Files
Jyotisha/references/rectification_sealed_holdout.v1.json
T
Jesse_ChenandClaude Opus 5.5 5731b0af6e chore(rectification): re-freeze research records for upstream sync 4 (ERR-110); scores unchanged, no version bump
scripts/shadbala.py is in the frozen scoring identity (dataset
frozen_scoring.files), so the ported Kala/Chesta fixes and the BPHS Sun
minimum (BUG-1188/1189) turned the integrity gate red although the scorer only
reads the Sthana/Drik/Naisargika components. Records re-frozen under the label
upstream_sync4_2026_10_02 (--freeze, then replay; PYTHONHASHSEED=0, chart cache
TTL 0); the functional_v2 records become "previous", byte-for-byte preserved.
Replays are identical to functional_v2: reported offset 0 of 900 trials
changed, sealed holdout 20 trials identical; memoization golden v2 scores
unchanged and the v5 77-case evaluation is byte-identical to a18f8d4e, so
ALGORITHM_VERSION stays rectification-v5-matrix-scoring-10 (decision 6 only
bumps on a score change).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
2026-10-02 14:40:04 +08:00

347 lines
23 KiB
JSON

{
"sealed_benchmark_id": "minute_rectification_fact_ranker_v4_holdout_v3",
"status": "not_ready",
"valid_public_aa_cases": 20,
"required_cases": 20,
"top_1_rate": 0.15,
"confirmation_coverage_rate": 0.0,
"previous_pilot_id": "minute_rectification_holdout_v2",
"dataset_path": "references/real_case_calibration/minute_rectification_holdout_v3.json",
"report_path": "references/real_case_calibration/minute_rectification_holdout_v3_report.json",
"source_audit_status": "corrected_known_date_errors",
"evaluated_on": "2026-10-02",
"evaluated_on_scope": "latest_fixed_protocol_rerun_not_historical_runtime_metrics",
"historical_source_audit_status": "invalidated_after_replay",
"report_status": "invalidated_after_source_audit",
"trial_count": 20,
"top_3_rate": 0.25,
"mean_absolute_minute_error": 6.95,
"metrics_produced_by": {
"implementation_sha256": "f41c298dd6cdcebe7a93e632f7191954be7987f6012ca2a34cecb6e447fbf196",
"algorithm_version": "birth-time-event-fact-ranker-v4-shadow",
"implementation_hash_matches_at_replay": true,
"source_report": "references/real_case_calibration/minute_rectification_holdout_v3_report.json",
"evaluated_on": "2026-07-21"
},
"current_tree_scorer": {
"implementation_sha256": "6ad12dfdc1ffe429f09103911aa49db9b92a4275f4e2909d3187aa9784c5b650",
"extended_identity": {
"historical_artifacts_manifest_sha256": "6102a26a840be207b5858b3a4c0509274468ae9071e86d308cbbac7371d6864e",
"production_scoring_files": [
"scripts/active_rectification_event_engine.py",
"scripts/active_rectification_events.py",
"scripts/ashtakavarga.py",
"scripts/dasha_analyzer.py",
"scripts/divisional_charts_extended.py",
"scripts/domain_calculation_service.py",
"scripts/functional_benefics.py",
"scripts/jaimini.py",
"scripts/minute_rectification_fact_ranker_v4.py",
"scripts/minute_rectification_feature_facts_v4.py",
"scripts/narayana_dasha.py",
"scripts/rectification/api_service.py",
"scripts/rectification/candidate_contrast.py",
"scripts/rectification/candidate_window.py",
"scripts/rectification/case_holdout.py",
"scripts/rectification/contracts.py",
