxGMUTtoizCj","uid":46,"duration_s":2549.6,"revision":"20085e1ef1dd3835e168c7bd3b35f48f5b4209a87eb270cd88c56c514fd17479","accepted":false,"error_code":null,"error_detail":"","z":0.08873376569784702,"margin":0.0038656772615019977,"se":0.04356489585560091,"n_paired_turns":993,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":9821297424128770917,"n":1000,"digest":"d57e5672308f848447168f460ff5445f22ddb864cd3b84208623629d70d5a75e","n_paired_turns":993,"n_forfeit_turns":8,"margin":0.0038656772615019977,"se":0.04356489585560091,"z":0.08873376569784702,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.0038656772615019977,"se":0.04356489585560091,"z":0.08873376569784702,"sd_diff":1.3728127511984247,"n_paired_turns":993,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"text":{"R":0.04939067777070689,"A":22.871811395526567,"Mc":0.17238571760692006},"bash":{"R":0.028835429184653854,"A":5.723151565723215,"Mc":0.15128510971560294},"tool_call":{"R":0.00863403907285963,"A":5.913698148836871,"Mc":0.19732787784607017},"terminus_json":{"R":0.0022992591003689346,"A":10.063823961865538,"Mc":0.09730296637546994},"boxed":{"R":0.06576975328843965,"A":4.597099305053285,"Mc":0.1478670384155494}},"challenger":{"mean":-0.8129106169147394,"mean_valid":-0.7220510077120165,"sd_valid":1.637668447028236,"n_turns":998,"n_valid":985,"n_forfeits":8,"n_unscorable":5,"mean_z_R":0.16552171121501633,"mean_typ_c":0.5768930671179702,"mean_z_A":-0.12767891230528203,"bind_frac":{"R":0.3248730964467005,"Gc":0.17563451776649747,"A":0.49949238578680205},"n_leg_dropped":{"R":0,"Gc":2,"A":0},"mean_content_share":0.32310545112095485,"mean_R":0.015678151137762997,"mean_A":1.7876053792491164,"mean_mc":-0.7126473269189532},"king":{"mean":-0.8167762941762414,"mean_valid":-0.7601810325070928,"sd_valid":1.7053750206753788,"n_turns":998,"n_valid":988,"n_forfeits":5,"n_unscorable":5,"mean_z_R":0.1277668980034422,"mean_typ_c":0.5214155803904404,"mean_z_A":-0.15158397372620624,"bind_frac":{"R":0.31275303643724695,"Gc":0.17105263157894737,"A":0.5161943319838057},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3214436392000693,"mean_R":0.015026252043488803,"mean_A":1.602826706047815,"mean_mc":-0.7089934668915611}},"rejection_reason":null,"reign_number":null,"score":0.003689582938269946,"score_king":0.0034868765430587194,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9118002,"blocks_since_crown":14773,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1179.5886932972242,"mean_len_y":633.2505077860528,"n_samples":3000,"think_close_rate":0.9763333333333334,"n_text_fallback":22,"by_dialect":{"boxed":{"n_turns":32,"zero_ref_turns":0,"mean_refs":2.90625,"ref_pair_agreement":0.5698924731182796,"ref_pair_n":31},"tool_call":{"n_turns":274,"zero_ref_turns":1,"mean_refs":2.937956204379562,"ref_pair_agreement":0.18407960199004977,"ref_pair_n":268},"text":{"n_turns":359,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":308,"zero_ref_turns":1,"mean_refs":2.9155844155844157,"ref_pair_agreement":0.16666666666666669,"ref_pair_n":302},"terminus_json":{"n_turns":27,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.5802469135802469,"ref_pair_n":27}},"ref_pair_agreement":0.21178343949044587,"ref_pair_n":628},"duel_seconds":2128.3247631071135,"challenger":{"reason":0.003689582938269946,"n_turns":998,"n_pairs":2930,"n_forfeits":8,"forfeit_rate":0.008016032064128256,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":3.922883021900152,"mean_len_z":814.4556313993174,"median_len_z":561.0,"mean_len_y":470.419795221843,"mean_b":0.09229028090461847,"b_gate_pass_rate":0.5146757679180888,"mean_r_leg":0.015678151137762997,"mean_g_leg":0.05972301589474611,"g_bind_frac":0.21616161616161617,"a_match":0.17891373801916932,"a_match_n":626,"a_match_centered":-0.03166935050993022,"n_turns_cap_raised":88,"mean_cap_tokens":2176.5961923847694,"max_cap_tokens":5087,"len_z_delta":-365.1330618979067,"len_y_delta":-162.83071256420982,"n_samples":1001,"think_close_rate":0.994005994005994,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":307,"n_valid":305,"parse_rate":0.993485342019544,"reason":0.008680420068325515,"mean_b":0.12302619521575806,"b_gate_pass_rate":0.8710762331838565,"median_len_z":435.5,"mean_r_leg":0.025588422381306267,"mean_g_leg":0.047116032043455235,"g_bind_frac":0.2721311475409836,"a_match":0.12349726775956284,"a_match_n":305,"a_match_centered":-0.04111111111111111},"boxed":{"n_turns":32,"n_valid":32,"parse_rate":1.0,"reason":0.009817368706885331,"mean_b":1.0400918361998193,"b_gate_pass_rate":0.6666666666666666,"median_len_z":1920.0,"mean_r_leg":0.06306374569523736,"mean_g_leg":0.02287919163303356,"g_bind_frac":0.5625,"a_match":0.5376344086021506,"a_match_n":31,"a_match_centered":-0.03225806451612903},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.005810599342979588,"mean_b":0.017781878198466595,"b_gate_pass_rate":0.14814814814814814,"median_len_z":640.0,"mean_r_leg":0.001938181089881078,"mean_g_leg":0.021731508111960902,"g_bind_frac":0.3333333333333333,"a_match":0.5925925925925926,"a_match_n":27,"a_match_centered":0.012345679012345677},"text":{"n_turns":359,"n_valid":353,"parse_rate":0.9832869080779945,"reason":0.0012045125412959122,"mean_b":0.03780731098265017,"b_gate_pass_rate":0.33994334277620397,"median_len_z":685.0,"mean_r_leg":0.011659880562080794,"mean_g_leg":0.06367341547349935,"g_bind_frac":0.1671388101983003,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":273,"n_valid":273,"parse_rate":1.0,"reason":0.0015663926473712768,"mean_b":0.027906014517752063,"b_gate_pass_rate":0.368944099378882,"median_len_z":498.0,"mean_r_leg":0.0056065648717877345,"mean_g_leg":0.07677580750593227,"g_bind_frac":0.16483516483516483,"a_match":0.15842839036755385,"a_match_n":263,"a_match_centered":-0.02534854245880862}}},"king":{"reason":0.0034868765430587194,"n_turns":998,"n_pairs":2939,"n_forfeits":5,"forfeit_rate":0.00501002004008016,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":3.4265392234133922,"mean_len_z":831.2881932630146,"median_len_z":569.0,"mean_len_y":466.0922082340932,"mean_b":0.08724484972490562,"b_gate_pass_rate":0.5059544062606328,"mean_r_leg":0.015026252043488803,"mean_g_leg":0.05904045383174579,"g_bind_frac":0.2134944612286002,"a_match":0.17809675704412548,"a_match_n":627,"a_match_centered":-0.03376205787781351,"n_turns_cap_raised":88,"mean_cap_tokens":2176.5961923847694,"max_cap_tokens":5087,"len_z_delta":-348.30050003420956,"len_y_delta":-167.1582995519596,"n_samples":998,"think_close_rate":0.9959919839679359,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":307,"n_valid":306,"parse_rate":0.996742671009772,"reason":0.007522124380536411,"mean_b":0.11720011344681391,"b_gate_pass_rate":0.8346368715083798,"median_len_z":456.0,"mean_r_leg":0.023001132484032766,"mean_g_leg":0.0461629314208018,"g_bind_frac":0.2679738562091503,"a_match":0.13071895424836602,"a_match_n":306,"a_match_centered":-0.036544850498338874},"boxed":{"n_turns":32,"n_valid":32,"parse_rate":1.0,"reason":0.013374958766079753,"mean_b":1.0050126819688003,"b_gate_pass_rate":0.6344086021505376,"median_len_z":1916.0,"mean_r_leg":0.06662569412234425,"mean_g_leg":0.02503230293067521,"g_bind_frac":0.59375,"a_match":0.5483870967741935,"a_match_n":31,"a_match_centered":-0.021505376344086023},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.0056026210219652815,"mean_b":0.015793100492248805,"b_gate_pass_rate":0.18518518518518517,"median_len_z":578.0,"mean_r_leg":0.0013615661418454742,"mean_g_leg":0.021682784875610987,"g_bind_frac":0.37037037037037035,"a_match":0.5925925925925926,"a_match_n":27,"a_match_centered":0.012345679012345677},"text":{"n_turns":359,"n_valid":355,"parse_rate":0.9888579387186629,"reason":0.0007723350145928341,"mean_b":0.03174586788749351,"b_gate_pass_rate":0.3352112676056338,"median_len_z":697.0,"mean_r_leg":0.011977444980542581,"mean_g_leg":0.0626852291760281,"g_bind_frac":0.18591549295774648,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":273,"n_valid":273,"parse_rate":1.0,"reason":0.00225866088640149,"mean_b":0.028526387507388812,"b_gate_pass_rate":0.3838509316770186,"median_len_z":513.0,"mean_r_leg":0.005355107227959327,"mean_g_leg":0.07641607471518365,"g_bind_frac":0.1282051282051282,"a_match":0.14702154626108999,"a_match_n":263,"a_match_centered":-0.036755386565272496}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T19:20:23.650040+00:00","challenge_id":"chal-00639","repo":"r2://affine-private-models/models/registrations/64bfb065b9f4a996f48fb0df23aa37c054dd2bb5d2d6457685e82a1866cb496c/","hotkey":"5CAriNN6WaE8oxPv3kpFHbRaAfkFu6dfn1hike5YboDdd4Fh","uid":248,"duration_s":2490.1,"revision":"8a51715cb7f0da84a8cbe6a780ed49109ba2d01d26c13496bfe9dd75d73f637c","accepted":false,"error_code":null,"error_detail":"","z":-2.3516719644610142,"margin":-0.1446251647280812,"se":0.061498868427947696,"n_paired_turns":977,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":15783099156519651106,"n":1000,"digest":"cfd572dae0e50ae3e06fa9cc8e4e4c254ea0bf57f1083e300dc05523c8cd748e","n_paired_turns":977,"n_forfeit_turns":8,"margin":-0.1446251647280812,"se":0.061498868427947696,"z":-2.3516719644610142,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.1446251647280812,"se":0.061498868427947696,"z":-2.3516719644610142,"sd_diff":1.9222700822480456,"n_paired_turns":977,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"tool_call":{"R":0.00852370901644948,"A":6.1872876743467575,"Mc":0.1911799834282062},"text":{"R":0.02014934839868227,"A":7.312239607610256,"Mc":0.18061590458106325},"bash":{"R":0.024104912662104173,"A":6.443628081722799,"Mc":0.1446514694777003},"boxed":{"R":0.15018670115830246,"A":4.64868978747762,"Mc":0.152235583537035},"terminus_json":{"R":0.0023633117464854636,"A":7.275139654825721,"Mc":0.13312639151722216}},"challenger":{"mean":-1.0256180209808312,"mean_valid":-0.9464214499982186,"sd_valid":1.8883913544013564,"n_turns":993,"n_valid":970,"n_forfeits":7,"n_unscorable":16,"mean_z_R":0.03169487873699726,"mean_typ_c":0.508189994099092,"mean_z_A":-0.2817527215645552,"bind_frac":{"R":0.3474226804123711,"Gc":0.16391752577319588,"A":0.488659793814433},"n_leg_dropped":{"R":1,"Gc":2,"A":1},"mean_content_share":0.33304865192531485,"mean_R":0.012313006378565524,"mean_A":1.6891021174837375,"mean_mc":-0.707829776022428},"king":{"mean":-0.8809928562527499,"mean_valid":-0.8237963174474657,"sd_valid":1.6869568704090236,"n_turns":993,"n_valid":972,"n_forfeits":5,"n_unscorable":16,"mean_z_R":0.19355669736147357,"mean_typ_c":0.6863877329007749,"mean_z_A":-0.2593423801240896,"bind_frac":{"R":0.3374485596707819,"Gc":0.13580246913580246,"A":0.5267489711934157},"n_leg_dropped":{"R":1,"Gc":4,"A":1},"mean_content_share":0.32635426669160056,"mean_R":0.014677607667772976,"mean_A":1.8251099219179665,"mean_mc":-0.6942150220848285}},"rejection_reason":null,"reign_number":null,"score":0.00224102264430249,"score_king":0.0031900975538782664,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9117789,"blocks_since_crown":14560,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1171.8002745367194,"mean_len_y":598.4128345916266,"n_samples":3000,"think_close_rate":0.9643333333333334,"n_text_fallback":16,"by_dialect":{"tool_call":{"n_turns":303,"zero_ref_turns":1,"mean_refs":2.8745874587458746,"ref_pair_agreement":0.19230769230769232,"ref_pair_n":286},"text":{"n_turns":348,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":294,"zero_ref_turns":6,"mean_refs":2.86734693877551,"ref_pair_agreement":0.1619718309859155,"ref_pair_n":284},"boxed":{"n_turns":31,"zero_ref_turns":0,"mean_refs":2.903225806451613,"ref_pair_agreement":0.7586206896551724,"ref_pair_n":29},"terminus_json":{"n_turns":24,"zero_ref_turns":0,"mean_refs":2.75,"ref_pair_agreement":0.6818181818181818,"ref_pair_n":22}},"ref_pair_agreement":0.2222222222222222,"ref_pair_n":621},"duel_seconds":2136.523499614559,"challenger":{"reason":0.00224102264430249,"n_turns":993,"n_pairs":2896,"n_forfeits":7,"forfeit_rate":0.007049345417925478,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.2631301683931657,"mean_len_z":816.797997237569,"median_len_z":565.0,"mean_len_y":453.31733425414365,"mean_b":0.09232185315238293,"b_gate_pass_rate":0.4861878453038674,"mean_r_leg":0.012313006378565524,"mean_g_leg":0.059143931968717825,"g_bind_frac":0.2028397565922921,"a_match":0.1847649918962723,"a_match_n":617,"a_match_centered":-0.02893711741791875,"n_turns_cap_raised":78,"mean_cap_tokens":2159.9194360523666,"max_cap_tokens":5105,"len_z_delta":-355.00227729915036,"len_y_delta":-145.09550033748297,"n_samples":996,"think_close_rate":0.9959839357429718,"n_text_fallback":14,"by_dialect":{"bash":{"n_turns":288,"n_valid":285,"parse_rate":0.9895833333333334,"reason":0.007504695033246291,"mean_b":0.111921133355087,"b_gate_pass_rate":0.8231780167264038,"median_len_z":448.0,"mean_r_leg":0.01712159968706044,"mean_g_leg":0.050966245568430116,"g_bind_frac":0.24912280701754386,"a_match":0.13976608187134504,"a_match_n":285,"a_match_centered":-0.02186761229314421},"boxed":{"n_turns":31,"n_valid":30,"parse_rate":0.967741935483871,"reason":-2.9715808400295678e-05,"mean_b":1.3191872931722912,"b_gate_pass_rate":0.4827586206896552,"median_len_z":1653.0,"mean_r_leg":0.1279405105238478,"mean_g_leg":0.026273707187854583,"g_bind_frac":0.43333333333333335,"a_match":0.6845238095238095,"a_match_n":28,"a_match_centered":-0.09259259259259259},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.006851451412048408,"mean_b":0.01908487667064571,"b_gate_pass_rate":0.30303030303030304,"median_len_z":629.0,"mean_r_leg":0.0010096815857204846,"mean_g_leg":0.039161581840453555,"g_bind_frac":0.2916666666666667,"a_match":0.611111111111111,"a_match_n":24,"a_match_centered":-0.01515151515151515},"text":{"n_turns":348,"n_valid":345,"parse_rate":0.9913793103448276,"reason":0.0011743671101025293,"mean_b":0.037576063537467605,"b_gate_pass_rate":0.2898550724637681,"median_len_z":699.0,"mean_r_leg":0.005832289711674513,"mean_g_leg":0.06378813461925673,"g_bind_frac":0.15942028985507245,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":302,"n_valid":302,"parse_rate":1.0,"reason":-0.0005938424309558562,"mean_b":0.021545322598808557,"b_gate_pass_rate":0.40987370838117104,"median_len_z":431.0,"mean_r_leg":0.004590664748850822,"mean_g_leg":0.06640907718775861,"g_bind_frac":0.17880794701986755,"a_match":0.14404761904761906,"a_match_n":280,"a_match_centered":-0.03109452736318408}}},"king":{"reason":0.0031900975538782664,"n_turns":993,"n_pairs":2902,"n_forfeits":5,"forfeit_rate":0.005035246727089627,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.2215707848641464,"mean_len_z":833.0110268780152,"median_len_z":557.0,"mean_len_y":473.67815299793244,"mean_b":0.09345432089471604,"b_gate_pass_rate":0.5124052377670572,"mean_r_leg":0.014677607667772976,"mean_g_leg":0.05880883672207999,"g_bind_frac":0.19635627530364372,"a_match":0.18011603375527424,"a_match_n":632,"a_match_centered":-0.03712737127371273,"n_turns_cap_raised":78,"mean_cap_tokens":2159.9194360523666,"max_cap_tokens":5105,"len_z_delta":-338.7892476587042,"len_y_delta":-124.73468159369418,"n_samples":993,"think_close_rate":0.9979859013091642,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":288,"n_valid":285,"parse_rate":0.9895833333333334,"reason":0.009006006172221383,"mean_b":0.1139769059782715,"b_gate_pass_rate":0.8351254480286738,"median_len_z":469.0,"mean_r_leg":0.020309119487419834,"mean_g_leg":0.0523312009192086,"g_bind_frac":0.22456140350877193,"a_match":0.13801169590643275,"a_match_n":285,"a_match_centered":-0.02364066193853428},"boxed":{"n_turns":31,"n_valid":30,"parse_rate":0.967741935483871,"reason":0.0022967586555859435,"mean_b":1.293463101419675,"b_gate_pass_rate":0.6206896551724138,"median_len_z":1899.0,"mean_r_leg":0.13771248071823844,"mean_g_leg":0.028271806001975805,"g_bind_frac":0.5,"a_match":0.755952380952381,"a_match_n":28,"a_match_centered":0.006172839506172838},"terminus_json":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":-0.005723071459891424,"mean_b":0.017251802531950675,"b_gate_pass_rate":0.2727272727272727,"median_len_z":618.0,"mean_r_leg":0.0010733700346555273,"mean_g_leg":0.039334159397180636,"g_bind_frac":0.25,"a_match":0.5277777777777778,"a_match_n":24,"a_match_centered":-0.10606060606060606},"text":{"n_turns":348,"n_valid":347,"parse_rate":0.9971264367816092,"reason":0.00033483375282606785,"mean_b":0.03519331158170733,"b_gate_pass_rate":0.3314121037463977,"median_len_z":627.0,"mean_r_leg":0.006561523832666327,"mean_g_leg":0.061206950647970486,"g_bind_frac":0.1642651296829971,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":302,"n_valid":302,"parse_rate":1.0,"reason":0.001734003788516948,"mean_b":0.029276260373679586,"b_gate_pass_rate":0.425947187141217,"median_len_z":514.0,"mean_r_leg":0.007547659766658767,"mean_g_leg":0.0667475249635868,"g_bind_frac":0.17218543046357615,"a_match":0.13785310734463277,"a_match_n":295,"a_match_centered":-0.04929577464788732}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T18:37:47.065192+00:00","challenge_id":"chal-00638","repo":"r2://affine-private-models/models/registrations/e0053273a78146747abbcb5d0c19edf123a1860cf95d614fa0aafa926be6d8e9/","hotkey":"5G4ytqaaiknbia4WwzcXQ36vLGY1VGb8R7XQmUmBrz8Wd9cd","uid":182,"duration_s":2530.7,"revision":"2c397869600af034f360fe813f4b209e45099db44a3b0bfda481b4fd6b116f88","accepted":false,"error_code":null,"error_detail":"","z":0.1369475369948744,"margin":0.00621155891157526,"se":0.045357215236428404,"n_paired_turns":979,"n_forfeit_turns":9,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":6983121023789036584,"n":1000,"digest":"d7b0e32fcd5bf4abfd6425632fa3f92bf618bebc06b308d67afe24dec71d4eac","n_paired_turns":979,"n_forfeit_turns":9,"margin":0.00621155891157526,"se":0.045357215236428404,"z":0.1369475369948744,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.00621155891157526,"se":0.045357215236428404,"z":0.1369475369948744,"sd_diff":1.4191808050948318,"n_paired_turns