347 lines
24 KiB
JSON
347 lines
24 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": "2026-10-07",
|
|
"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": "b1b5f5e4faa34033880113d481796544eb0bb62ce78aa917b0c8c172759c5dcf",
|
|
"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": "98ea64425d33095b33412f3a6373b2ad68b97eae94d49f85f52bb54f3c7b73ad",
|
|
"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": "173fd3e37a70a4e30717d1015cf6e4346820d544a0f3be24137165c810c8d4d8",
|
|
"file_sha256": {
|
|
"scripts/active_rectification_event_engine.py": "cdc0e68edc770a2a1810fbdb68cbfd46dcd50b267c739c496fcc078c5e26b5b4",
|
|
"scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
|
|
"scripts/ashtakavarga.py": "9bfc0b8a06af6122fa6c3881706e64f28b9ba58b53d98ff55957d4741d820f3f",
|
|
"scripts/dasha_analyzer.py": "5e53b1b4d4c7414c08dd0e7716f120a63c70ec3428ec93547f64d55c580da0e1",
|
|
"scripts/divisional_charts_extended.py": "e9820e80f14fddc86ab5495d11455d16c2d3c9502a9a242fcf9efc41186e0d11",
|
|
"scripts/domain_calculation_service.py": "9ee955874eea806c7b56f4246d90009c02ee8318b8f3dfe1d7132b1c0b4262e1",
|
|
"scripts/functional_benefics.py": "cbaac3b8c09b97f8724b5300e9a402cbf77089af6c7db8788550d40fd35ac57b",
|
|
"scripts/jaimini.py": "6b88658da5404da9b136686d92a04be462d61a39da6e8de4255021e2ed2d1173",
|
|
"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": "c7aaefd4b7b7ea98a5b94e0f7798e5d0139c7423d10ce4ebfff258a460d4456f",
|
|
"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": "80e8de4680d19a052213bb821d2a9c94143a2962235aeb27f6ad81374d2e60d5",
|
|
"scripts/rectification/event_probes.py": "9bbadc246e6b8e94bb047522c3e5645613f508b3473ef40b38a207c77fdad58c",
|
|
"scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
|
|
"scripts/rectification/scoring_service.py": "45d777d2d762a73c8b9193ba269572e6ab06cdee43afbfb22bce225e40a4a2dd",
|
|
"scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
|
|
"scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
|
|
"scripts/research/reported_offset_sweep.py": "6cc36e3a621bd23332951af53a091b1131fa350f6db1d52cb9fa52cc413c09f4",
|
|
"scripts/research/sealed_holdout_rerun.py": "e5ee47a1fba92f9cd5d4e63fd52c6104fc6680fe7da1beec3d0db2b4cfcb9abc",
|
|
"scripts/shadbala.py": "e949ff1cc925ccbc9a25b68981091d1d621b80a5b3839a3b3ade655d082424d6",
|
|
"scripts/varga.py": "c1f06967c3d4d214edadff139c24aa31e59fb628477174235abe14f799a99076"
|
|
},
|
|
"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_sync6_2026_10_07.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": "2026-10-07",
|
|
"report_path": "docs/research/sealed_holdout_rerun_upstream_sync6_2026_10_07.json",
|
|
"freeze_record_path": "docs/research/sealed_holdout_rerun_upstream_sync6_2026_10_07.freeze.json",
|
|
"implementation_sha256": "b1b5f5e4faa34033880113d481796544eb0bb62ce78aa917b0c8c172759c5dcf",
|
|
"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": "98ea64425d33095b33412f3a6373b2ad68b97eae94d49f85f52bb54f3c7b73ad",
|
|
"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": "173fd3e37a70a4e30717d1015cf6e4346820d544a0f3be24137165c810c8d4d8",
|
|
"file_sha256": {
|
|
"scripts/active_rectification_event_engine.py": "cdc0e68edc770a2a1810fbdb68cbfd46dcd50b267c739c496fcc078c5e26b5b4",
|
|
"scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
|
|
"scripts/ashtakavarga.py": "9bfc0b8a06af6122fa6c3881706e64f28b9ba58b53d98ff55957d4741d820f3f",
|
|
"scripts/dasha_analyzer.py": "5e53b1b4d4c7414c08dd0e7716f120a63c70ec3428ec93547f64d55c580da0e1",
|
|
"scripts/divisional_charts_extended.py": "e9820e80f14fddc86ab5495d11455d16c2d3c9502a9a242fcf9efc41186e0d11",
|
|
"scripts/domain_calculation_service.py": "9ee955874eea806c7b56f4246d90009c02ee8318b8f3dfe1d7132b1c0b4262e1",
|
|
"scripts/functional_benefics.py": "cbaac3b8c09b97f8724b5300e9a402cbf77089af6c7db8788550d40fd35ac57b",
|
|
"scripts/jaimini.py": "6b88658da5404da9b136686d92a04be462d61a39da6e8de4255021e2ed2d1173",
|
|
"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": "c7aaefd4b7b7ea98a5b94e0f7798e5d0139c7423d10ce4ebfff258a460d4456f",
|
|
"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": "80e8de4680d19a052213bb821d2a9c94143a2962235aeb27f6ad81374d2e60d5",
|
|
"scripts/rectification/event_probes.py": "9bbadc246e6b8e94bb047522c3e5645613f508b3473ef40b38a207c77fdad58c",
|
|
"scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
|
|
"scripts/rectification/scoring_service.py": "45d777d2d762a73c8b9193ba269572e6ab06cdee43afbfb22bce225e40a4a2dd",
|
|
"scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
|
|
"scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
|
|