"scripts/rectification/dasha_transition_proximity.py",
"scripts/rectification/decision_policy.py",
"scripts/rectification/event_probes.py",
"scripts/rectification/refinement_packet.py",
"scripts/rectification/scoring_service.py",
"scripts/shadbala.py",
"scripts/varga.py"
],
"production_scoring_sha256": "97ebaee6c886092c9c96ca05584f27f6551b4808f7a3c276dd80d11066b16c39",
"research_files": [
"scripts/research/reported_offset_sweep.py",
"scripts/research/cluster_width_lib.py",
"scripts/research/probe_supply_after_six.py",
"scripts/research/sealed_holdout_rerun.py",
"scripts/minute_rectification_blind_eval.py",
"scripts/minute_rectification_fact_blind_eval_v4.py",
"scripts/minute_rectification_holdout_validator.py"
],
"research_implementation_sha256": "f5a4d975b1ce84b4db6f6aec4c4039d2f8154ddd003803770edfb096c8fa75ae",
"file_sha256": {
"scripts/active_rectification_event_engine.py": "cdc0e68edc770a2a1810fbdb68cbfd46dcd50b267c739c496fcc078c5e26b5b4",
"scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
"scripts/ashtakavarga.py": "cc32776674cf60713634a360a6f09774b3af0ec5d0f650687f52b79597b0dfbe",
"scripts/dasha_analyzer.py": "5e53b1b4d4c7414c08dd0e7716f120a63c70ec3428ec93547f64d55c580da0e1",
"scripts/divisional_charts_extended.py": "73bd50a83ac444830940184d0988cea621855f91db76a3f1a232014b992eacea",
"scripts/domain_calculation_service.py": "9ee955874eea806c7b56f4246d90009c02ee8318b8f3dfe1d7132b1c0b4262e1",
"scripts/functional_benefics.py": "cbaac3b8c09b97f8724b5300e9a402cbf77089af6c7db8788550d40fd35ac57b",
"scripts/jaimini.py": "b98bf965603dd2e3cc871fe40f3c8184731a701875ca50fef3ca68e9682eda81",
"scripts/minute_rectification_blind_eval.py": "07aa30d8bad3278669495d5fea8be937aaf6367c8af980ff4f2fe9aa84ccc6ff",
"scripts/minute_rectification_fact_blind_eval_v4.py": "bdf460e3467208e8b87345c5beb2128f3e22de7eeffd68f72b281b3ad9affc92",
"scripts/minute_rectification_fact_ranker_v4.py": "f1a0d8d2482cd754d2e7f253a9606b0373519435a2bf58cfc3753e2b9ae0fb76",
"scripts/minute_rectification_feature_facts_v4.py": "3d899a2cdd4825b8e32062443d487edcd2173a4ea55a36eb9f3abe587c0faf0f",
"scripts/minute_rectification_holdout_validator.py": "b60b1c752e58672beaee8b36eb3b2348169726cda070ec969db0f13e7ed715af",
"scripts/narayana_dasha.py": "7ff2c3238cd113b11b815e14b41967bd8e486ff62e36650e55613b9c79d1bfe3",
"scripts/rectification/api_service.py": "e316ced0f3796d0378a0fe1aad950ee25922ae8afd53add578ed59ca8b2f0f79",
"scripts/rectification/candidate_contrast.py": "eee7da71c0574a08876404b78ca111153fa95fb83ace82b9fdca141d1992e273",
"scripts/rectification/candidate_window.py": "2fbc5058b12049b15fca375cdc125b8283e19f9f3e4bedcc291e344501891bef",
"scripts/rectification/case_holdout.py": "fe0e699b617d9e216acdfeff87af4221c1d6f4c101bf33e1dbf14e2bcd75a8b5",
"scripts/rectification/contracts.py": "c6dc6bd230e38f9f2126c224aae9ddbd6415304c15340f8c7cd3f06f6ef3160f",
"scripts/rectification/dasha_transition_proximity.py": "0afba494aa12899621173c3cc941c6c1d0be9cec0bdf4c4a1c9bcd004ab22de8",
"scripts/rectification/decision_policy.py": "d845896428e0f49f8b5ae946aff6203492e7383d387acf122cb0b7a523b0af28",