":979,"n_forfeit_turns":9,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.022807385366752666,"A":5.644770697650054,"Mc":0.16955002548685105},"text":{"R":0.01642628541889766,"A":12.904286607685366,"Mc":0.19059682712556905},"tool_call":{"R":0.009860656427811306,"A":6.225162470833053,"Mc":0.1902514275771112},"terminus_json":{"R":0.0015835314246551084,"A":7.8002225788705655,"Mc":0.15941384271817},"boxed":{"R":0.2373320324499553,"A":4.680660361224959,"Mc":0.12583703598844415}},"challenger":{"mean":-0.7822105233311577,"mean_valid":-0.7131070973968526,"sd_valid":1.4879048678251385,"n_turns":993,"n_valid":974,"n_forfeits":6,"n_unscorable":13,"mean_z_R":0.15807975785691436,"mean_typ_c":0.6624043256018575,"mean_z_A":-0.19604434746274144,"bind_frac":{"R":0.3182751540041068,"Gc":0.15811088295687886,"A":0.5236139630390144},"n_leg_dropped":{"R":0,"Gc":11,"A":0},"mean_content_share":0.32770593195809206,"mean_R":0.01110540823051423,"mean_A":1.5049936663675199,"mean_mc":-0.7275351119494506},"king":{"mean":-0.7769636660255023,"mean_valid":-0.6961393302870028,"sd_valid":1.497076659989353,"n_turns":993,"n_valid":972,"n_forfeits":7,"n_unscorable":14,"mean_z_R":0.2082117570882098,"mean_typ_c":0.659003258519439,"mean_z_A":-0.17450193853197152,"bind_frac":{"R":0.31584362139917693,"Gc":0.16358024691358025,"A":0.5205761316872428},"n_leg_dropped":{"R":0,"Gc":11,"A":0},"mean_content_share":0.3308478295545542,"mean_R":0.012268134874068292,"mean_A":1.5947368540866327,"mean_mc":-0.7248427318767079}},"rejection_reason":null,"reign_number":null,"score":0.0006834620709139207,"score_king":0.001175546377284596,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9117573,"blocks_since_crown":14344,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1146.3690150478797,"mean_len_y":660.5212038303694,"n_samples":3000,"think_close_rate":0.9603333333333334,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":323,"zero_ref_turns":4,"mean_refs":2.8854489164086687,"ref_pair_agreement":0.22151224707135247,"ref_pair_n":313},"tool_call":{"n_turns":292,"zero_ref_turns":2,"mean_refs":2.8972602739726026,"ref_pair_agreement":0.18571428571428572,"ref_pair_n":280},"text":{"n_turns":334,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":29,"zero_ref_turns":1,"mean_refs":2.7586206896551726,"ref_pair_agreement":0.5238095238095238,"ref_pair_n":28},"boxed":{"n_turns":22,"zero_ref_turns":0,"mean_refs":2.909090909090909,"ref_pair_agreement":0.7833333333333333,"ref_pair_n":20}},"ref_pair_agreement":0.23660946437857514,"ref_pair_n":641},"duel_seconds":2145.537597095128,"challenger":{"reason":0.0006834620709139207,"n_turns":993,"n_pairs":2908,"n_forfeits":6,"forfeit_rate":0.006042296072507553,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":757.9647930895079,"mean_len_z":833.6619669876203,"median_len_z":562.0,"mean_len_y":413.1155433287483,"mean_b":0.08636891452995432,"b_gate_pass_rate":0.500343878954608,"mean_r_leg":0.01110540823051423,"mean_g_leg":0.05530723282156954,"g_bind_frac":0.24012158054711247,"a_match":0.18433179723502305,"a_match_n":651,"a_match_centered":-0.04971219256933543,"n_turns_cap_raised":87,"mean_cap_tokens":2147.9506545820745,"max_cap_tokens":5095,"len_z_delta":-312.70704806025935,"len_y_delta":-247.40566050162107,"n_samples":996,"think_close_rate":0.9959839357429718,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":319,"n_valid":317,"parse_rate":0.9937304075235109,"reason":0.006447018517255537,"mean_b":0.11805928619762848,"b_gate_pass_rate":0.8631465517241379,"median_len_z":474.0,"mean_r_leg":0.018360308710307985,"mean_g_leg":0.049797018278291985,"g_bind_frac":0.26813880126182965,"a_match":0.167192429022082,"a_match_n":317,"a_match_centered":-0.05555555555555555},"boxed":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":0.004937218846297615,"mean_b":1.1873214706567157,"b_gate_pass_rate":0.609375,"median_len_z":1731.0,"mean_r_leg":0.056101158215280854,"mean_g_leg":0.022790486496009475,"g_bind_frac":0.45454545454545453,"a_match":0.7333333333333333,"a_match_n":20,"a_match_centered":-0.05263157894736842},"terminus_json":{"n_turns":28,"n_valid":28,"parse_rate":1.0,"reason":-0.002554079440217605,"mean_b":0.019809500741949794,"b_gate_pass_rate":0.3125,"median_len_z":499.0,"mean_r_leg":0.0017390207700276918,"mean_g_leg":0.05171912917724854,"g_bind_frac":0.25,"a_match":0.4404761904761905,"a_match_n":28,"a_match_centered":-0.08333333333333334},"text":{"n_turns":334,"n_valid":330,"parse_rate":0.9880239520958084,"reason":-0.003746499938873877,"mean_b":0.0430966909167365,"b_gate_pass_rate":0.2606060606060606,"median_len_z":668.5,"mean_r_leg":0.006677677350621024,"mean_g_leg":0.0564110644457052,"g_bind_frac":0.22727272727272727,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":290,"n_valid":290,"parse_rate":1.0,"reason":-0.000564464418260595,"mean_b":0.025251451149826284,"b_gate_pass_rate":0.39243498817966904,"median_len_z":491.5,"mean_r_leg":0.005704374049475939,"mean_g_leg":0.0628876083231472,"g_bind_frac":0.20689655172413793,"a_match":0.13986013986013987,"a_match_n":286,"a_match_centered":-0.039568345323741004}}},"king":{"reason":0.001175546377284596,"n_turns":993,"n_pairs":2903,"n_forfeits":7,"forfeit_rate":0.007049345417925478,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":518.2935622949275,"mean_len_z":843.2104719255942,"median_len_z":557.0,"mean_len_y":406.97554254219773,"mean_b":0.0819447468056555,"b_gate_pass_rate":0.5111953151911816,"mean_r_leg":0.012268134874068292,"mean_g_leg":0.055327752609410044,"g_bind_frac":0.22515212981744423,"a_match":0.18473282442748093,"a_match_n":655,"a_match_centered":-0.047991653625456446,"n_turns_cap_raised":87,"mean_cap_tokens":2147.9506545820745,"max_cap_tokens":5095,"len_z_delta":-303.15854312228544,"len_y_delta":-253.54566128817163,"n_samples":993,"think_close_rate":0.9939577039274925,"n_text_fallback":0,"by_dialect":{"bash":{"n_turns":319,"n_valid":318,"parse_rate":0.9968652037617555,"reason":0.0073166444277985455,"mean_b":0.11545012543333094,"b_gate_pass_rate":0.8503767491926802,"median_len_z":465.0,"mean_r_leg":0.01978201525680571,"mean_g_leg":0.04996244092163747,"g_bind_frac":0.25157232704402516,"a_match":0.16981132075471697,"a_match_n":318,"a_match_centered":-0.049145299145299144},"boxed":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":0.003272344482639766,"mean_b":1.1479445966466937,"b_gate_pass_rate":0.5625,"median_len_z":1755.0,"mean_r_leg":0.08399240831968484,"mean_g_leg":0.02357965659950719,"g_bind_frac":0.45454545454545453,"a_match":0.6833333333333333,"a_match_n":20,"a_match_centered":-0.10526315789473684},"terminus_json":{"n_turns":28,"n_valid":28,"parse_rate":1.0,"reason":-0.002560788613702486,"mean_b":0.019556813659432817,"b_gate_pass_rate":0.3375,"median_len_z":490.0,"mean_r_leg":0.001903093490974435,"mean_g_leg":0.051869585616211154,"g_bind_frac":0.25,"a_match":0.4404761904761905,"a_match_n":28,"a_match_centered":-0.08333333333333334},"text":{"n_turns":334,"n_valid":328,"parse_rate":0.9820359281437125,"reason":-0.004505170800415118,"mean_b":0.034011335532298216,"b_gate_pass_rate":0.3079268292682927,"median_len_z":666.5,"mean_r_leg":0.006375649575237543,"mean_g_leg":0.05631223873923308,"g_bind_frac":0.19817073170731708,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":290,"n_valid":290,"parse_rate":1.0,"reason":0.0011646397588969373,"mean_b":0.02616108747911233,"b_gate_pass_rate":0.3877068557919622,"median_len_z":480.0,"mean_r_leg":0.006252991285202949,"mean_g_leg":0.06283997486512437,"g_bind_frac":0.20689655172413793,"a_match":0.14186851211072665,"a_match_n":289,"a_match_centered":-0.039285714285714285}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T17:50:58.821587+00:00","challenge_id":"chal-00637","repo":"r2://affine-private-models/models/registrations/fae47b522ba219d9bf543e1b88d3a968c5ea76c906ad331347fd4da358ee759c/","hotkey":"5CPDkas3ePu2VBCpwGrDBm3zjejiHtWS3VTSbgh3LeoVrtkz","uid":31,"duration_s":2696.1,"revision":"6529b280fe5693c19554de2553fb96ec5bd88a94a98469a215ce0a8bf7f23285","accepted":false,"error_code":null,"error_detail":"","z":1.201264217635979,"margin":0.05422535174302704,"se":0.045140237215872056,"n_paired_turns":984,"n_forfeit_turns":9,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":14517150377891809974,"n":1000,"digest":"740fed59375717ca2eb121775310babcceb62100cf45754e681a4d0f064d6df4","n_paired_turns":984,"n_forfeit_turns":9,"margin":0.05422535174302704,"se":0.045140237215872056,"z":1.201264217635979,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":1},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.05422535174302704,"se":0.045140237215872056,"z":1.201264217635979,"sd_diff":1.4159939122929581,"n_paired_turns":984,"n_forfeit_turns":9,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02867781897188911,"A":10.948139371822506,"Mc":0.15090545440679595},"tool_call":{"R":0.007820384296766517,"A":6.51175162340823,"Mc":0.19528837583800235},"text":{"R":0.09806891196746775,"A":28.351745037957006,"Mc":0.1734266985743942},"terminus_json":{"R":0.002774380756204532,"A":6.8426190204274695,"Mc":0.10448382463243325},"boxed":{"R":0.1677193942894023,"A":6.915063316732194,"Mc":0.12340441011479224}},"challenger":{"mean":-0.6477375298233937,"mean_valid":-0.5780917477977704,"sd_valid":1.486509343228956,"n_turns":995,"n_valid":978,"n_forfeits":6,"n_unscorable":11,"mean_z_R":0.21899290338558905,"mean_typ_c":0.582113874966923,"mean_z_A":-0.04868778250403678,"bind_frac":{"R":0.32413087934560325,"Gc":0.18200408997955012,"A":0.4938650306748466},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.33219242455233466,"mean_R":0.016803987723240963,"mean_A":1.6231396872018788,"mean_mc":-0.7135357504912944},"king":{"mean":-0.7019628815664207,"mean_valid":-0.609356019939916,"sd_valid":1.5586886701989033,"n_turns":995,"n_valid":976,"n_forfeits":8,"n_unscorable":11,"mean_z_R":0.14766785387015224,"mean_typ_c":0.5811123812719363,"mean_z_A":-0.056938665584870506,"bind_frac":{"R":0.32684426229508196,"Gc":0.1711065573770492,"A":0.5020491803278688},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.32510376579183226,"mean_R":0.01600608612527652,"mean_A":1.7257380237061202,"mean_mc":-0.722194896462882}},"rejection_reason":null,"reign_number":null,"score":0.0025806101043127183,"score_king":0.0024879174973968694,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9117325,"blocks_since_crown":14096,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1198.8886239782016,"mean_len_y":603.0449591280654,"n_samples":3000,"think_close_rate":0.9673333333333334,"n_text_fallback":8,"by_dialect":{"tool_call":{"n_turns":296,"zero_ref_turns":3,"mean_refs":2.89527027027027,"ref_pair_agreement":0.1742690058479532,"ref_pair_n":285},"bash":{"n_turns":323,"zero_ref_turns":2,"mean_refs":2.9102167182662537,"ref_pair_agreement":0.1892744479495268,"ref_pair_n":317},"text":{"n_turns":336,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":22,"zero_ref_turns":0,"mean_refs":2.909090909090909,"ref_pair_agreement":0.7301587301587302,"ref_pair_n":21},"terminus_json":{"n_turns":23,"zero_ref_turns":0,"mean_refs":2.9130434782608696,"ref_pair_agreement":0.6666666666666666,"ref_pair_n":22}},"ref_pair_agreement":0.2165374677002584,"ref_pair_n":645},"duel_seconds":2180.494302263949,"challenger":{"reason":0.0025806101043127183,"n_turns":995,"n_pairs":2919,"n_forfeits":6,"forfeit_rate":0.006030150753768844,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.833908087292515,"mean_len_z":799.8934566632408,"median_len_z":528.0,"mean_len_y":410.2490578965399,"mean_b":0.09429884825355937,"b_gate_pass_rate":0.5145597807468311,"mean_r_leg":0.016803987723240963,"mean_g_leg":0.05738058736943324,"g_bind_frac":0.2568250758341759,"a_match":0.19022017409114184,"a_match_n":651,"a_match_centered":-0.021648408972352637,"n_turns_cap_raised":94,"mean_cap_tokens":2178.286432160804,"max_cap_tokens":5023,"len_z_delta":-398.9951673149608,"len_y_delta":-192.79590123152553,"n_samples":998,"think_close_rate":0.9959919839679359,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":321,"n_valid":319,"parse_rate":0.9937694704049844,"reason":0.006798932920129941,"mean_b":0.12390627936692987,"b_gate_pass_rate":0.8449197860962567,"median_len_z":431.0,"mean_r_leg":0.025887678386949747,"mean_g_leg":0.04102570619338929,"g_bind_frac":0.3510971786833856,"a_match":0.15256008359456635,"a_match_n":319,"a_match_centered":-0.03280423280423281},"boxed":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":0.005619108126376171,"mean_b":1.442250301762153,"b_gate_pass_rate":0.578125,"median_len_z":1893.0,"mean_r_leg":0.09168118548230664,"mean_g_leg":0.020473415084884195,"g_bind_frac":0.45454545454545453,"a_match":0.7142857142857143,"a_match_n":21,"a_match_centered":-0.015873015873015876},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0043585904531855115,"mean_b":0.016850193519993024,"b_gate_pass_rate":0.19402985074626866,"median_len_z":617.0,"mean_r_leg":0.0015041015577224972,"mean_g_leg":0.025351861471721294,"g_bind_frac":0.34782608695652173,"a_match":0.6376811594202898,"a_match_n":23,"a_match_centered":-0.045454545454545456},"text":{"n_turns":336,"n_valid":332,"parse_rate":0.9880952380952381,"reason":-0.000177730048987446,"mean_b":0.041339515069048205,"b_gate_pass_rate":0.3072289156626506,"median_len_z":631.0,"mean_r_leg":0.01292940765558199,"mean_g_leg":0.06322017451255386,"g_bind_frac":0.18674698795180722,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":293,"n_valid":293,"parse_rate":1.0,"reason":0.0014388876605195113,"mean_b":0.028936788280829708,"b_gate_pass_rate":0.41540256709451573,"median_len_z":416.0,"mean_r_leg":0.0068833812107739235,"mean_g_leg":0.07385527218018212,"g_bind_frac":0.21160409556313994,"a_match":0.1579861111111111,"a_match_n":288,"a_match_centered":-0.007710557532621589}}},"king":{"reason":0.0024879174973968694,"n_turns":995,"n_pairs":2912,"n_forfeits":8,"forfeit_rate":0.008040201005025126,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-2.3130565999966572,"mean_len_z":850.090315934066,"median_len_z":587.0,"mean_len_y":431.8643543956044,"mean_b":0.09527964166526959,"b_gate_pass_rate":0.5223214285714286,"mean_r_leg":0.01600608612527652,"mean_g_leg":0.057422800592152386,"g_bind_frac":0.24417426545086118,"a_match":0.18794871794871795,"a_match_n":650,"a_match_centered":-0.02586206896551724,"n_turns_cap_raised":94,"mean_cap_tokens":2178.286432160804,"max_cap_tokens":5023,"len_z_delta":-348.79830804413564,"len_y_delta":-171.18060473246106,"n_samples":995,"think_close_rate":0.9949748743718593,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":321,"n_valid":318,"parse_rate":0.9906542056074766,"reason":0.00692277272734986,"mean_b":0.12520580022003724,"b_gate_pass_rate":0.8313641245972073,"median_len_z":504.0,"mean_r_leg":0.02310985832528054,"mean_g_leg":0.042810261515108444,"g_bind_frac":0.33647798742138363,"a_match":0.16142557651991613,"a_match_n":318,"a_match_centered":-0.024416135881104035},"boxed":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":0.0033952337471585786,"mean_b":1.4638195839737707,"b_gate_pass_rate":0.40625,"median_len_z":1900.0,"mean_r_leg":0.09554431023169972,"mean_g_leg":0.016449618427168265,"g_bind_frac":0.4090909090909091,"a_match":0.7142857142857143,"a_match_n":21,"a_match_centered":-0.015873015873015876},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.005641171705999994,"mean_b":0.021172009717865866,"b_gate_pass_rate":0.3283582089552239,"median_len_z":702.0,"mean_r_leg":0.0013283533154200826,"mean_g_leg":0.021083108626168016,"g_bind_frac":0.43478260869565216,"a_match":0.6376811594202898,"a_match_n":23,"a_match_centered":-0.045454545454545456},"text":{"n_turns":336,"n_valid":331,"parse_rate":0.9851190476190477,"reason":0.0001285787323316848,"mean_b":0.04359281218313636,"b_gate_pass_rate":0.33534743202416917,"median_len_z":693.0,"mean_r_leg":0.013954659853545524,"mean_g_leg":0.06335941940818973,"g_bind_frac":0.18731117824773413,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":293,"n_valid":293,"parse_rate":1.0,"reason":0.0009048369186609054,"mean_b":0.026250963828631988,"b_gate_pass_rate":0.42707117852975496,"median_len_z":454.0,"mean_r_leg":0.0057936952059149845,"mean_g_leg":0.07250467609126128,"g_bind_frac":0.18088737201365188,"a_match":0.1429398148148148,"a_match_n":288,"a_match_centered":-0.026690391459074734}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T17:03:06.025718+00:00","challenge_id":"chal-00636","repo":"r2://affine-private-models/models/registrations/fc00e45d29a59fa22f140850ff82d7eae0089e005d6e17dc64edab1dd906618f/","hotkey":"5GiNnGQuzVCJTHGi6MJgoUHYWX8wWMLFrZxCsMc3oPmK1h48","uid":155,"duration_s":2646.2,"revision":"6068a25a3114b5d4cb53058ad2c205fbefaa186aeae1398bb3b6d207294acbd8","accepted":false,"error_code":null,"error_detail":"","z":0.17517120349132134,"margin":0.007672930301812882,"se":0.04380246381188463,"n_paired_turns":983,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2571859334179157218,"n":1000,"digest":"4dbb238b64b4ce0afc670f37ed0cd6464251193238a4c1da53c10387fe0bec02","n_paired_turns":983,"n_forfeit_turns":8,"margin":0.007672930301812882,"se":0.04380246381188463,"z":0.17517120349132134,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.007672930301812882,"se":0.04380246381188463,"z":0.17517120349132134,"sd_diff":1.3733312370945356,"n_paired_turns":983,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.022639416979534303,"A":5.135910956976119,"Mc":0.16101773687442594},"text":{"R":0.055326957972054294,"A":12.084716633523152,"Mc":0.17899269043811644},"tool_call":{"R":0.00787442856624895,"A":5.899554028372057,"Mc":0.1947200283509378},"terminus_json":{"R":0.0027565878395464033,"A":10.17570129464792,"Mc":0.12651303718711268},"boxed":{"R":0.07994942256585094,"A":5.309489528329066,"Mc":0.10172961716253988}},"challenger":{"mean":-0.837945205163288,"mean_valid":-0.7578894842986803,"sd_valid":1.5379237280091735,"n_turns":992,"n_valid":976,"n_forfeits":7,"n_unscorable":9,"mean_z_R":0.16249472