diff --git a/progress.md b/progress.md index 86df79ff..270529d6 100644 --- a/progress.md +++ b/progress.md @@ -1030,3 +1030,11 @@ - 真实状态来自 `minute_rectification_holdout_v3.json` 与 `minute_rectification_holdout_v3_report.json`(evaluated_on 2026-07-21):20 个公开 AA 案例已存在;source audit 失败(`invalidated_after_replay`);`top_1_rate=0.15`、`top_3_rate=0.25`、`mean_absolute_minute_error=6.95` 均未过门;`confirmation_coverage_rate=0.0`。 - 合同六键已改为 v3 数字,`status` 仍为 `not_ready`。确认门保持关闭:案例数已满,但 status 非 ready 且 confirmation_coverage_rate 为 0。 - 防复发:holdout 集一旦回放,必须把真实 status / 案例数 / 指标写回 `rectification_sealed_holdout.v1.json`;不得把合同留在上一版的计数上。 + +## 2026-08-29 - C2: 两例日期审计 + v4 intake + 诊断回放(非盲测) + +- `robbins_marriage_1968`:submitted `1968`(year);verified `1967-03-10`(day)。原 URL `https://www.johnrobbins.info/about/` 无结婚日期,已替换为 `https://en.wikipedia.org/wiki/John_Robbins_(author)`。v3 盲测 working `date` 仍保留 submitted `1968`。 +- `takamoto_joined_disney_1947`:submitted `1947`(year);verified `1945`(year)。原 URL `https://en.wikipedia.org/wiki/Iwao_Takamoto` 已写明 1945 入职 Disney,URL 保留。v3 盲测 working `date` 仍保留 submitted `1947`。未把 year-precision 编造成 day。 +- v3 `source_audit_status` 仍为 `invalidated_after_replay`。未改已发布的 `minute_rectification_holdout_v3_report.json` 数字。 +- v4 intake `day_precision_events_per_case=3` 未放宽:20 例中仅 4 例入列(`barack_obama_1961_aa_v4_holdout`、`paul_ryan_1970_aa_v4_holdout`、`sean_lennon_1975_aa_v4_holdout`、`kurt_cobain_1967_aa_v4_holdout`)。其余 16 例在补齐 review safeguards 后仍为 `insufficient_day_precision_events`;Robbins/Takamoto 校正后仍不够 3 个 day 事件。intake 保持 `production_tuning_allowed=false`、`verified_minute_claim_allowed=false`。 +- 诊断回放文件:`minute_rectification_holdout_v3_post_audit_diagnostic.json` / `_report.json`。这是 post-audit diagnostic rerun,不是盲测,不可声称 release gate 通过,不可用于调参。官方 eval runner 因当前树 scoring 文件哈希已偏离 2026-07-21 v3 freeze 而 `implementation_hash_matches=false`、trial_count=0;本任务未改 `frozen_scoring.files`。确认门仍关闭。 diff --git a/references/real_case_calibration/minute_rectification_holdout_v3.json b/references/real_case_calibration/minute_rectification_holdout_v3.json index 5d4088a0..1805443c 100644 --- a/references/real_case_calibration/minute_rectification_holdout_v3.json +++ b/references/real_case_calibration/minute_rectification_holdout_v3.json @@ -8,13 +8,27 @@ "source_audit_issues": [ { "event_id": "robbins_marriage_1968", - "issue": "The cited public biography gives 1967-03-10, not 1968." + "issue": "The cited public biography gives 1967-03-10, not 1968.", + "submitted_date": "1968", + "verified_date": "1967-03-10", + "cited_url": "https://www.johnrobbins.info/about/", + "cited_url_outcome": "replaced", + "cited_url_note": "The original about page has no marriage date.", + "replacement_url": "https://en.wikipedia.org/wiki/John_Robbins_(author)" }, { "event_id": "takamoto_joined_disney_1947", - "issue": "Multiple public biographies give 1945, not 1947." + "issue": "Multiple public biographies give 1945, not 1947.", + "submitted_date": "1947", + "verified_date": "1945", + "cited_url": "https://en.wikipedia.org/wiki/Iwao_Takamoto", + "cited_url_outcome": "kept", + "cited_url_note": "The cited Wikipedia page states hired by Walt Disney Productions in 1945, not 1947." } ], + "post_audit_diagnostic_dataset": "references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic.json", + "post_audit_diagnostic_report": "references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic_report.json", + "post_audit_diagnostic_note": "The historical blind working date fields below remain the submitted values. Verified dates live on the events as verified_date and in the diagnostic dataset. Do not treat a re-run of this file as a new blind holdout.", "minimum_gate": { "public_aa_cases": 20, "events_per_case": 3, @@ -303,7 +317,7 @@ "source": {"publisher": "Astro-Databank", "url": "https://www.astro.com/astro-databank/Robbins%2C_John", "rodden_rating": "AA", "record_type": "birth_record"} }, "events": [ - {"id": "robbins_marriage_1968", "domain": "relationship", "date": "1968", "precision": "year", "description": "Married Deo Robbins.", "source": {"publisher": "John Robbins", "url": "https://www.johnrobbins.info/about/", "independent_of_birth_source": true}}, + {"id": "robbins_marriage_1968", "domain": "relationship", "date": "1968", "precision": "year", "submitted_date": "1968", "verified_date": "1967-03-10", "source_audit_note": "Blind working date remains submitted 1968. Verified 1967-03-10 from Wikipedia; original johnrobbins.info/about/ has no marriage date.", "description": "Married Deo Robbins.", "source": {"publisher": "Wikipedia", "url": "https://en.wikipedia.org/wiki/John_Robbins_(author)", "independent_of_birth_source": true}}, {"id": "robbins_diet_book_1987", "domain": "career", "date": "1987", "precision": "year", "description": "Published Diet for a New America.", "source": {"publisher": "Wikipedia", "url": "https://en.wikipedia.org/wiki/John_Robbins_(author)", "independent_of_birth_source": true}}, {"id": "robbins_health_book_1996", "domain": "career", "date": "1996", "precision": "year", "description": "Published Reclaiming Our Health.", "source": {"publisher": "John Robbins", "url": "https://www.johnrobbins.info/books/", "independent_of_birth_source": true}} ] @@ -348,7 +362,7 @@ "source": {"publisher": "Astro-Databank", "url": "https://www.astro.com/astro-databank/Takamoto%2C_Iwao", "rodden_rating": "AA", "record_type": "birth_record"} }, "events": [ - {"id": "takamoto_joined_disney_1947", "domain": "career", "date": "1947", "precision": "year", "description": "Joined Walt Disney Animation Studios.", "source": {"publisher": "Wikipedia", "url": "https://en.wikipedia.org/wiki/Iwao_Takamoto", "independent_of_birth_source": true}}, + {"id": "takamoto_joined_disney_1947", "domain": "career", "date": "1947", "precision": "year", "submitted_date": "1947", "verified_date": "1945", "source_audit_note": "Blind working date remains submitted 1947. Cited Wikipedia states hired by Walt Disney Productions in 1945; URL kept.", "description": "Joined Walt Disney Animation Studios.", "source": {"publisher": "Wikipedia", "url": "https://en.wikipedia.org/wiki/Iwao_Takamoto", "independent_of_birth_source": true}}, {"id": "takamoto_hanna_barbera_1961", "domain": "career", "date": "1961", "precision": "year", "description": "Moved to Hanna-Barbera and began designing its characters.", "source": {"publisher": "Animation Magazine", "url": "https://www.animationmagazine.net/2007/01/animation-legend-iwao-takamoto-dies/", "independent_of_birth_source": true}}, {"id": "takamoto_heart_attack_2007", "domain": "health_pressure", "date": "2007-01-08", "precision": "day", "description": "Died following a heart attack.", "source": {"publisher": "The New York Times", "url": "https://www.nytimes.com/2007/01/10/arts/10takamoto.html", "independent_of_birth_source": true}} ] diff --git a/references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic.json b/references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic.json new file mode 100644 index 00000000..d1a5ddb7 --- /dev/null +++ b/references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic.json @@ -0,0 +1,1462 @@ +{ + "schema_version": "minute-rectification-holdout-v3", + "benchmark_id": "minute_rectification_fact_ranker_v4_holdout_v3_post_audit_diagnostic", + "description": "Post-audit diagnostic copy of the v3 public AA set. Verified event dates are the working dates. This is not a new sealed blind holdout.", + "truth_hidden_from_ranker": true, + "frozen_before_replay": true, + "source_audit_status": "invalidated_after_replay", + "source_audit_issues": [ + { + "event_id": "robbins_marriage_1968", + "issue": "The cited public biography gives 1967-03-10, not 1968.", + "submitted_date": "1968", + "verified_date": "1967-03-10", + "cited_url": "https://www.johnrobbins.info/about/", + "cited_url_outcome": "replaced", + "cited_url_note": "The original about page has no marriage date.", + "replacement_url": "https://en.wikipedia.org/wiki/John_Robbins_(author)" + }, + { + "event_id": "takamoto_joined_disney_1947", + "issue": "Multiple public biographies give 1945, not 1947.", + "submitted_date": "1947", + "verified_date": "1945", + "cited_url": "https://en.wikipedia.org/wiki/Iwao_Takamoto", + "cited_url_outcome": "kept", + "cited_url_note": "The cited Wikipedia page states hired by Walt Disney Productions in 1945, not 1947." + } + ], + "post_audit_diagnostic_dataset": "references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic.json", + "post_audit_diagnostic_report": "references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic_report.json", + "post_audit_diagnostic_note": "Working dates on the two audited events are the verified values (Robbins 1967-03-10 day; Takamoto 1945 year). This file is a post-audit diagnostic rerun, not a blind evaluation, and must not be used to claim the release gate passed or to tune scoring.", + "minimum_gate": { + "public_aa_cases": 20, + "events_per_case": 3, + "domains_per_case": 2, + "independent_event_sources_per_case": 2, + "negative_minutes_per_case": 4 + }, + "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 + }, + "frozen_scoring": { + "algorithm_version": "birth-time-event-fact-ranker-v4-shadow", + "implementation_sha256": "f41c298dd6cdcebe7a93e632f7191954be7987f6012ca2a34cecb6e447fbf196", + "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" + ], + "tie_breaker": "sha256(benchmark_id:case_id:candidate_time); published minute is never passed to the ranker" + }, + "cases": [ + { + "case_id": "barack_obama_1961_aa_v4_holdout", + "subject_label": "Barack Obama", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1961-08-04", + "time": "19:24", + "place": "Honolulu, Hawaii, United States", + "latitude": 21.3069, + "longitude": -157.8583, + "timezone_offset": -10.