"scripts/rectification/event_probes.py": "9bbadc246e6b8e94bb047522c3e5645613f508b3473ef40b38a207c77fdad58c",
"scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
"scripts/rectification/scoring_service.py": "4f13c6a78d2dda55454ac20e4091fce280e3626ecfe8a9d723217ef3ebc05d02",
"scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
"scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
"scripts/research/reported_offset_sweep.py": "2495d7e86e78091ed407b5df68cbe26e26be6f80ef66d7ac05944d5c4500cde9",
"scripts/research/sealed_holdout_rerun.py": "ff86058caad0a7cf379229117096b260934cd55d4e0b66e0d8f25d6eafb1752a",
"scripts/shadbala.py": "355e6dee4f9f632e83896d0e606b29fe12183dc083ed912a18377b0e999771c1",
"scripts/varga.py": "4331de5a25ea08729af91aae863943c4223183937f419d52dc63fd6fe7f27be6"
},
"hash_scope": "explicit_identity_file_sets_not_a_transitive_dependency_lock"
},
"matches_metrics_scorer": false,
"official_eval_implementation_hash_matches": false,
"official_eval_trial_count": 0,
"source_report": "docs/research/sealed_holdout_rerun_upstream_sync4_2026_10_02.json",
"fixed_protocol_rerun_trial_count": 20,
"fixed_protocol_rerun_hash_matches": true,
"metrics": {
"top_1_rate": 0.45,
"top_3_rate": 0.5,
"mean_absolute_minute_error": 6.45,
"false_confirmation_rate": 0.0,
"correct_insufficient_evidence_rejection_rate": 1.0,
"confirmation_coverage_rate": 0.0
}
},
"current_tree_fixed_protocol_rerun": {
"evaluated_on": "2026-10-02",
"report_path": "docs/research/sealed_holdout_rerun_upstream_sync4_2026_10_02.json",
"freeze_record_path": "docs/research/sealed_holdout_rerun_upstream_sync4_2026_10_02.freeze.json",
"implementation_sha256": "c913c6f061458fb682f6d520ae08b2d64d6f6cee20ccd1abd7e6c43d5a41685d",
"extended_identity": {
"historical_artifacts_manifest_sha256": "6102a26a840be207b5858b3a4c0509274468ae9071e86d308cbbac7371d6864e",
"production_scoring_files": [
"scripts/active_rectification_event_engine.py",
"scripts/active_rectification_events.py",
"scripts/ashtakavarga.py",
"scripts/dasha_analyzer.py",
"scripts/divisional_charts_extended.py",
"scripts/domain_calculation_service.py",
"scripts/functional_benefics.py",
"scripts/jaimini.py",
"scripts/minute_rectification_fact_ranker_v4.py",
"scripts/minute_rectification_feature_facts_v4.py",
"scripts/narayana_dasha.py",
"scripts/rectification/api_service.py",
"scripts/rectification/candidate_contrast.py",
"scripts/rectification/candidate_window.py",
"scripts/rectification/case_holdout.py",
"scripts/rectification/contracts.py",
"scripts/rectification/dasha_transition_proximity.py",
"scripts/rectification/decision_policy.py",
"scripts/rectification/event_probes.py",
"scripts/rectification/refinement_packet.py",
"scripts/rectification/scoring_service.py",
"scripts/shadbala.py",
"scripts/varga.py"
],
"production_scoring_sha256": "97ebaee6c886092c9c96ca05584f27f6551b4808f7a3c276dd80d11066b16c39",
"research_files": [
"scripts/research/reported_offset_sweep.py",
"scripts/research/cluster_width_lib.py",
"scripts/research/probe_supply_after_six.py",
"scripts/research/sealed_holdout_rerun.py",
"scripts/minute_rectification_blind_eval.py",
"scripts/minute_rectification_fact_blind_eval_v4.py",