"scripts/research/reported_offset_sweep.py": "6cc36e3a621bd23332951af53a091b1131fa350f6db1d52cb9fa52cc413c09f4",
|
|
"scripts/research/sealed_holdout_rerun.py": "e5ee47a1fba92f9cd5d4e63fd52c6104fc6680fe7da1beec3d0db2b4cfcb9abc",
|
|
"scripts/shadbala.py": "e949ff1cc925ccbc9a25b68981091d1d621b80a5b3839a3b3ade655d082424d6",
|
|
"scripts/varga.py": "c1f06967c3d4d214edadff139c24aa31e59fb628477174235abe14f799a99076"
|
|
},
|
|
"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": "c92192274cdbf9a2c09b86ff90ec0786707a105e2404cb30216402f6a5c2865b",
|
|
"freeze_record_sha256": "c93fe5299644ee99e22b8c80ba149a422ae10b06b8b1a65e9c4469df387c5a2d",
|
|
"replay_started_at_utc": "2026-10-07T09:51:45.563938+00:00",
|
|
"replay_finished_at_utc": "2026-10-07T09:51:49.611695+00:00"
|
|
},
|
|
"previous_fixed_protocol_rerun": {
|
|
"evaluated_on": "2026-10-03",
|
|
"report_path": "docs/research/sealed_holdout_rerun_astrologer_rulings_batch1_2026_10_03.json",
|
|
"freeze_record_path": "docs/research/sealed_holdout_rerun_astrologer_rulings_batch1_2026_10_03.freeze.json",
|
|
"implementation_sha256": "114c60c45fa35a77bb6bfe2c177bbcc90b2e0748e2a33e61975f7393802f96f2",
|
|
"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": "788745f7b7aba1d551a73a67a56daff3e730c1d408cd77dde155e410ad9d00bb",
|
|
"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": "fa74b52f52ca7beeb1c6c6647b11ef075c16bcb6fadb656196770d91004cd0ad",
|
|
"file_sha256": {
|
|
"scripts/active_rectification_event_engine.py": "cdc0e68edc770a2a1810fbdb68cbfd46dcd50b267c739c496fcc078c5e26b5b4",
|
|
"scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
|
|
"scripts/ashtakavarga.py": "9bfc0b8a06af6122fa6c3881706e64f28b9ba58b53d98ff55957d4741d820f3f",
|
|
"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": "6b88658da5404da9b136686d92a04be462d61a39da6e8de4255021e2ed2d1173",
|
|
"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": "80e8de4680d19a052213bb821d2a9c94143a2962235aeb27f6ad81374d2e60d5",
|
|
"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": "f63c1c58d334e083577736397b4acc00757550fa3b863b02784c9d6f0f018c80",
|
|
"scripts/research/sealed_holdout_rerun.py": "1178ebfb9dd61d4aefe9961d83f19e7a943a4ca3de9fa2efffff6f8ba8c09161",
|
|
"scripts/shadbala.py": "e949ff1cc925ccbc9a25b68981091d1d621b80a5b3839a3b3ade655d082424d6",
|
|
"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 2026-10-03 astrologer rulings batch 1 re-freeze. Superseded by the 2026-10-07 upstream sync 6 re-freeze (ERR-110: scripts/varga.py, scripts/divisional_charts_extended.py, scripts/narayana_dasha.py and scripts/rectification/scoring_service.py bytes changed by the PVR 6.2 D5/D6/D8/D11 maps and the scoring-11 identity, BUG-1260/1264). Shadow trial fields versus the 2026-09-20 historical report are unchanged (changed_trial_count 0). Report and freeze preserved byte-for-byte.",
|
|
"report_sha256": "b39b53c1f2aa0ad6ac363b4c359116c30bc89b446cb670e6172c8cee5ccc5efd",
|
|
"freeze_record_sha256": "c1c11e7abc03b9174aeb1e0b280f550808f887818f578e5d10ad667e0da67e24",
|
|
"replay_started_at_utc": "2026-10-03T06:53:04.851491+00:00",
|
|
"replay_finished_at_utc": "2026-10-03T06:53:07.509845+00:00",
|
|
"previous_fixed_protocol_rerun": {
|
|
"report_path": "docs/research/sealed_holdout_rerun_upstream_sync5_2026_10_02.json",
|
|
"freeze_record_path": "docs/research/sealed_holdout_rerun_upstream_sync5_2026_10_02.freeze.json",
|
|
"superseded_reason": "Upstream sync round 6 (ERR-110). Prior sync5 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_sync6_2026_10_07.json",
|
|
"report_sha256": "1b9c9c18b6820a2beca8d7ddef20b6fa0778c5d43dd987c0c214e2f9ff00660f",
|
|
"freeze_record_path": "docs/research/reported_offset_upstream_sync6_2026_10_07.freeze.json",
|
|
"freeze_record_sha256": "65c7ab537b3fecc6d3e175bb2ab702b5630fe41bcff40bd551917cc32977b366",
|
|
"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_astrologer_rulings_batch1_2026_10_03.json",
|
|
"report_sha256": "480eb771c2c7e5a300589561dc66be950a711ffa205a8fa370db6a11f1e04270",
|
|
"freeze_record_path": "docs/research/reported_offset_astrologer_rulings_batch1_2026_10_03.freeze.json",
|
|
"freeze_record_sha256": "6be6a997f610c341aecc1f782fa27a5b86b66d43d00fcfa10750c81189c34748",
|
|
"superseded_reason": "Upstream sync 6 (ERR-110: scripts/varga.py, scripts/divisional_charts_extended.py, scripts/narayana_dasha.py and scripts/rectification/scoring_service.py). 5 of 900 trials differ from the batch1 replay (delivery_width_minutes on 4, top_1_minute_error on 1). Versus the 2026-09-20 historical report, changed_trial_count is 235 (batch1 was 230). Prior report and freeze preserved byte-for-byte."
|
|
}
|
|
}
|