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/adbvip/adbvip_08_04.htm?lang=r&nho2=161&nhor=1", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "obama_wedding_1992_v4", + "domain": "relationship", + "date": "1992-10-03", + "precision": "day", + "description": "Married Michelle Robinson.", + "source": { + "publisher": "Obama Foundation", + "url": "https://obama.org/about/administration/chicago-where-it-began/", + "independent_of_birth_source": true + } + }, + { + "id": "obama_illinois_senate_1996_v4", + "domain": "career", + "date": "1996-11-05", + "precision": "day", + "description": "Elected to the Illinois State Senate.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Illinois_Senate_career_of_Barack_Obama", + "independent_of_birth_source": true + } + }, + { + "id": "obama_presidential_election_2008_v4", + "domain": "career", + "date": "2008-11-04", + "precision": "day", + "description": "Elected President of the United States.", + "source": { + "publisher": "White House Archives", + "url": "https://obamawhitehouse.archives.gov/1600/presidents/barackobama/", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "angelina_jolie_1975_aa_v4_holdout", + "subject_label": "Angelina Jolie", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1975-06-04", + "time": "09:09", + "place": "Los Angeles, California, United States", + "latitude": 34.0961, + "longitude": -118.2944, + "timezone_offset": -7.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Jolie%2C_Angelina", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "jolie_oscar_2000", + "domain": "career", + "date": "2000", + "precision": "year", + "description": "Won the Academy Award for supporting actress.", + "source": { + "publisher": "Academy of Motion Picture Arts and Sciences", + "url": "https://www.oscars.org/oscars/ceremonies/2000", + "independent_of_birth_source": true + } + }, + { + "id": "jolie_mastectomy_2013", + "domain": "health_pressure", + "date": "2013", + "precision": "year", + "description": "Underwent preventive double mastectomy treatment.", + "source": { + "publisher": "The New York Times", + "url": "https://www.nytimes.com/2013/05/14/opinion/my-medical-choice.html", + "independent_of_birth_source": true + } + }, + { + "id": "jolie_marriage_2014", + "domain": "relationship", + "date": "2014-08-23", + "precision": "day", + "description": "Married Brad Pitt.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Angelina-Jolie", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "tiger_woods_1975_aa_v4_holdout", + "subject_label": "Tiger Woods", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1975-12-30", + "time": "22:50", + "place": "Long Beach, California, United States", + "latitude": 33.7667, + "longitude": -118.1833, + "timezone_offset": -8.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Woods%2C_Tiger", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "woods_turned_professional_1996", + "domain": "career", + "date": "1996", + "precision": "year", + "description": "Turned professional as a golfer.", + "source": { + "publisher": "PGA Tour", + "url": "https://www.pgatour.com/player/08793/tiger-woods/bio", + "independent_of_birth_source": true + } + }, + { + "id": "woods_marriage_2004", + "domain": "relationship", + "date": "2004-10-05", + "precision": "day", + "description": "Married Elin Nordegren.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Tiger-Woods", + "independent_of_birth_source": true + } + }, + { + "id": "woods_car_crash_2021", + "domain": "health_pressure", + "date": "2021-02-23", + "precision": "day", + "description": "Sustained serious injuries in a motor-vehicle crash.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Tiger_Woods", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "elizabeth_taylor_1932_aa_v4_holdout", + "subject_label": "Elizabeth Taylor", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1932-02-27", + "time": "02:30", + "place": "London, England", + "latitude": 51.5, + "longitude": -0.1667, + "timezone_offset": 0.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Taylor%2C_Elizabeth", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "taylor_first_marriage_1950", + "domain": "relationship", + "date": "1950-05-06", + "precision": "day", + "description": "Married Conrad Hilton Jr.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Elizabeth-Taylor-American-actress", + "independent_of_birth_source": true + } + }, + { + "id": "taylor_oscar_1961", + "domain": "career", + "date": "1961", + "precision": "year", + "description": "Won the Academy Award for Butterfield 8.", + "source": { + "publisher": "Academy of Motion Picture Arts and Sciences", + "url": "https://www.oscars.org/oscars/ceremonies/1961", + "independent_of_birth_source": true + } + }, + { + "id": "taylor_brain_surgery_1997", + "domain": "health_pressure", + "date": "1997", + "precision": "year", + "description": "Underwent surgery for a benign brain tumor.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Elizabeth-Taylor-American-actress/Final-films-and-HIV-AIDS-activism", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "elizabeth_montgomery_1933_aa_v4_holdout", + "subject_label": "Elizabeth Montgomery", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1933-04-15", + "time": "16:38", + "place": "Los Angeles, California, United States", + "latitude": 34.05, + "longitude": -118.25, + "timezone_offset": -8.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Montgomery%2C_Elizabeth", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "montgomery_marriage_asher_1963", + "domain": "relationship", + "date": "1963", + "precision": "year", + "description": "Married producer William Asher.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Elizabeth_Montgomery", + "independent_of_birth_source": true + } + }, + { + "id": "montgomery_bewitched_1964", + "domain": "career", + "date": "1964-09-17", + "precision": "day", + "description": "Bewitched premiered on television.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Bewitched", + "independent_of_birth_source": true + } + }, + { + "id": "montgomery_cancer_1995", + "domain": "health_pressure", + "date": "1995", + "precision": "year", + "description": "Was diagnosed with colorectal cancer and died later that year.", + "source": { + "publisher": "The New York Times", + "url": "https://www.nytimes.com/1995/05/19/obituaries/elizabeth-montgomery-62-star-of-the-tv-comedy-bewitched.html", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "pablo_picasso_1881_aa_v4_holdout", + "subject_label": "Pablo Picasso", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1881-10-25", + "time": "23:15", + "place": "Malaga, Spain", + "latitude": 36.7167, + "longitude": -4.4167, + "timezone_offset": -0.29444, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Picasso%2C_Pablo", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "picasso_moved_paris_1904", + "domain": "relocation", + "date": "1904", + "precision": "year", + "description": "Settled permanently in Paris.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Pablo-Picasso/Blue-Period", + "independent_of_birth_source": true + } + }, + { + "id": "picasso_marriage_1918", + "domain": "relationship", + "date": "1918-07-12", + "precision": "day", + "description": "Married Olga Khokhlova.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Pablo_Picasso", + "independent_of_birth_source": true + } + }, + { + "id": "picasso_guernica_1937", + "domain": "career", + "date": "1937", + "precision": "year", + "description": "Created and exhibited Guernica.", + "source": { + "publisher": "Museum of Modern Art", + "url": "https://www.moma.org/collection/works/79018", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "sigmund_freud_1856_aa_v4_holdout", + "subject_label": "Sigmund Freud", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1856-05-06", + "time": "18:30", + "place": "Freiberg in Mahren, Austrian Empire", + "latitude": 49.65, + "longitude": 18.1667, + "timezone_offset": 0.96222, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Freud%2C_Sigmund", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "freud_marriage_1886", + "domain": "relationship", + "date": "1886-09-14", + "precision": "day", + "description": "Married Martha Bernays.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Sigmund_Freud", + "independent_of_birth_source": true + } + }, + { + "id": "freud_dreams_publication_1899", + "domain": "career", + "date": "1899", + "precision": "year", + "description": "Published The Interpretation of Dreams.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Sigmund-Freud/Psychoanalytic-theory", + "independent_of_birth_source": true + } + }, + { + "id": "freud_moved_london_1938", + "domain": "relocation", + "date": "1938", + "precision": "year", + "description": "Fled Nazi-occupied Vienna and settled in London.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Freud_Museum", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "salma_hayek_1966_aa_v4_holdout", + "subject_label": "Salma Hayek", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1966-09-02", + "time": "06:40", + "place": "Coatzacoalcos, Mexico", + "latitude": 18.15, + "longitude": -94.4167, + "timezone_offset": -6.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Hayek%2C_Salma", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "hayek_moved_los_angeles_1991", + "domain": "relocation", + "date": "1991", + "precision": "year", + "description": "Moved to Los Angeles to pursue acting in Hollywood.