986716942,"mean_typ_c":0.6748338152156348,"mean_z_A":-0.20916445521100382,"bind_frac":{"R":0.33401639344262296,"Gc":0.15163934426229508,"A":0.514344262295082},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.3215649081884865,"mean_R":0.015765293228916052,"mean_A":2.1231953642021875,"mean_mc":-0.7167775335555938},"king":{"mean":-0.8456181354651008,"mean_valid":-0.7656174458629038,"sd_valid":1.5964409147542253,"n_turns":992,"n_valid":976,"n_forfeits":7,"n_unscorable":9,"mean_z_R":0.15349193685830337,"mean_typ_c":0.6741826921224879,"mean_z_A":-0.2260865177234555,"bind_frac":{"R":0.3206967213114754,"Gc":0.15061475409836064,"A":0.5286885245901639},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.32146771122094703,"mean_R":0.01489517552477085,"mean_A":1.9509568148877763,"mean_mc":-0.715529851924207}},"rejection_reason":null,"reign_number":null,"score":0.0019681055820218564,"score_king":0.002609750047629727,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9117090,"blocks_since_crown":13861,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1235.7801973460362,"mean_len_y":631.9649540660089,"n_samples":3000,"think_close_rate":0.9723333333333334,"n_text_fallback":17,"by_dialect":{"tool_call":{"n_turns":253,"zero_ref_turns":2,"mean_refs":2.9011857707509883,"ref_pair_agreement":0.17289073305670816,"ref_pair_n":241},"bash":{"n_turns":317,"zero_ref_turns":5,"mean_refs":2.8958990536277605,"ref_pair_agreement":0.19326818675352878,"ref_pair_n":307},"text":{"n_turns":369,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":27,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.5308641975308642,"ref_pair_n":27},"boxed":{"n_turns":34,"zero_ref_turns":1,"mean_refs":2.911764705882353,"ref_pair_agreement":0.6770833333333334,"ref_pair_n":32}},"ref_pair_agreement":0.2257001647446458,"ref_pair_n":607},"duel_seconds":2109.2309241783805,"challenger":{"reason":0.0019681055820218564,"n_turns":992,"n_pairs":2918,"n_forfeits":7,"forfeit_rate":0.007056451612903226,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.711998057265638,"mean_len_z":843.6583276216587,"median_len_z":619.0,"mean_len_y":471.8680603152844,"mean_b":0.10354896648591752,"b_gate_pass_rate":0.49554489376285127,"mean_r_leg":0.015765293228916052,"mean_g_leg":0.05759382250132846,"g_bind_frac":0.2233502538071066,"a_match":0.17207792207792208,"a_match_n":616,"a_match_centered":-0.047933884297520664,"n_turns_cap_raised":102,"mean_cap_tokens":2182.7268145161293,"max_cap_tokens":5091,"len_z_delta":-392.12186972437746,"len_y_delta":-160.09689375072446,"n_samples":995,"think_close_rate":0.9939698492462311,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":312,"n_valid":311,"parse_rate":0.9967948717948718,"reason":0.007190081674031415,"mean_b":0.11859077787428253,"b_gate_pass_rate":0.8524590163934426,"median_len_z":440.0,"mean_r_leg":0.016531590422023915,"mean_g_leg":0.05090147430846756,"g_bind_frac":0.26688102893890675,"a_match":0.1414790996784566,"a_match_n":311,"a_match_centered":-0.04684095860566449},"boxed":{"n_turns":33,"n_valid":33,"parse_rate":1.0,"reason":0.005786022583662759,"mean_b":1.205813592532127,"b_gate_pass_rate":0.5151515151515151,"median_len_z":1956.0,"mean_r_leg":0.07544936364181268,"mean_g_leg":0.022159332687043624,"g_bind_frac":0.48484848484848486,"a_match":0.5625,"a_match_n":32,"a_match_centered":-0.11458333333333333},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.005068045264833467,"mean_b":0.01595167566851465,"b_gate_pass_rate":0.3333333333333333,"median_len_z":761.0,"mean_r_leg":0.0008663127519680968,"mean_g_leg":0.030873441665435524,"g_bind_frac":0.3333333333333333,"a_match":0.5185185185185185,"a_match_n":27,"a_match_centered":-0.01234567901234568},"text":{"n_turns":369,"n_valid":363,"parse_rate":0.983739837398374,"reason":-0.0009351713834010984,"mean_b":0.048809336940280494,"b_gate_pass_rate":0.2699724517906336,"median_len_z":721.0,"mean_r_leg":0.017163764518340983,"mean_g_leg":0.06018051091980061,"g_bind_frac":0.18181818181818182,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":251,"n_valid":251,"parse_rate":1.0,"reason":1.2738020923587248e-07,"mean_b":0.027008614622810765,"b_gate_pass_rate":0.40054495912806537,"median_len_z":605.0,"mean_r_leg":0.006549096592000562,"mean_g_leg":0.06967804894959484,"g_bind_frac":0.18326693227091634,"a_match":0.12195121951219512,"a_match_n":246,"a_match_centered":-0.04444444444444444}}},"king":{"reason":0.002609750047629727,"n_turns":992,"n_pairs":2918,"n_forfeits":7,"forfeit_rate":0.007056451612903226,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-6.134217977765297,"mean_len_z":844.2738176833448,"median_len_z":604.0,"mean_len_y":476.5445510623715,"mean_b":0.10519730653166638,"b_gate_pass_rate":0.5047978067169294,"mean_r_leg":0.01489517552477085,"mean_g_leg":0.057681032296566064,"g_bind_frac":0.21928934010152284,"a_match":0.17619825708061002,"a_match_n":612,"a_match_centered":-0.04409317803660566,"n_turns_cap_raised":102,"mean_cap_tokens":2182.7268145161293,"max_cap_tokens":5091,"len_z_delta":-391.5063796626914,"len_y_delta":-155.42040300363738,"n_samples":992,"think_close_rate":0.9949596774193549,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":312,"n_valid":310,"parse_rate":0.9935897435897436,"reason":0.007397179221349526,"mean_b":0.11604058803890459,"b_gate_pass_rate":0.8179824561403509,"median_len_z":448.0,"mean_r_leg":0.016669815597374148,"mean_g_leg":0.05081629718861147,"g_bind_frac":0.27419354838709675,"a_match":0.15913978494623657,"a_match_n":310,"a_match_centered":-0.029508196721311476},"boxed":{"n_turns":33,"n_valid":33,"parse_rate":1.0,"reason":0.009395523026520929,"mean_b":1.2267806559686774,"b_gate_pass_rate":0.5454545454545454,"median_len_z":1873.0,"mean_r_leg":0.06617140436021336,"mean_g_leg":0.02667397973363627,"g_bind_frac":0.45454545454545453,"a_match":0.5833333333333334,"a_match_n":32,"a_match_centered":-0.09375},"terminus_json":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":-0.003223490697727466,"mean_b":0.015728903463685443,"b_gate_pass_rate":0.25925925925925924,"median_len_z":799.0,"mean_r_leg":0.001605473540034512,"mean_g_leg":0.035408009859112,"g_bind_frac":0.25925925925925924,"a_match":0.5308641975308642,"a_match_n":27,"a_match_centered":-2.05596856412066e-18},"text":{"n_turns":369,"n_valid":364,"parse_rate":0.986449864498645,"reason":0.0001635592854236767,"mean_b":0.05329594883782233,"b_gate_pass_rate":0.30494505494505497,"median_len_z":687.0,"mean_r_leg":0.015572654466140645,"mean_g_leg":0.06063002017683013,"g_bind_frac":0.1813186813186813,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":251,"n_valid":251,"parse_rate":1.0,"reason":-9.638474781867214e-06,"mean_b":0.027537087078422263,"b_gate_pass_rate":0.43460490463215257,"median_len_z":553.5,"mean_r_leg":0.0064089828747814085,"mean_g_leg":0.06835529777639773,"g_bind_frac":0.17131474103585656,"a_match":0.10493827160493827,"a_match_n":243,"a_match_centered":-0.06118143459915612}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T15:53:17.449875+00:00","challenge_id":"chal-00635","repo":"r2://affine-private-models/models/registrations/710df2266087c2fb634e3f5da3fc9f7afcd4a1d7385ecb01a7febfe6a18f63b1/","hotkey":"5DCMbHiDRgQP47WM6YpmnxAYmvf1tZaZXAGNm9y5Uvq1dB65","uid":197,"duration_s":2267.0,"revision":"8e39f8b70259f949e41b824482a044a4ff2ad85882b281acc33772043253f86c","accepted":false,"error_code":null,"error_detail":"","z":-1.012193142626939,"margin":-0.04892339881457843,"se":0.04833405479077622,"n_paired_turns":987,"n_forfeit_turns":10,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":3603321766972137632,"n":1000,"digest":"e216a10df5bc6cbb9464b8641bd67cac262810c3a44df2b78c1948caa9c5ffdf","n_paired_turns":987,"n_forfeit_turns":10,"margin":-0.04892339881457843,"se":0.04833405479077622,"z":-1.012193142626939,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.04892339881457843,"se":0.04833405479077622,"z":-1.012193142626939,"sd_diff":1.5184895460407446,"n_paired_turns":987,"n_forfeit_turns":10,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.026709272124533605,"A":6.1606876650612845,"Mc":0.1602759290237981},"tool_call":{"R":0.008099468386219019,"A":5.256678344874805,"Mc":0.18311266944285834},"text":{"R":0.28974760172966146,"A":23.37904985304302,"Mc":0.16906463662895418},"terminus_json":{"R":0.001929006007161439,"A":6.485294216128122,"Mc":0.1138383149923523},"boxed":{"R":0.19867768518118525,"A":4.70470963535742,"Mc":0.11830810588613552}},"challenger":{"mean":-0.8505292647848121,"mean_valid":-0.7823367832238629,"sd_valid":1.6834206911000225,"n_turns":995,"n_valid":981,"n_forfeits":6,"n_unscorable":8,"mean_z_R":0.19183363716784196,"mean_typ_c":0.5181790849281992,"mean_z_A":-0.17713761987706028,"bind_frac":{"R":0.3119266055045872,"Gc":0.18144750254842,"A":0.5066258919469928},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.32391597623985074,"mean_R":0.022063167099499466,"mean_A":1.775268534008005,"mean_mc":-0.7297180691445768},"king":{"mean":-0.8016058659702336,"mean_valid":-0.6869856598900927,"sd_valid":1.4939681455346034,"n_turns":995,"n_valid":977,"n_forfeits":10,"n_unscorable":8,"mean_z_R":0.19840248181188794,"mean_typ_c":0.6223268290266295,"mean_z_A":-0.16912452447114254,"bind_frac":{"R":0.3132036847492323,"Gc":0.1862845445240532,"A":0.5005117707267144},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.32372331961863626,"mean_R":0.02347930523284794,"mean_A":1.8293116979897086,"mean_mc":-0.7110078566257051}},"rejection_reason":null,"reign_number":null,"score":0.0029824979664519963,"score_king":0.0027422677703423733,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9116772,"blocks_since_crown":13543,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1213.9416979202183,"mean_len_y":666.217183770883,"n_samples":3000,"think_close_rate":0.9676666666666667,"n_text_fallback":14,"by_dialect":{"tool_call":{"n_turns":262,"zero_ref_turns":1,"mean_refs":2.9083969465648853,"ref_pair_agreement":0.15616797900262466,"ref_pair_n":254},"bash":{"n_turns":344,"zero_ref_turns":4,"mean_refs":2.877906976744186,"ref_pair_agreement":0.16816816816816818,"ref_pair_n":333},"text":{"n_turns":341,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":28,"zero_ref_turns":0,"mean_refs":2.9642857142857144,"ref_pair_agreement":0.6785714285714286,"ref_pair_n":28},"terminus_json":{"n_turns":25,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.45333333333333337,"ref_pair_n":25}},"ref_pair_agreement":0.196875,"ref_pair_n":640},"duel_seconds":2181.0016569341533,"challenger":{"reason":0.0029824979664519963,"n_turns":995,"n_pairs":2919,"n_forfeits":6,"forfeit_rate":0.006030150753768844,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-4.0261495701738115,"mean_len_z":865.1541623843782,"median_len_z":570.0,"mean_len_y":458.59095580678314,"mean_b":0.10387499908056098,"b_gate_pass_rate":0.5351147653305927,"mean_r_leg":0.022063167099499466,"mean_g_leg":0.055758732842925346,"g_bind_frac":0.2639029322548028,"a_match":0.15633074935400515,"a_match_n":645,"a_match_centered":-0.03898482469911041,"n_turns_cap_raised":94,"mean_cap_tokens":2183.883417085427,"max_cap_tokens":5056,"len_z_delta":-348.7875355358401,"len_y_delta":-207.62622796409988,"n_samples":998,"think_close_rate":0.996993987975952,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":340,"n_valid":337,"parse_rate":0.9911764705882353,"reason":0.008675912061872825,"mean_b":0.12158738681985579,"b_gate_pass_rate":0.8324873096446701,"median_len_z":447.0,"mean_r_leg":0.023906948339096467,"mean_g_leg":0.049089704408869235,"g_bind_frac":0.3056379821958457,"a_match":0.14638971315529178,"a_match_n":337,"a_match_centered":-0.019076305220883532},"boxed":{"n_turns":28,"n_valid":28,"parse_rate":1.0,"reason":0.017929318940861683,"mean_b":1.4016084671624114,"b_gate_pass_rate":0.7228915662650602,"median_len_z":2078.0,"mean_r_leg":0.09913270433097982,"mean_g_leg":0.03558071350000416,"g_bind_frac":0.5714285714285714,"a_match":0.6296296296296297,"a_match_n":27,"a_match_centered":-0.07407407407407407},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.005893212583952114,"mean_b":0.02221438360937239,"b_gate_pass_rate":0.36,"median_len_z":652.0,"mean_r_leg":0.0014454546102028328,"mean_g_leg":0.028331418901671422,"g_bind_frac":0.28,"a_match":0.42666666666666664,"a_match_n":25,"a_match_centered":-0.02666666666666667},"text":{"n_turns":341,"n_valid":338,"parse_rate":0.9912023460410557,"reason":-0.0008841354903940181,"mean_b":0.043217924542087824,"b_gate_pass_rate":0.3224852071005917,"median_len_z":719.5,"mean_r_leg":0.027452948329607207,"mean_g_leg":0.05750377340697321,"g_bind_frac":0.22781065088757396,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":261,"n_valid":261,"parse_rate":1.0,"reason":-0.00013572811470493647,"mean_b":0.02837925100753206,"b_gate_pass_rate":0.4304461942257218,"median_len_z":434.0,"mean_r_leg":0.006409509767048737,"mean_g_leg":0.06690166871174479,"g_bind_frac":0.2222222222222222,"a_match":0.09309895833333333,"a_match_n":256,"a_match_centered":-0.06258234519104085}}},"king":{"reason":0.0027422677703423733,"n_turns":995,"n_pairs":2908,"n_forfeits":10,"forfeit_rate":0.010050251256281407,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-2.3900704285160415,"mean_len_z":836.2795735900963,"median_len_z":555.0,"mean_len_y":454.45495185694637,"mean_b":0.10259450058531817,"b_gate_pass_rate":0.5006877579092159,"mean_r_leg":0.02347930523284794,"mean_g_leg":0.05744314586966746,"g_bind_frac":0.2517766497461929,"a_match":0.16692506459948322,"a_match_n":645,"a_match_centered":-0.0282574568288854,"n_turns_cap_raised":94,"mean_cap_tokens":2183.883417085427,"max_cap_tokens":5056,"len_z_delta":-377.66212433012197,"len_y_delta":-211.76223191393666,"n_samples":995,"think_close_rate":0.992964824120603,"n_text_fallback":5,"by_dialect":{"bash":{"n_turns":340,"n_valid":336,"parse_rate":0.9882352941176471,"reason":0.0081492247306711,"mean_b":0.11914302712451885,"b_gate_pass_rate":0.8168870803662258,"median_len_z":436.0,"mean_r_leg":0.024083264423455,"mean_g_leg":0.05081624794203246,"g_bind_frac":0.29464285714285715,"a_match":0.15575396825396826,"a_match_n":336,"a_match_centered":-0.010070493454179255},"boxed":{"n_turns":28,"n_valid":28,"parse_rate":1.0,"reason":0.016250592206893167,"mean_b":1.3819943840411149,"b_gate_pass_rate":0.6506024096385542,"median_len_z":1826.0,"mean_r_leg":0.07732670457922342,"mean_g_leg":0.034828997055966905,"g_bind_frac":0.5714285714285714,"a_match":0.625,"a_match_n":28,"a_match_centered":-0.05357142857142857},"terminus_json":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":-0.012359272632317769,"mean_b":0.02317411673256565,"b_gate_pass_rate":0.32,"median_len_z":610.0,"mean_r_leg":0.0015653749608100721,"mean_g_leg":0.023243459371510452,"g_bind_frac":0.24,"a_match":0.42666666666666664,"a_match_n":25,"a_match_centered":-0.02666666666666667},"text":{"n_turns":341,"n_valid":335,"parse_rate":0.9824046920821115,"reason":-0.0010850484845403947,"mean_b":0.044321967798028425,"b_gate_pass_rate":0.31343283582089554,"median_len_z":686.0,"mean_r_leg":0.03332560005425758,"mean_g_leg":0.0594251564855874,"g_bind_frac":0.22388059701492538,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":261,"n_valid":261,"parse_rate":1.0,"reason":0.000696501112282367,"mean_b":0.026561734608044202,"b_gate_pass_rate":0.34120734908136485,"median_len_z":433.5,"mean_r_leg":0.006386132902910134,"mean_g_leg":0.06913223581828706,"g_bind_frac":0.19923371647509577,"a_match":0.10611979166666666,"a_match_n":256,"a_match_centered":-0.04940711462450593}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T15:09:41.958894+00:00","challenge_id":"chal-00634","repo":"r2://affine-private-models/models/registrations/a75d9240293c9a938af24fc0646d1fafa289cf90bedb306141c20b50108c7322/","hotkey":"5D21jaDr6Pq7AQbrPA2rvz9ybw2iCcDjZycnnG9FG9uHmyeU","uid":202,"duration_s":2894.4,"revision":"fe1c9b57f765ddf214e45439727e778233ca82d34462fa517fe983268c54b9a0","accepted":false,"error_code":null,"error_detail":"","z":-7.140301390683478,"margin":-0.590521083153783,"se":0.08270254305011314,"n_paired_turns":984,"n_forfeit_turns":23,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":2624386473885853540,"n":1000,"digest":"21acaf2e02736a157a62f0c904697ea1fe09529f0e3bbee510b4e093ea52aeda","n_paired_turns":984,"n_forfeit_turns":23,"margin":-0.590521083153783,"se":0.08270254305011314,"z":-7.140301390683478,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.590521083153783,"se":0.08270254305011314,"z":-7.140301390683478,"sd_diff":2.5942774055456224,"n_paired_turns":984,"n_forfeit_turns":23,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02084973830739082,"A":6.252443761091622,"Mc":0.14589127749303588},"text":{"R":0.013478223619726308,"A":16.07317428479745,"Mc":0.1821263454892285},"tool_call":{"R":0.007224982953721688,"A":5.6627471717697935,"Mc":0.19267819291816457},"terminus_json":{"R":0.0022203159868232772,"A":11.114936264168696,"Mc":0.11234788949237785},"boxed":{"R":0.179649162214516,"A":5.637273758878572,"Mc":0.09924957572049913}},"challenger":{"mean":-1.454302154776849,"mean_valid":-1.17996037940684,"sd_valid":2.277214487455566,"n_turns":998,"n_valid":961,"n_forfeits":25,"n_unscorable":12,"mean_z_R":0.20713908572885686,"mean_typ_c":0.12353820441995415,"mean_z_A":-0.30197570676224367,"bind_frac":{"R":0.2601456815816857,"Gc":0.23100936524453694,"A":0.5088449531737773},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.32599866035822334,"mean_R":0.012433408612578802,"mean_A":0.5312049153915546,"mean_mc":-0.7447392936897442},"king":{"mean":-0.8423467264091979,"mean_valid":-0.7968052844761743,"sd_valid":1.7026276506747167,"n_turns":998,"n_valid":980,"n_forfeits":4,"n_unscorable":14,"mean_z_R":0.21906869831910572,"mean_typ_c":0.5562483115848357,"mean_z_A":-0.21772464930804072,"bind_frac":{"R":0.32142857142857145,"Gc":0.1653061224489796,"A":0.513265306122449},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3210616039168999,"mean_R":0.01318733475549045,"mean