{"schema":"site-data/1","kind":"release","release":"2026-10-31-m5-codex","generated_at":"2026-10-31T02:34:42.400893Z","source":"results/2026-10-31-m5-codex","boards":[{"id":"track-s","title":"Track S","description":"Service layer. An MCP proxy in front of mock services delivers the same bytes to every harness.","rows":[{"config_id":"cc-claude","harness":{"name":"claude-code","version":"2.1.289"},"model":{"id":"claude-sonnet-5-5","route":"anthropic-api","reasoning":"medium"},"axis":"fixed","trials":73,"excluded":0,"metrics":{"faulted_success":{"value":0.5833,"lo":0.3611,"hi":0.8056},"clean_pass1":{"value":1,"lo":1,"hi":1},"rr":{"value":0.5833,"lo":0.3611,"hi":0.8056},"pass3_moderate":{"value":0.3333,"lo":0.1667,"hi":0.6667},"overclaim_rate":{"value":0.6667,"lo":0.2857,"hi":1},"poison_propagation_rate":{"value":0.2059,"lo":0,"hi":0.6316},"dollars_per_success":0.3067,"tokens_total":11188350},"faulted_counts":{"succeeded":21,"sent":36},"curve":null,"trial_links":["results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-change-release__qy2jGne","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-client-retry__GqQkgy3","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-cycle-count__ddtYHCo","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-damage-claims__wQoMJGs","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-duplicate-merge__MiMTsff","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-error-catalog__S2625Je","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-followups__mjmQBYM","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-incident-rollback__N6oYdyG","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-p1-report__YKvs9j5","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-release-train__XBjwJLe","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-release-train__puccn3U","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-replenish__NYKdKex","results/pilot/2026-10-19-m5-s/cc-claude-clean-a0/s-shipment-backfill__eQTeU9L","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-change-release__9NKXMu5","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-client-retry__xzpGjrZ","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-cycle-count__g3vodpt","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-damage-claims__uZVkpzX","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-duplicate-merge__NkkvXKV","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-error-catalog__VEcWm4P","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-followups__rJA9cri","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-incident-rollback__JxgEDSo","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-p1-report__cLiUknh","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-release-train__8obqBgE","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-replenish__QPnmn9P","results/pilot/2026-10-19-m5-s/cc-claude-clean-a1/s-shipment-backfill__AVZUjJd","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-change-release__Q978C9q","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-client-retry__KYfT6Vx","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-cycle-count__cjXB59Q","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-damage-claims__GMa9WEW","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-duplicate-merge__CcxuhAe","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-error-catalog__y7xGuof","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-followups__jQECBDd","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-incident-rollback__RLvpdr2","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-p1-report__USR2yzd","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-release-train__h3LChzE","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-replenish__DJssEJY","results/pilot/2026-10-19-m5-s/cc-claude-clean-a2/s-shipment-backfill__XuRBEc2","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-change-release__HS6fdf6","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-client-retry__29HnZNg","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-cycle-count__4hbQtvd","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-damage-claims__yxWZsys","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-duplicate-merge__skNSeEs","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-error-catalog__r8uSXvw","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-followups__UyCdsFx","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-incident-rollback__6f3vANr","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-p1-report__WbEdkwE","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-release-train__6Kh6jeY","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-replenish__jaYuvZg","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a0/s-shipment-backfill__dpSFYEa","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-change-release__Aieq22h","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-client-retry__od5wgRm","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-cycle-count__eu35B7U","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-damage-claims__rRRoMMs","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-duplicate-merge__7aQWWQv","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-error-catalog__F65prmB","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-followups__CArxUy6","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-incident-rollback__gLhpV8J","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-p1-report__UFhL34u","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-release-train__UVzUPF3","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-replenish__LvG6Ly4","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a1/s-shipment-backfill__Y5hrCod","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-change-release__qKSuK74","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-client-retry__bm4cbDo","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-cycle-count__gbWxR7y","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-damage-claims__44kdZig","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-duplicate-merge__iJuxdPh","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-error-catalog__r8Z2nmS","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-followups__sRQKmcV","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-incident-rollback__qzkRFEu","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-p1-report__oQ4tBWm","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-release-train__RdMirEA","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-replenish__QRGi3CU","results/pilot/2026-10-19-m5-s/cc-claude-moderate-a2/s-shipment-backfill__LUnQwFe"]},{"config_id":"codex-claude","harness":{"name":"codex","version":"0.163.0"},"model":{"id":"claude-sonnet-5-5","route":"anthropic-api","reasoning":"medium"},"axis":"fixed","trials":72,"excluded":0,"metrics":{"faulted_success":{"value":0.6944,"lo":0.4722,"hi":0.8889},"clean_pass1":{"value":1,"lo":1,"hi":1},"rr":{"value":0.6944,"lo":0.4722,"hi":0.8889},"pass3_moderate":{"value":0.5,"lo":0.25,"hi":0.8333},"overclaim_rate":{"value":0.9091,"lo":0.6,"hi":1},"poison_propagation_rate":{"value":0.0645,"lo":0,"hi":0.2353},"dollars_per_success":0.237,"tokens_total":8986432},"faulted_counts":{"succeeded":25,"sent":36},"curve":null,"trial_links":["results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-change-release__ap3hWMW","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-client-retry__YyrzTvJ","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-cycle-count__amUTzHv","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-damage-claims__ayHh5ZK","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-duplicate-merge__LBjZUof","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-error-catalog__4oAYdPW","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-followups__9ZEmhWt","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-incident-rollback__KGc2D29","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-p1-report__bdaswqJ","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-release-train__WFpqTjr","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-replenish__EqbhENb","results/pilot/2026-10-30-codex-s/codex-claude-clean-a0/s-shipment-backfill__a6vZD9L","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-change-release__A7Y6Cv7","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-client-retry__sJhRcy2","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-cycle-count__rUFeNNt","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-damage-claims__6AXLEQc","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-duplicate-merge__9Etwmsr","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-error-catalog__uuVo5zr","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-followups__H6macRW","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-incident-rollback__YzmQtUK","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-p1-report__GjYhAHZ","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-release-train__BfQTTQi","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-replenish__MboUdzM","results/pilot/2026-10-30-codex-s/codex-claude-clean-a1/s-shipment-backfill__4qXaEAP","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-change-release__sXZyLJj","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-client-retry__rJ2qvdX","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-cycle-count__WawJ4mo","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-damage-claims__YFhpGcR","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-duplicate-merge__wEsJPbq","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-error-catalog__bYuuXEv","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-followups__xve4Z5P","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-incident-rollback__ZBeoWdi","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-p1-report__GEpSJMK","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-release-train__h2kAWrQ","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-replenish__Ni5cC7E","results/pilot/2026-10-30-codex-s/codex-claude-clean-a2/s-shipment-backfill__4og8fg3","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-change-release__kDdcwbr","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-client-retry__K56rJup","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-cycle-count__nv8qBYK","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-damage-claims__PcYzeeh","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-duplicate-merge__efGPTTt","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-error-catalog__ktqPtZt","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-followups__u36993F","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-incident-rollback__NPLWJxD","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-p1-report__XL2kyWD","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-release-train__BJGSQTV","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-replenish__9a2avGP","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a0/s-shipment-backfill__AxpQyVp","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-change-release__k3sTP2c","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-client-retry__HytFqTH","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-cycle-count__w5vzZMo","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-damage-claims__ashFgzk","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-duplicate-merge__wBRio7H","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-error-catalog__yK5aorQ","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-followups__rzY7NRa","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-incident-rollback__H966fue","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-p1-report__i8a62Nc","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-release-train__ERbfv2w","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-replenish__5v4FDq3","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a1/s-shipment-backfill__KMei9xf","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-change-release__KhNjXHs","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-client-retry__vnxYs9i","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-cycle-count__otAzPZQ","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-damage-claims__Y5pihqA","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-duplicate-merge__8nXBwDQ","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-error-catalog__tCGxNNh","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-followups__Ht58WP6","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-incident-rollback__gtDERo5","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-p1-report__Z7SrCyj","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-release-train__wbArvJS","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-replenish__z4e7eYA","results/pilot/2026-10-30-codex-s/codex-claude-moderate-a2/s-shipment-backfill__mEivNxs"]},{"config_id":"fx-claude","harness":{"name":"fx","version":"0.0.13"},"model":{"id":"anthropic/claude-sonnet-5.5","route":"vercel-ai-gateway","reasoning":"medium"},"axis":"fixed","trials":72,"excluded":0,"metrics":{"faulted_success":{"value":0.6944,"lo":0.4722,"hi":0.8889},"clean_pass1":{"value":0.9722,"lo":0.8889,"hi":1},"rr":{"value":0.7143,"lo":0.4722,"hi":0.9429},"pass3_moderate":{"value":0.5,"lo":0.25,"hi":0.8333},"overclaim_rate":{"value":0.7273,"lo":0.3333,"hi":1},"poison_propagation_rate":{"value":0.2571,"lo":0,"hi":0.6364},"dollars_per_success":0.3301,"tokens_total":15942666},"faulted_counts":{"succeeded":25,"sent":36},"curve":null,"trial_links":["results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-change-release__DB3Wvdm","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-client-retry__6XnwsMo","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-cycle-count__NKKCVRP","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-damage-claims__nc2LNRm","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-duplicate-merge__nChyoiS","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-error-catalog__sKZ8Esy","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-followups__tvNLZV7","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-incident-rollback__MgGYfw4","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-p1-report__ZYwnMaw","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-release-train__EwYPw9H","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-replenish__GMQNTLJ","results/pilot/2026-10-19-m5-s/fx-claude-clean-a0/s-shipment-backfill__tCt3JUX","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-change-release__DZfyvgN","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-client-retry__tdmqXsS","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-cycle-count__U6Aa4P3","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-damage-claims__Q4CckVM","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-duplicate-merge__DiP88oN","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-error-catalog__6p5p5jP","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-followups__8XGPGGP","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-incident-rollback__vjXBGR9","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-p1-report__QyYvCxQ","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-release-train__mTeMr8R","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-replenish__dha5gPF","results/pilot/2026-10-19-m5-s/fx-claude-clean-a1/s-shipment-backfill__KsiAZpy","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-change-release__LhD6mAQ","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-client-retry__wdxYkMQ","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-cycle-count__ANksM5Q","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-damage-claims__RwhvwHG","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-duplicate-merge__baMwF5T","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-error-catalog__CEvNRuJ","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-followups__Hy3nmBu","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-incident-rollback__PLjBrKp","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-p1-report__oHakoJL","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-release-train__mjZXYFj","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-replenish__eCNawaY","results/pilot/2026-10-19-m5-s/fx-claude-clean-a2/s-shipment-backfill__4kNdkbM","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-change-release__FvXUiN3","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-client-retry__ZXBEdNi","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-cycle-count__KwrkShu","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-damage-claims__sLumKKW","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-duplicate-merge__Las6hTy","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-error-catalog__cjhgk8E","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-followups__B36haWB","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-incident-rollback__gWnzozc","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-p1-report__nXsy3cG","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-release-train__ZJ2Eaku","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-replenish__PCewsZ4","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a0/s-shipment-backfill__scBkRUo","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-change-release__uYptnnv","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-client-retry__Bs7e2hd","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-cycle-count__2Zt3ygJ","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-damage-claims__KWNWURT","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-duplicate-merge__VYdvvzm","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-error-catalog__KdH2inP","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-followups__65xT6NP","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-incident-rollback__tgQkvUx","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-p1-report__zzGpwiE","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-release-train__7Qt9NoY","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-replenish__vSVHkmM","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a1/s-shipment-backfill__Y8CUC9P","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-change-release__pubWQUA","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-client-retry__QgrPyGs","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-cycle-count__dnqVRpu","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-damage-claims__StHFtyi","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-duplicate-merge__SYQVhoZ","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-error-catalog__CSxM9K8","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-followups__JaZUDFk","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-incident-rollback__yZscNjc","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-p1-report__mFbKkmk","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-release-train__mGno9sA","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-replenish__4Cvd3Fy","results/pilot/2026-10-19-m5-s/fx-claude-moderate-a2/s-shipment-backfill__kUzS9R4"]},{"config_id":"opencode-claude","harness":{"name":"opencode","version":"1.18.35"},"model":{"id":"claude-sonnet-5-5","route":"anthropic-api","reasoning":"medium"},"axis":"fixed","trials":72,"excluded":0,"metrics":{"faulted_success":{"value":0.6944,"lo":0.4722,"hi":0.8889},"clean_pass1":{"value":1,"lo":1,"hi":1},"rr":{"value":0.6944,"lo":0.4722,"hi":0.8889},"pass3_moderate":{"value":0.5,"lo":0.25,"hi":0.8333},"overclaim_rate":{"value":0.8182,"lo":0.4,"hi":1},"poison_propagation_rate":{"value":0.1481,"lo":0,"hi":0.4815},"dollars_per_success":0.2035,"tokens_total":8212511},"faulted_counts":{"succeeded":25,"sent":36},"curve":null,"trial_links":["results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-change-release__HS8bDJy","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-client-retry__GzdBye6","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-cycle-count__eSkLTrx","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-damage-claims__YTdwsE3","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-duplicate-merge__RfQL9kG","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-error-catalog__PAR7V5B","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-followups__Yr7dXLz","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-incident-rollback__2URZMVD","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-p1-report__GZSJrPd","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-release-train__8aFMrDU","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-replenish__bsxKXCR","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a0/s-shipment-backfill__bbHVH6F","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-change-release__LoDnYTK","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-client-retry__izeuvkr","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-cycle-count__rJE7UDg","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-damage-claims__QMsx7kb","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-duplicate-merge__9CyCjRJ","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-error-catalog__f5jjdLH","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-followups__aP42uVG","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-incident-rollback__WwNXMxN","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-p1-report__wCJgLGH","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-release-train__3mecUP3","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-replenish__gxCvaYS","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a1/s-shipment-backfill__CbuBMyL","