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Salma-Hayek", + "independent_of_birth_source": true + } + }, + { + "id": "hayek_frida_2002", + "domain": "career", + "date": "2002", + "precision": "year", + "description": "Produced and starred in Frida.", + "source": { + "publisher": "Academy of Motion Picture Arts and Sciences", + "url": "https://www.oscars.org/oscars/ceremonies/2003", + "independent_of_birth_source": true + } + }, + { + "id": "hayek_marriage_2009", + "domain": "relationship", + "date": "2009-02-14", + "precision": "day", + "description": "Married Francois-Henri Pinault.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Salma-Hayek/Personal-life", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "steve_reich_1936_aa_v4_holdout", + "subject_label": "Steve Reich", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1936-10-03", + "time": "18:21", + "place": "Manhattan, New York, United States", + "latitude": 40.7667, + "longitude": -73.9833, + "timezone_offset": -5.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Reich%2C_Steve", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "reich_cornell_degree_1957", + "domain": "education", + "date": "1957", + "precision": "year", + "description": "Graduated from Cornell University.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Steve-Reich", + "independent_of_birth_source": true + } + }, + { + "id": "reich_moved_california_1963", + "domain": "relocation", + "date": "1963", + "precision": "year", + "description": "Moved to the San Francisco Bay Area.", + "source": { + "publisher": "Boosey and Hawkes", + "url": "https://www.boosey.com/composer/Steve+Reich", + "independent_of_birth_source": true + } + }, + { + "id": "reich_music_18_premiere_1976", + "domain": "career", + "date": "1976-04-24", + "precision": "day", + "description": "Music for 18 Musicians received its world premiere.", + "source": { + "publisher": "Pulitzer Prizes", + "url": "https://www.pulitzer.org/winners/steve-reich", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "albert_brooks_1947_aa_v4_holdout", + "subject_label": "Albert Brooks", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1947-07-22", + "time": "03:00", + "place": "Los Angeles, California, United States", + "latitude": 34.05, + "longitude": -118.25, + "timezone_offset": -8.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Brooks%2C_Albert", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "brooks_real_life_1979", + "domain": "career", + "date": "1979", + "precision": "year", + "description": "Made his feature directing debut with Real Life.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Albert_Brooks", + "independent_of_birth_source": true + } + }, + { + "id": "brooks_oscar_nomination_1988", + "domain": "career", + "date": "1988", + "precision": "year", + "description": "Received an Academy Award nomination for Broadcast News.", + "source": { + "publisher": "Academy of Motion Picture Arts and Sciences", + "url": "https://www.oscars.org/oscars/ceremonies/1988", + "independent_of_birth_source": true + } + }, + { + "id": "brooks_marriage_1997", + "domain": "relationship", + "date": "1997", + "precision": "year", + "description": "Married Kimberly Shlain.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Kimberly_Brooks_(artist)", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "paul_ryan_1970_aa_v4_holdout", + "subject_label": "Paul Ryan", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1970-01-29", + "time": "02:37", + "place": "Janesville, Wisconsin, United States", + "latitude": 42.6833, + "longitude": -89.0167, + "timezone_offset": -6.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Ryan%2C_Paul", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "ryan_elected_house_1998", + "domain": "career", + "date": "1998-11-03", + "precision": "day", + "description": "Was elected to the United States House of Representatives.", + "source": { + "publisher": "United States House of Representatives", + "url": "https://history.house.gov/People/Detail/20147", + "independent_of_birth_source": true + } + }, + { + "id": "ryan_marriage_2000", + "domain": "relationship", + "date": "2000-12-02", + "precision": "day", + "description": "Married Janna Little.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Paul-Ryan", + "independent_of_birth_source": true + } + }, + { + "id": "ryan_speaker_2015", + "domain": "career", + "date": "2015-10-29", + "precision": "day", + "description": "Was elected Speaker of the House.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/October_2015_Speaker_of_the_United_States_House_of_Representatives_election", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "tom_kennedy_1927_aa_v4_holdout", + "subject_label": "Tom Kennedy", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1927-02-26", + "time": "17:25", + "place": "Louisville, Kentucky, United States", + "latitude": 38.25, + "longitude": -85.7667, + "timezone_offset": -6.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Kennedy%2C_Tom", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "kennedy_marriage_1952", + "domain": "relationship", + "date": "1952", + "precision": "year", + "description": "Married Betty Gevedon.", + "source": { + "publisher": "The Hollywood Reporter", + "url": "https://www.hollywoodreporter.com/tv/tv-news/tom-kennedy-dead-game-show-host-name-that-tune-was-93-4074025/", + "independent_of_birth_source": true + } + }, + { + "id": "kennedy_big_game_1958", + "domain": "career", + "date": "1958", + "precision": "year", + "description": "Began hosting his first national game show, The Big Game.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Tom_Kennedy_(television_host)", + "independent_of_birth_source": true + } + }, + { + "id": "kennedy_name_that_tune_1974", + "domain": "career", + "date": "1974", + "precision": "year", + "description": "Began hosting the syndicated Name That Tune.", + "source": { + "publisher": "The Hollywood Reporter", + "url": "https://www.hollywoodreporter.com/tv/tv-news/tom-kennedy-dead-game-show-host-name-that-tune-was-93-4074025/", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "andrew_windsor_1960_aa_v4_holdout", + "subject_label": "Andrew Mountbatten-Windsor", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1960-02-19", + "time": "15:30", + "place": "London, England", + "latitude": 51.5, + "longitude": -0.1667, + "timezone_offset": 0.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Andrew%2C_Prince", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "andrew_royal_navy_1979", + "domain": "career", + "date": "1979", + "precision": "year", + "description": "Entered the Royal Navy as an officer trainee.", + "source": { + "publisher": "The Royal Family", + "url": "https://www.royal.uk/the-duke-of-york", + "independent_of_birth_source": true + } + }, + { + "id": "andrew_marriage_1986", + "domain": "relationship", + "date": "1986-07-23", + "precision": "day", + "description": "Married Sarah Ferguson.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Prince-Andrew-duke-of-York", + "independent_of_birth_source": true + } + }, + { + "id": "andrew_divorce_1996", + "domain": "relationship", + "date": "1996-05-30", + "precision": "day", + "description": "Divorce from Sarah Ferguson became final.", + "source": { + "publisher": "The Royal Family", + "url": "https://www.royal.uk/duke-york", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "sean_lennon_1975_aa_v4_holdout", + "subject_label": "Sean Lennon", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1975-10-09", + "time": "02:00", + "place": "Manhattan, New York, United States", + "latitude": 40.7667, + "longitude": -73.9833, + "timezone_offset": -4.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Lennon%2C_Sean", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "lennon_father_death_1980", + "domain": "health_pressure", + "date": "1980-12-08", + "precision": "day", + "description": "His father John Lennon was murdered.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/John-Lennon", + "independent_of_birth_source": true + } + }, + { + "id": "lennon_into_sun_1998", + "domain": "career", + "date": "1998-05-19", + "precision": "day", + "description": "Released his debut album Into the Sun.", + "source": { + "publisher": "AllMusic", + "url": "https://www.allmusic.com/album/into-the-sun-mw0000036772", + "independent_of_birth_source": true + } + }, + { + "id": "lennon_friendly_fire_2006", + "domain": "career", + "date": "2006-09-26", + "precision": "day", + "description": "Released the album Friendly Fire.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Friendly_Fire_(Sean_Lennon_album)", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout", + "subject_label": "Joseph Kennedy III", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1980-10-04", + "time": "21:42", + "place": "Boston, Massachusetts, United States", + "latitude": 42.3667, + "longitude": -71.0667, + "timezone_offset": -4.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Kennedy%2C_Joseph_Patrick_III", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "kennedy_stanford_2003", + "domain": "education", + "date": "2003", + "precision": "year", + "description": "Graduated from Stanford University.", + "source": { + "publisher": "United States Congress", + "url": "https://bioguide.congress.gov/search/bio/K000379", + "independent_of_birth_source": true + } + }, + { + "id": "kennedy_elected_house_2012", + "domain": "career", + "date": "2012-11-06", + "precision": "day", + "description": "Was elected to the United States House of Representatives.