_A":1.4391270160338414,"mean_mc":-0.6906072598156479}},"rejection_reason":null,"reign_number":null,"score":-0.0016641159725369807,"score_king":0.0020304035798275407,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9116502,"blocks_since_crown":13273,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1246.6425170068028,"mean_len_y":612.7309523809524,"n_samples":3000,"think_close_rate":0.9743333333333334,"n_text_fallback":16,"by_dialect":{"boxed":{"n_turns":32,"zero_ref_turns":0,"mean_refs":2.84375,"ref_pair_agreement":0.6551724137931034,"ref_pair_n":29},"tool_call":{"n_turns":279,"zero_ref_turns":1,"mean_refs":2.921146953405018,"ref_pair_agreement":0.17901234567901236,"ref_pair_n":270},"text":{"n_turns":335,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":317,"zero_ref_turns":1,"mean_refs":2.9022082018927446,"ref_pair_agreement":0.19201725997842503,"ref_pair_n":309},"terminus_json":{"n_turns":37,"zero_ref_turns":0,"mean_refs":2.945945945945946,"ref_pair_agreement":0.5225225225225225,"ref_pair_n":37}},"ref_pair_agreement":0.22635658914728682,"ref_pair_n":645},"duel_seconds":2156.6608108449727,"challenger":{"reason":-0.0016641159725369807,"n_turns":998,"n_pairs":2870,"n_forfeits":25,"forfeit_rate":0.025050100200400802,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":3.0175465076728596,"mean_len_z":814.2317073170732,"median_len_z":459.0,"mean_len_y":514.098606271777,"mean_b":0.09392164335637905,"b_gate_pass_rate":0.4808362369337979,"mean_r_leg":0.012433408612578802,"mean_g_leg":0.055556337789691414,"g_bind_frac":0.26002055498458376,"a_match":0.18328141225337488,"a_match_n":642,"a_match_centered":-0.03556263269639066,"n_turns_cap_raised":98,"mean_cap_tokens":2174.3416833667334,"max_cap_tokens":5077,"len_z_delta":-432.4108096897296,"len_y_delta":-98.63234610917539,"n_samples":1001,"think_close_rate":0.985014985014985,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":316,"n_valid":304,"parse_rate":0.9620253164556962,"reason":0.001047134898165417,"mean_b":0.112181419953246,"b_gate_pass_rate":0.8008998875140607,"median_len_z":326.0,"mean_r_leg":0.017664881470711213,"mean_g_leg":0.04608816076938325,"g_bind_frac":0.32894736842105265,"a_match":0.14144736842105263,"a_match_n":304,"a_match_centered":-0.03567447045707915},"boxed":{"n_turns":32,"n_valid":31,"parse_rate":0.96875,"reason":0.005912263210355015,"mean_b":1.2326997490285265,"b_gate_pass_rate":0.4090909090909091,"median_len_z":2337.0,"mean_r_leg":0.07878206778829082,"mean_g_leg":0.020111854179519703,"g_bind_frac":0.6129032258064516,"a_match":0.5555555555555556,"a_match_n":30,"a_match_centered":-0.07407407407407407},"terminus_json":{"n_turns":37,"n_valid":36,"parse_rate":0.972972972972973,"reason":-0.007155247292239983,"mean_b":0.013009856973022035,"b_gate_pass_rate":0.19811320754716982,"median_len_z":400.0,"mean_r_leg":0.0008330790229924672,"mean_g_leg":0.029552078674089644,"g_bind_frac":0.3055555555555556,"a_match":0.6018518518518519,"a_match_n":36,"a_match_centered":0.06481481481481481},"text":{"n_turns":335,"n_valid":325,"parse_rate":0.9701492537313433,"reason":-0.0034896035596373525,"mean_b":0.03824119079914721,"b_gate_pass_rate":0.31384615384615383,"median_len_z":662.0,"mean_r_leg":0.008468654647728863,"mean_g_leg":0.06070434119361969,"g_bind_frac":0.2276923076923077,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":278,"n_valid":277,"parse_rate":0.9964028776978417,"reason":-0.0026874584491084407,"mean_b":0.027936022551173632,"b_gate_pass_rate":0.37561576354679804,"median_len_z":384.0,"mean_r_leg":0.005426118794824334,"mean_g_leg":0.06725365558021121,"g_bind_frac":0.17689530685920576,"a_match":0.13357843137254902,"a_match_n":272,"a_match_centered":-0.045112781954887216}}},"king":{"reason":0.0020304035798275407,"n_turns":998,"n_pairs":2928,"n_forfeits":4,"forfeit_rate":0.004008016032064128,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-9.265462426860976,"mean_len_z":837.244193989071,"median_len_z":567.5,"mean_len_y":456.3101092896175,"mean_b":0.09642879186075251,"b_gate_pass_rate":0.4979508196721312,"mean_r_leg":0.01318733475549045,"mean_g_leg":0.058754779421231786,"g_bind_frac":0.23138832997987926,"a_match":0.1940222897669706,"a_match_n":658,"a_match_centered":-0.030161206448257927,"n_turns_cap_raised":98,"mean_cap_tokens":2174.3416833667334,"max_cap_tokens":5077,"len_z_delta":-409.39832301773174,"len_y_delta":-156.42084309133492,"n_samples":998,"think_close_rate":0.996993987975952,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":316,"n_valid":315,"parse_rate":0.9968354430379747,"reason":0.005397067212255066,"mean_b":0.1149763437044045,"b_gate_pass_rate":0.8233369683751364,"median_len_z":413.0,"mean_r_leg":0.01882005621473991,"mean_g_leg":0.04655737433553212,"g_bind_frac":0.31746031746031744,"a_match":0.17724867724867727,"a_match_n":315,"a_match_centered":-0.011363636363636364},"boxed":{"n_turns":32,"n_valid":32,"parse_rate":1.0,"reason":0.012934422389716576,"mean_b":1.2686417928516365,"b_gate_pass_rate":0.6043956043956044,"median_len_z":2253.0,"mean_r_leg":0.0965305138054755,"mean_g_leg":0.024700591949580644,"g_bind_frac":0.5625,"a_match":0.4583333333333333,"a_match_n":32,"a_match_centered":-0.1839080459770115},"terminus_json":{"n_turns":37,"n_valid":37,"parse_rate":1.0,"reason":-0.004173625081290675,"mean_b":0.016921788400914666,"b_gate_pass_rate":0.3119266055045872,"median_len_z":629.0,"mean_r_leg":0.0016621692245207468,"mean_g_leg":0.02758945007417486,"g_bind_frac":0.24324324324324326,"a_match":0.5405405405405406,"a_match_n":37,"a_match_centered":0.018018018018018014},"text":{"n_turns":335,"n_valid":332,"parse_rate":0.991044776119403,"reason":0.0007261997866598332,"mean_b":0.03898358101103072,"b_gate_pass_rate":0.2891566265060241,"median_len_z":668.0,"mean_r_leg":0.007779427486895588,"mean_g_leg":0.0653512006858678,"g_bind_frac":0.1746987951807229,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":278,"n_valid":278,"parse_rate":1.0,"reason":-0.0006542618107875354,"mean_b":0.02551125229344689,"b_gate_pass_rate":0.4,"median_len_z":507.0,"mean_r_leg":0.005203764066843947,"mean_g_leg":0.07276564966249144,"g_bind_frac":0.1618705035971223,"a_match":0.1356447688564477,"a_match_n":274,"a_match_centered":-0.041822721598002495}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T12:29:32.648205+00:00","challenge_id":"chal-00633","repo":"r2://affine-private-models/models/registrations/c5a8e173c8eff7d334e8bbe976a8719f5877090a9118d1c45ce6a2dfa179e852/","hotkey":"5FuaG67HYSUEBKz2aEwGFsUxuWBEMn9oiY7T5RbVoyTpcbK4","uid":185,"duration_s":226.4,"revision":"e17038ba63190acdb312cc7ad6ce691da757f40fa2c4e4f642c77aacc1b47460","accepted":false,"error_code":null,"error_detail":"","z":null,"margin":null,"se":null,"n_paired_turns":null,"n_forfeit_turns":null,"near_miss":null,"protocol_probe":null,"sd_meter":null,"rejection_reason":"unservable:challenger failed to load in vLLM: (APIServer pid=240648) RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}","reign_number":null,"score":null,"score_king":null,"gates":null,"duel_params":null,"teacher":null,"duel_seconds":null,"challenger":null,"king":null,"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T12:24:30.880747+00:00","challenge_id":"chal-00632","repo":"r2://affine-private-models/models/registrations/28b888d313844070d4cddcd9e26e7a1c067a586c54c25f88c1ebc90cc6ef718e/","hotkey":"5GHcziZze9kpBtbPhF47z79sdhBqLMDxhyjsVCtA2N2zboMR","uid":28,"duration_s":2996.6,"revision":"65779549fd6d3b1d6ecd0b82be25dd7bcf43403694b08fcd444e3060b14c8569","accepted":false,"error_code":null,"error_detail":"","z":-0.48806289165372163,"margin":-0.02297927555224934,"se":0.04708261157570863,"n_paired_turns":984,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":3547940654413234084,"n":1000,"digest":"099f6ed64464cf57b900ef0bb8e53e5fff0569fb0b990a6bd87ada29ba98dca5","n_paired_turns":984,"n_forfeit_turns":4,"margin":-0.02297927555224934,"se":0.04708261157570863,"z":-0.48806289165372163,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.02297927555224934,"se":0.04708261157570863,"z":-0.48806289165372163,"sd_diff":1.476923815159207,"n_paired_turns":984,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"text":{"R":0.03061806162516895,"A":17.968727310319387,"Mc":0.1743076055837921},"bash":{"R":0.023761695544430344,"A":6.4935488721790415,"Mc":0.15685270185593703},"tool_call":{"R":0.00840849786681557,"A":5.373792324445846,"Mc":0.18807061333137876},"boxed":{"R":0.10212946822146926,"A":3.3675483153168506,"Mc":0.12272228198816981},"terminus_json":{"R":0.0019844836940039546,"A":6.735921759178645,"Mc":0.1509629626177866}},"challenger":{"mean":-0.6751820513647006,"mean_valid":-0.6289583046355769,"sd_valid":1.345597882425699,"n_turns":997,"n_valid":980,"n_forfeits":4,"n_unscorable":13,"mean_z_R":0.2083920974946649,"mean_typ_c":0.6986941602885999,"mean_z_A":-0.09403934548179804,"bind_frac":{"R":0.3193877551020408,"Gc":0.1704081632653061,"A":0.5102040816326531},"n_leg_dropped":{"R":0,"Gc":1,"A":0},"mean_content_share":0.3207386231020657,"mean_R":0.013755028513204525,"mean_A":2.1612357462657688,"mean_mc":-0.6971784706412056},"king":{"mean":-0.6522027758124512,"mean_valid":-0.6175000320075963,"sd_valid":1.3552840913604447,"n_turns":997,"n_valid":981,"n_forfeits":3,"n_unscorable":13,"mean_z_R":0.1625424709443388,"mean_typ_c":0.7101907821218746,"mean_z_A":-0.11536008961097789,"bind_frac":{"R":0.34046890927624873,"Gc":0.14169215086646278,"A":0.5178389398572885},"n_leg_dropped":{"R":0,"Gc":2,"A":0},"mean_content_share":0.32608647906996785,"mean_R":0.012955013085098945,"mean_A":2.1711334986452444,"mean_mc":-0.6995045324656345}},"rejection_reason":null,"reign_number":null,"score":0.002927327001813636,"score_king":0.003511680525761892,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9115667,"blocks_since_crown":12438,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1274.7247956403269,"mean_len_y":598.0929836512262,"n_samples":3000,"think_close_rate":0.974,"n_text_fallback":13,"by_dialect":{"text":{"n_turns":344,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":330,"zero_ref_turns":0,"mean_refs":2.903030303030303,"ref_pair_agreement":0.18059855521155832,"ref_pair_n":323},"tool_call":{"n_turns":278,"zero_ref_turns":2,"mean_refs":2.902877697841727,"ref_pair_agreement":0.2188679245283019,"ref_pair_n":265},"boxed":{"n_turns":25,"zero_ref_turns":1,"mean_refs":2.84,"ref_pair_agreement":0.6956521739130435,"ref_pair_n":23},"terminus_json":{"n_turns":23,"zero_ref_turns":0,"mean_refs":2.9565217391304346,"ref_pair_agreement":0.4782608695652174,"ref_pair_n":23}},"ref_pair_agreement":0.22607781282860148,"ref_pair_n":634},"duel_seconds":2447.900128927082,"challenger":{"reason":0.002927327001813636,"n_turns":997,"n_pairs":2924,"n_forfeits":4,"forfeit_rate":0.004012036108324975,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.310874694984767,"mean_len_z":892.5287277701779,"median_len_z":604.0,"mean_len_y":332.8659370725034,"mean_b":0.0886171929831308,"b_gate_pass_rate":0.6049931600547196,"mean_r_leg":0.013755028513204525,"mean_g_leg":0.058022524323052334,"g_bind_frac":0.23162134944612287,"a_match":0.14669738863287252,"a_match_n":651,"a_match_centered":-0.07714586624539231,"n_turns_cap_raised":108,"mean_cap_tokens":2187.7582748244736,"max_cap_tokens":5073,"len_z_delta":-382.196067870149,"len_y_delta":-265.22704657872276,"n_samples":1000,"think_close_rate":0.996,"n_text_fallback":0,"by_dialect":{"bash":{"n_turns":330,"n_valid":330,"parse_rate":1.0,"reason":0.006257791301343187,"mean_b":0.10745173242716534,"b_gate_pass_rate":0.848643006263048,"median_len_z":477.0,"mean_r_leg":0.021716670520640687,"mean_g_leg":0.042589085427075006,"g_bind_frac":0.33636363636363636,"a_match":0.09848484848484848,"a_match_n":330,"a_match_centered":-0.07997936016511868},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":0.004570768102398756,"mean_b":1.1320771675027517,"b_gate_pass_rate":0.7605633802816901,"median_len_z":1772.0,"mean_r_leg":0.07825792640457806,"mean_g_leg":0.02237655594160719,"g_bind_frac":0.5,"a_match":0.638888888888889,"a_match_n":24,"a_match_centered":-0.028985507246376815},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0005350468622893652,"mean_b":0.02291118414564903,"b_gate_pass_rate":0.4264705882352941,"median_len_z":444.0,"mean_r_leg":0.0015910156321504274,"mean_g_leg":0.04688257307777627,"g_bind_frac":0.13043478260869565,"a_match":0.4057971014492754,"a_match_n":23,"a_match_centered":-0.07246376811594202},"text":{"n_turns":344,"n_valid":340,"parse_rate":0.9883720930232558,"reason":6.765233713076145e-05,"mean_b":0.04577569754262955,"b_gate_pass_rate":0.4323529411764706,"median_len_z":757.0,"mean_r_leg":0.00790196547671221,"mean_g_leg":0.0642570892535047,"g_bind_frac":0.16470588235294117,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":276,"n_valid":276,"parse_rate":1.0,"reason":0.0026551055462574157,"mean_b":0.03414034908224089,"b_gate_pass_rate":0.5353159851301115,"median_len_z":603.0,"mean_r_leg":0.006850689081410077,"mean_g_leg":0.07282326663868548,"g_bind_frac":0.17391304347826086,"a_match":0.13990267639902676,"a_match_n":274,"a_match_centered":-0.07828282828282829}}},"king":{"reason":0.003511680525761892,"n_turns":997,"n_pairs":2927,"n_forfeits":3,"forfeit_rate":0.003009027081243731,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-0.27444893604497617,"mean_len_z":825.6340963443799,"median_len_z":555.0,"mean_len_y":453.62418858899895,"mean_b":0.08536505383580109,"b_gate_pass_rate":0.5196446873932354,"mean_r_leg":0.012955013085098945,"mean_g_leg":0.05886347605730936,"g_bind_frac":0.21830985915492956,"a_match":0.18031942297784648,"a_match_n":647,"a_match_centered":-0.042194092827004225,"n_turns_cap_raised":108,"mean_cap_tokens":2187.7582748244736,"max_cap_tokens":5073,"len_z_delta":-449.09069929594693,"len_y_delta":-144.46879506222723,"n_samples":997,"think_close_rate":0.9969909729187563,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":330,"n_valid":330,"parse_rate":1.0,"reason":0.007612394024100246,"mean_b":0.10955349769771267,"b_gate_pass_rate":0.8131524008350731,"median_len_z":437.0,"mean_r_leg":0.0180697429880351,"mean_g_leg":0.045238616926302565,"g_bind_frac":0.296969696969697,"a_match":0.13737373737373737,"a_match_n":330,"a_match_centered":-0.04024767801857585},"boxed":{"n_turns":24,"n_valid":24,"parse_rate":1.0,"reason":0.007090411316670411,"mean_b":1.0977199250082008,"b_gate_pass_rate":0.6338028169014085,"median_len_z":1978.0,"mean_r_leg":0.09067696931356777,"mean_g_leg":0.02395292059823158,"g_bind_frac":0.625,"a_match":0.6527777777777778,"a_match_n":24,"a_match_centered":-0.01449275362318841},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0004681496267702371,"mean_b":0.02060400321966486,"b_gate_pass_rate":0.2647058823529412,"median_len_z":361.0,"mean_r_leg":0.001667213912162775,"mean_g_leg":0.04387378354488624,"g_bind_frac":0.21739130434782608,"a_match":0.4057971014492754,"a_match_n":23,"a_match_centered":-0.07246376811594202},"text":{"n_turns":344,"n_valid":341,"parse_rate":0.9912790697674418,"reason":-0.0004135129155931244,"mean_b":0.041150686794987755,"b_gate_pass_rate":0.3255131964809384,"median_len_z":684.0,"mean_r_leg":0.008302300531930325,"mean_g_leg":0.0631922233884984,"g_bind_frac":0.17595307917888564,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":276,"n_valid":276,"parse_rate":1.0,"reason":0.0035213821340984983,"mean_b":0.02908912304484403,"b_gate_pass_rate":0.42874845105328374,"median_len_z":517.0,"mean_r_leg":0.006770254187112886,"mean_g_leg":0.0740907113185426,"g_bind_frac":0.14130434782608695,"a_match":0.17160493827160495,"a_match_n":270,"a_match_centered":-0.04435994930291508}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T11:03:57.130956+00:00","challenge_id":"chal-00631","repo":"r2://affine-private-models/models/registrations/bb24028c26f447861290a3c3215af7a4bd2a7715584a4c68e807fc4e9b8984a5/","hotkey":"5FNFfupHodaruL3cc6tn8z7UnY9UofQ5DvJVMYvxF8ZibXMJ","uid":162,"duration_s":3378.5,"revision":"cf78e1a48167d43299a461f133c09145518e5612fdcce055c72e16a5fda9815c","accepted":false,"error_code":null,"error_detail":"","z":3.3222865425646075,"margin":0.15386225749667462,"se":0.04631215746306522,"n_paired_turns":989,"n_forfeit_turns":6,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":1182469612760322531,"n":1000,"digest":"b9431ff408fd61854b848208411726b3319b8fbbf135602685bc514d8ab32378","n_paired_turns":989,"n_forfeit_turns":6,"margin":0.15386225749667462,"se":0.04631215746306522,"z":3.3222865425646075,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.15386225749667462,"se":0.04631215746306522,"z":3.3222865425646075,"sd_diff":1.4564418813210591,"n_paired_turns":989,"n_forfeit_turns":6,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02649753941945802,"A":6.119318099828651,"Mc":0.1592383041760259},"text":{"R":0.042931348149646206,"A":22.986396323200157,"Mc":0.18421938079555586},"tool_call":{"R":0.006898459339335437,"A":5.766101294068093,"Mc":0.18425263199393102},"terminus_json":{"R":0.0028488546464134515,"A":6.946708884543086,"Mc":0.12747295893937272},"boxed":{"R":0.09291804485818456,"A":5.365587531157652,"Mc":0.12690145807109685}},"challenger":{"mean":-0.6363087342218705,"mean_valid":-0.5901617646146496,"sd_valid":1.3969176923443052,"n_turns":997,"n_valid":985,"n_forfeits":4,"n_unscorable":8,"mean_z_R":0.15277315048191858,"mean_typ_c":0.7848952222899283,"mean_z_A":-0.10741675647410866,"bind_frac":{"R":0.3269035532994924,"Gc":0.13401015228426397,"A":0.5390862944162437},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3209829129030946,"mean_R":0.014431220395037064,"mean_A":2.187591804561948,"mean_mc":-0.6657033963202699},"king":{"mean":-0.8014940513228698,"mean_valid":-0.7332104784650825,"sd_valid":1.5702300076672362,"n_turns":997,"n_valid":984,"n_forfeits":6,"n_unscorable":7,"mean_z_R":0.12579766695681802,"mean_typ_c":0.6392994712211919,"mean_z_A":-0.18524755895664155,"bind_frac":{"R":0.31097560975609756,"Gc":0.16158536585365