"scripts/minute_rectification_holdout_validator.py"
],
"research_implementation_sha256": "f5a4d975b1ce84b4db6f6aec4c4039d2f8154ddd003803770edfb096c8fa75ae",
"file_sha256": {
"scripts/active_rectification_event_engine.py": "cdc0e68edc770a2a1810fbdb68cbfd46dcd50b267c739c496fcc078c5e26b5b4",
"scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
"scripts/ashtakavarga.py": "cc32776674cf60713634a360a6f09774b3af0ec5d0f650687f52b79597b0dfbe",
"scripts/dasha_analyzer.py": "5e53b1b4d4c7414c08dd0e7716f120a63c70ec3428ec93547f64d55c580da0e1",
"scripts/divisional_charts_extended.py": "73bd50a83ac444830940184d0988cea621855f91db76a3f1a232014b992eacea",
"scripts/domain_calculation_service.py": "9ee955874eea806c7b56f4246d90009c02ee8318b8f3dfe1d7132b1c0b4262e1",
"scripts/functional_benefics.py": "cbaac3b8c09b97f8724b5300e9a402cbf77089af6c7db8788550d40fd35ac57b",
"scripts/jaimini.py": "b98bf965603dd2e3cc871fe40f3c8184731a701875ca50fef3ca68e9682eda81",
"scripts/minute_rectification_blind_eval.py": "07aa30d8bad3278669495d5fea8be937aaf6367c8af980ff4f2fe9aa84ccc6ff",
"scripts/minute_rectification_fact_blind_eval_v4.py": "bdf460e3467208e8b87345c5beb2128f3e22de7eeffd68f72b281b3ad9affc92",
"scripts/minute_rectification_fact_ranker_v4.py": "f1a0d8d2482cd754d2e7f253a9606b0373519435a2bf58cfc3753e2b9ae0fb76",
"scripts/minute_rectification_feature_facts_v4.py": "3d899a2cdd4825b8e32062443d487edcd2173a4ea55a36eb9f3abe587c0faf0f",
"scripts/minute_rectification_holdout_validator.py": "b60b1c752e58672beaee8b36eb3b2348169726cda070ec969db0f13e7ed715af",
"scripts/narayana_dasha.py": "7ff2c3238cd113b11b815e14b41967bd8e486ff62e36650e55613b9c79d1bfe3",
"scripts/rectification/api_service.py": "e316ced0f3796d0378a0fe1aad950ee25922ae8afd53add578ed59ca8b2f0f79",
"scripts/rectification/candidate_contrast.py": "eee7da71c0574a08876404b78ca111153fa95fb83ace82b9fdca141d1992e273",
"scripts/rectification/candidate_window.py": "2fbc5058b12049b15fca375cdc125b8283e19f9f3e4bedcc291e344501891bef",
"scripts/rectification/case_holdout.py": "fe0e699b617d9e216acdfeff87af4221c1d6f4c101bf33e1dbf14e2bcd75a8b5",
"scripts/rectification/contracts.py": "c6dc6bd230e38f9f2126c224aae9ddbd6415304c15340f8c7cd3f06f6ef3160f",
"scripts/rectification/dasha_transition_proximity.py": "0afba494aa12899621173c3cc941c6c1d0be9cec0bdf4c4a1c9bcd004ab22de8",
"scripts/rectification/decision_policy.py": "d845896428e0f49f8b5ae946aff6203492e7383d387acf122cb0b7a523b0af28",
"scripts/rectification/event_probes.py": "9bbadc246e6b8e94bb047522c3e5645613f508b3473ef40b38a207c77fdad58c",
"scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
"scripts/rectification/scoring_service.py": "4f13c6a78d2dda55454ac20e4091fce280e3626ecfe8a9d723217ef3ebc05d02",
"scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
"scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
"scripts/research/reported_offset_sweep.py": "2495d7e86e78091ed407b5df68cbe26e26be6f80ef66d7ac05944d5c4500cde9",
"scripts/research/sealed_holdout_rerun.py": "ff86058caad0a7cf379229117096b260934cd55d4e0b66e0d8f25d6eafb1752a",
"scripts/shadbala.py": "355e6dee4f9f632e83896d0e606b29fe12183dc083ed912a18377b0e999771c1",