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/2012_United_States_House_of_Representatives_elections_in_Massachusetts", + "independent_of_birth_source": true + } + }, + { + "id": "kennedy_marriage_2012", + "domain": "relationship", + "date": "2012-12-01", + "precision": "day", + "description": "Married Lauren Birchfield.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Joe_Kennedy_III", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "kurt_cobain_1967_aa_v4_holdout", + "subject_label": "Kurt Cobain", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1967-02-20", + "time": "19:38", + "place": "Aberdeen, Washington, United States", + "latitude": 46.9833, + "longitude": -123.8167, + "timezone_offset": -8.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Cobain%2C_Kurt", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "cobain_nevermind_1991", + "domain": "career", + "date": "1991-09-24", + "precision": "day", + "description": "Nirvana released Nevermind.", + "source": { + "publisher": "Rock and Roll Hall of Fame", + "url": "https://www.rockhall.com/inductees/nirvana", + "independent_of_birth_source": true + } + }, + { + "id": "cobain_marriage_1992", + "domain": "relationship", + "date": "1992-02-24", + "precision": "day", + "description": "Married Courtney Love.", + "source": { + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Kurt-Cobain", + "independent_of_birth_source": true + } + }, + { + "id": "cobain_overdose_1994", + "domain": "health_pressure", + "date": "1994-03-04", + "precision": "day", + "description": "Was hospitalized after an overdose in Rome.", + "source": { + "publisher": "The Seattle Times", + "url": "https://www.seattletimes.com/entertainment/music/kurt-cobain-a-timeline-of-his-life/", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "john_robbins_1947_aa_v4_holdout", + "subject_label": "John Robbins", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1947-10-26", + "time": "02:56", + "place": "Glendale, California, United States", + "latitude": 34.15, + "longitude": -118.25, + "timezone_offset": -8.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Robbins%2C_John", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "robbins_marriage_1968", + "domain": "relationship", + "date": "1967-03-10", + "precision": "day", + "submitted_date": "1968", + "verified_date": "1967-03-10", + "source_audit_note": "Blind working date remains submitted 1968. Verified 1967-03-10 from Wikipedia; original johnrobbins.info/about/ has no marriage date.", + "description": "Married Deo Robbins.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/John_Robbins_(author)", + "independent_of_birth_source": true + } + }, + { + "id": "robbins_diet_book_1987", + "domain": "career", + "date": "1987", + "precision": "year", + "description": "Published Diet for a New America.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/John_Robbins_(author)", + "independent_of_birth_source": true + } + }, + { + "id": "robbins_health_book_1996", + "domain": "career", + "date": "1996", + "precision": "year", + "description": "Published Reclaiming Our Health.", + "source": { + "publisher": "John Robbins", + "url": "https://www.johnrobbins.info/books/", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "chad_everett_1937_aa_v4_holdout", + "subject_label": "Chad Everett", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1937-06-11", + "time": "22:20", + "place": "South Bend, Indiana, United States", + "latitude": 41.6833, + "longitude": -86.25, + "timezone_offset": -5.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Everett%2C_Chad", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "everett_marriage_1966", + "domain": "relationship", + "date": "1966-05-22", + "precision": "day", + "description": "Married actress Shelby Grant.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Chad_Everett", + "independent_of_birth_source": true + } + }, + { + "id": "everett_medical_center_1969", + "domain": "career", + "date": "1969", + "precision": "year", + "description": "Began starring in Medical Center.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Medical_Center_(TV_series)", + "independent_of_birth_source": true + } + }, + { + "id": "everett_lung_cancer_2012", + "domain": "health_pressure", + "date": "2012", + "precision": "year", + "description": "Died after a battle with lung cancer.", + "source": { + "publisher": "The New York Times", + "url": "https://www.nytimes.com/2012/07/26/arts/television/chad-everett-medical-center-star-dies-at-75.html", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "bernd_eichinger_1949_aa_v4_holdout", + "subject_label": "Bernd Eichinger", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1949-04-11", + "time": "13:15", + "place": "Neuburg an der Donau, Germany", + "latitude": 48.7333, + "longitude": 11.1833, + "timezone_offset": 2.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Eichinger%2C_Bernd", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "eichinger_constantin_1979", + "domain": "career", + "date": "1979", + "precision": "year", + "description": "Bought a stake in Neue Constantin Film and became executive director.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Constantin_Film", + "independent_of_birth_source": true + } + }, + { + "id": "eichinger_summit_1991", + "domain": "career", + "date": "1991", + "precision": "year", + "description": "Co-founded Summit Entertainment.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Summit_Entertainment", + "independent_of_birth_source": true + } + }, + { + "id": "eichinger_marriage_2006", + "domain": "relationship", + "date": "2006", + "precision": "year", + "description": "Married Katja Hofmann.", + "source": { + "publisher": "Reuters", + "url": "https://www.reuters.com/article/us-berndeichinger/film-producer-bernd-eichinger-dies-at-61-idUSTRE70O6BJ20110125", + "independent_of_birth_source": true + } + } + ] + }, + { + "case_id": "iwao_takamoto_1925_aa_v4_holdout", + "subject_label": "Iwao Takamoto", + "holdout_partition": "sealed_evaluation", + "excluded_from_tuning": true, + "candidate_radius_minutes": 10, + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "birth": { + "date": "1925-04-29", + "time": "20:00", + "place": "Los Angeles, California, United States", + "latitude": 34.05, + "longitude": -118.25, + "timezone_offset": -8.0, + "source": { + "publisher": "Astro-Databank", + "url": "https://www.astro.com/astro-databank/Takamoto%2C_Iwao", + "rodden_rating": "AA", + "record_type": "birth_record" + } + }, + "events": [ + { + "id": "takamoto_joined_disney_1947", + "domain": "career", + "date": "1945", + "precision": "year", + "submitted_date": "1947", + "verified_date": "1945", + "source_audit_note": "Blind working date remains submitted 1947. Cited Wikipedia states hired by Walt Disney Productions in 1945; URL kept.", + "description": "Joined Walt Disney Animation Studios.", + "source": { + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Iwao_Takamoto", + "independent_of_birth_source": true + } + }, + { + "id": "takamoto_hanna_barbera_1961", + "domain": "career", + "date": "1961", + "precision": "year", + "description": "Moved to Hanna-Barbera and began designing its characters.", + "source": { + "publisher": "Animation Magazine", + "url": "https://www.animationmagazine.net/2007/01/animation-legend-iwao-takamoto-dies/", + "independent_of_birth_source": true + } + }, + { + "id": "takamoto_heart_attack_2007", + "domain": "health_pressure", + "date": "2007-01-08", + "precision": "day", + "description": "Died following a heart attack.", + "source": { + "publisher": "The New York Times", + "url": "https://www.nytimes.com/2007/01/10/arts/10takamoto.html", + "independent_of_birth_source": true + } + } + ] + } + ], + "boundary": "This sealed set was invalidated by post-replay source-content audit and may only be used as development evidence. A future release replay requires a new scorer version and a fresh source-audited sealed evaluation set.", + "evaluation_kind": "post_audit_diagnostic_rerun", + "is_blind_evaluation": false, + "must_not_claim_release_gate_passed": true, + "must_not_use_for_tuning": true, + "verified_minute_claim_allowed": false, + "implementation_hash_note": "Keeps the v3 frozen implementation_sha256. Official eval will report implementation_hash_matches=false because current staging scoring files drifted after the 2026-07-21 replay. This diagnostic does not retune or rewrite that freeze.", + "historical_blind_dataset": "references/real_case_calibration/minute_rectification_holdout_v3.json", + "historical_blind_report": "references/real_case_calibration/minute_rectification_holdout_v3_report.json" +} diff --git a/references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic_report.json b/references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic_report.json new file mode 100644 index 00000000..39046e97 --- /dev/null +++ b/references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic_report.json @@ -0,0 +1,1534 @@ +{ + "scope": "minute_rectification_fact_ranker_v4_post_audit_diagnostic_rerun", + "benchmark_id": "minute_rectification_fact_ranker_v4_holdout_v3_post_audit_diagnostic", + "status": "blocked", + "validation": { + "scope": "minute_rectification_holdout_validation", + "benchmark_id": "minute_rectification_fact_ranker_v4_holdout_v3_post_audit_diagnostic", + "status": "blocked_awaiting_public_aa_cases", + "valid_public_aa_cases": 20, + "minimum_public_aa_cases": 