854,"A":0.5274390243902439},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.31818938875055247,"mean_R":0.013325144783913261,"mean_A":1.7218896949092255,"mean_mc":-0.7066595194251796}},"rejection_reason":null,"reign_number":null,"score":0.003836213934007489,"score_king":0.0030401883114510226,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9115233,"blocks_since_crown":12004,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1176.6908228919742,"mean_len_y":639.1683034202506,"n_samples":3000,"think_close_rate":0.9753333333333334,"n_text_fallback":23,"by_dialect":{"boxed":{"n_turns":34,"zero_ref_turns":1,"mean_refs":2.8823529411764706,"ref_pair_agreement":0.6666666666666666,"ref_pair_n":33},"tool_call":{"n_turns":292,"zero_ref_turns":1,"mean_refs":2.921232876712329,"ref_pair_agreement":0.17142857142857143,"ref_pair_n":280},"text":{"n_turns":343,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":308,"zero_ref_turns":0,"mean_refs":2.948051948051948,"ref_pair_agreement":0.1628415300546448,"ref_pair_n":305},"terminus_json":{"n_turns":23,"zero_ref_turns":1,"mean_refs":2.8260869565217392,"ref_pair_agreement":0.6515151515151515,"ref_pair_n":22}},"ref_pair_agreement":0.209375,"ref_pair_n":640},"duel_seconds":2818.490958751994,"challenger":{"reason":0.003836213934007489,"n_turns":997,"n_pairs":2941,"n_forfeits":4,"forfeit_rate":0.004012036108324975,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":1.4678309573896544,"mean_len_z":903.8524311458688,"median_len_z":648.0,"mean_len_y":387.36042162529753,"mean_b":0.10671269777036024,"b_gate_pass_rate":0.5882352941176471,"mean_r_leg":0.014431220395037064,"mean_g_leg":0.05995297597070779,"g_bind_frac":0.22457200402819738,"a_match":0.1687211093990755,"a_match_n":649,"a_match_centered":-0.03834115805946792,"n_turns_cap_raised":90,"mean_cap_tokens":2159.6449348044134,"max_cap_tokens":4987,"len_z_delta":-272.83839174610546,"len_y_delta":-251.80788179495306,"n_samples":1000,"think_close_rate":0.997,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":308,"n_valid":308,"parse_rate":1.0,"reason":0.008525587489464057,"mean_b":0.12781417722633337,"b_gate_pass_rate":0.8755506607929515,"median_len_z":452.0,"mean_r_leg":0.019128111963114244,"mean_g_leg":0.050257772296645624,"g_bind_frac":0.30844155844155846,"a_match":0.12229437229437229,"a_match_n":308,"a_match_centered":-0.03934426229508197},"boxed":{"n_turns":33,"n_valid":32,"parse_rate":0.9696969696969697,"reason":0.007525276010784159,"mean_b":1.2794976737991153,"b_gate_pass_rate":0.7263157894736842,"median_len_z":1726.0,"mean_r_leg":0.06013271594067896,"mean_g_leg":0.0405269890328641,"g_bind_frac":0.375,"a_match":0.6770833333333334,"a_match_n":32,"a_match_centered":-0.01041666666666667},"terminus_json":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":-0.0063581029324144885,"mean_b":0.021846302375335833,"b_gate_pass_rate":0.4153846153846154,"median_len_z":579.0,"mean_r_leg":0.0008913170061186374,"mean_g_leg":0.029556041769861492,"g_bind_frac":0.3181818181818182,"a_match":0.6363636363636364,"a_match_n":22,"a_match_centered":-0.015151515151515154},"text":{"n_turns":343,"n_valid":340,"parse_rate":0.9912536443148688,"reason":0.002738515018860808,"mean_b":0.046976719584966284,"b_gate_pass_rate":0.40588235294117647,"median_len_z":788.5,"mean_r_leg":0.01472212812569761,"mean_g_leg":0.06667035376292921,"g_bind_frac":0.18235294117647058,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":291,"n_valid":291,"parse_rate":1.0,"reason":0.0005190991413694892,"mean_b":0.031533679459719105,"b_gate_pass_rate":0.49824150058616645,"median_len_z":604.0,"mean_r_leg":0.005118089074429871,"mean_g_leg":0.06680032448165446,"g_bind_frac":0.16151202749140894,"a_match":0.12601626016260162,"a_match_n":287,"a_match_centered":-0.04226190476190476}}},"king":{"reason":0.0030401883114510226,"n_turns":997,"n_pairs":2938,"n_forfeits":6,"forfeit_rate":0.006018054162487462,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":1.1988575056869286,"mean_len_z":907.7821647379169,"median_len_z":615.0,"mean_len_y":480.60857726344454,"mean_b":0.09590954281236802,"b_gate_pass_rate":0.5051055139550715,"mean_r_leg":0.013325144783913261,"mean_g_leg":0.05876120990544858,"g_bind_frac":0.23814328960645811,"a_match":0.1705668226729069,"a_match_n":641,"a_match_centered":-0.033648790746582544,"n_turns_cap_raised":90,"mean_cap_tokens":2159.6449348044134,"max_cap_tokens":4987,"len_z_delta":-268.9086581540573,"len_y_delta":-158.55972615680605,"n_samples":997,"think_close_rate":0.995987963891675,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":308,"n_valid":306,"parse_rate":0.9935064935064936,"reason":0.008172288894872069,"mean_b":0.11740273636754364,"b_gate_pass_rate":0.856353591160221,"median_len_z":460.0,"mean_r_leg":0.01873691897961451,"mean_g_leg":0.05068968339975309,"g_bind_frac":0.31699346405228757,"a_match":0.14270152505446623,"a_match_n":306,"a_match_centered":-0.01644736842105263},"boxed":{"n_turns":33,"n_valid":32,"parse_rate":0.9696969696969697,"reason":0.004483158790599768,"mean_b":1.169526291639994,"b_gate_pass_rate":0.5684210526315789,"median_len_z":1749.0,"mean_r_leg":0.06353294299198539,"mean_g_leg":0.040476257043042016,"g_bind_frac":0.3125,"a_match":0.625,"a_match_n":32,"a_match_centered":-0.03125},"terminus_json":{"n_turns":22,"n_valid":22,"parse_rate":1.0,"reason":-0.00813417774572723,"mean_b":0.02182358072308935,"b_gate_pass_rate":0.3230769230769231,"median_len_z":434.0,"mean_r_leg":0.0009196030243309431,"mean_g_leg":0.027695614421422456,"g_bind_frac":0.4090909090909091,"a_match":0.6060606060606061,"a_match_n":22,"a_match_centered":-0.045454545454545456},"text":{"n_turns":343,"n_valid":340,"parse_rate":0.9912536443148688,"reason":0.0013571834278562071,"mean_b":0.03692046776681499,"b_gate_pass_rate":0.3176470588235294,"median_len_z":712.0,"mean_r_leg":0.011478480517625202,"mean_g_leg":0.06500686468553148,"g_bind_frac":0.2,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":291,"n_valid":291,"parse_rate":1.0,"reason":0.00027318392253470827,"mean_b":0.0297190536871732,"b_gate_pass_rate":0.3634232121922626,"median_len_z":559.0,"mean_r_leg":0.005208771322421372,"mean_g_leg":0.06431078405582735,"g_bind_frac":0.17869415807560138,"a_match":0.11506524317912219,"a_match_n":281,"a_match_centered":-0.05193236714975845}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T05:39:46.837057+00:00","challenge_id":"chal-00630","repo":"r2://affine-private-models/models/registrations/5029bc9ada2a315f2077d06f09d3c63b8f533c2eaeb99655ac0a89788444f880/","hotkey":"5EmLDNtbm8Q17XjNdtjNfrKUR7J4wyN4ccPvHvwCv8rrs3Lu","uid":21,"duration_s":2971.2,"revision":"c76c2c7e2d8147a07c443dd5fca4e331a4262af9fa45dec10306eb0ee74c0054","accepted":false,"error_code":null,"error_detail":"","z":1.3313671096117636,"margin":0.06892777557817803,"se":0.05177217844766938,"n_paired_turns":991,"n_forfeit_turns":6,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":710654434544347487,"n":1000,"digest":"285c125d9927069790c29f26b9d7e12cb372a06863f3016ba0963e4360c3fb04","n_paired_turns":991,"n_forfeit_turns":6,"margin":0.06892777557817803,"se":0.05177217844766938,"z":1.3313671096117636,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.06892777557817803,"se":0.05177217844766938,"z":1.3313671096117636,"sd_diff":1.6297960716195037,"n_paired_turns":991,"n_forfeit_turns":6,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"text":{"R":0.04298448872396755,"A":18.22350008389197,"Mc":0.17151763867730815},"tool_call":{"R":0.008654319795526834,"A":5.676259076553286,"Mc":0.17623244767886484},"bash":{"R":0.022998189536290035,"A":6.9267975912622575,"Mc":0.15491922463469537},"terminus_json":{"R":0.0011772723226371829,"A":6.903856653891775,"Mc":0.12793210564079244},"boxed":{"R":0.1629479706816136,"A":3.3651274490356955,"Mc":0.14842918100946081}},"challenger":{"mean":-0.7384291703807232,"mean_valid":-0.6927895722870281,"sd_valid":1.4380567215814526,"n_turns":995,"n_valid":987,"n_forfeits":4,"n_unscorable":4,"mean_z_R":0.14966164059186265,"mean_typ_c":0.6057548613231842,"mean_z_A":-0.1779326902181755,"bind_frac":{"R":0.3140830800405269,"Gc":0.18642350557244175,"A":0.49949341438703143},"n_leg_dropped":{"R":0,"Gc":2,"A":0},"mean_content_share":0.33396380774568163,"mean_R":0.013161960910832776,"mean_A":2.471926447052106,"mean_mc":-0.7140649719947936},"king":{"mean":-0.8073569459589013,"mean_valid":-0.7391784095891077,"sd_valid":1.6465288697992908,"n_turns":995,"n_valid":985,"n_forfeits":6,"n_unscorable":4,"mean_z_R":0.15457395803169297,"mean_typ_c":0.6037497741718052,"mean_z_A":-0.1910519268342797,"bind_frac":{"R":0.32284263959390863,"Gc":0.15837563451776648,"A":0.5187817258883248},"n_leg_dropped":{"R":0,"Gc":2,"A":0},"mean_content_share":0.32792053144422184,"mean_R":0.013213686038357297,"mean_A":2.0828395570088594,"mean_mc":-0.6911763094975484}},"rejection_reason":null,"reign_number":null,"score":0.0031044533772571713,"score_king":0.003725480433707132,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9113646,"blocks_since_crown":10417,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1187.0535230352305,"mean_len_y":607.1304200542005,"n_samples":3000,"think_close_rate":0.974,"n_text_fallback":14,"by_dialect":{"text":{"n_turns":326,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":27,"zero_ref_turns":0,"mean_refs":2.925925925925926,"ref_pair_agreement":0.7777777777777778,"ref_pair_n":27},"terminus_json":{"n_turns":32,"zero_ref_turns":2,"mean_refs":2.8125,"ref_pair_agreement":0.5666666666666667,"ref_pair_n":30},"tool_call":{"n_turns":252,"zero_ref_turns":2,"mean_refs":2.9166666666666665,"ref_pair_agreement":0.19183673469387755,"ref_pair_n":245},"bash":{"n_turns":363,"zero_ref_turns":1,"mean_refs":2.9476584022038566,"ref_pair_agreement":0.191272051996286,"ref_pair_n":359}},"ref_pair_agreement":0.23247604639435202,"ref_pair_n":661},"duel_seconds":2422.54106901295,"challenger":{"reason":0.0031044533772571713,"n_turns":995,"n_pairs":2940,"n_forfeits":4,"forfeit_rate":0.004020100502512563,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-728.9148183362904,"mean_len_z":832.2408163265306,"median_len_z":609.0,"mean_len_y":469.1108843537415,"mean_b":0.10115053457495628,"b_gate_pass_rate":0.5227891156462585,"mean_r_leg":0.013161960910832776,"mean_g_leg":0.05893610583497792,"g_bind_frac":0.23107971745711403,"a_match":0.20877998979070955,"a_match_n":653,"a_match_centered":-0.021604938271604937,"n_turns_cap_raised":92,"mean_cap_tokens":2174.875376884422,"max_cap_tokens":5056,"len_z_delta":-354.8127067086998,"len_y_delta":-138.01953570045902,"n_samples":998,"think_close_rate":0.996993987975952,"n_text_fallback":14,"by_dialect":{"bash":{"n_turns":362,"n_valid":361,"parse_rate":0.9972375690607734,"reason":0.007359787487385253,"mean_b":0.12578987295633512,"b_gate_pass_rate":0.8303655107778819,"median_len_z":582.0,"mean_r_leg":0.01716913793634069,"mean_g_leg":0.05064382194078628,"g_bind_frac":0.27146814404432135,"a_match":0.19113573407202217,"a_match_n":361,"a_match_centered":0.0018621973929236486},"boxed":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":0.006434637495363688,"mean_b":1.348061261690148,"b_gate_pass_rate":0.5443037974683544,"median_len_z":1947.0,"mean_r_leg":0.051104962387174366,"mean_g_leg":0.02594473364564704,"g_bind_frac":0.4444444444444444,"a_match":0.6419753086419753,"a_match_n":27,"a_match_centered":-0.13580246913580246},"terminus_json":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":-0.006777575132802012,"mean_b":0.013752273771202285,"b_gate_pass_rate":0.26666666666666666,"median_len_z":522.0,"mean_r_leg":0.0008372563272670515,"mean_g_leg":0.03983177587900876,"g_bind_frac":0.3,"a_match":0.5777777777777777,"a_match_n":30,"a_match_centered":0.011111111111111108},"text":{"n_turns":326,"n_valid":323,"parse_rate":0.99079754601227,"reason":-0.00014491884602291127,"mean_b":0.03569219451100858,"b_gate_pass_rate":0.29411764705882354,"median_len_z":638.0,"mean_r_leg":0.011544901825998351,"mean_g_leg":0.06591319521840798,"g_bind_frac":0.22291021671826625,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":250,"n_valid":250,"parse_rate":1.0,"reason":0.0020060945014005343,"mean_b":0.028359859063761504,"b_gate_pass_rate":0.40680272108843535,"median_len_z":545.0,"mean_r_leg":0.0068459580141884205,"mean_g_leg":0.06775135208596306,"g_bind_frac":0.152,"a_match":0.13900709219858154,"a_match_n":235,"a_match_centered":-0.04864091559370529}}},"king":{"reason":0.003725480433707132,"n_turns":995,"n_pairs":2934,"n_forfeits":6,"forfeit_rate":0.006030150753768844,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1260.7400271996194,"mean_len_z":800.2539195637355,"median_len_z":547.5,"mean_len_y":441.44989775051124,"mean_b":0.09807063324911965,"b_gate_pass_rate":0.5378323108384458,"mean_r_leg":0.013213686038357297,"mean_g_leg":0.061189974267327515,"g_bind_frac":0.2103134479271992,"a_match":0.19494949494949493,"a_match_n":660,"a_match_centered":-0.034148827726809376,"n_turns_cap_raised":92,"mean_cap_tokens":2174.875376884422,"max_cap_tokens":5056,"len_z_delta":-386.79960347149495,"len_y_delta":-165.68052230368926,"n_samples":995,"think_close_rate":0.9959798994974874,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":362,"n_valid":360,"parse_rate":0.994475138121547,"reason":0.007946407171546193,"mean_b":0.11726369910103407,"b_gate_pass_rate":0.856203007518797,"median_len_z":455.5,"mean_r_leg":0.018198169841659933,"mean_g_leg":0.052915842765917286,"g_bind_frac":0.25,"a_match":0.16296296296296295,"a_match_n":360,"a_match_centered":-0.026143790849673203},"boxed":{"n_turns":27,"n_valid":27,"parse_rate":1.0,"reason":0.00840659995130291,"mean_b":1.3705744651540464,"b_gate_pass_rate":0.5569620253164557,"median_len_z":2423.0,"mean_r_leg":0.05533433367861697,"mean_g_leg":0.02695468517536698,"g_bind_frac":0.4444444444444444,"a_match":0.7222222222222222,"a_match_n":27,"a_match_centered":-0.05555555555555555},"terminus_json":{"n_turns":30,"n_valid":30,"parse_rate":1.0,"reason":-0.004527345629894705,"mean_b":0.013975981797808228,"b_gate_pass_rate":0.2,"median_len_z":544.5,"mean_r_leg":0.0016438620918898129,"mean_g_leg":0.04431862228795933,"g_bind_frac":0.2,"a_match":0.5444444444444444,"a_match_n":30,"a_match_centered":-0.022222222222222223},"text":{"n_turns":326,"n_valid":322,"parse_rate":0.9877300613496932,"reason":0.00022022018906348506,"mean_b":0.03382120037155074,"b_gate_pass_rate":0.30124223602484473,"median_len_z":657.0,"mean_r_leg":0.011093567176050492,"mean_g_leg":0.06651772003831165,"g_bind_frac":0.21428571428571427,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":250,"n_valid":250,"parse_rate":1.0,"reason":0.0026692160960633637,"mean_b":0.02825328087282498,"b_gate_pass_rate":0.4272108843537415,"median_len_z":476.0,"mean_r_leg":0.005606091384680719,"mean_g_leg":0.0719645605357866,"g_bind_frac":0.124,"a_match":0.14060356652949244,"a_match_n":243,"a_match_centered":-0.04513888888888889}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T03:57:41.286960+00:00","challenge_id":"chal-00629","repo":"r2://affine-private-models/models/registrations/f1e53f197f2a8f7483abc441ba9c673ddd868cb98c534161a1bc10f7f34a2a15/","hotkey":"5GWgJt3PZ3CvkuWHFqWXnUSphkx7LTv8Xggf799VFmUNFMrA","uid":62,"duration_s":3184.1,"revision":"346cb1262e1bd0629595962c0ebef78387edc2e623ea548867afdb259afec05e","accepted":false,"error_code":null,"error_detail":"","z":-3.8465780056058256,"margin":-0.2985837171219427,"se":0.0776232060514048,"n_paired_turns":984,"n_forfeit_turns":34,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":16189011842076498983,"n":1000,"digest":"4f197c32eda462098cb39696c1e4f6bb4c785b48be7f2b2b974049a2f4fddaa9","n_paired_turns":984,"n_forfeit_turns":34,"margin":-0.2985837171219427,"se":0.0776232060514048,"z":-3.8465780056058256,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.95,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":1},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.2985837171219427,"se":0.0776232060514048,"z":-3.8465780056058256,"sd_diff":2.4349448297272906,"n_paired_turns":984,"n_forfeit_turns":34,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"tool_call":{"R":0.007749168141239619,"A":6.537497648199542,"Mc":0.1830514309216064},"text":{"R":0.0429678157897598,"A":16.635112307097177,"Mc":0.1688797173679383},"bash":{"R":0.025000341530444226,"A":6.606788293165526,"Mc":0.15464093967802123},"terminus_json":{"R":0.0015786588564124543,"A":7.709840273085881,"Mc":0.10942662292948906},"boxed":{"R":0.17773312218877146,"A":3.882592467079423,"Mc":0.12194194027452712}},"challenger":{"mean":-1.1691810195111076,"mean_valid":-0.7705704366329676,"sd_valid":1.584161886266394,"n_turns":997,"n_valid":951,"n_forfeits":35,"n_unscorable":11,"mean_z_R":0.17712132567746505,"mean_typ_c":0.5451356489160951,"mean_z_A":-0.19572410935042434,"bind_frac":{"R":0.29863301787592006,"Gc":0.1808622502628812,"A":0.5205047318611987},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.2916035976078959,"mean_R":0.014455958592008903,"mean_A":1.5537356927192303,"mean_mc":-0.7047645849960655},"king":{"mean":-0.8599046777563052,"mean_valid":-0.8030674567244496,"sd_valid":1.8535488698778295,"n_turns":997,"n_valid":980,"n_forfeits":5,"n_unscorable":12,"mean_z_R":0.3066144465632112,"mean_typ_c":0.5357290071649856,"mean_z_A":-0.19193243650765368,"bind_frac":{"R":0.3112244897959184,"Gc":0.1653061224489796,"A":0.523469387755102},"n_leg_dropped":{"R":1,"Gc":3,"A":1},"mean_content_share":0.32377793167829483,"mean_R":0.0202971763297516,"mean_A":1.4935154430585904,"mean_mc":-0.6889039691566866}},"rejection_reason":null,"reign_number":null,"score":0.00016481444798337275,"score_king":0.003297976603013737,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9113118,"blocks_since_crown":9889,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1235.1709314227226,"mean_len_y":589.8232685090413,"n_samples":3000,"think_close_rate":0.975,"n_text_fallback":27,"by_dialect":{"tool_call":{"n_turns":283,"zero_ref