jesse-ux
b85c4a686a
Carry explicit local date intervals instead of inferring the day from clock order. Cluster width, delivery, adoption, and reports keep the actual civil date; adopted date is stored separately from the reported birth_date. Algorithm identity is scoring-9 / spec-v5. Scoring weights, confirmation thresholds, and Skill version are unchanged. Isolated Linux final-3 gates passed; four pre-existing Python failures remain. This is not a production release.
322 lines
21 KiB
JSON
322 lines
21 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": "2026-09-20",
|
|
"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": "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/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": "102f3bce580ebf917f36724722ebc841de88a119c4787b8ea5e9e21339261768",
|
|
"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": "f6c06b348a809f7316351914a92157485ff5e42dc5691873dbf58864b0f31d13",
|
|
"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/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": "45478ee3fdc36dc36e1a602bee5dd0627a5464275e370e64adb5826fe2aa58f5",
|
|
"scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
|
|
"scripts/rectification/scoring_service.py": "4940f47c5fcc0843b3f79692c1044cc871e738a866aa8cb96a4757998afa3921",
|
|
"scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
|
|
"scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
|
|
"scripts/research/reported_offset_sweep.py": "4898c605b745cba5c67311149fdfe0e2e1af7c620a41a172e746be55b19a84b3",
|
|
"scripts/research/sealed_holdout_rerun.py": "5d26d782648bbef42b5dcfe603ef2cbe697b317df6000f7c9c3fa0272504b027",
|
|
"scripts/shadbala.py": "912e0e6d169c2172aab85f71e4347e3e39193020777b43825b775d906400956b",
|
|
"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_midnight_anchor_2026_09_21.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": "2026-09-20",
|
|
"report_path": "docs/research/sealed_holdout_rerun_midnight_anchor_2026_09_21.json",
|
|
"freeze_record_path": "docs/research/sealed_holdout_rerun_midnight_anchor_2026_09_21.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/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": "102f3bce580ebf917f36724722ebc841de88a119c4787b8ea5e9e21339261768",
|
|
"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": "f6c06b348a809f7316351914a92157485ff5e42dc5691873dbf58864b0f31d13",
|
|
"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/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": "45478ee3fdc36dc36e1a602bee5dd0627a5464275e370e64adb5826fe2aa58f5",
|
|
"scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
|
|
"scripts/rectification/scoring_service.py": "4940f47c5fcc0843b3f79692c1044cc871e738a866aa8cb96a4757998afa3921",
|
|
"scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
|
|
"scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
|
|
"scripts/research/reported_offset_sweep.py": "4898c605b745cba5c67311149fdfe0e2e1af7c620a41a172e746be55b19a84b3",
|
|
"scripts/research/sealed_holdout_rerun.py": "5d26d782648bbef42b5dcfe603ef2cbe697b317df6000f7c9c3fa0272504b027",
|
|
"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": "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": "05458f29215d9784623f1b05f09ef590915caf46a87947f0af31dcae85808620",
|
|
"freeze_record_sha256": "9b9bb4b9093a9987e84f04f50b3291ceca23691f89b1d5800c81652aec13824e",
|
|
"replay_started_at_utc": "2026-09-20T17:01:53.362316+00:00",
|
|
"replay_finished_at_utc": "2026-09-20T17:01:56.147759+00:00"
|
|
},
|
|
"previous_fixed_protocol_rerun": {
|
|
"evaluated_on": "2026-09-20",
|
|