"scripts/varga.py": "4331de5a25ea08729af91aae863943c4223183937f419d52dc63fd6fe7f27be6"
},
"hash_scope": "explicit_identity_file_sets_not_a_transitive_dependency_lock"
},
"scorer_frozen_before_rerun": true,
"source_audit_status": "corrected_known_date_errors",
"trial_count": 20,
"official_valid_independent_blind": false,
"is_blind_evaluation": false,
"truth_hidden_from_ranker": true,
"results_previously_seen": true,
"must_not_claim_as_release_metrics": true,
"must_not_use_for_tuning": true,
"verified_minute_claim_allowed": false,
"metric_gates_passed": false,
"events_per_case": 3,
"boundary": "Three-event low-information protocol, not a mathematical accuracy lower bound and not representative of real sessions. Historical v3/v4 exposure cannot be undone by freezing today's scorer. No tuning or release claims.",
"report_sha256": "57f2dba6bfde617a6e24da9c5a596bf7e0d322f06aa873359265a60ad08e7640",
"freeze_record_sha256": "5907864c1fec517cabc6dc83873d644891e19db0895b955921163742937e367b",
"replay_started_at_utc": "2026-10-02T06:30:41.977644+00:00",
"replay_finished_at_utc": "2026-10-02T06:30:44.951323+00:00"
},
"previous_fixed_protocol_rerun": {
"evaluated_on": "2026-10-02",
"report_path": "docs/research/sealed_holdout_rerun_functional_v2_2026_10_02.json",
"freeze_record_path": "docs/research/sealed_holdout_rerun_functional_v2_2026_10_02.freeze.json",
"implementation_sha256": "c913c6f061458fb682f6d520ae08b2d64d6f6cee20ccd1abd7e6c43d5a41685d",
"extended_identity": {
"historical_artifacts_manifest_sha256": "6102a26a840be207b5858b3a4c0509274468ae9071e86d308cbbac7371d6864e",
"production_scoring_files": [
"scripts/active_rectification_event_engine.py",
"scripts/active_rectification_events.py",
"scripts/ashtakavarga.py",
"scripts/dasha_analyzer.py",
"scripts/divisional_charts_extended.py",
"scripts/domain_calculation_service.py",
"scripts/functional_benefics.py",
"scripts/jaimini.py",
"scripts/minute_rectification_fact_ranker_v4.py",
"scripts/minute_rectification_feature_facts_v4.py",
"scripts/narayana_dasha.py",
"scripts/rectification/api_service.py",
"scripts/rectification/candidate_contrast.py",
"scripts/rectification/candidate_window.py",
"scripts/rectification/case_holdout.py",
"scripts/rectification/contracts.py",
"scripts/rectification/dasha_transition_proximity.py",
"scripts/rectification/decision_policy.py",
"scripts/rectification/event_probes.py",
"scripts/rectification/refinement_packet.py",
"scripts/rectification/scoring_service.py",
"scripts/shadbala.py",
"scripts/varga.py"
],
"production_scoring_sha256": "01f2d36e715801242c9bf657d70a017a77b46761a100ceeb9fd8369cd39f2c0e",
"research_files": [
"scripts/research/reported_offset_sweep.py",
"scripts/research/cluster_width_lib.py",
"scripts/research/probe_supply_after_six.py",
"scripts/research/sealed_holdout_rerun.py",
"scripts/minute_rectification_blind_eval.py",
"scripts/minute_rectification_fact_blind_eval_v4.py",
"scripts/minute_rectification_holdout_validator.py"
],
"research_implementation_sha256": "a2d555508e2a4063fffdabc14463da546e2cef090c8e2bbd4ecff288942e9e95",
"file_sha256": {
"scripts/active_rectification_event_engine.py": "cdc0e68edc770a2a1810fbdb68cbfd46dcd50b267c739c496fcc078c5e26b5b4",
"scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
"scripts/ashtakavarga.py": "cc32776674cf60713634a360a6f09774b3af0ec5d0f650687f52b79597b0dfbe",
"scripts/dasha_analyzer.py": "5e53b1b4d4c7414c08dd0e7716f120a63c70ec3428ec93547f64d55c580da0e1",
"scripts/divisional_charts_extended.py": "73bd50a83ac444830940184d0988cea621855f91db76a3f1a232014b992eacea",
"scripts/domain_calculation_service.py": "9ee955874eea806c7b56f4246d90009c02ee8318b8f3dfe1d7132b1c0b4262e1",
"scripts/functional_benefics.py": "cbaac3b8c09b97f8724b5300e9a402cbf77089af6c7db8788550d40fd35ac57b",
"scripts/jaimini.py": "b98bf965603dd2e3cc871fe40f3c8184731a701875ca50fef3ca68e9682eda81",
"scripts/minute_rectification_blind_eval.py": "07aa30d8bad3278669495d5fea8be937aaf6367c8af980ff4f2fe9aa84ccc6ff",
"scripts/minute_rectification_fact_blind_eval_v4.py": "bdf460e3467208e8b87345c5beb2128f3e22de7eeffd68f72b281b3ad9affc92",
"scripts/minute_rectification_fact_ranker_v4.py": "f1a0d8d2482cd754d2e7f253a9606b0373519435a2bf58cfc3753e2b9ae0fb76",
"scripts/minute_rectification_feature_facts_v4.py": "3d899a2cdd4825b8e32062443d487edcd2173a4ea55a36eb9f3abe587c0faf0f",
"scripts/minute_rectification_holdout_validator.py": "b60b1c752e58672beaee8b36eb3b2348169726cda070ec969db0f13e7ed715af",
"scripts/narayana_dasha.py": "7ff2c3238cd113b11b815e14b41967bd8e486ff62e36650e55613b9c79d1bfe3",
"scripts/rectification/api_service.py": "e316ced0f3796d0378a0fe1aad950ee25922ae8afd53add578ed59ca8b2f0f79",
"scripts/rectification/candidate_contrast.py": "eee7da71c0574a08876404b78ca111153fa95fb83ace82b9fdca141d1992e273",
"scripts/rectification/candidate_window.py": "2fbc5058b12049b15fca375cdc125b8283e19f9f3e4bedcc291e344501891bef",
"scripts/rectification/case_holdout.py": "fe0e699b617d9e216acdfeff87af4221c1d6f4c101bf33e1dbf14e2bcd75a8b5",
"scripts/rectification/contracts.py": "c6dc6bd230e38f9f2126c224aae9ddbd6415304c15340f8c7cd3f06f6ef3160f",
"scripts/rectification/dasha_transition_proximity.py": "0afba494aa12899621173c3cc941c6c1d0be9cec0bdf4c4a1c9bcd004ab22de8",
"scripts/rectification/decision_policy.py": "d845896428e0f49f8b5ae946aff6203492e7383d387acf122cb0b7a523b0af28",
"scripts/rectification/event_probes.py": "9bbadc246e6b8e94bb047522c3e5645613f508b3473ef40b38a207c77fdad58c",
"scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
"scripts/rectification/scoring_service.py": "4f13c6a78d2dda55454ac20e4091fce280e3626ecfe8a9d723217ef3ebc05d02",
"scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
"scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
"scripts/research/reported_offset_sweep.py": "f2acca1c5d5307b013e098cc28c803348bf9207d318a27733fb7735b9640dd7f",
"scripts/research/sealed_holdout_rerun.py": "f49eae74e27ecf1c417b3a6423eeb473ce8c8c565a5b7c8768ddb407659e3592",
"scripts/shadbala.py": "912e0e6d169c2172aab85f71e4347e3e39193020777b43825b775d906400956b",
"scripts/varga.py": "4331de5a25ea08729af91aae863943c4223183937f419d52dc63fd6fe7f27be6"
},
"hash_scope": "explicit_identity_file_sets_not_a_transitive_dependency_lock"
},
"scorer_frozen_before_rerun": true,
"source_audit_status": "corrected_known_date_errors",
"trial_count": 20,