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-change-release__4cn6RAt","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-client-retry__vgBAkwA","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-cycle-count__VagbCsf","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-damage-claims__BZsSeiP","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-duplicate-merge__mb6LNfA","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-error-catalog__5ws58N2","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-followups__7cxrUkY","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-incident-rollback__HK549zs","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-p1-report__WdPcC4j","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-release-train__ZJBRPYK","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-replenish__jpsJt65","results/pilot/2026-10-19-m5-s/opencode-claude-clean-a2/s-shipment-backfill__3tHvkaF","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-change-release__7NNHneU","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-client-retry__pk8vrQe","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-cycle-count__iy7djHb","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-damage-claims__6TAM2P8","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-duplicate-merge__ouegDYp","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-error-catalog__PjgBpoD","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-followups__uirZE9i","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-incident-rollback__5JNLiKX","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-p1-report__kZv7r7U","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-release-train__sCzzFwz","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-replenish__sp7M3iU","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a0/s-shipment-backfill__fZ9Jdtm","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-change-release__eVN4CFt","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-client-retry__ywjpfTN","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-cycle-count__QsB7gTT","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-damage-claims__g7KxXRX","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-duplicate-merge__pki9LBd","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-error-catalog__4pzGpg5","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-followups__gVAtF9K","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-incident-rollback__3uzMZaB","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-p1-report__z7bJP9S","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-release-train__e4TtYn3","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-replenish__o7sd4q6","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a1/s-shipment-backfill__k934YaD","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-change-release__n3VyDcf","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-client-retry__gNCnDWS","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-cycle-count__rLGUnhm","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-damage-claims__DcbzaBr","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-duplicate-merge__4qCSzDS","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-error-catalog__tEYFvdG","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-followups__LMsnywz","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-incident-rollback__FowCZh9","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-p1-report__fgXP92u","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-release-train__ne6diTo","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-replenish__rQKMxD2","results/pilot/2026-10-19-m5-s/opencode-claude-moderate-a2/s-shipment-backfill__X5243G9"]},{"config_id":"pi-claude","harness":{"name":"pi","version":"1.0.3"},"model":{"id":"claude-sonnet-5-5","route":"anthropic-api","reasoning":"medium"},"axis":"fixed","trials":72,"excluded":0,"metrics":{"faulted_success":{"value":0.6667,"lo":0.4444,"hi":0.8611},"clean_pass1":{"value":0.9444,"lo":0.8333,"hi":1},"rr":{"value":0.7059,"lo":0.4571,"hi":0.9394},"pass3_moderate":{"value":0.4167,"lo":0.25,"hi":0.75},"overclaim_rate":{"value":0.75,"lo":0.3333,"hi":1},"poison_propagation_rate":{"value":0.0333,"lo":0,"hi":0.2},"dollars_per_success":0.197,"tokens_total":5083174},"faulted_counts":{"succeeded":24,"sent":36},"curve":null,"trial_links":["results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-change-release__4AGmQsZ","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-client-retry__BJiCvdk","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-cycle-count__mR97sFG","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-damage-claims__yN2Wxcg","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-duplicate-merge__PqLDrxr","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-error-catalog__VdYEgnB","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-followups__t58YUfo","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-incident-rollback__8LxU96G","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-p1-report__e29EZce","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-release-train__53pJdtt","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-replenish__MX8Tkt2","results/pilot/2026-10-19-m5-s/pi-claude-clean-a0/s-shipment-backfill__fcYgRbb","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-change-release__bDtq9wR","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-client-retry__tkvDeN7","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-cycle-count__PGPAzdb","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-damage-claims__W3Uyffp","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-duplicate-merge__CAKtphJ","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-error-catalog__kDcXdLN","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-followups__jfHyoXT","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-incident-rollback__TXZLZMj","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-p1-report__2HCFBSa","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-release-train__MDFApzf","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-replenish__scHkz7v","results/pilot/2026-10-19-m5-s/pi-claude-clean-a1/s-shipment-backfill__uvjshQQ","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-change-release__LD6CuEL","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-client-retry__FxBhLEA","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-cycle-count__vkzgXNv","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-damage-claims__zUvmpNP","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-duplicate-merge__Hor9CWP","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-error-catalog__ktGFJRs","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-followups__zr8UpQN","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-incident-rollback__iivZGSB","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-p1-report__y4VcBkg","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-release-train__4yrbB8Q","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-replenish__jwvonmA","results/pilot/2026-10-19-m5-s/pi-claude-clean-a2/s-shipment-backfill__FYswcLy","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-change