"report_path": "docs/research/sealed_holdout_rerun_cross_midnight_2026_09_20.json",
|
|
"freeze_record_path": "docs/research/sealed_holdout_rerun_cross_midnight_2026_09_20.final.freeze.json",
|
|
"implementation_sha256": "b15d9ea15227cd58b3097555537fa7c37fb5a993905ada4f5aa04f52de1f8f18",
|
|
"extended_identity": {
|
|
"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/jaimini.py",
|
|
"scripts/minute_rectification_fact_ranker_v4.py",
|
|
"scripts/minute_rectification_feature_facts_v4.py",
|
|
"scripts/narayana_dasha.py",
|
|
"scripts/rectification/candidate_contrast.py",
|
|
"scripts/rectification/case_holdout.py",
|
|
"scripts/rectification/contracts.py",
|
|
"scripts/rectification/dasha_transition_proximity.py",
|
|
"scripts/rectification/event_probes.py",
|
|
"scripts/rectification/scoring_service.py",
|
|
"scripts/shadbala.py",
|
|
"scripts/varga.py"
|
|
],
|
|
"production_scoring_sha256": "7fffd1db612af1f244a8b5d5eac2f1a3f5a8e9e138c09ac6b3743b98f9a47a51",
|
|
"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": "2931d4661bf53dde5c57f6492de65be4c00877293b7277353279a05eda5af215",
|
|
"historical_artifacts_manifest_sha256": "6102a26a840be207b5858b3a4c0509274468ae9071e86d308cbbac7371d6864e",
|
|
"file_sha256": {
|
|
"scripts/active_rectification_event_engine.py": "edbe93ef3c8bd65f986139dba6b95b96d9b0fa9920341fbe677cd6f53e4db84f",
|
|
"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/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/candidate_contrast.py": "10a360586359e72846593ef6d7c15a2cea79358245a34c288851406fe9e47ca8",
|
|
"scripts/rectification/case_holdout.py": "fe0e699b617d9e216acdfeff87af4221c1d6f4c101bf33e1dbf14e2bcd75a8b5",
|
|
"scripts/rectification/contracts.py": "fdd1a47b2e3dac8579e870a282ed74c68518b39f6c0576b27df766a4b8021143",
|
|
"scripts/rectification/dasha_transition_proximity.py": "0afba494aa12899621173c3cc941c6c1d0be9cec0bdf4c4a1c9bcd004ab22de8",
|
|
"scripts/rectification/event_probes.py": "45478ee3fdc36dc36e1a602bee5dd0627a5464275e370e64adb5826fe2aa58f5",
|
|
"scripts/rectification/scoring_service.py": "0adf5700bb22dd8c4c3147027251210e21ec66a2c9f9a91217edba3ad9e5d1f5",
|
|
"scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
|
|
"scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
|
|
"scripts/research/reported_offset_sweep.py": "f81c681fd0fe257e90a761dfab370f623e5f8a881b62cc6b1c596cbd58800f8f",
|
|
"scripts/research/sealed_holdout_rerun.py": "34a6724530fbecdecff9e5e07fa64980b8e8aff1fac2e000f4268debe1ee96e1",
|
|
"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 BUG-981. Production identity is contextual: shadow scorer does not call transition proximity. Prior shadow metrics are not presumed incorrect. Three-event low-information protocol is neither representative of real sessions nor a mathematical accuracy lower bound. No independent blind evidence or release claim.",
|
|
"previous_fixed_protocol_rerun": {
|
|
"report_path": "docs/research/sealed_holdout_rerun_2026_09_20.json",
|
|
"freeze_record_path": "docs/research/sealed_holdout_rerun_2026_09_20.freeze.json",
|
|
"superseded_reason": "New production and evaluator identity; prior shadow report and freeze preserved byte-for-byte, not relabelled as new results."
|
|
}
|
|
},
|
|
"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_midnight_anchor_2026_09_21.json",
|
|
"report_sha256": "093d50953d7772f037401b99517b8dcaf2a1b20aa3e8ae2e692d83c6510dd02f",
|
|
"freeze_record_path": "docs/research/reported_offset_midnight_anchor_2026_09_21.freeze.json",
|
|
"freeze_record_sha256": "73848f421b133f53578dd0e0713f24fbb38a2bcf3b27609398b1ba98dbfc224c",
|
|
"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
|
|
}
|
|
}
|