_turns":2,"mean_refs":2.908127208480565,"ref_pair_agreement":0.14856429463171036,"ref_pair_n":267},"bash":{"n_turns":339,"zero_ref_turns":0,"mean_refs":2.893805309734513,"ref_pair_agreement":0.17223910840932116,"ref_pair_n":329},"terminus_json":{"n_turns":30,"zero_ref_turns":1,"mean_refs":2.8,"ref_pair_agreement":0.5862068965517241,"ref_pair_n":29},"text":{"n_turns":323,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":25,"zero_ref_turns":0,"mean_refs":2.96,"ref_pair_agreement":0.753623188405797,"ref_pair_n":23}},"ref_pair_agreement":0.20164609053497942,"ref_pair_n":648},"duel_seconds":2646.459618420922,"challenger":{"reason":0.00016481444798337275,"n_turns":997,"n_pairs":2836,"n_forfeits":35,"forfeit_rate":0.03510531594784353,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.9807917044948709,"mean_len_z":1185.8963328631876,"median_len_z":722.5,"mean_len_y":481.9019746121298,"mean_b":0.10058703791513678,"b_gate_pass_rate":0.5190409026798307,"mean_r_leg":0.014455958592008903,"mean_g_leg":0.05675460796520026,"g_bind_frac":0.22245322245322247,"a_match":0.18333333333333332,"a_match_n":640,"a_match_centered":-0.01910828025477707,"n_turns_cap_raised":93,"mean_cap_tokens":2169.812437311936,"max_cap_tokens":5103,"len_z_delta":-49.27459855953498,"len_y_delta":-107.92129389691155,"n_samples":1000,"think_close_rate":0.968,"n_text_fallback":10,"by_dialect":{"bash":{"n_turns":339,"n_valid":332,"parse_rate":0.9793510324483776,"reason":0.0054255622374767085,"mean_b":0.12561091706008212,"b_gate_pass_rate":0.8528497409326425,"median_len_z":621.0,"mean_r_leg":0.017511887988539695,"mean_g_leg":0.04708385329442335,"g_bind_frac":0.29518072289156627,"a_match":0.1536144578313253,"a_match_n":332,"a_match_centered":-0.023662551440329218},"boxed":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":0.009418276188419977,"mean_b":1.3399207247684781,"b_gate_pass_rate":0.7567567567567568,"median_len_z":1729.0,"mean_r_leg":0.1276993010473056,"mean_g_leg":0.029913766423102346,"g_bind_frac":0.36,"a_match":0.717391304347826,"a_match_n":23,"a_match_centered":-0.036231884057971016},"terminus_json":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":-0.005422727415944917,"mean_b":0.02138921142396946,"b_gate_pass_rate":0.2261904761904762,"median_len_z":725.0,"mean_r_leg":0.0010909536988153844,"mean_g_leg":0.03689140870364219,"g_bind_frac":0.1724137931034483,"a_match":0.6609195402298851,"a_match_n":29,"a_match_centered":0.07471264367816091},"text":{"n_turns":323,"n_valid":308,"parse_rate":0.9535603715170279,"reason":-0.002977765005331032,"mean_b":0.043349831068823154,"b_gate_pass_rate":0.22402597402597402,"median_len_z":799.5,"mean_r_leg":0.010073071021451812,"mean_g_leg":0.06035062301792761,"g_bind_frac":0.17857142857142858,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":281,"n_valid":268,"parse_rate":0.9537366548042705,"reason":-0.002816104294631157,"mean_b":0.029206886266508567,"b_gate_pass_rate":0.46514575411913817,"median_len_z":643.0,"mean_r_leg":0.006589773489783369,"mean_g_leg":0.06925524875473585,"g_bind_frac":0.17537313432835822,"a_match":0.11979166666666666,"a_match_n":256,"a_match_centered":-0.02248677248677249}}},"king":{"reason":0.003297976603013737,"n_turns":997,"n_pairs":2920,"n_forfeits":5,"forfeit_rate":0.0050150451354062184,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-2.4130030020647752,"mean_len_z":812.7061643835616,"median_len_z":593.0,"mean_len_y":484.4547945205479,"mean_b":0.09582557512025715,"b_gate_pass_rate":0.5256849315068494,"mean_r_leg":0.0202971763297516,"mean_g_leg":0.05610289696722786,"g_bind_frac":0.21673387096774194,"a_match":0.17553191489361702,"a_match_n":658,"a_match_centered":-0.02199792960662526,"n_turns_cap_raised":93,"mean_cap_tokens":2169.812437311936,"max_cap_tokens":5103,"len_z_delta":-422.46476703916096,"len_y_delta":-105.3684739884934,"n_samples":997,"think_close_rate":0.9979939819458375,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":339,"n_valid":336,"parse_rate":0.9911504424778761,"reason":0.007518882057853983,"mean_b":0.1161439239930967,"b_gate_pass_rate":0.8493852459016393,"median_len_z":469.5,"mean_r_leg":0.01664329422562539,"mean_g_leg":0.04861995924322332,"g_bind_frac":0.2708333333333333,"a_match":0.15426587301587302,"a_match_n":336,"a_match_centered":-0.01778455284552846},"boxed":{"n_turns":25,"n_valid":25,"parse_rate":1.0,"reason":0.0077820315724948875,"mean_b":1.30911649311057,"b_gate_pass_rate":0.6891891891891891,"median_len_z":1543.0,"mean_r_leg":0.1345113941162973,"mean_g_leg":0.029116634078826507,"g_bind_frac":0.28,"a_match":0.717391304347826,"a_match_n":23,"a_match_centered":-0.03623188405797102},"terminus_json":{"n_turns":29,"n_valid":29,"parse_rate":1.0,"reason":-0.0054478388960506685,"mean_b":0.01867937748448175,"b_gate_pass_rate":0.20238095238095238,"median_len_z":598.0,"mean_r_leg":0.001124769886634554,"mean_g_leg":0.03971946311753698,"g_bind_frac":0.13793103448275862,"a_match":0.6666666666666666,"a_match_n":29,"a_match_centered":0.08045977011494251},"text":{"n_turns":323,"n_valid":321,"parse_rate":0.9938080495356038,"reason":0.000721232725494657,"mean_b":0.04571696323912285,"b_gate_pass_rate":0.3115264797507788,"median_len_z":684.0,"mean_r_leg":0.028666340817546238,"mean_g_leg":0.05852245675636266,"g_bind_frac":0.18691588785046728,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":281,"n_valid":281,"parse_rate":1.0,"reason":0.0016713879855178586,"mean_b":0.02914348206043077,"b_gate_pass_rate":0.4106925880923451,"median_len_z":526.0,"mean_r_leg":0.006922966111214523,"mean_g_leg":0.06637821560354216,"g_bind_frac":0.18861209964412812,"a_match":0.10308641975308641,"a_match_n":270,"a_match_centered":-0.03724747474747475}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-21T00:19:27.947063+00:00","challenge_id":"chal-00628","repo":"r2://affine-private-models/models/registrations/b8621c2d10c543e8ad5680f3cdf35c7eeeff8854b4f0407bba825548f233472b/","hotkey":"5ChoGKCm5HmGxpZPw8v1xMpJMfGrdAQH83EkNCSLH3Yruu6g","uid":17,"duration_s":3042.4,"revision":"742bdaee1ecbd3d1b65f7ca87a5668f9cf7edf0252dc97f65ab25405d00c574b","accepted":false,"error_code":null,"error_detail":"","z":1.5560425075857276,"margin":0.0905363252676068,"se":0.05818370952351303,"n_paired_turns":988,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":8153785742903002762,"n":1000,"digest":"beee6154d14da3062e8f1d1e57cf8eb2e17568a11c52abe5594782a782a948af","n_paired_turns":988,"n_forfeit_turns":8,"margin":0.0905363252676068,"se":0.05818370952351303,"z":1.5560425075857276,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.0905363252676068,"se":0.05818370952351303,"z":1.5560425075857276,"sd_diff":1.8288575464670678,"n_paired_turns":988,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.022430792114678858,"A":8.392923189254947,"Mc":0.14555978980133777},"tool_call":{"R":0.013009886720425483,"A":5.658038197286508,"Mc":0.18062650402387936},"text":{"R":0.012861553396669653,"A":7.691557684221771,"Mc":0.18072136574640557},"boxed":{"R":0.0421620868769341,"A":3.375434428708337,"Mc":0.10651455124409678},"terminus_json":{"R":0.0012251274544028987,"A":10.395012417243057,"Mc":0.125314112410882}},"challenger":{"mean":-0.8172850847084067,"mean_valid":-0.7604045408869846,"sd_valid":1.3621789843619556,"n_turns":997,"n_valid":983,"n_forfeits":5,"n_unscorable":9,"mean_z_R":0.2476633234095191,"mean_typ_c":0.6110621374356191,"mean_z_A":-0.2358504118459271,"bind_frac":{"R":0.2950152594099695,"Gc":0.1790437436419125,"A":0.525940996948118},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.31359095412256366,"mean_R":0.011950845728800733,"mean_A":2.316520570976899,"mean_mc":-0.7325386425860014},"king":{"mean":-0.9078214099760135,"mean_valid":-0.8627312531059973,"sd_valid":1.6904550261538784,"n_turns":997,"n_valid":984,"n_forfeits":4,"n_unscorable":9,"mean_z_R":0.12446117935847,"mean_typ_c":0.5445012372892363,"mean_z_A":-0.29246589329978734,"bind_frac":{"R":0.31402439024390244,"Gc":0.16361788617886178,"A":0.5223577235772358},"n_leg_dropped":{"R":0,"Gc":4,"A":0},"mean_content_share":0.31900345476140896,"mean_R":0.009990652622122743,"mean_A":1.909950768239342,"mean_mc":-0.7104535102795705}},"rejection_reason":null,"reign_number":null,"score":0.0018619412390018203,"score_king":0.0020696416609963016,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9112038,"blocks_since_crown":8809,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1289.8080842391305,"mean_len_y":601.4130434782609,"n_samples":3000,"think_close_rate":0.9743333333333334,"n_text_fallback":18,"by_dialect":{"bash":{"n_turns":299,"zero_ref_turns":1,"mean_refs":2.9331103678929766,"ref_pair_agreement":0.22033898305084745,"ref_pair_n":295},"boxed":{"n_turns":39,"zero_ref_turns":1,"mean_refs":2.8205128205128207,"ref_pair_agreement":0.7207207207207208,"ref_pair_n":37},"tool_call":{"n_turns":299,"zero_ref_turns":1,"mean_refs":2.9130434782608696,"ref_pair_agreement":0.14763552479815456,"ref_pair_n":289},"text":{"n_turns":340,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"terminus_json":{"n_turns":23,"zero_ref_turns":0,"mean_refs":2.869565217391304,"ref_pair_agreement":0.5454545454545454,"ref_pair_n":22}},"ref_pair_agreement":0.22757905650596166,"ref_pair_n":643},"duel_seconds":2466.6753984029638,"challenger":{"reason":0.0018619412390018203,"n_turns":997,"n_pairs":2930,"n_forfeits":5,"forfeit_rate":0.0050150451354062184,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-3.6896746810054086,"mean_len_z":1026.7378839590444,"median_len_z":735.0,"mean_len_y":506.740614334471,"mean_b":0.10503176761593719,"b_gate_pass_rate":0.5006825938566553,"mean_r_leg":0.011950845728800733,"mean_g_leg":0.055905149936562745,"g_bind_frac":0.23286290322580644,"a_match":0.19413919413919414,"a_match_n":637,"a_match_centered":-0.03455608718766614,"n_turns_cap_raised":101,"mean_cap_tokens":2178.4433299899697,"max_cap_tokens":5090,"len_z_delta":-263.07020028008606,"len_y_delta":-94.67242914378988,"n_samples":1000,"think_close_rate":0.999,"n_text_fallback":15,"by_dialect":{"bash":{"n_turns":298,"n_valid":295,"parse_rate":0.9899328859060402,"reason":0.008372381438471726,"mean_b":0.11795012634125579,"b_gate_pass_rate":0.8527042577675489,"median_len_z":655.0,"mean_r_leg":0.019502611038669574,"mean_g_leg":0.0473725673557626,"g_bind_frac":0.27796610169491526,"a_match":0.18983050847457628,"a_match_n":295,"a_match_centered":-0.02054794520547945},"boxed":{"n_turns":38,"n_valid":38,"parse_rate":1.0,"reason":0.0032424163839888547,"mean_b":1.1675310401494239,"b_gate_pass_rate":0.7181818181818181,"median_len_z":1634.0,"mean_r_leg":0.03146720290024606,"mean_g_leg":0.029689902118982113,"g_bind_frac":0.3684210526315789,"a_match":0.6140350877192983,"a_match_n":38,"a_match_centered":-0.11711711711711711},"terminus_json":{"n_turns":23,"n_valid":22,"parse_rate":0.9565217391304348,"reason":-0.009658353286917906,"mean_b":0.016397758466870933,"b_gate_pass_rate":0.2222222222222222,"median_len_z":540.0,"mean_r_leg":0.001067288925144994,"mean_g_leg":0.03204663417264765,"g_bind_frac":0.18181818181818182,"a_match":0.5454545454545454,"a_match_n":22,"a_match_centered":-2.64338815386942e-18},"text":{"n_turns":340,"n_valid":340,"parse_rate":1.0,"reason":-0.0016369830068321428,"mean_b":0.052015088025753484,"b_gate_pass_rate":0.27941176470588236,"median_len_z":728.0,"mean_r_leg":0.009013828116910075,"mean_g_leg":0.05540525345535337,"g_bind_frac":0.2,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":298,"n_valid":297,"parse_rate":0.9966442953020134,"reason":5.667876493524914e-05,"mean_b":0.0261838206659293,"b_gate_pass_rate":0.4009216589861751,"median_len_z":748.0,"mean_r_leg":0.006121323502528071,"mean_g_leg":0.07007398303023758,"g_bind_frac":0.21212121212121213,"a_match":0.11465721040189127,"a_match_n":282,"a_match_centered":-0.04091456077015644}}},"king":{"reason":0.0020696416609963016,"n_turns":997,"n_pairs":2932,"n_forfeits":4,"forfeit_rate":0.004012036108324975,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":0.21116169927640557,"mean_len_z":927.2510231923602,"median_len_z":611.0,"mean_len_y":445.37141882673944,"mean_b":0.10363326080084459,"b_gate_pass_rate":0.5231923601637107,"mean_r_leg":0.009990652622122743,"mean_g_leg":0.05694088049852102,"g_bind_frac":0.20745216515609266,"a_match":0.19054956343091936,"a_match_n":649,"a_match_centered":-0.037153322867608585,"n_turns_cap_raised":101,"mean_cap_tokens":2178.4433299899697,"max_cap_tokens":5090,"len_z_delta":-362.5570610467703,"len_y_delta":-156.04162465152143,"n_samples":997,"think_close_rate":0.9969909729187563,"n_text_fallback":7,"by_dialect":{"bash":{"n_turns":298,"n_valid":297,"parse_rate":0.9966442953020134,"reason":0.008430382110997578,"mean_b":0.11498713291685761,"b_gate_pass_rate":0.8627002288329519,"median_len_z":475.0,"mean_r_leg":0.01753710022470983,"mean_g_leg":0.047669344709473406,"g_bind_frac":0.22895622895622897,"a_match":0.18742985409652074,"a_match_n":297,"a_match_centered":-0.02834467120181406},"boxed":{"n_turns":38,"n_valid":38,"parse_rate":1.0,"reason":0.0036511940894860756,"mean_b":1.1809670952909863,"b_gate_pass_rate":0.6272727272727273,"median_len_z":1805.0,"mean_r_leg":0.02612508967849089,"mean_g_leg":0.030047806585890496,"g_bind_frac":0.34210526315789475,"a_match":0.6228070175438597,"a_match_n":38,"a_match_centered":-0.10810810810810811},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0023363318270172534,"mean_b":0.018515472799586773,"b_gate_pass_rate":0.3787878787878788,"median_len_z":576.5,"mean_r_leg":0.0010899516311747184,"mean_g_leg":0.032292049979345004,"g_bind_frac":0.17391304347826086,"a_match":0.5072463768115941,"a_match_n":23,"a_match_centered":-0.015151515151515154},"text":{"n_turns":340,"n_valid":337,"parse_rate":0.9911764705882353,"reason":-0.001737768088494145,"mean_b":0.046319563822399,"b_gate_pass_rate":0.3026706231454006,"median_len_z":755.0,"mean_r_leg":0.005770943880148281,"mean_g_leg":0.05736512892099244,"g_bind_frac":0.19584569732937684,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":298,"n_valid":298,"parse_rate":1.0,"reason":0.0001913096431039264,"mean_b":0.029157848206103558,"b_gate_pass_rate":0.4362801377726751,"median_len_z":526.0,"mean_r_leg":0.005871036591004768,"mean_g_leg":0.07103327755085417,"g_bind_frac":0.18456375838926176,"a_match":0.1122565864833906,"a_match_n":291,"a_match_centered":-0.03873239436619718}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-20T16:43:55.593432+00:00","challenge_id":"chal-00627","repo":"r2://affine-private-models/models/registrations/8354a87a77cc58c65dfce2ecb3fdc811ce9cedf3772d413666d9dbee4db10a0a/","hotkey":"5HP4hBcEEFbKHczQMr47XSsqQnJJvWnKkKWGi6QbNWb5aESv","uid":92,"duration_s":152.3,"revision":"5a9338149a89ddb72ce4eca673ca00d1b653e6d6ee01b0cab1b795ae14da6d52","accepted":false,"error_code":null,"error_detail":"","z":null,"margin":null,"se":null,"n_paired_turns":null,"n_forfeit_turns":null,"near_miss":null,"protocol_probe":null,"sd_meter":null,"rejection_reason":"unservable:challenger failed to load in vLLM","reign_number":null,"score":null,"score_king":null,"gates":null,"duel_params":null,"teacher":null,"duel_seconds":null,"challenger":null,"king":null,"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-20T16:40:15.074076+00:00","challenge_id":"chal-00626","repo":"r2://affine-private-models/models/registrations/b7ea28d23e8f67ad4b73746bf0c5e7be9340caab66f9cf157e0818619489101f/","hotkey":"5Gr3g3jLxR3ZAwKy3sQVoMz1ohfmn3Lu966u5mFiPZSGiFxJ","uid":8,"duration_s":3030.3,"revision":"8eaccc2614876f199c62981c0cc4d99ed802bae85a617dffa351f7c23c9cebcc","accepted":false,"error_code":null,"error_detail":"","z":-2.213562358485968,"margin":-0.11947310062867611,"se":0.05397322563363126,"n_paired_turns":991,"n_forfeit_turns":8,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":11305727060815861171,"n":1000,"digest":"e475f0f56008f45d2fb3afd9e891871465550ffcae454b795365ceae8382ccc9","n_paired_turns":991,"n_forfeit_turns":8,"margin":-0.11947310062867611,"se":0.05397322563363126,"z":-2.213562358485968,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":1.0,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":true,"reasons":[]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.11947310062867611,"se":0.05397322563363126,"z":-2.213562358485968,"sd_diff":1.6990853726435233,"n_paired_turns":991,"n_forfeit_turns":8,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02691843642854575,"A":6.284839740143067,"Mc":0.15212431648147193},"tool_call":{"R":0.008503568810417679,"A":6.396307162376761,"Mc":0.18443016091953976},"text":{"R":0.019551705729525245,"A":20.833490483867163,"Mc":0.17354336610386142},"boxed":{"R":0.20281814929361366,"A":5.131025197486322,"Mc":0.11186739589238069},"terminus_json":{"R":0.001180722713257724,"A":6.145291209044601,"Mc":0.09509738683077723}},"challenger":{"mean":-0.8197716046769501,"mean_valid":-0.7287829707373933,"sd_valid":1.75193572927614,"n_turns":997,"n_valid":983,"n_forfeits":8,"n_unscorable":6,"mean_z_R":0.092184207694886,"mean_typ_c":0.5403297772773485,"mean_z_A":-0.07585323325270153,"bind_frac":{"R":0.34384537131230924,"Gc":0.18209562563580875,"A":0.474059003051882},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.33362741339717733,"mean_R":0.012377283330039547,"mean_A":2.2621976784896813,"mean_mc":-0.6878904640193969},"king":{"mean":-0.700298504048274,"mean_valid":-0.6545043743787635,"sd_valid":1.492336731154415,"n_turns":997,"n_valid":987,"n_forfeits":4,"n_unscorable":6,"mean_z_R":0.13029790913911588,"mean_typ_c":0.6073095547994997,"mean_z_A":-0.08547640367899656,"bind_frac":{"R":0.3404255319148936,"Gc":0.17426545086119555,"A":0.48530901722391084},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.3233872246733246,"mean_R":0.012480430560043197,"mean_A":2.147548941967525,"mean_mc":-0.6971310672257115}},"rejection_reason":null,"reign_number":null,"score":0.0022724873434455685,"score_king":0.002603827137272391,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9109756,"blocks_since_crown":6527,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1159.9590108401085,"mean_len_y":651.2452574525745,"n_samples":3000,"think_close_rate":0.976,"n_text_fallback":22,"by_dialect":{"text":{"n_turns":324,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"tool_call":{"n_turns":289,"zero_ref_turns":1,"mean_refs":2.930795847750865,"ref_pair_agreement":0.14166666666666666,"ref_pair_n":280},"bash":{"n_turns":344,"zero_ref_turns":2,"mean_refs":2.9244186046511627,"ref_pair_agreement":0.1854043392504931,"ref_pair_n":338},"boxed":{"n_turns":20,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.5833333333333333,"ref_pair_n":20},"terminus_json":{"n_turns":23,"zero_ref_turns":0,"mean_refs":2.9130434782608696,"ref_pair_agreement":0.5217391304347826,"ref_pair_n":23}},"ref_pair_agreement":0.19062027231467474,"ref_pair_n":661},"duel_seconds":2480.233938505058,"challenger":{"reason":0.0022724873434455685,"n_turns":997,"n_pairs":2928,"n_forfeits":8,"forfeit_rate":0.00802407221664995,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-6.531928814784326,"mean_len_z":831.8005464480874,"median_len_z":563.0,"mean_len_y":461.7018442622951,"mean_b":0.08929866712074384,"b_gate_pass_rate":0.5382513661202186,"mean_r_leg":0.012377283330039547,"mean_g_leg":0.05749859362230423,"g_bind_frac":0.21334681496461072,"a_match":0.17857142857142858,"a_match_n":658,"a_match_centered":-0.010991820040899797,"n_turns_cap_raised":87,"mean_cap_tokens":2165.098294884654,"max_cap_tokens":5072,"len_z_delta":-328.1584643920211,"len_y_delta":-189.5434131902794,"n_samples":1000,"think_close_rate":0.994,"n_text_fallback":12,"by_dialect":{"bash":{"n_turns":342,"n_valid":340,"parse_rate":0.9941520467836257,"reason":0.006099197207625182,"mean_b":0.11116163165256632,"b_gate_pass_rate":0.885,"median_len_z":435.0,"mean_r_leg":0.017495789655064806,"mean_g_leg":0.047482043206644016,"g_bind_frac":0.27941176470588236,"a_match":0.16274509803921566,"a_match_n":340,"a_match_centered":-0.021825396825396824},"boxed":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":0.01628723800469839,"mean_b":1.509567679556764,"b_gate_pass_rate":0.5,"median_len_z":1617.5,"mean_r_leg":0.1458437963584014,"mean_g_leg":0.024235534853287454,"g_bind_frac":0.65,"a_match":0.5833333333333333,"a_match_n":20,"a_match_centered":-5.551115123125783e-18},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.002113733724758532,"mean_b":0.01631498340014369,"b_gate_pass_rate":0.2537313432835821,"median_len_z":501.0,"mean_r_leg":0.0013281427511146705,"mean_g_leg":0.03260351278166195,"g_bind_frac":0.21739130434782608,"a_match":0.5579710144927537,"a_match_n":23,"a_match_centered":0.03623188405797101},"text":{"n_turns":324,"n_valid":318,"parse_rate":0.9814814814814815,"reason":-0.0004059625360712401,"mean_b":0.04260361278587689,"b_gate_pass_rate":0.3238993710691824,"median_len_z":716.5,"mean_r_leg":0.006365292408690646,"mean_g_leg":0.0634362743049148,"g_bind_frac":0.16352201257861634,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":288,"n_valid":288,"parse_rate":1.0,"reason":0.00011856740857631952,"mean_b":0.021244220092124715,"b_gate_pass_rate":0.3955135773317591,"median_len_z":446.0,"mean_r_leg":0.0045867310218048185,"mean_g_leg":0.06706558222983693,"g_bind_frac":0.1597222222222222,"a_match":0.13696969696969696,"a_match_n":275,"a_match_centered":-0.0024420024420024433}}},"king":{"reason":0.002603827137272391,"n_turns":997,"n_pairs":2940,"n_forfeits":4,"forfeit_rate":0.004012036108324975,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-12.195063734780103,"mean_len_z":863.6455782312925,"median_len_z":575.0,"mean_len_y":459.50374149659865,"mean_b":0.08941601868109535,"b_gate_pass_rate":0.5306122448979592,"mean_r_leg":0.012480430560043197,"mean_g_leg":0.05731447977582304,"g_bind_frac":0.2104733131923464,"a_match":0.16919575113808802,"a_match_n":659,"a_match_centered":-0.018631955079122,"n_turns_cap_raised":87,"mean_cap_tokens":2165.098294884654,"max_cap_tokens":5072,"len_z_delta":-296.313432608816,"len_y_delta":-191.74151595597584,"n_samples":997,"think_close_rate":0.9979939819458375,"n_text_fallback":11,"by_dialect":{"bash":{"n_turns":342,"n_valid":340,"parse_rate":0.9941520467836257,"reason":0.006082323559520766,"mean_b":0.11835284047956503,"b_gate_pass_rate":0.863,"median_len_z":449.0,"mean_r_leg":0.0170563767668749,"mean_g_leg":0.047362119608241396,"g_bind_frac":0.27647058823529413,"a_match":0.1588235294117647,"a_match_n":340,"a_match_centered":-0.02281746031746032},"boxed":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":0.017143269633074665,"mean_b":1.3424446491071291,"b_gate_pass_rate":0.65,"median_len_z":1573.5,"mean_r_leg":0.13579282318045058,"mean_g_leg":0.02598398612544602,"g_bind_frac":0.65,"a_match":0.65,"a_match_n":20,"a_match_centered":0.06666666666666667},"terminus_json":{"n_turns":23,"n_valid":23,"parse_rate":1.0,"reason":-0.0001185198594309636,"mean_b":0.022135966965073438,"b_gate_pass_rate":0.26865671641791045,"median_len_z":514.0,"mean_r_leg":0.0013659000721195783,"mean_g_leg":0.032033855816995145,"g_bind_frac":0.17391304347826086,"a_match":0.572463768115942,"a_match_n":23,"a_match_centered":0.05072463768115942},"text":{"n_turns":324,"n_valid":322,"parse_rate":0.9938271604938271,"reason":-0.0005381934170281317,"mean_b":0.042555021627267285,"b_gate_pass_rate":0.33540372670807456,"median_len_z":776.0,"mean_r_leg":0.006976321334188222,"mean_g_leg":0.06025929017107936,"g_bind_frac":0.16459627329192547,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":288,"n_valid":288,"parse_rate":1.0,"reason":0.0012156119087743241,"mean_b":0.025256570032854107,"b_gate_pass_rate":0.3730814639905549,"median_len_z":501.0,"mean_r_leg":0.005556429897600902,"mean_g_leg":0.06996599968473209,"g_bind_frac":0.15625,"a_match":0.11352657004830917,"a_match_n":276,"a_match_centered":-0.025547445255474453}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-20T15:48:45.863839+00:00","challenge_id":"chal-00625","repo":"r2://affine-private-models/models/registrations/b90de1a68c49e3ad46e0fbeb1faac0c6449ee0c893c43cc19968091d0925001a/","hotkey":"5HXZMeZSP8kW7CfY8zJY3mKd6qaLuYHRqnWeYCZXzSooN2ed","uid":153,"duration_s":3131.4,"revision":"9ce31f787f27207499c206cd1d3a33f19570e3c8061230d57498b4d3de939d7b","accepted":false,"error_code":null,"error_detail":"","z":-0.40059234235131136,"margin":-0.017281247824343874,"se":0.04313923656880233,"n_paired_turns":984,"n_forfeit_turns":4,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":16934201842838451475,"n":1000,"digest":"cdc695e5977e4c78abfa4ba151e3595eb1695c34eb91ad2b96a529f2336f9609","n_paired_turns":984,"n_forfeit_turns":4,"margin":-0.017281247824343874,"se":0.04313923656880233,"z":-0.40059234235131136,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.017281247824343874,"se":0.04313923656880233,"z":-0.40059234235131136,"sd_diff":1.3532249746554588,"n_paired_turns":984,"n_forfeit_turns":4,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.02356709577248315,"A":6.062576263233123,"Mc":0.16033257058249653},"text":{"R":0.021838747098419063,"A":24.879183767635617,"Mc":0.18434540472468344},"tool_call":{"R":0.012268213089079875,"A":5.9106769808121715,"Mc":0.19197039471880906},"terminus_json":{"R":0.00316592056757442,"A":8.331473410602495,"Mc":0.11004990666134508},"boxed":{"R":0.13819176106909004,"A":4.1643303726971945,"Mc":0.09663421527366908}},"challenger":{"mean":-0.6985712227234768,"mean_valid":-0.6524429419998993,"sd_valid":1.5223131345786483,"n_turns":994,"n_valid":980,"n_forfeits":4,"n_unscorable":10,"mean_z_R":0.15251559040590518,"mean_typ_c":0.6460061306675978,"mean_z_A":-0.1350211097490859,"bind_frac":{"R":0.3193877551020408,"Gc":0.17346938775510204,"A":0.5071428571428571},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.3295546710508891,"mean_R":0.011744116281492797,"mean_A":1.5053633580483528,"mean_mc":-0.6860400518464048},"king":{"mean":-0.6927810510667481,"mean_valid":-0.6466761827734423,"sd_valid":1.5457208055023453,"n_turns":994,"n_valid":981,"n_forfeits":4,"n_unscorable":9,"mean_z_R":0.17167413620382121,"mean_typ_c":0.6727822529374191,"mean_z_A":-0.09349908630834827,"bind_frac":{"R":0.31906218144750254,"Gc":0.16309887869520898,"A":0.5178389398572885},"n_leg_dropped":{"R":0,"Gc":5,"A":0},"mean_content_share":0.328100400049208,"mean_R":0.012246336031714392,"mean_A":1.6069006295744805,"mean_mc":-0.6939579138316079}},"rejection_reason":null,"reign_number":null,"score":0.0031114159249391493,"score_king":0.003453836447755595,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9109491,"blocks_since_crown":6262,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1199.1532175689479,"mean_len_y":684.123595505618,"n_samples":3000,"think_close_rate":0.9676666666666667,"n_text_fallback":5,"by_dialect":{"tool_call":{"n_turns":264,"zero_ref_turns":1,"mean_refs":2.912878787878788,"ref_pair_agreement":0.19325551232166016,"ref_pair_n":257},"bash":{"n_turns":322,"zero_ref_turns":3,"mean_refs":2.909937888198758,"ref_pair_agreement":0.182010582010582,"ref_pair_n":315},"text":{"n_turns":357,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":22,"zero_ref_turns":1,"mean_refs":2.772727272727273,"ref_pair_agreement":0.75,"ref_pair_n":20},"terminus_json":{"n_turns":35,"zero_ref_turns":1,"mean_refs":2.8285714285714287,"ref_pair_agreement":0.5784313725490197,"ref_pair_n":34}},"ref_pair_agreement":0.2263045793397231,"ref_pair_n":626},"duel_seconds":2579.0742368979845,"challenger":{"reason":0.0031114159249391493,"n_turns":994,"n_pairs":2925,"n_forfeits":4,"forfeit_rate":0.004024144869215292,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-1.5969810178842918,"mean_len_z":868.2591452991453,"median_len_z":585.0,"mean_len_y":476.27008547008546,"mean_b":0.08083241039327373,"b_gate_pass_rate":0.49504273504273505,"mean_r_leg":0.011744116281492797,"mean_g_leg":0.05596309946023455,"g_bind_frac":0.22525252525252526,"a_match":0.1896460644479662,"a_match_n":631,"a_match_centered":-0.03322615219721329,"n_turns_cap_raised":97,"mean_cap_tokens":2174.784708249497,"max_cap_tokens":5102,"len_z_delta":-330.89407226980256,"len_y_delta":-207.85351003553257,"n_samples":997,"think_close_rate":0.995987963891675,"n_text_fallback":2,"by_dialect":{"bash":{"n_turns":319,"n_valid":319,"parse_rate":1.0,"reason":0.009818694116810646,"mean_b":0.1165742168637491,"b_gate_pass_rate":0.8452508004268944,"median_len_z":463.0,"mean_r_leg":0.020938088247939576,"mean_g_leg":0.0479627298029076,"g_bind_frac":0.2601880877742947,"a_match":0.14629049111807732,"a_match_n":319,"a_match_centered":-0.03386243386243386},"boxed":{"n_turns":21,"n_valid":20,"parse_rate":0.9523809523809523,"reason":0.010092055009935456,"mean_b":1.1389778090397895,"b_gate_pass_rate":0.6206896551724138,"median_len_z":1715.0,"mean_r_leg":0.03152956210772358,"mean_g_leg":0.03963581893504708,"g_bind_frac":0.3,"a_match":0.6666666666666666,"a_match_n":19,"a_match_centered":-0.07017543859649124},"terminus_json":{"n_turns":34,"n_valid":34,"parse_rate":1.0,"reason":-0.0005605102963227972,"mean_b":0.012880611937367626,"b_gate_pass_rate":0.2828282828282828,"median_len_z":476.0,"mean_r_leg":0.0014112030545027734,"mean_g_leg":0.041453206196463775,"g_bind_frac":0.08823529411764706,"a_match":0.5490196078431373,"a_match_n":34,"a_match_centered":-0.029411764705882353},"text":{"n_turns":357,"n_valid":354,"parse_rate":0.9915966386554622,"reason":-0.0013304205342181635,"mean_b":0.03537950825712268,"b_gate_pass_rate":0.2627118644067797,"median_len_z":715.5,"mean_r_leg":0.0072296648847602835,"mean_g_leg":0.06067863686735798,"g_bind_frac":0.211864406779661,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":263,"n_valid":263,"parse_rate":1.0,"reason":0.0009226932764605828,"mean_b":0.028993274283252636,"b_gate_pass_rate":0.4070221066319896,"median_len_z":489.0,"mean_r_leg":0.006500195636397103,"mean_g_leg":0.0624372426542937,"g_bind_frac":0.21292775665399238,"a_match":0.16087516087516088,"a_match_n":259,"a_match_centered":-0.030183727034120734}}},"king":{"reason":0.003453836447755595,"n_turns":994,"n_pairs":2927,"n_forfeits":4,"forfeit_rate":0.004024144869215292,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-2.026443295008342,"mean_len_z":852.0655961735565,"median_len_z":586.0,"mean_len_y":457.63990433891354,"mean_b":0.08192077858803677,"b_gate_pass_rate":0.5295524427741715,"mean_r_leg":0.012246336031714392,"mean_g_leg":0.056176394916725984,"g_bind_frac":0.23535353535353534,"a_match":0.19096671949286848,"a_match_n":631,"a_match_centered":-0.03403001071811362,"n_turns_cap_raised":97,"mean_cap_tokens":2174.784708249497,"max_cap_tokens":5102,"len_z_delta":-347.08762139539135,"len_y_delta":-226.4836911667045,"n_samples":994,"think_close_rate":0.9969818913480886,"n_text_fallback":4,"by_dialect":{"bash":{"n_turns":319,"n_valid":319,"parse_rate":1.0,"reason":0.009915405141234169,"mean_b":0.11797067413489824,"b_gate_pass_rate":0.847385272145144,"median_len_z":473.0,"mean_r_leg":0.021095021029364953,"mean_g_leg":0.04826437940292571,"g_bind_frac":0.2727272727272727,"a_match":0.1588296760710554,"a_match_n":319,"a_match_centered":-0.021164021164021166},"boxed":{"n_turns":21,"n_valid":20,"parse_rate":0.9523809523809523,"reason":0.012775944080894044,"mean_b":1.1576725997022113,"b_gate_pass_rate":0.65,"median_len_z":1985.0,"mean_r_leg":0.043882287707977585,"mean_g_leg":0.037302795620089535,"g_bind_frac":0.45,"a_match":0.7,"a_match_n":20,"a_match_centered":-0.05},"terminus_json":{"n_turns":34,"n_valid":34,"parse_rate":1.0,"reason":0.0006801563802958811,"mean_b":0.016452619444808195,"b_gate_pass_rate":0.3434343434343434,"median_len_z":473.0,"mean_r_leg":0.001521414456939117,"mean_g_leg":0.0385664381755498,"g_bind_frac":0.08823529411764706,"a_match":0.5196078431372549,"a_match_n":34,"a_match_centered":-0.058823529411764705},"text":{"n_turns":357,"n_valid":354,"parse_rate":0.9915966386554622,"reason":-0.0009156761092884749,"mean_b":0.03334196086658958,"b_gate_pass_rate":0.307909604519774,"median_len_z":715.5,"mean_r_leg":0.007399848406890258,"mean_g_leg":0.060495076780173615,"g_bind_frac":0.22033898305084745,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":263,"n_valid":263,"parse_rate":1.0,"reason":0.0011618837163593623,"mean_b":0.0295777236869924,"b_gate_pass_rate":0.46293888166449937,"median_len_z":495.0,"mean_r_leg":0.0070176455562554925,"mean_g_leg":0.06367194656834023,"g_bind_frac":0.21292775665399238,"a_match":0.1479328165374677,"a_match_n":258,"a_match_centered":-0.045454545454545456}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-20T06:37:32.075969+00:00","challenge_id":"chal-00624","repo":"r2://affine-private-models/models/registrations/9c880e6a155b21d7e42dd7318d13e38462e5e3d34b73b0bdd9878be68cc88b8c/","hotkey":"5DpcXTCu5H2mhNvjMsZLMko134pZHhLcXngLfGDc3Et7ebUK","uid":71,"duration_s":339.4,"revision":"211f68f6cab1478fdcacbd95eb2d2351ba3fd9ab6a6a6f02edc493b0a37aab00","accepted":false,"error_code":null,"error_detail":"","z":null,"margin":null,"se":null,"n_paired_turns":null,"n_forfeit_turns":null,"near_miss":null,"protocol_probe":null,"sd_meter":null,"rejection_reason":"unservable:challenger failed to load in vLLM","reign_number":null,"score":null,"score_king":null,"gates":null,"duel_params":null,"teacher":null,"duel_seconds":null,"challenger":null,"king":null,"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-20T06:31:01.969447+00:00","challenge_id":"chal-00623","repo":"r2://affine-private-models/models/registrations/d40bf8ac9b66f23573c3f926bd99282c8028f937b3edf9af3f48496623232bb1/","hotkey":"5GZ3ht9n6NVr2D1Hy7KAcahLY51mNy31r3APVnSAfLKv7YR1","uid":99,"duration_s":3251.5,"revision":"799eceb8db50e53d48f54eaffd5489c3b77b5ec27364000f7b7dd771b7715778","accepted":false,"error_code":null,"error_detail":"","z":0.19876412373664357,"margin":0.010849871470303784,"se":0.054586669195289664,"n_paired_turns":991,"n_forfeit_turns":11,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":4703139946628678386,"n":1000,"digest":"198c6fc8ff08ff2d3c64ae5b78284aad371ccd73d9381bde6a322a21c4508a2e","n_paired_turns":991,"n_forfeit_turns":11,"margin":0.010849871470303784,"se":0.054586669195289664,"z":0.19876412373664357,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":0.010849871470303784,"se":0.054586669195289664,"z":0.19876412373664357,"sd_diff":1.7183966695008057,"n_paired_turns":991,"n_forfeit_turns":11,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.021377081077232254,"A":5.625114016201446,"Mc":0.15082722420424016},"text":{"R":0.04394388377802737,"A":17.205689379112364,"Mc":0.19087944068474463},"tool_call":{"R":0.006049977052164296,"A":5.422411656637557,"Mc":0.2002686854698376},"boxed":{"R":0.11269555659042074,"A":4.2620459323529545,"Mc":0.11293875463327231},"terminus_json":{"R":0.0015103391452807038,"A":7.121941758375911,"Mc":0.13972604702380526}},"challenger":{"mean":-0.7389110320682984,"mean_valid":-0.6357034957023256,"sd_valid":1.5131290018711008,"n_turns":1000,"n_valid":982,"n_forfeits":9,"n_unscorable":9,"mean_z_R":0.20899971716107205,"mean_typ_c":0.7449483427710636,"mean_z_A":-0.09911810286313338,"bind_frac":{"R":0.34317718940936864,"Gc":0.14052953156822812,"A":0.5162932790224033},"n_leg_dropped":{"R":0,"Gc":7,"A":0},"mean_content_share":0.32160250729329504,"mean_R":0.014988661869968011,"mean_A":1.6810948131276342,"mean_mc":-0.6792193935040355},"king":{"mean":-0.7497609035386023,"mean_valid":-0.669728714844263,"sd_valid":1.5588936777842626,"n_turns":1000,"n_valid":984,"n_forfeits":7,"n_unscorable":9,"mean_z_R":0.21375071557775202,"mean_typ_c":0.6711820886380812,"mean_z_A":-0.10558026050710728,"bind_frac":{"R":0.3333333333333333,"Gc":0.15752032520325204,"A":0.5091463414634146},"n_leg_dropped":{"R":0,"Gc":6,"A":0},"mean_content_share":0.3227585629809729,"mean_R":0.014289354177347578,"mean_A":1.4443886989484669,"mean_mc":-0.7188569766300996}},"rejection_reason":null,"reign_number":null,"score":0.002885659827438899,"score_king":0.002683350727747338,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9106736