-release__csCFXv3","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-client-retry__7z2AHqa","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-cycle-count__CeyFNDR","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-damage-claims__dygoHrt","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-duplicate-merge__zXVofce","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-error-catalog__rpXPqbE","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-followups__e6WvJL4","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-incident-rollback__YDd8TY2","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-p1-report__DjWyDoR","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-release-train__NJvaURe","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-replenish__sWXnrPy","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a0/s-shipment-backfill__EY7daUj","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-change-release__aMvEt7T","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-client-retry__fwJfbjs","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-cycle-count__JQJcxxL","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-damage-claims__j33myeG","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-duplicate-merge__beT8QiV","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-error-catalog__dR5vdKx","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-followups__TFMueGT","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-incident-rollback__cuqHNZb","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-p1-report__TjiF32b","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-release-train__vivVsbq","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-replenish__KLGfKEC","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a1/s-shipment-backfill__JQpuEuE","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-change-release__gRMvcto","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-client-retry__zNpWEbZ","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-cycle-count__4T3JGQN","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-damage-claims__8VRW5Vm","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-duplicate-merge__og63Jgm","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-error-catalog__DG8fhQ8","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-followups__6xfygN5","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-incident-rollback__2nE53ye","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-p1-report__iJQL6yx","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-release-train__yvYj6Ga","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-replenish__MAPBeqW","results/pilot/2026-10-19-m5-s/pi-claude-moderate-a2/s-shipment-backfill__xxzZSN3"]}]},{"id":"track-n-fixed","title":"Track N fixed model","description":"Built-in tools, same model in every harness. Faults come from each harness's own hooks; rows compare only within the fixed-model parity set (SPEC 6.4).","rows":[{"config_id":"cc-claude","harness":{"name":"claude-code","version":"2.1.289"},"model":{"id":"claude-sonnet-5-5","route":"anthropic-api","reasoning":"medium"},"axis":"fixed","trials":79,"excluded":6,"metrics":{"faulted_success":{"value":0.8333,"lo":0.6389,"hi":0.9722},"clean_pass1":{"value":0.9444,"lo":0.8056,"hi":1},"rr":{"value":0.8824,"lo":0.6667,"hi":1.0303},"pass3_moderate":null,"overclaim_rate":{"value":0.8333,"lo":0,"hi":1},"poison_propagation_rate":{"value":0.2222,"lo":0,"hi":0.6667},"dollars_per_success":0.4659,"tokens_total":29804771},"faulted_counts":{"succeeded":28,"sent":34},"curve":null,"trial_links":["results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-bisect-regression__R7f3iy6","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-config-threading__D8Ugnkh","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-csv-export__UBJJvt7","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-db-build__eN4Agoh","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-invoice-fix__ey4vzm3","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-ledger-fix__eYZcj3P","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-make-build__9BANrV3","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-port-conflict__UUL2cJk","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-rate-limiter__2FkWk8r","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-shipments-summary__ccRuKGK","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-split-reports__nMzPmn8","results/pilot/2026-10-19-m5-n/cc-claude-clean-a0/n-timesheet-payroll__RYLFQGL","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-bisect-regression__xAiPRrW","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-config-threading__sJPF2Cd","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-csv-export__YHTaFj9","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-db-build__YsKcBJG","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-invoice-fix__WrJoyZo","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-ledger-fix__EbZRM9t","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-make-build__SmF6HwB","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-port-conflict__9gv4Lav","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-rate-limiter__fWkyqxt","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-shipments-summary__jAsdRdp","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-split-reports__mjzdE7R","results/pilot/2026-10-19-m5-n/cc-claude-clean-a1/n-timesheet-payroll__3VXcpGt","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-bisect-regression__5b7pv2J","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-config-threading__hUvipLF","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-csv-export__fV87abC","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-db-build__k73waBq","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-invoice-fix__PG7Un4g","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-ledger-fix__Znaegvq","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-make-build__3ZZtHur","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-port-conflict__PcqmBqw","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-rate-limiter__uv5NF7a","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-shipments-summary__JuAsRNs","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-split-reports__jaeixaQ","results/pilot/2026-10-19-m5-n/cc-claude-clean-a2/n-timesheet-payroll__YcP8wyR","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-bisect-regression__GqHncJZ","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-config-threading__NPDP6Ut","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-csv-export__xNcLasu","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-db-build__SZaeuZh","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-db-build__gAZYvMG","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-db-build__yn29Lq6","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-invoice-fix__K5BQNW7","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-ledger-fix__cbQyu9B","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-make-build__GTe3Uiz","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-make-build__baCyZxr","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-port-conflict__VCxmCBN