"official_valid_independent_blind": false,
"is_blind_evaluation": false,
"truth_hidden_from_ranker": true,
"results_previously_seen": true,
"must_not_claim_as_release_metrics": true,
"must_not_use_for_tuning": true,
"verified_minute_claim_allowed": false,
"metric_gates_passed": false,
"events_per_case": 3,
"boundary": "Previously exposed v3 shadow fixed-protocol rerun after the BUG-1181 functional profile v2 re-freeze. Superseded by the 2026-10-02 upstream sync round 4 re-freeze (ERR-110: scripts/shadbala.py bytes changed by the Kala/Chesta fixes and the BPHS Sun minimum, BUG-1188/1189; ALGORITHM_VERSION unchanged); shadow trials identical; report and freeze preserved byte-for-byte.",
"report_sha256": "0138a730eff4fba1325689adfdb37427ed006eb1ee60994431749f4b615dda0c",
"freeze_record_sha256": "2c802655428b209fe027e2d3632e845b937478ecdc0709b59cbbd72724cea33d",
"replay_started_at_utc": "2026-10-02T04:23:10.353143+00:00",
"replay_finished_at_utc": "2026-10-02T04:23:13.490679+00:00",
"previous_fixed_protocol_rerun": {
"report_path": "docs/research/sealed_holdout_rerun_quality_wording_2026_09_29.json",
"freeze_record_path": "docs/research/sealed_holdout_rerun_quality_wording_2026_09_29.freeze.json",
"superseded_reason": "BUG-1181 functional profile v2 re-freeze (scoring-10); prior report and freeze preserved byte-for-byte."
}
},
"current_tree_unfrozen_diagnostic": {
"is_blind_evaluation": false,
"results_already_seen": true,
"scorer_frozen": false,
"source_audit_passed": false,
"must_not_claim_as_release_metrics": true,
"must_not_use_for_tuning": true,
"report_path": "references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic_report.json",
"implementation_sha256": "99730c84c6434f52669a05e4d9a4a87df0a218e3237b5436b933252f2028384e",
"trial_count": 20,
"top_1_rate": 0.45,
"top_3_rate": 0.5,
"mean_absolute_minute_error": 5.8,
"confirmation_coverage_rate": 0.0,
"metric_gates_passed": false,
"verified_minute_claim_allowed": false
},
"current_tree_reported_offset_replay": {
"report_path": "docs/research/reported_offset_upstream_sync4_2026_10_02.json",
"report_sha256": "b80a6051ff334e2e04f0df0326118a0c44d3336c1ba1482e2c5642726c549a4a",
"freeze_record_path": "docs/research/reported_offset_upstream_sync4_2026_10_02.freeze.json",
"freeze_record_sha256": "af730fe8a1256b80f4dab07598e206c4277860cd13a428756a2ab1ce40d0f694",
"scope": "reported_offset_sensitivity_not_product_accuracy",
"trial_count": 900,
"official_valid_independent_blind": false,
"official_blind_trial_count": 0,
"must_not_use_for_tuning": true,
"must_not_claim_as_release_metrics": true
},
"previous_reported_offset_replay": {
"report_path": "docs/research/reported_offset_functional_v2_2026_10_02.json",
"report_sha256": "d5bacd0422dece57acb0ebb913a1a849b058751290faebebe9dea0e0198ed930",
"freeze_record_path": "docs/research/reported_offset_functional_v2_2026_10_02.freeze.json",
"freeze_record_sha256": "0c584207674106597afc129d89c7f395e3aa624954b9b59358ab29d8a75373b7",
"superseded_reason": "Upstream sync round 4 (ERR-110 re-freeze: scripts/shadbala.py bytes changed); 0 of 900 native trials changed; prior report and freeze preserved byte-for-byte."
}
}