root/Jyotisha
1
0
Fork 0
Code Issues 1 Pull Requests 3 Actions Packages Projects Releases Wiki Activity

data: add real-case holdout evidence

Browse Source
This commit is contained in:
732642856
2026-07-16 23:31:45 +08:00
parent fa434fa7c5
commit 90ffef89b0
22 changed files with 35072 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/benchmark/public_real_case_20_case_closure_2026_07_11.json
+6125
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_23_case_observation_2026_07_11.json
+6900
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_batch1_comparison_2026_07_11.json
+140
View File
@@ -0,0 +1,140 @@
{
"benchmark_id": "public_real_case_holdout_comparison_2026_07_11",
"boundary": "Blind positive-event holdout comparison; no negative controls and no scientific accuracy claim.",
"case_deltas": [
{
"added_signals": [
"active_dasha_matches_Amatyakaraka:Moon",
"active_dasha_matches_D10_10L:Moon"
],
"case_id": "aniston_emmy_2002",
"score_delta": 2,
"v1_result_class": "weak_hit",
"v1_score": 5,
"v2_result_class": "strong_hit",
"v2_score": 7
},
{
"added_signals": [
"Rahu_dispositor_Venus_occupies_event_house:5",
"Rahu_dispositor_Venus_owns_event_house"
],
"case_id": "disney_marriage_1925",
"score_delta": 2,
"v1_result_class": "strong_hit",
"v1_score": 8,
"v2_result_class": "strong_hit",
"v2_score": 10
},
{
"added_signals": [
"Ketu_dispositor_Mercury_occupies_event_house:6",
"Ketu_dispositor_Mercury_owns_event_house"
],
"case_id": "jobs_iphone_2007",
"score_delta": 2,
"v1_result_class": "weak_hit",
"v1_score": 5,
"v2_result_class": "strong_hit",
"v2_score": 7
},
{
"added_signals": [
"Ketu_dispositor_Venus_owns_event_house",
"active_dasha_matches_Darakaraka:Venus"
],
"case_id": "jolie_marriage_2014",
"score_delta": 2,
"v1_result_class": "weak_hit",
"v1_score": 4,
"v2_result_class": "weak_hit",
"v2_score": 6
},
{
"added_signals": [],
"case_id": "kahlo_marriage_1929",
"score_delta": 0,
"v1_result_class": "strong_hit",
"v1_score": 7,
"v2_result_class": "strong_hit",
"v2_score": 7
},
{
"added_signals": [],
"case_id": "obama_election_2008",
"score_delta": 0,
"v1_result_class": "miss",
"v1_score": 1,
"v2_result_class": "miss",
"v2_score": 1
},
{
"added_signals": [],
"case_id": "schwarzenegger_governor_2003",
"score_delta": 0,
"v1_result_class": "miss",
"v1_score": 2,
"v2_result_class": "miss",
"v2_score": 2
},
{
"added_signals": [],
"case_id": "snoop_marriage_1997",
"score_delta": 0,
"v1_result_class": "strong_hit",
"v1_score": 10,
"v2_result_class": "strong_hit",
"v2_score": 10
},
{
"added_signals": [
"Rahu_dispositor_Jupiter_owns_event_house"
],
"case_id": "streep_oscar_1983",
"score_delta": 1,
"v1_result_class": "weak_hit",
"v1_score": 5,
"v2_result_class": "weak_hit",
"v2_score": 6
},
{
"added_signals": [],
"case_id": "william_marriage_2011",
"score_delta": 0,
"v1_result_class": "weak_hit",
"v1_score": 6,
"v2_result_class": "weak_hit",
"v2_score": 6
}
],
"promotion": {
"promote": true,
"reason": "holdout_metrics_improved"