","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-rate-limiter__2cQuHTL","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-shipments-summary__RsJvrZq","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-split-reports__Z9NecVs","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a0/n-timesheet-payroll__cSBWgqu","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-bisect-regression__tXjZzZF","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-config-threading__eD9stQY","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-csv-export__Dtk7Edi","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-db-build__sBLBTp9","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-db-build__sUPSSAJ","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-invoice-fix__n9afK5S","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-ledger-fix__UkEusJJ","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-make-build__Ddfrxny","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-make-build__KC5RRtu","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-port-conflict__F98oCca","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-rate-limiter__sgUg8Jr","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-shipments-summary__Lctjumg","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-split-reports__crZX49E","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a1/n-timesheet-payroll__8ruSAvE","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-bisect-regression__NSbpGAF","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-config-threading__dxc5nXV","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-csv-export__Jy9SsM4","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-db-build__ZnxRWMH","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-invoice-fix__BAhXuku","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-invoice-fix__BKa33Lq","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-invoice-fix__KbShW2B","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-ledger-fix__TEoZJ2S","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-make-build__Y9H9Xjv","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-port-conflict__tw6bA74","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-rate-limiter__j7BtoZ7","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-shipments-summary__RG4b2fe","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-split-reports__GrWku4D","results/pilot/2026-10-19-m5-n/cc-claude-moderate-a2/n-timesheet-payroll__TzpxSaa"]},{"config_id":"codex-claude","harness":{"name":"codex","version":"0.163.0"},"model":{"id":"claude-sonnet-5-5","route":"anthropic-api","reasoning":"medium"},"axis":"fixed","trials":72,"excluded":1,"metrics":{"faulted_success":{"value":0.8333,"lo":0.6667,"hi":0.9722},"clean_pass1":{"value":1,"lo":1,"hi":1},"rr":{"value":0.8333,"lo":0.6667,"hi":0.9722},"pass3_moderate":null,"overclaim_rate":{"value":0.8333,"lo":0.25,"hi":1},"poison_propagation_rate":{"value":0.1923,"lo":0,"hi":0.5295},"dollars_per_success":0.4198,"tokens_total":29648757},"faulted_counts":{"succeeded":29,"sent":35},"curve":null,"trial_links":["results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-bisect-regression__49yTAFt","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-config-threading__ReGBigJ","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-csv-export__L8XSXS6","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-db-build__nZ2EDaT","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-invoice-fix__tP8YqxF","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-ledger-fix__L6qXtUQ","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-make-build__TQL5FEK","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-port-conflict__MZBBoSJ","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-rate-limiter__3kwF3a8","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-shipments-summary__9iUV9Fz","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-split-reports__iTJXeim","results/pilot/2026-10-30-codex-n/codex-claude-clean-a0/n-timesheet-payroll__wMVQsNL","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-bisect-regression__vnn2fJa","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-config-threading__MEUtudS","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-csv-export__HcHKSEj","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-db-build__Z8jTxUe","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-invoice-fix__Knrz4nV","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-ledger-fix__LtjcyA5","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-make-build__ZiqP5MH","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-port-conflict__YrHKPzu","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-rate-limiter__2e72WbT","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-shipments-summary__9mor6Yq","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-split-reports__cswRMpD","results/pilot/2026-10-30-codex-n/codex-claude-clean-a1/n-timesheet-payroll__CBzBXKQ","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-bisect-regression__sTsNs8A","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-config-threading__wkrHocR","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-csv-export__edyq8Jr","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-db-build__D2BTPi6","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-invoice-fix__8BxF7qV","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-ledger-fix__nYFmtYg","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-make-build__D6s7CKR","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-port-conflict__mevuYqW","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-rate-limiter__V5GyA3q","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-shipments-summary__RHTDjEC","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-split-reports__cJRLSRs","results/pilot/2026-10-30-codex-n/codex-claude-clean-a2/n-timesheet-payroll__hgGDcDt","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-bisect-regression__5Qj2JWn","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-config-threading__kmDCqKE","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-csv-export__4fuKLDy","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-db-build__7sRLiBH","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-invoice-fix__bDsaWqA","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-ledger-fix__8JJEVWX","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-make-build__KzTcWUp","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-port-conflict__CZjWKgS","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-rate-limiter__VWYDtjA","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-shipments-summary__QaUij3C","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-split-reports__2x45PcZ","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a0/n-timesheet-payroll__sYxc659","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-bisect-regression__zB48M4B","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-config-threading__dRMm2mZ","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-csv-export__Jws2hBz","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-db-build__P6TNyVd","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-invoice-fix__CQeG2SN","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-ledger-fix__YpqELxT","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-make-build__2WqcARN","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-port-conflict__tXsBuAL","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-rate-limiter__s2BdPTJ","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-shipments-summary__vPXUsgc","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-split-reports__zcwJXMq","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a1/n-timesheet-payroll__bQLCy2W","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-bisect-regression__QB5XNWH","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-config-threading__hmC57fH","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-csv-export__kEtSEJA","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-db-build__PoEoamo","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-invoice-fix__eVkNwmG","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-ledger-fix__3D3fRBP","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-make-build__EXXbDtS","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-port-conflict__mskw5vT","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-rate-limiter__ixFGArR","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-shipments-summary__WG6YkjE","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-split-reports__oqX3Jcm","results/pilot/2026-10-30-codex-n/codex-claude-moderate-a2/n-timesheet-payroll__BVa9KQb"]},{"config_id":"opencode-claude","harness":{"name":"opencode","version":"1.18.35"},"model":{"id":"claude-sonnet-5-5","route":"anthropic-api","reasoning":"medium"},"axis":"fixed","trials":72,"excluded":0,"metrics":{"faulted_success":{"value":0.8056,"lo":0.6389,"hi":0.9444},"clean_pass1":{"value":0.9444,"lo":0.8056,"hi":1},"rr":{"value":0.8529,"lo":0.6563,"hi":1},"pass3_moderate":{"value":0.5,"lo":0.3333,"hi":0.9167},"overclaim_rate":{"value":0.6667,"lo":0,"hi":1},"poison_propagation_rate":{"value":0.1852,"lo":0,"hi":0.65},"dollars_per_success":0.3531,"tokens_total":24372000},"faulted_counts":{"succeeded":29,"sent":36},"curve":null,"trial_links":["results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-bisect-regression__EFprLZ7","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-config-threading__VgAgso8","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-csv-export__CNda6H4","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-db-build__bE2Uxmg","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-invoice-fix__caM4ZRg","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-ledger-fix__wxZNiMF","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-make-build__zhaUfML","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-port-conflict__EggRXWi","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-rate-limiter__SYEezMt","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-shipments-summary__zmud3N9","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-split-reports__XYuFWYn","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a0/n-timesheet-payroll__Gznd2Ux","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-bisect-regression__J3QS5QA","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-config-threading__uz728Ga","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-csv-export__VpGsihW","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-db-build__WdLx2Vc","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-invoice-fix__p4Emxfd","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-ledger-fix__BHSKHsT","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-make-build__CuQyXmL","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-port-conflict__DHJ4QCV","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-rate-limiter__U4KgMtX","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-shipments-summary__Z5hUJJd","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-split-reports__B2KCzSh","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a1/n-timesheet-payroll__6G48cFq","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-bisect-regression__K3ERvLo","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-config-threading__furRjrj","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-csv-export__y9nfgZf","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-db-build__RnT8fqE","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-invoice-fix__PXaaeiw","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-ledger-fix__xHCHPoa","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-make-build__NPDBXFi","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-port-conflict__aFzrdFr","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-rate-limiter__8Tme3DQ","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-shipments-summary__5GMKCdK","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-split-reports__ViQ6R6v","results/pilot/2026-10-19-m5-n/opencode-claude-clean-a2/n-timesheet-payroll__TJHCWta","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-bisect-regression__FvCaSXB","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-config-threading__pk6bP6r","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-csv-export__3ho9bQe","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-db-build__eMMvRFx","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-invoice-fix__FcUhmtb","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-ledger-fix__Frfsvjq","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-make-build__dV7ipmJ","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-port-conflict__DuNR7Nq","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-rate-limiter__TrDGNe8","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-shipments-summary__if2UeWc","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-split-reports__gpEC3p3","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a0/n-timesheet-payroll__Ske3S9N","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-bisect-regression__oG5oiSD","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-config-threading__HTG4no7","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-csv-export__o5L2aYk","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-db-build__3gabf6M","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-invoice-fix__FSVgfPQ","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-ledger-fix__qBWDUb2","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-make-build__vXpuXzn","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-port-conflict__T7esVXH","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-rate-limiter__YutQ2dy","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-shipments-summary__L7aYdh6","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-split-reports__YNf2eRM","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a1/n-timesheet-payroll__rqovmsa","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-bisect-regression__cpvf6gH","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-config-threading__yP7iDUH","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-csv-export__H6R8DaV","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-db-build__Trp7okG","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-invoice