root/Jyotisha
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions 1 Packages Projects Releases Wiki Activity
Files
3fed71ab6daa63c672b3df71c43fa9be22a2e621
Jyotisha/docs/research/sealed_holdout_rerun_2026_09_20.json
T
jesse-uxandClaude Code 932f2fffba
Independent Staging Quality Gate / validate (push) Successful in 12m7s
Details
Independent Staging Quality Gate / publish (push) Successful in 3m46s
Details
research(rectification): add reported-offset evaluation and frozen rerun integrity 
Preserve closed confirmation gates and previously-exposed dataset boundaries. Add auditable 900-trial sensitivity results, current scorer freshness checks, and the v5 collection protocol.

Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-09-20 12:03:52 +08:00

627 lines
20 KiB
JSON
Raw Blame History

{
"scope": "fixed_protocol_previously_exposed_v3_rerun",
"evaluated_on": "2026-09-20",
"frozen_record": {
"record_version": "exposed-v3-fixed-protocol-rerun-v1",
"frozen_at_utc": "2026-09-20T03:27:26.670869+00:00",
"dataset_path": "references/real_case_calibration/minute_rectification_holdout_v3.json",
"dataset_sha256": "45aa76ab79dfc6c6404b6252083e1aa5c7e2e2b7de811fc11042a8ad2da3f0ea",
"algorithm_version": "birth-time-event-fact-ranker-v4-shadow",
"implementation_sha256": "b15d9ea15227cd58b3097555537fa7c37fb5a993905ada4f5aa04f52de1f8f18",
"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/shadbala.py",
"scripts/varga.py"
],
"historical_frozen_sha256": "f41c298dd6cdcebe7a93e632f7191954be7987f6012ca2a34cecb6e447fbf196",
"evaluator_sha256": "3bf35de5f8a0b9588808178d47ba2457c398cf2fd2d2fcb03c5c71420f998da5",
"ayanamsa": "raman",
"node_mode": "mean",
"candidate_radius_minutes": [
10
],
"minute_step": 1,
"release_metrics": {
"top_1_rate_minimum": 0.6,
"top_3_rate_minimum": 0.85,
"mean_absolute_minute_error_maximum": 2.0,
"false_confirmation_rate_maximum": 0.05,
"correct_insufficient_evidence_rejection_rate_minimum": 0.9
},
"results_previously_seen": true,
"official_valid_independent_blind": false,
"must_not_use_for_tuning": true,
"tie_breaker": "sha256(benchmark_id:case_id:candidate_time); published minute is never passed to the ranker",
"metric_rank_definition": "competition_rank_1_plus_strictly_higher_scores_legacy_protocol",
"extra_metric_rank_definition": "score_desc_then_existing_opaque_sha256_total_order"
},
"implementation_hash_matches_at_replay": true,
"dataset_hash_matches_at_replay": true,
"source_audit_status": "corrected_known_date_errors",
"validation_status": "blocked_awaiting_public_aa_cases",
"valid_public_aa_cases": 20,
"excluded_cases": [],
"trial_count": 20,
"trials": [
{
"case_ordinal": 1,
"candidate_count": 21,
"event_count": 3,
"true_rank": 5,
"opaque_true_rank": 8,
"minute_error": 10,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 2,
"candidate_count": 21,
"event_count": 3,
"true_rank": 2,
"opaque_true_rank": 8,
"minute_error": 3,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"insufficient_events",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 3,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 12,
"minute_error": 5,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 4,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 1,
"minute_error": 0,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"insufficient_events",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 5,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 10,
"minute_error": 1,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 6,
"candidate_count": 21,
"event_count": 3,
"true_rank": 7,
"opaque_true_rank": 12,
"minute_error": 6,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 7,
"candidate_count": 21,
"event_count": 3,
"true_rank": 5,
"opaque_true_rank": 7,
"minute_error": 9,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 8,
"candidate_count": 21,
"event_count": 3,
"true_rank": 5,
"opaque_true_rank": 8,
"minute_error": 10,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"insufficient_events",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 9,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 3,
"minute_error": 1,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"missing_mandatory_layers",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"missing_mandatory_layers",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 10,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 8,
"minute_error": 5,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 11,
"candidate_count": 21,
"event_count": 3,
"true_rank": 6,
"opaque_true_rank": 17,
"minute_error": 5,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 12,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 4,
"minute_error": 5,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 13,
"candidate_count": 21,
"event_count": 3,
"true_rank": 5,
"opaque_true_rank": 7,
"minute_error": 10,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 14,
"candidate_count": 21,
"event_count": 3,
"true_rank": 17,
"opaque_true_rank": 19,
"minute_error": 10,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 15,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 7,
"minute_error": 9,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"missing_mandatory_layers",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"missing_mandatory_layers",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 16,
"candidate_count": 21,
"event_count": 3,
"true_rank": 12,
"opaque_true_rank": 12,
"minute_error": 10,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 17,
"candidate_count": 21,
"event_count": 3,
"true_rank": 6,
"opaque_true_rank": 6,
"minute_error": 6,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 18,
"candidate_count": 21,
"event_count": 3,
"true_rank": 11,
"opaque_true_rank": 14,
"minute_error": 10,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"insufficient_events",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 19,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 6,
"minute_error": 4,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
},
{
"case_ordinal": 20,
"candidate_count": 21,
"event_count": 3,
"true_rank": 1,
"opaque_true_rank": 7,
"minute_error": 10,
"would_confirm": false,
"false_confirmation": false,
"insufficient_evidence_rejected": true,
"full_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
],
"sparse_trial_reasons": [
"unique_minute_not_found",
"insufficient_events",
"insufficient_domains",
"neighbor_stability_not_passed",
"leave_one_event_out_not_passed",
"top_candidate_feature_not_unique",
"fact_ranker_v4_holdout_not_ready"
]
}
],
"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
},
"metric_gates_passed": false,
"opaque_exact_top_1_rate": 0.05,
"opaque_exact_top_3_rate": 0.1,
"official_valid_independent_blind": false,
"official_blind_trial_count": 0,
"is_blind_evaluation": false,
"truth_hidden_from_ranker": true,
"results_previously_seen": true,
"verified_minute_claim_allowed": false,
"status": "blocked_independent_blind_evidence",
"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."
}
Reference in New Issue View Git Blame Copy Permalink