},
"v1_summary": {
"balanced_accuracy": null,
"balanced_accuracy_blocked_reason": "no_verified_negative_control_dates",
"blocked_events": 0,
"blocked_rate": 0.0,
"evaluated_events": 10,
"exact_label_rate": 0.3,
"misses": 2,
"positive_event_recall": 0.8,
"strong_hits": 3,
"total_events": 10,
"weak_hits": 5
},
"v2_summary": {
"balanced_accuracy": null,
"balanced_accuracy_blocked_reason": "no_verified_negative_control_dates",
"blocked_events": 0,
"blocked_rate": 0.0,
"evaluated_events": 10,
"exact_label_rate": 0.5,
"misses": 2,
"positive_event_recall": 0.8,
"strong_hits": 5,
"total_events": 10,
"weak_hits": 3
}
}
docs/benchmark/public_real_case_batch1_v21_2026_07_11.json
+3573
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_batch1_v2_2026_07_11.json
+3090
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_benchmark_2026_07_11.json
+3067
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_holdout_comparison_2026_07_11.json
+137
View File
@@ -0,0 +1,137 @@
{
"benchmark_id": "public_real_case_holdout_comparison_2026_07_11",
"boundary": "Blind positive-event holdout comparison; no negative controls and no scientific accuracy claim.",
"case_deltas": [
{
"added_signals": [],
"case_id": "albert_ii_accession_2005",
"score_delta": 0,
"v1_result_class": "strong_hit",
"v1_score": 9,
"v2_result_class": "strong_hit",
"v2_score": 9
},
{
"added_signals": [
"active_dasha_matches_D10_Lagna_lord:Sun"
],
"case_id": "bergman_oscar_1945",
"score_delta": 1,
"v1_result_class": "strong_hit",
"v1_score": 7,
"v2_result_class": "strong_hit",
"v2_score": 8
},
{
"added_signals": [
"active_dasha_matches_D10_Lagna_lord:Venus"
],
"case_id": "boy_george_grammy_1984",
"score_delta": 1,
"v1_result_class": "weak_hit",
"v1_score": 5,
"v2_result_class": "weak_hit",
"v2_score": 6
},
{
"added_signals": [
"active_dasha_matches_D9_7L:Venus"
],
"case_id": "chelsea_clinton_marriage_2010",
"score_delta": 1,
"v1_result_class": "weak_hit",
"v1_score": 4,
"v2_result_class": "weak_hit",
"v2_score": 5
},
{
"added_signals": [],
"case_id": "demi_moore_marriage_1987",
"score_delta": 0,
"v1_result_class": "miss",
"v1_score": 0,
"v2_result_class": "miss",
"v2_score": 0
},
{
"added_signals": [
"active_dasha_matches_D9_7L:Jupiter"
],
"case_id": "depp_marriage_2015",
"score_delta": 1,
"v1_result_class": "weak_hit",
"v1_score": 5,
"v2_result_class": "weak_hit",
"v2_score": 6
},
{
"added_signals": [
"active_dasha_matches_Amatyakaraka:Mercury",
"active_dasha_matches_D10_Lagna_lord:Mercury"
],
"case_id": "dion_eurovision_1988",
"score_delta": 2,
"v1_result_class": "miss",
"v1_score": 3,
"v2_result_class": "weak_hit",
"v2_score": 5
},
{
"added_signals": [],
"case_id": "kidman_marriage_2006",
"score_delta": 0,
"v1_result_class": "miss",
"v1_score": 3,
"v2_result_class": "miss",
"v2_score": 3
},
{
"added_signals": [],
"case_id": "mccartney_marriage_1969",
"score_delta": 0,
"v1_result_class": "strong_hit",
"v1_score": 7,
"v2_result_class": "strong_hit",
"v2_score": 7
},
{
"added_signals": [],
"case_id": "morissette_grammy_1996",
"score_delta": 0,
"v1_result_class": "weak_hit",
"v1_score": 4,
"v2_result_class": "weak_hit",
"v2_score": 4
}
],
"promotion": {
"promote": true,
"reason": "holdout_metrics_improved"
},
"v1_summary": {
"balanced_accuracy": null,
"balanced_accuracy_blocked_reason": "no_verified_negative_control_dates",
"blocked_events": 0,
"blocked_rate": 0.0,
"evaluated_events": 10,
"exact_label_rate": 0.3,
"misses": 3,
"positive_event_recall": 0.7,
"strong_hits": 3,
"total_events": 10,
"weak_hits": 4
},
"v2_summary": {
"balanced_accuracy": null,
"balanced_accuracy_blocked_reason": "no_verified_negative_control_dates",
"blocked_events": 0,
"blocked_rate": 0.0,
"evaluated_events": 10,
"exact_label_rate": 0.3,
"misses": 2,
"positive_event_recall": 0.8,
"strong_hits": 3,
"total_events": 10,
"weak_hits": 5
}
}
docs/benchmark/public_real_case_holdout_v1_2026_07_11.json
+2978
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_holdout_v21_2026_07_11.json
+3470
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_holdout_v2_2026_07_11.json
+2987
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_probe3_v21_2026_07_11.json
+1058
View File
File diff suppressed because it is too large Load Diff
docs/benchmark/public_real_case_probe3_v2_2026_07_11.json
+908
View File
@@ -0,0 +1,908 @@
{
"benchmark_id": "public_real_case_benchmark_2026_07_11",
"cases": [
{
"actual_label": null,
"birth_time_rating": "AA",
"blocked": false,
"case_id": "trump_inauguration_2017",
"domain": "career",
"event_date": "2017-01-20",
"evidence": {
"arudha_lord": "Mercury",
"ascendant": {
"degree": 6.8497,
"degree_in_sign": 6.8497,
"degree_in_sign_raw": 126.84968959703062,
"degree_raw": 126.8497,
"lon": 126.8497,
"lord": "Sun",
"sign": "Leo",
"sign_cn": "狮子座"
},
"birth_source": {
"evidence_basis": "BC/BR in hand",
"source_grade": "primary",
"time_accuracy_rating": "AA",
"url": "https://www.astro.com/astro-databank/Trump,_Donald"
},
"domain_varga": {
"birth_info": "1946-06-14 10:54",
"divisional_charts": {
"D10_Dasamsa": {
"Jupiter": {
"sign": "Capricorn",
"sign_cn": "摩羯座"
},
"Ketu": {
"sign": "Aries",
"sign_cn": "白羊座"
},
"Mars": {
"sign": "Virgo",
"sign_cn": "处女座"
},
"Mercury": {
"sign": "Scorpio",
"sign_cn": "天蝎座"
},
"Moon": {
"sign": "Aries",
"sign_cn": "白羊座"
},
"Rahu": {
"sign": "Libra",
"sign_cn": "天秤座"
},
"Saturn": {
"sign": "Pisces",
"sign_cn": "双鱼座"
},
"Sun": {
"sign": "Libra",
"sign_cn": "天秤座"
},
"Venus": {
"sign": "Pisces",
"sign_cn": "双鱼座"
},
"ascendant": "Libra"
}
}
},
"double_transit_pac": {
"cl": {
"jupiter": {},
"saturn": {}
},
"d1": {
"jupiter": {},
"saturn": {}
},
"d9": {
"jupiter": {
"D9_10宫(Pisces)": [
{
"desc": "9宫相位",
"offset": 9,
"type": "Aspect"
}
],
"D9_Jupiter(宫主)": [
{
"desc": "同宫(4宫)",
"type": "Position"
},
{
"desc": "合相(4.27°)",
"type": "Conjunction"
}
],
"Sun_D9(Virgo)": [
{
"desc": "同宫(4宫)",
"type": "Position"
}
]
},
"saturn": {
"D9_10宫(Pisces)": [
{
"desc": "7宫相位",
"offset": 7,
"type": "Aspect"