-fix__qkNTBhY","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-ledger-fix__UkE4iTU","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-make-build__y39Gxrd","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-port-conflict__GncuWsd","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-rate-limiter__NkDudto","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-shipments-summary__bsDdZu9","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-split-reports__Tr3UomC","results/pilot/2026-10-19-m5-n/opencode-claude-moderate-a2/n-timesheet-payroll__vwvooqf"]},{"config_id":"pi-claude","harness":{"name":"pi","version":"1.0.3"},"model":{"id":"claude-sonnet-5-5","route":"anthropic-api","reasoning":"medium"},"axis":"fixed","trials":75,"excluded":0,"metrics":{"faulted_success":{"value":0.7222,"lo":0.5,"hi":0.9167},"clean_pass1":{"value":0.8889,"lo":0.6944,"hi":1},"rr":{"value":0.7813,"lo":0.5385,"hi":0.9722},"pass3_moderate":{"value":0.5,"lo":0.3333,"hi":0.8333},"overclaim_rate":{"value":0.9,"lo":0.5833,"hi":1},"poison_propagation_rate":{"value":0.1304,"lo":0,"hi":0.5333},"dollars_per_success":0.4334,"tokens_total":20770822},"faulted_counts":{"succeeded":26,"sent":36},"curve":null,"trial_links":["results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-bisect-regression__qUvTgEd","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-config-threading__9nvtFY2","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-csv-export__GU86fJi","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-db-build__SQUh3yd","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-invoice-fix__r885FDR","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-ledger-fix__4ckrnD5","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-make-build__iyh8Awr","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-port-conflict__7cKT2BP","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-rate-limiter__54gyjVH","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-shipments-summary__3vmkTeM","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-split-reports__eaFJRi8","results/pilot/2026-10-19-m5-n/pi-claude-clean-a0/n-timesheet-payroll__CnwPNym","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-bisect-regression__Fbtdb52","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-config-threading__sFoVMGY","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-csv-export__idsxUkJ","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-db-build__mENbi7K","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-invoice-fix__yEc4fVg","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-ledger-fix__BtMZVKe","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-make-build__7T8TsNW","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-port-conflict__utaVrYG","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-rate-limiter__nubuwsd","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-shipments-summary__A58K7c4","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-split-reports__ae8UvZ9","results/pilot/2026-10-19-m5-n/pi-claude-clean-a1/n-timesheet-payroll__CdAes8T","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-bisect-regression__S2WstQL","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-config-threading__moT7LDo","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-csv-export__rNVkfvL","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-db-build__C8rXKco","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-invoice-fix__RQXxuSJ","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-ledger-fix__DBctLnV","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-make-build__j87yaym","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-port-conflict__qRSvfaP","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-rate-limiter__CCxuuYP","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-shipments-summary__yGqd7KD","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-split-reports__hhE7gas","results/pilot/2026-10-19-m5-n/pi-claude-clean-a2/n-timesheet-payroll__6rMWVhU","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-bisect-regression__ymJ3xFD","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-config-threading__J488Gsz","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-csv-export__AXSC7iH","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-db-build__imvd5sR","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-invoice-fix__ZcXQ2dt","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-ledger-fix__8WhCTAW","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-make-build__GALRsKV","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-port-conflict__jBw3AKQ","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-port-conflict__q6veWJR","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-rate-limiter__VNMpoGY","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-shipments-summary__bFkTB5q","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-split-reports__etGU4Zc","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a0/n-timesheet-payroll__vXA296G","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-bisect-regression__qTDM8AM","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-config-threading__WRTFK8d","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-csv-export__mZXtyvJ","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-db-build__J5CBpep","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-invoice-fix__gNho93z","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-ledger-fix__airfn3V","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-make-build__8P63YEe","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-port-conflict__Uj8eLAh","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-rate-limiter__Rxh3ZES","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-shipments-summary__WywYUzw","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-split-reports__ru7sVKn","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-split-reports__vb7ieZt","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a1/n-timesheet-payroll__miSJ7UW","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-bisect-regression__fBrpamg","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-config-threading__3aC4qcX","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-csv-export__mSM6yAn","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-db-build__bdrYhuY","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-invoice-fix__CLFZj2C","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-invoice-fix__kr3kwdL","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-ledger-fix__Tsz6VBs","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-make-build__oqEefTE","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-port-conflict__BJgEwrj","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-rate-limiter__LdXsy4H","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-shipments-summary__Lf3o6Q8","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-split-reports__9mHqLCz","results/pilot/2026-10-19-m5-n/pi-claude-moderate-a2/n-timesheet-payroll__wsvqZAH"]}]}],"not_measurable":[{"board":"track-n-fixed","config_id":"fx-claude","reason":"No interception point for fx built-in tools (D-0027, V-22), so Track N faults cannot reach it."}]}