20, + "manifest_errors": [ + "source_content_audit_not_passed_before_freeze" + ], + "invalid_cases": [], + "invalid_case_details": [], + "verified_minute_claim_allowed": false, + "boundary": "This sealed set was invalidated by post-replay source-content audit and may only be used as development evidence. A future release replay requires a new scorer version and a fresh source-audited sealed evaluation set." + }, + "frozen_scoring": { + "algorithm_matches": true, + "implementation_hash_matches": false, + "expected_sha256": "f41c298dd6cdcebe7a93e632f7191954be7987f6012ca2a34cecb6e447fbf196", + "actual_sha256": "99730c84c6434f52669a05e4d9a4a87df0a218e3237b5436b933252f2028384e" + }, + "trial_count": 0, + "trials": [], + "metrics": { + "top_1_rate": null, + "top_3_rate": null, + "mean_absolute_minute_error": null, + "false_confirmation_rate": null, + "correct_insufficient_evidence_rejection_rate": null, + "confirmation_coverage_rate": null + }, + "metric_gates_passed": false, + "verified_minute_claim_allowed": false, + "boundary": "This is a post-audit diagnostic rerun, not a blind evaluation. Results have been seen. Must not be used to claim the release gate passed. Must not be used for tuning.", + "evaluation_kind": "post_audit_diagnostic_rerun", + "is_blind_evaluation": false, + "must_not_claim_release_gate_passed": true, + "must_not_use_for_tuning": true, + "historical_blind_dataset": "references/real_case_calibration/minute_rectification_holdout_v3.json", + "historical_blind_report": "references/real_case_calibration/minute_rectification_holdout_v3_report.json", + "trials_skipped_reason": "Official eval runner skipped trials because implementation_sha256 does not match the v3 freeze. This worktree did not modify frozen_scoring.files. Current staging scorer drifted after the 2026-07-21 v3 replay.", + "current_tree_unfrozen_diagnostic": { + "note": "Sidecar trials used the current worktree scorer. They are not the v3 frozen identity, not blind, not a release gate, and not for tuning.", + "implementation_hash_matches": false, + "expected_v3_sha256": "f41c298dd6cdcebe7a93e632f7191954be7987f6012ca2a34cecb6e447fbf196", + "actual_sha256": "99730c84c6434f52669a05e4d9a4a87df0a218e3237b5436b933252f2028384e", + "trial_count": 20, + "trials": [ + { + "case_id": "barack_obama_1961_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "19:14", + "true_rank": 5, + "minute_error": 10, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "19:14", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 1, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 2, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 2, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 5, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "obama_wedding_1992_v4", + "winning_segment": { + "start_time": "19:17", + "end_time": "19:29", + "representative_time": "19:23", + "width_minutes": 13 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "obama_illinois_senate_1996_v4", + "winning_segment": { + "start_time": "19:17", + "end_time": "19:19", + "representative_time": "19:18", + "width_minutes": 3 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "obama_presidential_election_2008_v4", + "winning_segment": { + "start_time": "19:14", + "end_time": "19:14", + "representative_time": "19:14", + "width_minutes": 1 + }, + "original_unique_leader_retained": true + } + ] + } + }, + { + "case_id": "angelina_jolie_1975_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "09:12", + "true_rank": 2, + "minute_error": 3, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "09:12", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "pass", + "lead_points": 17.5, + "compared_candidate_count": 2, + "reason": "unique_minute_leads_neighbor_candidates" + }, + { + "radius_minutes": 2, + "status": "pass", + "lead_points": 17.5, + "compared_candidate_count": 4, + "reason": "unique_minute_leads_neighbor_candidates" + }, + { + "radius_minutes": 5, + "status": "pass", + "lead_points": 17.5, + "compared_candidate_count": 10, + "reason": "unique_minute_leads_neighbor_candidates" + } + ], + "all_required_passed": true, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "jolie_oscar_2000", + "winning_segment": { + "start_time": "09:12", + "end_time": "09:12", + "representative_time": "09:12", + "width_minutes": 1 + }, + "original_unique_leader_retained": true + }, + { + "removed_event_id": "jolie_mastectomy_2013", + "winning_segment": { + "start_time": "09:06", + "end_time": "09:12", + "representative_time": "09:09", + "width_minutes": 7 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "jolie_marriage_2014", + "winning_segment": { + "start_time": "09:12", + "end_time": "09:19", + "representative_time": "09:15", + "width_minutes": 8 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "tiger_woods_1975_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "22:41", + "true_rank": 1, + "minute_error": 9, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "22:50", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "woods_turned_professional_1996", + "winning_segment": { + "start_time": "22:40", + "end_time": "23:00", + "representative_time": "22:50", + "width_minutes": 21 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "woods_marriage_2004", + "winning_segment": { + "start_time": "22:40", + "end_time": "23:00", + "representative_time": "22:50", + "width_minutes": 21 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "woods_car_crash_2021", + "winning_segment": { + "start_time": "22:40", + "end_time": "23:00", + "representative_time": "22:50", + "width_minutes": 21 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "elizabeth_taylor_1932_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "02:30", + "true_rank": 1, + "minute_error": 0, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "02:30", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "pass", + "lead_points": 17.5, + "compared_candidate_count": 2, + "reason": "unique_minute_leads_neighbor_candidates" + }, + { + "radius_minutes": 2, + "status": "pass", + "lead_points": 17.5, + "compared_candidate_count": 4, + "reason": "unique_minute_leads_neighbor_candidates" + }, + { + "radius_minutes": 5, + "status": "pass", + "lead_points": 17.5, + "compared_candidate_count": 10, + "reason": "unique_minute_leads_neighbor_candidates" + } + ], + "all_required_passed": true, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "taylor_first_marriage_1950", + "winning_segment": { + "start_time": "02:30", + "end_time": "02:40", + "representative_time": "02:35", + "width_minutes": 11 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "taylor_oscar_1961", + "winning_segment": { + "start_time": "02:30", + "end_time": "02:30", + "representative_time": "02:30", + "width_minutes": 1 + }, + "original_unique_leader_retained": true + }, + { + "removed_event_id": "taylor_brain_surgery_1997", + "winning_segment": { + "start_time": "02:26", + "end_time": "02:30", + "representative_time": "02:28", + "width_minutes": 5 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "elizabeth_montgomery_1933_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "16:41", + "true_rank": 1, + "minute_error": 3, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "16:41", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "montgomery_marriage_asher_1963", + "winning_segment": { + "start_time": "16:37", + "end_time": "16:46", + "representative_time": "16:41", + "width_minutes": 10 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "montgomery_bewitched_1964", + "winning_segment": { + "start_time": "16:28", + "end_time": "16:28", + "representative_time": "16:28", + "width_minutes": 1 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "montgomery_cancer_1995", + "winning_segment": { + "start_time": "16:28", + "end_time": "16:28", + "representative_time": "16:28", + "width_minutes": 1 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "pablo_picasso_1881_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "23:09", + "true_rank": 7, + "minute_error": 6, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "23:08", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 8, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "picasso_moved_paris_1904", + "winning_segment": { + "start_time": "23:08", + "end_time": "23:09", + "representative_time": "23:08", + "width_minutes": 2 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "picasso_marriage_1918", + "winning_segment": { + "start_time": "23:05", + "end_time": "23:09", + "representative_time": "23:07", + "width_minutes": 5 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "picasso_guernica_1937", + "winning_segment": { + "start_time": "23:20", + "end_time": "23:20", + "representative_time": "23:20", + "width_minutes": 1 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "sigmund_freud_1856_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "18:40", + "true_rank": 5, + "minute_error": 10, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "18:38", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 7, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "freud_marriage_1886", + "winning_segment": { + "start_time": "18:37", + "end_time": "18:40", + "representative_time": "18:38", + "width_minutes": 4 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "freud_dreams_publication_1899", + "winning_segment": { + "start_time": "18:28", + "end_time": "18:31", + "representative_time": "18:29", + "width_minutes": 4 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "freud_moved_london_1938", + "winning_segment": { + "start_time": "18:37", + "end_time": "18:40", + "representative_time": "18:38", + "width_minutes": 