}
],
"D9_Jupiter(宫主)": [
{
"desc": "10宫相位",
"offset": 10,
"type": "Aspect"
}
],
"Sun_D9(Virgo)": [
{
"desc": "10宫相位",
"offset": 10,
"type": "Aspect"
}
]
}
},
"double_transit": [
{
"jupiter_pac": [
{
"desc": "同宫(4宫)",
"type": "Position"
}
],
"layer": "D9",
"saturn_pac": [
{
"desc": "10宫相位",
"offset": 10,
"type": "Aspect"
}
],
"strength": "strong",
"target": "Sun_D9(Virgo)"
},
{
"jupiter_pac": [
{
"desc": "9宫相位",
"offset": 9,
"type": "Aspect"
}
],
"layer": "D9",
"saturn_pac": [
{
"desc": "7宫相位",
"offset": 7,
"type": "Aspect"
}
],
"strength": "strong",
"target": "D9_10宫(Pisces)"
},
{
"jupiter_pac": [
{
"desc": "同宫(4宫)",
"type": "Position"
},
{
"desc": "合相(4.27°)",
"type": "Conjunction"
}
],
"layer": "D9",
"saturn_pac": [
{
"desc": "10宫相位",
"offset": 10,
"type": "Aspect"
}
],
"strength": "strong",
"target": "D9_Jupiter(宫主)"
}
],
"event_house": 10,
"stats": {
"chandra_lagna": "Scorpio",
"cl_jupiter_targets": [],
"cl_overlap": [],
"cl_saturn_targets": [],
"d1_jupiter_targets": [],
"d1_overlap": [],
"d1_saturn_targets": [],
"d9_ascendant": "Gemini",
"d9_jupiter_targets": [
"D9_10宫(Pisces)",
"D9_Jupiter(宫主)",
"Sun_D9(Virgo)"
],
"d9_overlap": [
"D9_10宫(Pisces)",
"D9_Jupiter(宫主)",
"Sun_D9(Virgo)"
],
"d9_saturn_targets": [
"D9_10宫(Pisces)",
"D9_Jupiter(宫主)",
"Sun_D9(Virgo)"
],
"event_lord_d9_sign": "Cancer"
},
"summary": "⚠️ D9 层 Double Transit 激活，D1/CL 层未确认",
"transit_date": "2017-01-20"
},
"event_source": {
"source_grade": "primary",
"url": "https://www.inaugural.senate.gov/58th-inaugural-ceremonies/"
},
"functional_benefic_malefic": {
"ascendant": "Leo",
"effect_on_confidence": "高严谨模式下必须叠加功能性宫主吉凶与自然吉凶；若功能属性与自然属性冲突，应降低置信度或显式标记冲突。",
"functional_benefics": [
"Jupiter",
"Mars",
"Sun"
],
"functional_malefics": [
"Mercury",
"Moon",
"Saturn",
"Venus"
],
"functional_neutrals": [],
"owned_houses": {
"Jupiter": [
5,
8
],
"Mars": [
4,
9
],
"Mercury": [
2,
11
],
"Moon": [
12
],
"Saturn": [
6,
7
],
"Sun": [
1
],
"Venus": [
3,
10
]
},
"source": "strict_functional_benefic_malefic_v1",
"status": "used",
"yogakarakas": [
"Mars"
]
},
"narayana": {
"ad": {
"end_age": 71.5714,
"lord": "Sun",
"sign": "Leo",
"sign_idx": 4,
"start_age": 70.2857,
"years": 1.2857
},
"md": {
"end_age": 80.0,
"lord": "Mercury",
"sign": "Gemini",
"sign_idx": 2,
"start_age": 68.0,
"years": 12
},
"pd": {
"end_age": 70.699,
"lord": "Venus",
"sign": "Libra",
"sign_idx": 6,
"start_age": 70.5612,
"years": 0.1378
},
"remaining_years": 9.39
},
"vimshottari": {
"antardasha": "Jupiter",
"mahadasha": "Jupiter"
}
},
"expected_label": "career_status",
"matched_expected_label": false,
"name": "Donald Trump",
"outcome": "Sworn in as President of the United States",
"result_class": "miss",
"rule_version": "v2",
"score": 3,
"signals": [
"narayana_lord_owns_event_house:Mercury",
"double_transit_pac_strong"
]
},
{
"actual_label": null,
"birth_time_rating": "AA",
"blocked": false,
"case_id": "dicaprio_oscar_2016",
"domain": "career",
"event_date": "2016-02-28",
"evidence": {