,"blocks_since_crown":3507,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1303.0420338983051,"mean_len_y":700.1006779661017,"n_samples":3000,"think_close_rate":0.969,"n_text_fallback":17,"by_dialect":{"bash":{"n_turns":337,"zero_ref_turns":0,"mean_refs":2.943620178041543,"ref_pair_agreement":0.18473895582329317,"ref_pair_n":332},"text":{"n_turns":301,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"boxed":{"n_turns":21,"zero_ref_turns":0,"mean_refs":2.857142857142857,"ref_pair_agreement":0.7368421052631579,"ref_pair_n":19},"tool_call":{"n_turns":307,"zero_ref_turns":0,"mean_refs":2.9250814332247557,"ref_pair_agreement":0.16833890746934227,"ref_pair_n":299},"terminus_json":{"n_turns":34,"zero_ref_turns":0,"mean_refs":2.8529411764705883,"ref_pair_agreement":0.48484848484848486,"ref_pair_n":33}},"ref_pair_agreement":0.20741825280624693,"ref_pair_n":683},"duel_seconds":2718.77463987004,"challenger":{"reason":0.002885659827438899,"n_turns":1000,"n_pairs":2926,"n_forfeits":9,"forfeit_rate":0.009,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-25.810845877838123,"mean_len_z":974.6537935748462,"median_len_z":577.0,"mean_len_y":500.03315105946683,"mean_b":0.08742437378635538,"b_gate_pass_rate":0.4914559125085441,"mean_r_leg":0.014988661869968011,"mean_g_leg":0.0616234521829733,"g_bind_frac":0.21089808274470231,"a_match":0.17562984496124032,"a_match_n":688,"a_match_centered":-0.030280649926144758,"n_turns_cap_raised":105,"mean_cap_tokens":2189.645,"max_cap_tokens":5088,"len_z_delta":-328.38824032345894,"len_y_delta":-200.06752690663484,"n_samples":1003,"think_close_rate":0.9950149551345963,"n_text_fallback":3,"by_dialect":{"bash":{"n_turns":337,"n_valid":332,"parse_rate":0.9851632047477745,"reason":0.007173266412735871,"mean_b":0.11243368647040884,"b_gate_pass_rate":0.8030612244897959,"median_len_z":447.0,"mean_r_leg":0.01930752920910664,"mean_g_leg":0.04858879296700495,"g_bind_frac":0.2891566265060241,"a_match":0.15261044176706826,"a_match_n":332,"a_match_centered":-0.03150406504065041},"boxed":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":0.006338898368953562,"mean_b":1.546673679069353,"b_gate_pass_rate":0.4,"median_len_z":2391.5,"mean_r_leg":0.19344872385224215,"mean_g_leg":0.026309726724882864,"g_bind_frac":0.42857142857142855,"a_match":0.675,"a_match_n":20,"a_match_centered":-0.02631578947368421},"terminus_json":{"n_turns":34,"n_valid":34,"parse_rate":1.0,"reason":-0.005883517155651048,"mean_b":0.0166553360167898,"b_gate_pass_rate":0.29896907216494845,"median_len_z":548.0,"mean_r_leg":0.0012294293044768753,"mean_g_leg":0.03190573072145177,"g_bind_frac":0.2647058823529412,"a_match":0.4754901960784314,"a_match_n":34,"a_match_centered":0.005050505050505049},"text":{"n_turns":301,"n_valid":297,"parse_rate":0.9867109634551495,"reason":-0.00036668935923251186,"mean_b":0.033876314959910454,"b_gate_pass_rate":0.27946127946127947,"median_len_z":708.0,"mean_r_leg":0.009329475943271616,"mean_g_leg":0.06435806658873712,"g_bind_frac":0.18181818181818182,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":307,"n_valid":307,"parse_rate":1.0,"reason":0.002102818439804585,"mean_b":0.023406369700228486,"b_gate_pass_rate":0.388641425389755,"median_len_z":511.0,"mean_r_leg":0.005109400857700086,"mean_g_leg":0.07878083702173966,"g_bind_frac":0.13355048859934854,"a_match":0.13410596026490065,"a_match_n":302,"a_match_centered":-0.03310886644219978}}},"king":{"reason":0.002683350727747338,"n_turns":1000,"n_pairs":2931,"n_forfeits":7,"forfeit_rate":0.007,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":-22.82829129553304,"mean_len_z":874.0491299897645,"median_len_z":589.0,"mean_len_y":482.98021153190035,"mean_b":0.08751289055707938,"b_gate_pass_rate":0.49982940975776186,"mean_r_leg":0.014289354177347578,"mean_g_leg":0.061587448195460005,"g_bind_frac":0.21248741188318226,"a_match":0.186531007751938,"a_match_n":688,"a_match_centered":-0.019174041297935103,"n_turns_cap_raised":105,"mean_cap_tokens":2189.645,"max_cap_tokens":5088,"len_z_delta":-428.9929039085406,"len_y_delta":-217.12046643420132,"n_samples":1000,"think_close_rate":0.996,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":337,"n_valid":334,"parse_rate":0.9910979228486647,"reason":0.007021820532981431,"mean_b":0.11438577453255919,"b_gate_pass_rate":0.8152284263959391,"median_len_z":485.0,"mean_r_leg":0.019221424971408586,"mean_g_leg":0.04860449413903799,"g_bind_frac":0.3023952095808383,"a_match":0.16966067864271456,"a_match_n":334,"a_match_centered":-0.010101010101010102},"boxed":{"n_turns":21,"n_valid":21,"parse_rate":1.0,"reason":0.004167790848524009,"mean_b":1.4680891156163596,"b_gate_pass_rate":0.55,"median_len_z":2455.0,"mean_r_leg":0.16688277510077518,"mean_g_leg":0.024176027002594597,"g_bind_frac":0.38095238095238093,"a_match":0.7,"a_match_n":20,"a_match_centered":-0.05263157894736842},"terminus_json":{"n_turns":34,"n_valid":34,"parse_rate":1.0,"reason":-0.0041630060244652505,"mean_b":0.015925206063342072,"b_gate_pass_rate":0.31958762886597936,"median_len_z":621.0,"mean_r_leg":0.0009686283597949173,"mean_g_leg":0.03415005145624467,"g_bind_frac":0.29411764705882354,"a_match":0.4852941176470588,"a_match_n":34,"a_match_centered":0.01515151515151515},"text":{"n_turns":301,"n_valid":297,"parse_rate":0.9867109634551495,"reason":-0.0007726582305702383,"mean_b":0.03606543754533466,"b_gate_pass_rate":0.30303030303030304,"median_len_z":724.0,"mean_r_leg":0.008515767211686369,"mean_g_leg":0.0636410990002784,"g_bind_frac":0.16835016835016836,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":307,"n_valid":307,"parse_rate":1.0,"reason":0.0019660779561793207,"mean_b":0.024572268964599017,"b_gate_pass_rate":0.36525612472160357,"median_len_z":486.0,"mean_r_leg":0.005546313532363258,"mean_g_leg":0.07932322571988146,"g_bind_frac":0.13680781758957655,"a_match":0.13722222222222222,"a_match_n":300,"a_match_centered":-0.030968468468468468}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-20T05:17:29.269643+00:00","challenge_id":"chal-00622","repo":"r2://affine-private-models/models/registrations/99efe87571640640b9e818f02b59262dabd5761739a57f1569520255bba260d7/","hotkey":"5DPLqYeEo5t3B9ZAyjSir6mQYmqe4x8DhzdcFrWUshAMVP9J","uid":9,"duration_s":678.9,"revision":"5033d59996fe7d9ce127dbb94815bd1d8f1f08f732bdd5d8249da0a5431ec5fc","accepted":false,"error_code":null,"error_detail":"","z":null,"margin":null,"se":null,"n_paired_turns":null,"n_forfeit_turns":null,"near_miss":null,"protocol_probe":{"mode":"enforce","passed":false,"pass_rate":0.7,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":6},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_search":{"ok":false,"reasons":["multiple_tool_calls"]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":null,"rejection_reason":"protocol:pass_rate=0.70<0.9;multiple_tool_calls=6","reign_number":null,"score":null,"score_king":null,"gates":null,"duel_params":null,"teacher":null,"duel_seconds":null,"challenger":null,"king":null,"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null},{"event":"verdict","at":"2026-09-20T05:04:55.484727+00:00","challenge_id":"chal-00621","repo":"r2://affine-private-models/models/registrations/dcdcbcc53019d7104f565ebceb681f735f2042b0187226dcb87502b739a8133b/","hotkey":"5Hk7fzYv86P6qK64jCuvqaCn1bgkYtR4yikpu2KTcQuXFbGz","uid":194,"duration_s":3138.2,"revision":"71cdfbcfe0f122da0640acccaba2420d48b40d880256d9bb33edb7d0508442f4","accepted":false,"error_code":null,"error_detail":"","z":-0.6916833439888861,"margin":-0.03646104027159798,"se":0.05271348600261196,"n_paired_turns":986,"n_forfeit_turns":7,"near_miss":{"enabled":false,"low":0.001,"high":0.003,"window_mode":"absolute","window":[0.001,0.003],"extra_slices":1,"triggered":false,"slices":[{"index":0,"seed":9963207202822210833,"n":1000,"digest":"73b3aa7dc9d001a9a042b9ec075159e769a1eee3f5dc935ec7a14f01834f05e3","n_paired_turns":986,"n_forfeit_turns":7,"margin":-0.03646104027159798,"se":0.05271348600261196,"z":-0.6916833439888861,"challenger_wins":false}],"pooled":null},"protocol_probe":{"mode":"enforce","passed":true,"pass_rate":0.9,"min_pass_rate":0.9,"think_close_rate":1.0,"n":20,"by_reason":{"multiple_tool_calls":2},"by_prompt":{"assistant_bash":{"ok":true,"reasons":[]},"assistant_greeting":{"ok":true,"reasons":[]},"ide_code_question":{"ok":true,"reasons":[]},"ide_explain_snippet":{"ok":true,"reasons":[]},"ide_followup":{"ok":true,"reasons":[]},"ide_greeting":{"ok":true,"reasons":[]},"ide_tool_answer_or_call":{"ok":false,"reasons":["multiple_tool_calls"]},"ide_tool_read":{"ok":true,"reasons":[]},"ide_tool_search":{"ok":true,"reasons":[]},"no_system_greeting":{"ok":true,"reasons":[]}},"settings":{"min_pass_rate":0.9,"n_samples":2,"temperature":0.7,"max_tokens":1024}},"sd_meter":{"role":"rule","anchor":"loo","margin":-0.03646104027159798,"se":0.05271348600261196,"z":-0.6916833439888861,"sd_diff":1.6552370356102784,"n_paired_turns":986,"n_forfeit_turns":7,"would_crown":false,"live_gates_pass":true,"knobs":{"content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true},"sigma_by_dialect":{"bash":{"R":0.021189641895589792,"A":5.790305173262201,"Mc":0.16677980586830446},"text":{"R":0.18405288239485623,"A":14.170416461038196,"Mc":0.18705130406102233},"tool_call":{"R":0.008049276065042287,"A":5.257558031862886,"Mc":0.19289045123850773},"terminus_json":{"R":0.002633187285024514,"A":9.49636504704743,"Mc":0.11881713748132819},"boxed":{"R":0.0973973303577682,"A":3.3250590720824285,"Mc":0.13531737512456019}},"challenger":{"mean":-0.7698959141422985,"mean_valid":-0.7241521093119209,"sd_valid":1.6415675047043676,"n_turns":997,"n_valid":982,"n_forfeits":4,"n_unscorable":11,"mean_z_R":0.1684048413143493,"mean_typ_c":0.6987236495433771,"mean_z_A":-0.17327064615991847,"bind_frac":{"R":0.33095723014256617,"Gc":0.14969450101832993,"A":0.5193482688391039},"n_leg_dropped":{"R":0,"Gc":3,"A":0},"mean_content_share":0.3286935439760369,"mean_R":0.014693079056120353,"mean_A":1.3971696191592964,"mean_mc":-0.7044379677853679},"king":{"mean":-0.7334348738707005,"mean_valid":-0.6760109945326307,"sd_valid":1.508928279641827,"n_turns":997,"n_valid":981,"n_forfeits":5,"n_unscorable":11,"mean_z_R":0.20763990898039614,"mean_typ_c":0.7324107106928396,"mean_z_A":-0.16421010581987863,"bind_frac":{"R":0.31396534148827726,"Gc":0.1559633027522936,"A":0.5300713557594292},"n_leg_dropped":{"R":0,"Gc":2,"A":0},"mean_content_share":0.32219942599660634,"mean_R":0.02029413231210711,"mean_A":1.5510963565265907,"mean_mc":-0.7040716695599022}},"rejection_reason":null,"reign_number":null,"score":0.001717039756419052,"score_king":0.002996215516026661,"gates":null,"duel_params":{"n_turns":1000,"k_sigma":2.0,"min_margin":0.002,"min_thought_chars":80,"causality_gate":true,"causality_gamma":0.3,"tau":0.03,"n_teacher_samples":3,"n_miner_samples":1,"score_mode":"sd_min_rga","band_c":4.0,"band_floor":0.002,"forfeit_turn_score":-0.1,"action_norm_bytes":128.0,"require_think_close":true,"thought_rendering":"as_generated","allowed_action_kinds":["bash","tool_call","boxed","text","terminus_json"],"max_thought_tokens":2048,"max_action_tokens":768,"text_fallback_at_tool_turns":true,"confirmation_required":false,"thought_cap_ratio":1.25,"thought_cap_rule":"max(fixed, 1.25*L_T)","thought_cap_tokenizer":"Qwen/Qwen3.8-27B","ref_max_tokens":4096,"max_tokens_by_kind":{},"near_miss_enabled":false,"near_miss_low":0.001,"near_miss_high":0.003,"near_miss_extra_slices":1,"near_miss_window_mode":"absolute","min_z":0.0,"min_margin_mode":"fixed","min_margin_base":0.002,"min_margin_effective":0.002,"crown_block":9103229,"crown_block_source":"king","decision_block":9106320,"blocks_since_crown":3091,"sd_meter":{"role":"rule","anchor":"loo","content_lift_nats":1.0,"content_min_tokens":10,"typicality_width":2.0,"a_norm_bytes":1.0,"forfeit_sd":-12.0,"k_sigma":2.0,"min_margin_sd":0.2,"cross_echo":true}},"teacher":{"mean_len_z":1153.3563413804827,"mean_len_y":622.4240054403264,"n_samples":3000,"think_close_rate":0.9733333333333334,"n_text_fallback":15,"by_dialect":{"text":{"n_turns":348,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":null,"ref_pair_n":0},"bash":{"n_turns":331,"zero_ref_turns":3,"mean_refs":2.897280966767372,"ref_pair_agreement":0.22703818369453044,"ref_pair_n":323},"tool_call":{"n_turns":261,"zero_ref_turns":0,"mean_refs":2.9157088122605366,"ref_pair_agreement":0.16133333333333336,"ref_pair_n":250},"terminus_json":{"n_turns":40,"zero_ref_turns":0,"mean_refs":2.925,"ref_pair_agreement":0.6333333333333333,"ref_pair_n":40},"boxed":{"n_turns":20,"zero_ref_turns":0,"mean_refs":3.0,"ref_pair_agreement":0.7368421052631579,"ref_pair_n":19}},"ref_pair_agreement":0.24208860759493672,"ref_pair_n":632},"duel_seconds":2585.998782973038,"challenger":{"reason":0.001717039756419052,"n_turns":997,"n_pairs":2929,"n_forfeits":4,"forfeit_rate":0.004012036108324975,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":1.6042148101798774,"mean_len_z":820.352338682144,"median_len_z":567.0,"mean_len_y":460.12017753499487,"mean_b":0.08791294394320545,"b_gate_pass_rate":0.5124615909866849,"mean_r_leg":0.014693079056120353,"mean_g_leg":0.05801747408634153,"g_bind_frac":0.2175226586102719,"a_match":0.19600207684319834,"a_match_n":642,"a_match_centered":-0.04312169312169312,"n_turns_cap_raised":86,"mean_cap_tokens":2155.3891675025075,"max_cap_tokens":5098,"len_z_delta":-333.0040026983387,"len_y_delta":-162.3038279053315,"n_samples":1000,"think_close_rate":0.996,"n_text_fallback":6,"by_dialect":{"bash":{"n_turns":328,"n_valid":328,"parse_rate":1.0,"reason":0.006267796373369601,"mean_b":0.11692106326644768,"b_gate_pass_rate":0.8446298227320125,"median_len_z":455.0,"mean_r_leg":0.01593309859066499,"mean_g_leg":0.05161902175904997,"g_bind_frac":0.24695121951219512,"a_match":0.18851626016260165,"a_match_n":328,"a_match_centered":-0.03560371517027864},"boxed":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":0.004044899949882141,"mean_b":1.2948455368827936,"b_gate_pass_rate":0.6,"median_len_z":2480.5,"mean_r_leg":0.09671791132423031,"mean_g_leg":0.021992243741213377,"g_bind_frac":0.4,"a_match":0.6491228070175439,"a_match_n":19,"a_match_centered":-0.08771929824561404},"terminus_json":{"n_turns":40,"n_valid":40,"parse_rate":1.0,"reason":-0.004012348934756598,"mean_b":0.016675095686969385,"b_gate_pass_rate":0.2222222222222222,"median_len_z":675.0,"mean_r_leg":0.0005764815935620354,"mean_g_leg":0.03375426550747419,"g_bind_frac":0.25,"a_match":0.5791666666666667,"a_match_n":40,"a_match_centered":-0.05416666666666666},"text":{"n_turns":348,"n_valid":344,"parse_rate":0.9885057471264368,"reason":-0.0007524009840158132,"mean_b":0.04442673561267708,"b_gate_pass_rate":0.3168604651162791,"median_len_z":715.0,"mean_r_leg":0.01599082240093799,"mean_g_leg":0.061855797049484094,"g_bind_frac":0.17151162790697674,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":261,"n_valid":261,"parse_rate":1.0,"reason":-9.643955882414138e-06,"mean_b":0.026123000757555397,"b_gate_pass_rate":0.3968462549277267,"median_len_z":488.0,"mean_r_leg":0.0073023401104967,"mean_g_leg":0.06747855536637158,"g_bind_frac":0.2222222222222222,"a_match":0.11176470588235295,"a_match_n":255,"a_match_centered":-0.04771505376344086}}},"king":{"reason":0.002996215516026661,"n_turns":997,"n_pairs":2926,"n_forfeits":5,"forfeit_rate":0.0050150451354062184,"gate_pass_rate":0.0,"bank_frac":null,"calib_ratio":null,"baseline_abs":null,"mean_l1lift":null,"mean_eta":0.054345810294661005,"mean_len_z":840.1302118933697,"median_len_z":576.0,"mean_len_y":456.73137388926864,"mean_b":0.08677858524079161,"b_gate_pass_rate":0.5146958304853042,"mean_r_leg":0.02029413231210711,"mean_g_leg":0.05996511611047727,"g_bind_frac":0.20665322580645162,"a_match":0.19523060796645703,"a_match_n":636,"a_match_centered":-0.0456,"n_turns_cap_raised":86,"mean_cap_tokens":2155.3891675025075,"max_cap_tokens":5098,"len_z_delta":-313.226129487113,"len_y_delta":-165.69263155105773,"n_samples":997,"think_close_rate":0.995987963891675,"n_text_fallback":9,"by_dialect":{"bash":{"n_turns":328,"n_valid":328,"parse_rate":1.0,"reason":0.0066849080547616135,"mean_b":0.11991776404758568,"b_gate_pass_rate":0.862356621480709,"median_len_z":474.0,"mean_r_leg":0.016014761956361222,"mean_g_leg":0.052887992845510795,"g_bind_frac":0.25,"a_match":0.18851626016260165,"a_match_n":328,"a_match_centered":-0.03560371517027864},"boxed":{"n_turns":20,"n_valid":20,"parse_rate":1.0,"reason":0.00240957458410349,"mean_b":1.1972700067718525,"b_gate_pass_rate":0.6,"median_len_z":2291.0,"mean_r_leg":0.06420043716879316,"mean_g_leg":0.015380442780942314,"g_bind_frac":0.5,"a_match":0.7017543859649124,"a_match_n":19,"a_match_centered":-0.03508771929824562},"terminus_json":{"n_turns":40,"n_valid":39,"parse_rate":0.975,"reason":-0.006040490631780678,"mean_b":0.015375581197663933,"b_gate_pass_rate":0.30701754385964913,"median_len_z":649.0,"mean_r_leg":0.0008050082168934901,"mean_g_leg":0.03241748629195037,"g_bind_frac":0.23076923076923078,"a_match":0.5598290598290598,"a_match_n":39,"a_match_centered":-0.08974358974358974},"text":{"n_turns":348,"n_valid":345,"parse_rate":0.9913793103448276,"reason":0.0009188358655590922,"mean_b":0.04397049549062874,"b_gate_pass_rate":0.3072463768115942,"median_len_z":722.0,"mean_r_leg":0.03362693739254557,"mean_g_leg":0.06301785221196551,"g_bind_frac":0.17391304347826086,"a_match":null,"a_match_n":0,"a_match_centered":null},"tool_call":{"n_turns":261,"n_valid":260,"parse_rate":0.9961685823754789,"reason":0.002560345899966917,"mean_b":0.026140534561050175,"b_gate_pass_rate":0.38258575197889183,"median_len_z":489.0,"mean_r_leg":0.007547076414080166,"mean_g_leg":0.07240416805435732,"g_bind_frac":0.16923076923076924,"a_match":0.10866666666666666,"a_match_n":250,"a_match_centered":-0.05259562841530055}}},"challenger_wins":false,"crown_mode":null,"window_id":null,"outcome":null,"via":null,"revoked_reason":null,"revoked_code":null,"revoked_by":null,"confirmation":null}],"next_cursor":2237}