4 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "salma_hayek_1966_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "06:30", + "true_rank": 5, + "minute_error": 10, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "06:30", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 1, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 2, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 2, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 5, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "hayek_moved_los_angeles_1991", + "winning_segment": { + "start_time": "06:30", + "end_time": "06:30", + "representative_time": "06:30", + "width_minutes": 1 + }, + "original_unique_leader_retained": true + }, + { + "removed_event_id": "hayek_frida_2002", + "winning_segment": { + "start_time": "06:30", + "end_time": "06:30", + "representative_time": "06:30", + "width_minutes": 1 + }, + "original_unique_leader_retained": true + }, + { + "removed_event_id": "hayek_marriage_2009", + "winning_segment": { + "start_time": "06:44", + "end_time": "06:46", + "representative_time": "06:45", + "width_minutes": 3 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "steve_reich_1936_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "18:22", + "true_rank": 1, + "minute_error": 1, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "18:22", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "reich_cornell_degree_1957", + "winning_segment": { + "start_time": "18:19", + "end_time": "18:26", + "representative_time": "18:22", + "width_minutes": 8 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "reich_moved_california_1963", + "winning_segment": { + "start_time": "18:19", + "end_time": "18:26", + "representative_time": "18:22", + "width_minutes": 8 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "reich_music_18_premiere_1976", + "winning_segment": { + "start_time": "18:11", + "end_time": "18:31", + "representative_time": "18:21", + "width_minutes": 21 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "albert_brooks_1947_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "02:59", + "true_rank": 1, + "minute_error": 1, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "02:59", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "brooks_real_life_1979", + "winning_segment": { + "start_time": "02:55", + "end_time": "03:03", + "representative_time": "02:59", + "width_minutes": 9 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "brooks_oscar_nomination_1988", + "winning_segment": { + "start_time": "02:55", + "end_time": "03:03", + "representative_time": "02:59", + "width_minutes": 9 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "brooks_marriage_1997", + "winning_segment": { + "start_time": "02:51", + "end_time": "03:03", + "representative_time": "02:57", + "width_minutes": 13 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "paul_ryan_1970_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "02:43", + "true_rank": 6, + "minute_error": 6, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "02:41", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "ryan_elected_house_1998", + "winning_segment": { + "start_time": "02:39", + "end_time": "02:45", + "representative_time": "02:42", + "width_minutes": 7 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "ryan_marriage_2000", + "winning_segment": { + "start_time": "02:39", + "end_time": "02:43", + "representative_time": "02:41", + "width_minutes": 5 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "ryan_speaker_2015", + "winning_segment": { + "start_time": "02:27", + "end_time": "02:43", + "representative_time": "02:35", + "width_minutes": 17 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "tom_kennedy_1927_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "17:30", + "true_rank": 1, + "minute_error": 5, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "17:27", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "kennedy_marriage_1952", + "winning_segment": { + "start_time": "17:24", + "end_time": "17:35", + "representative_time": "17:29", + "width_minutes": 12 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "kennedy_big_game_1958", + "winning_segment": { + "start_time": "17:24", + "end_time": "17:31", + "representative_time": "17:27", + "width_minutes": 8 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "kennedy_name_that_tune_1974", + "winning_segment": { + "start_time": "17:24", + "end_time": "17:31", + "representative_time": "17:27", + "width_minutes": 8 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "andrew_windsor_1960_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "15:21", + "true_rank": 5, + "minute_error": 9, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": null, + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 0, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 2, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 0, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 0, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "andrew_royal_navy_1979", + "winning_segment": null, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "andrew_marriage_1986", + "winning_segment": null, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "andrew_divorce_1996", + "winning_segment": { + "start_time": "15:20", + "end_time": "15:34", + "representative_time": "15:27", + "width_minutes": 15 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "sean_lennon_1975_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "02:10", + "true_rank": 17, + "minute_error": 10, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "02:10", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 1, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 2, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 2, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 5, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "lennon_father_death_1980", + "winning_segment": { + "start_time": "02:04", + "end_time": "02:10", + "representative_time": "02:07", + "width_minutes": 7 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "lennon_into_sun_1998", + "winning_segment": { + "start_time": "02:10", + "end_time": "02:10", + "representative_time": "02:10", + "width_minutes": 1 + }, + "original_unique_leader_retained": true + }, + { + "removed_event_id": "lennon_friendly_fire_2006", + "winning_segment": { + "start_time": "02:10", + "end_time": "02:10", + "representative_time": "02:10", + "width_minutes": 1 + }, + "original_unique_leader_retained": true + } + ] + } + }, + { + "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "21:39", + "true_rank": 1, + "minute_error": 3, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "21:37", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "kennedy_stanford_2003", + "winning_segment": { + "start_time": "21:32", + "end_time": "21:42", + "representative_time": "21:37", + "width_minutes": 11 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "kennedy_elected_house_2012", + "winning_segment": { + "start_time": "21:46", + "end_time": "21:52", + "representative_time": "21:49", + "width_minutes": 7 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "kennedy_marriage_2012", + "winning_segment": { + "start_time": "21:32", + "end_time": "21:42", + "representative_time": "21:37", + "width_minutes": 11 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "kurt_cobain_1967_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "19:29", + "true_rank": 12, + "minute_error": 9, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "19:29", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 3, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 6, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "cobain_nevermind_1991", + "winning_segment": { + "start_time": "19:28", + "end_time": "19:30", + "representative_time": "19:29", + "width_minutes": 3 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "cobain_marriage_1992", + "winning_segment": { + "start_time": "19:28", + "end_time": "19:30", + "representative_time": "19:29", + "width_minutes": 3 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "cobain_overdose_1994", + "winning_segment": { + "start_time": "19:28", + "end_time": "19:30", + "representative_time": "19:29", + "width_minutes": 3 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "john_robbins_1947_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "02:46", + "true_rank": 6, + "minute_error": 10, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "02:48", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 7, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "robbins_marriage_1968", + "winning_segment": { + "start_time": "03:06", + "end_time": "03:06", + "representative_time": "03:06", + "width_minutes": 1 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "robbins_diet_book_1987", + "winning_segment": { + "start_time": "02:46", + "end_time": "02:57", + "representative_time": "02:51", + "width_minutes": 12 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "robbins_health_book_1996", + "winning_segment": { + "start_time": "03:06", + "end_time": "03:06", + "representative_time": "03:06", + "width_minutes": 1 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "chad_everett_1937_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "22:10", + "true_rank": 11, + "minute_error": 10, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "22:10", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 1, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 2, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 2, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + }, + { + "radius_minutes": 5, + "status": "blocked", + "lead_points": null, + "compared_candidate_count": 5, + "reason": "candidate_range_does_not_cover_both_sides_of_neighborhood" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "everett_marriage_1966", + "winning_segment": { + "start_time": "22:23", + "end_time": "22:29", + "representative_time": "22:26", + "width_minutes": 7 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "everett_medical_center_1969", + "winning_segment": { + "start_time": "22:10", + "end_time": "22:10", + "representative_time": "22:10", + "width_minutes": 1 + }, + "original_unique_leader_retained": true + }, + { + "removed_event_id": "everett_lung_cancer_2012", + "winning_segment": { + "start_time": "22:23", + "end_time": "22:29", + "representative_time": "22:26", + "width_minutes": 7 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "bernd_eichinger_1949_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "13:15", + "true_rank": 1, + "minute_error": 0, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "13:17", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "eichinger_constantin_1979", + "winning_segment": { + "start_time": "13:14", + "end_time": "13:25", + "representative_time": "13:19", + "width_minutes": 12 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "eichinger_summit_1991", + "winning_segment": { + "start_time": "13:14", + "end_time": "13:20", + "representative_time": "13:17", + "width_minutes": 7 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "eichinger_marriage_2006", + "winning_segment": { + "start_time": "13:05", + "end_time": "13:20", + "representative_time": "13:12", + "width_minutes": 16 + }, + "original_unique_leader_retained": false + } + ] + } + }, + { + "case_id": "iwao_takamoto_1925_aa_v4_holdout", + "candidate_count": 21, + "predicted_time": "19:59", + "true_rank": 1, + "minute_error": 1, + "would_confirm": false, + "false_confirmation": false, + "insufficient_evidence_rejected": true, + "neighbor_stability": { + "scope": "candidate_neighbor_stability", + "representative_time": "20:00", + "neighborhoods": [ + { + "radius_minutes": 1, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 2, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 2, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 4, + "reason": "minute_not_uniquely_separated_from_neighbors" + }, + { + "radius_minutes": 5, + "status": "fail", + "lead_points": 0.0, + "compared_candidate_count": 10, + "reason": "minute_not_uniquely_separated_from_neighbors" + } + ], + "all_required_passed": false, + "boundary": "Neighbor separation is a diagnostic only until thresholds are frozen before public holdout replay." + }, + "leave_one_event_out": { + "status": "fail", + "runs": [ + { + "removed_event_id": "takamoto_joined_disney_1947", + "winning_segment": { + "start_time": "19:50", + "end_time": "20:10", + "representative_time": "20:00", + "width_minutes": 21 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "takamoto_hanna_barbera_1961", + "winning_segment": { + "start_time": "19:50", + "end_time": "20:10", + "representative_time": "20:00", + "width_minutes": 21 + }, + "original_unique_leader_retained": false + }, + { + "removed_event_id": "takamoto_heart_attack_2007", + "winning_segment": { + "start_time": "19:50", + "end_time": "20:10", + "representative_time": "20:00", + "width_minutes": 21 + }, + "original_unique_leader_retained": false + } + ] + } + } + ], + "metrics": { + "top_1_rate": 0.45, + "top_3_rate": 0.5, + "mean_absolute_minute_error": 5.8, + "false_confirmation_rate": 0.0, + "correct_insufficient_evidence_rejection_rate": 1.0, + "confirmation_coverage_rate": 0.0 + }, + "metric_gates_passed": false, + "verified_minute_claim_allowed": false + } +} diff --git a/references/real_case_calibration/minute_rectification_holdout_v4_intake.json b/references/real_case_calibration/minute_rectification_holdout_v4_intake.json index 0de46d91..e02c3cc0 100644 --- a/references/real_case_calibration/minute_rectification_holdout_v4_intake.json +++ b/references/real_case_calibration/minute_rectification_holdout_v4_intake.json @@ -1,16 +1,449 @@ { - "schema_version": "minute-rectification-holdout-v4-intake", - "status": "collecting_independently_reviewed_cases", + "boundary": "This intake queue is not a frozen holdout. Promotion requires a new version, a passed source audit and a scoring identity frozen before blind replay.", + "cases": [ + { + "adjudicator": "v3_sealed_set_post_audit_migration", + "birth": { + "date": "1961-08-04", + "latitude": 21.3069, + "longitude": -157.8583, + "place": "Honolulu, Hawaii, United States", + "source": { + "publisher": "Astro-Databank", + "record_type": "birth_record", + "rodden_rating": "AA", + "url": "https://www.astro.com/adbvip/adbvip_08_04.htm?lang=r&nho2=161&nhor=1" + }, + "time": "19:24", + "timezone_offset": -10.0 + }, + "candidate_radius_minutes": 10, + "case_id": "barack_obama_1961_aa_v4_holdout", + "events": [ + { + "date": "1992-10-03", + "description": "Married Michelle Robinson.", + "domain": "relationship", + "id": "obama_wedding_1992_v4", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "Obama Foundation", + "url": "https://obama.org/about/administration/chicago-where-it-began/" + } + }, + { + "date": "1996-11-05", + "description": "Elected to the Illinois State Senate.", + "domain": "career", + "id": "obama_illinois_senate_1996_v4", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Illinois_Senate_career_of_Barack_Obama" + } + }, + { + "date": "2008-11-04", + "description": "Elected President of the United States.", + "domain": "career", + "id": "obama_presidential_election_2008_v4", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "White House Archives", + "url": "https://obamawhitehouse.archives.gov/1600/presidents/barackobama/" + } + } + ], + "excluded_from_tuning": true, + "false_minute_commitments": [ + { + "commitment_hash": "557feee24f6fdfc80f64082695026f9f8b69c44d84ca77b0ba380a27a19f8db0", + "offset_minutes": -10 + }, + { + "commitment_hash": "22a3140ec461b71aad9a02ca07a642293908be11066b125feeeed00e9d336fee", + "offset_minutes": -5 + }, + { + "commitment_hash": "e6a63445423e4f20e25aff4422a6c2e2171e8b5b1f817b7c942a6d45ac93ad42", + "offset_minutes": -2 + }, + { + "commitment_hash": "2ca091c950d96413e45c35524031356dd2387b85a3444386c5b1c9562c884d6e", + "offset_minutes": -1 + }, + { + "commitment_hash": "0d4cf78bcd4d3b9e7ba2385d1c13978ab1a634b299711bd4c0b899cad18a4067", + "offset_minutes": 1 + }, + { + "commitment_hash": "30242701a0c8d92f807da66e7fb53ca894dea6e36e354f406c74f444d8fbecb8", + "offset_minutes": 2 + }, + { + "commitment_hash": "7267b8aaf5c73b49953b946fba31ca1fb5ea707720e65ca030ba4327eda3c4fe", + "offset_minutes": 5 + }, + { + "commitment_hash": "b1d28e8285438f26532f5bfd2447df34eddbe24e26d53d7d4069b87d1420704c", + "offset_minutes": 10 + } + ], + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "frozen_before_scoring": true, + "holdout_partition": "sealed_evaluation", + "independent_human_reviewed": true, + "ingested_at": "2026-08-28T16:29:41.362489Z", + "review_attestation": "Attests the v3 sealed-set review already recorded for this public AA case; not a new biography audit.", + "subject_label": "Barack Obama" + }, + { + "adjudicator": "v3_sealed_set_post_audit_migration", + "birth": { + "date": "1970-01-29", + "latitude": 42.6833, + "longitude": -89.0167, + "place": "Janesville, Wisconsin, United States", + "source": { + "publisher": "Astro-Databank", + "record_type": "birth_record", + "rodden_rating": "AA", + "url": "https://www.astro.com/astro-databank/Ryan%2C_Paul" + }, + "time": "02:37", + "timezone_offset": -6.0 + }, + "candidate_radius_minutes": 10, + "case_id": "paul_ryan_1970_aa_v4_holdout", + "events": [ + { + "date": "1998-11-03", + "description": "Was elected to the United States House of Representatives.", + "domain": "career", + "id": "ryan_elected_house_1998", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "United States House of Representatives", + "url": "https://history.house.gov/People/Detail/20147" + } + }, + { + "date": "2000-12-02", + "description": "Married Janna Little.", + "domain": "relationship", + "id": "ryan_marriage_2000", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Paul-Ryan" + } + }, + { + "date": "2015-10-29", + "description": "Was elected Speaker of the House.", + "domain": "career", + "id": "ryan_speaker_2015", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/October_2015_Speaker_of_the_United_States_House_of_Representatives_election" + } + } + ], + "excluded_from_tuning": true, + "false_minute_commitments": [ + { + "commitment_hash": "557feee24f6fdfc80f64082695026f9f8b69c44d84ca77b0ba380a27a19f8db0", + "offset_minutes": -10 + }, + { + "commitment_hash": "22a3140ec461b71aad9a02ca07a642293908be11066b125feeeed00e9d336fee", + "offset_minutes": -5 + }, + { + "commitment_hash": "e6a63445423e4f20e25aff4422a6c2e2171e8b5b1f817b7c942a6d45ac93ad42", + "offset_minutes": -2 + }, + { + "commitment_hash": "2ca091c950d96413e45c35524031356dd2387b85a3444386c5b1c9562c884d6e", + "offset_minutes": -1 + }, + { + "commitment_hash": "0d4cf78bcd4d3b9e7ba2385d1c13978ab1a634b299711bd4c0b899cad18a4067", + "offset_minutes": 1 + }, + { + "commitment_hash": "30242701a0c8d92f807da66e7fb53ca894dea6e36e354f406c74f444d8fbecb8", + "offset_minutes": 2 + }, + { + "commitment_hash": "7267b8aaf5c73b49953b946fba31ca1fb5ea707720e65ca030ba4327eda3c4fe", + "offset_minutes": 5 + }, + { + "commitment_hash": "b1d28e8285438f26532f5bfd2447df34eddbe24e26d53d7d4069b87d1420704c", + "offset_minutes": 10 + } + ], + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "frozen_before_scoring": true, + "holdout_partition": "sealed_evaluation", + "independent_human_reviewed": true, + "ingested_at": "2026-08-28T16:29:41.658178Z", + "review_attestation": "Attests the v3 sealed-set review already recorded for this public AA case; not a new biography audit.", + "subject_label": "Paul Ryan" + }, + { + "adjudicator": "v3_sealed_set_post_audit_migration", + "birth": { + "date": "1975-10-09", + "latitude": 40.7667, + "longitude": -73.9833, + "place": "Manhattan, New York, United States", + "source": { + "publisher": "Astro-Databank", + "record_type": "birth_record", + "rodden_rating": "AA", + "url": "https://www.astro.com/astro-databank/Lennon%2C_Sean" + }, + "time": "02:00", + "timezone_offset": -4.0 + }, + "candidate_radius_minutes": 10, + "case_id": "sean_lennon_1975_aa_v4_holdout", + "events": [ + { + "date": "1980-12-08", + "description": "His father John Lennon was murdered.", + "domain": "health_pressure", + "id": "lennon_father_death_1980", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/John-Lennon" + } + }, + { + "date": "1998-05-19", + "description": "Released his debut album Into the Sun.", + "domain": "career", + "id": "lennon_into_sun_1998", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "AllMusic", + "url": "https://www.allmusic.com/album/into-the-sun-mw0000036772" + } + }, + { + "date": "2006-09-26", + "description": "Released the album Friendly Fire.", + "domain": "career", + "id": "lennon_friendly_fire_2006", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "Wikipedia", + "url": "https://en.wikipedia.org/wiki/Friendly_Fire_(Sean_Lennon_album)" + } + } + ], + "excluded_from_tuning": true, + "false_minute_commitments": [ + { + "commitment_hash": "557feee24f6fdfc80f64082695026f9f8b69c44d84ca77b0ba380a27a19f8db0", + "offset_minutes": -10 + }, + { + "commitment_hash": "22a3140ec461b71aad9a02ca07a642293908be11066b125feeeed00e9d336fee", + "offset_minutes": -5 + }, + { + "commitment_hash": "e6a63445423e4f20e25aff4422a6c2e2171e8b5b1f817b7c942a6d45ac93ad42", + "offset_minutes": -2 + }, + { + "commitment_hash": "2ca091c950d96413e45c35524031356dd2387b85a3444386c5b1c9562c884d6e", + "offset_minutes": -1 + }, + { + "commitment_hash": "0d4cf78bcd4d3b9e7ba2385d1c13978ab1a634b299711bd4c0b899cad18a4067", + "offset_minutes": 1 + }, + { + "commitment_hash": "30242701a0c8d92f807da66e7fb53ca894dea6e36e354f406c74f444d8fbecb8", + "offset_minutes": 2 + }, + { + "commitment_hash": "7267b8aaf5c73b49953b946fba31ca1fb5ea707720e65ca030ba4327eda3c4fe", + "offset_minutes": 5 + }, + { + "commitment_hash": "b1d28e8285438f26532f5bfd2447df34eddbe24e26d53d7d4069b87d1420704c", + "offset_minutes": 10 + } + ], + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "frozen_before_scoring": true, + "holdout_partition": "sealed_evaluation", + "independent_human_reviewed": true, + "ingested_at": "2026-08-28T16:29:41.829087Z", + "review_attestation": "Attests the v3 sealed-set review already recorded for this public AA case; not a new biography audit.", + "subject_label": "Sean Lennon" + }, + { + "adjudicator": "v3_sealed_set_post_audit_migration", + "birth": { + "date": "1967-02-20", + "latitude": 46.9833, + "longitude": -123.8167, + "place": "Aberdeen, Washington, United States", + "source": { + "publisher": "Astro-Databank", + "record_type": "birth_record", + "rodden_rating": "AA", + "url": "https://www.astro.com/astro-databank/Cobain%2C_Kurt" + }, + "time": "19:38", + "timezone_offset": -8.0 + }, + "candidate_radius_minutes": 10, + "case_id": "kurt_cobain_1967_aa_v4_holdout", + "events": [ + { + "date": "1991-09-24", + "description": "Nirvana released Nevermind.", + "domain": "career", + "id": "cobain_nevermind_1991", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "Rock and Roll Hall of Fame", + "url": "https://www.rockhall.com/inductees/nirvana" + } + }, + { + "date": "1992-02-24", + "description": "Married Courtney Love.", + "domain": "relationship", + "id": "cobain_marriage_1992", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "Encyclopaedia Britannica", + "url": "https://www.britannica.com/biography/Kurt-Cobain" + } + }, + { + "date": "1994-03-04", + "description": "Was hospitalized after an overdose in Rome.", + "domain": "health_pressure", + "id": "cobain_overdose_1994", + "precision": "day", + "source": { + "independent_of_birth_source": true, + "publisher": "The Seattle Times", + "url": "https://www.seattletimes.com/entertainment/music/kurt-cobain-a-timeline-of-his-life/" + } + } + ], + "excluded_from_tuning": true, + "false_minute_commitments": [ + { + "commitment_hash": "557feee24f6fdfc80f64082695026f9f8b69c44d84ca77b0ba380a27a19f8db0", + "offset_minutes": -10 + }, + { + "commitment_hash": "22a3140ec461b71aad9a02ca07a642293908be11066b125feeeed00e9d336fee", + "offset_minutes": -5 + }, + { + "commitment_hash": "e6a63445423e4f20e25aff4422a6c2e2171e8b5b1f817b7c942a6d45ac93ad42", + "offset_minutes": -2 + }, + { + "commitment_hash": "2ca091c950d96413e45c35524031356dd2387b85a3444386c5b1c9562c884d6e", + "offset_minutes": -1 + }, + { + "commitment_hash": "0d4cf78bcd4d3b9e7ba2385d1c13978ab1a634b299711bd4c0b899cad18a4067", + "offset_minutes": 1 + }, + { + "commitment_hash": "30242701a0c8d92f807da66e7fb53ca894dea6e36e354f406c74f444d8fbecb8", + "offset_minutes": 2 + }, + { + "commitment_hash": "7267b8aaf5c73b49953b946fba31ca1fb5ea707720e65ca030ba4327eda3c4fe", + "offset_minutes": 5 + }, + { + "commitment_hash": "b1d28e8285438f26532f5bfd2447df34eddbe24e26d53d7d4069b87d1420704c", + "offset_minutes": 10 + } + ], + "false_minute_offsets": [ + -10, + -5, + -2, + -1, + 1, + 2, + 5, + 10 + ], + "frozen_before_scoring": true, + "holdout_partition": "sealed_evaluation", + "independent_human_reviewed": true, + "ingested_at": "2026-08-28T16:29:41.971107Z", + "review_attestation": "Attests the v3 sealed-set review already recorded for this public AA case; not a new biography audit.", + "subject_label": "Kurt Cobain" + } + ], "minimum_gate": { - "public_aa_cases": 20, - "events_per_case": 3, + "day_precision_events_per_case": 3, "domains_per_case": 2, + "events_per_case": 3, "independent_event_sources_per_case": 2, "negative_minutes_per_case": 4, - "day_precision_events_per_case": 3 + "public_aa_cases": 20 }, - "cases": [], "production_tuning_allowed": false, - "verified_minute_claim_allowed": false, - "boundary": "This intake queue is not a frozen holdout. Promotion requires a new version, a passed source audit and a scoring identity frozen before blind replay." + "schema_version": "minute-rectification-holdout-v4-intake", + "status": "collecting_independently_reviewed_cases", + "verified_minute_claim_allowed": false } diff --git a/tests/test_minute_rectification_holdout_intake.py b/tests/test_minute_rectification_holdout_intake.py index 1003753a..4ed4abe0 100644 --- a/tests/test_minute_rectification_holdout_intake.py +++ b/tests/test_minute_rectification_holdout_intake.py @@ -4,7 +4,15 @@ from copy import deepcopy from pathlib import Path from scripts.minute_rectification_holdout_intake import DEFAULT_INTAKE, append_case -from scripts.minute_rectification_holdout_validator import DEFAULT_MANIFEST +from scripts.minute_rectification_holdout_validator import DEFAULT_MANIFEST, case_errors + +V3_HOLDOUT = Path(__file__).resolve().parents[1] / "references" / "real_case_calibration" / "minute_rectification_holdout_v3.json" +EXPECTED_V4_INTAKE_CASE_IDS = { + "barack_obama_1961_aa_v4_holdout", + "paul_ryan_1970_aa_v4_holdout", + "sean_lennon_1975_aa_v4_holdout", + "kurt_cobain_1967_aa_v4_holdout", +} def _reviewed_case() -> dict: @@ -65,9 +73,40 @@ def test_intake_rejects_missing_review_and_commitments(tmp_path: Path) -> None: assert "false_minute_commitments_do_not_match_offsets" in report["errors"] -def test_default_intake_is_non_production_and_empty() -> None: +def test_default_intake_is_non_production_and_contains_day_precision_v3_cases() -> None: data = json.loads(DEFAULT_INTAKE.read_text(encoding="utf-8")) - assert data["cases"] == [] + assert {case["case_id"] for case in data["cases"]} == EXPECTED_V4_INTAKE_CASE_IDS + assert len(data["cases"]) == 4 assert data["production_tuning_allowed"] is False assert data["verified_minute_claim_allowed"] is False + + +def test_year_precision_v3_cases_are_rejected_for_insufficient_day_precision() -> None: + v3 = json.loads(V3_HOLDOUT.read_text(encoding="utf-8")) + gate = json.loads(DEFAULT_INTAKE.read_text(encoding="utf-8"))["minimum_gate"] + rejected: dict[str, list[str]] = {} + for case in v3["cases"]: + payload = deepcopy(case) + payload.update({ + "adjudicator": "v3_sealed_set_post_audit_migration", + "independent_human_reviewed": True, + "frozen_before_scoring": True, + "false_minute_commitments": [ + { + "offset_minutes": offset, + "commitment_hash": hashlib.sha256(f"control:{offset}".encode()).hexdigest(), + } + for offset in case["false_minute_offsets"] + ], + }) + errors = case_errors(payload, gate, require_review_safeguards=True) + if errors: + rejected[str(case["case_id"])] = errors + + assert "insufficient_day_precision_events" in rejected["john_robbins_1947_aa_v4_holdout"] + assert "insufficient_day_precision_events" in rejected["iwao_takamoto_1925_aa_v4_holdout"] + assert "insufficient_day_precision_events" in rejected["angelina_jolie_1975_aa_v4_holdout"] + for case_id in EXPECTED_V4_INTAKE_CASE_IDS: + assert case_id not in rejected + assert all("insufficient_day_precision_events" in errors for errors in rejected.values())