"arudha_lord": "Saturn",
"ascendant": {
"degree": 9.6131,
"degree_in_sign": 9.6131,
"degree_in_sign_raw": 159.61308341512213,
"degree_raw": 159.6131,
"lon": 159.6131,
"lord": "Mercury",
"sign": "Virgo",
"sign_cn": "处女座"
},
"birth_source": {
"evidence_basis": "BC/BR in hand",
"source_grade": "primary",
"time_accuracy_rating": "AA",
"url": "https://www.astro.com/astro-databank/DiCaprio,_Leonardo"
},
"domain_varga": {
"birth_info": "1974-11-11 02:47",
"divisional_charts": {
"D10_Dasamsa": {
"Jupiter": {
"sign": "Gemini",
"sign_cn": "双子座"
},
"Ketu": {
"sign": "Gemini",
"sign_cn": "双子座"
},
"Mars": {
"sign": "Pisces",
"sign_cn": "双鱼座"
},
"Mercury": {
"sign": "Sagittarius",
"sign_cn": "射手座"
},
"Moon": {
"sign": "Sagittarius",
"sign_cn": "射手座"
},
"Rahu": {
"sign": "Sagittarius",
"sign_cn": "射手座"
},
"Saturn": {
"sign": "Aquarius",
"sign_cn": "水瓶座"
},
"Sun": {
"sign": "Gemini",
"sign_cn": "双子座"
},
"Venus": {
"sign": "Gemini",
"sign_cn": "双子座"
},
"ascendant": "Leo"
}
}
},
"double_transit_pac": {
"cl": {
"jupiter": {},
"saturn": {
"CL_10宫(Gemini)": [
{
"desc": "7宫相位",
"offset": 7,
"type": "Aspect"
}
]
}
},
"d1": {
"jupiter": {},
"saturn": {
"10宫(Gemini)": [
{
"desc": "7宫相位",
"offset": 7,
"type": "Aspect"
}
],
"Jupiter(对宫主)": [
{
"desc": "3宫相位",
"offset": 3,
"type": "Aspect"
}
]
}
},
"d9": {
"jupiter": {
"D9_10宫(Sagittarius)": [
{
"desc": "7宫相位",
"offset": 7,
"type": "Aspect"
}
]
},
"saturn": {
"D9_Jupiter(宫主)": [
{
"desc": "3宫相位",
"offset": 3,
"type": "Aspect"
}
],
"Mercury_D9(Scorpio)": [
{
"desc": "同宫(9宫)",
"type": "Position"
},
{
"desc": "合相(6.78°)",
"type": "Conjunction"
}
]
}
},
"double_transit": [],
"event_house": 10,
"stats": {
"chandra_lagna": "Virgo",
"cl_jupiter_targets": [],
"cl_overlap": [],
"cl_saturn_targets": [
"CL_10宫(Gemini)"
],
"d1_jupiter_targets": [],
"d1_overlap": [],
"d1_saturn_targets": [
"10宫(Gemini)",
"Jupiter(对宫主)"
],
"d9_ascendant": "Pisces",
"d9_jupiter_targets": [
"D9_10宫(Sagittarius)"
],
"d9_overlap": [],
"d9_saturn_targets": [
"D9_Jupiter(宫主)",
"Mercury_D9(Scorpio)"
],
"event_lord_d9_sign": "Scorpio"
},
"summary": "❌ 无 Double Transit PAC 激活",
"transit_date": "2016-02-28"
},
"event_source": {
"source_grade": "primary",
"url": "https://www.oscars.org/oscars/ceremonies/2016"
},
"functional_benefic_malefic": {
"ascendant": "Virgo",
"effect_on_confidence": "高严谨模式下必须叠加功能性宫主吉凶与自然吉凶；若功能属性与自然属性冲突，应降低置信度或显式标记冲突。",
"functional_benefics": [
"Mercury",
"Saturn",
"Venus"
],
"functional_malefics": [
"Mars",
"Moon",
"Sun"
],
"functional_neutrals": [
"Jupiter"
],
"owned_houses": {
"Jupiter": [
4,
7
],
"Mars": [
3,
8
],
"Mercury": [
1,
10
],
"Moon": [
11
],
"Saturn": [
5,
6
],
"Sun": [
12
],
"Venus": [
2,
9
]
},
"source": "strict_functional_benefic_malefic_v1",
"status": "used",
"yogakarakas": [
"Mercury"
]
},
"narayana": {
"ad": {
"end_age": 42.2769,
"lord": "Venus",
"sign": "Libra",
"sign_idx": 6,
"start_age": 40.2462,
"years": 2.0308
},
"md": {
"end_age": 46.0,
"lord": "Jupiter",
"sign": "Pisces",
"sign_idx": 11,
"start_age": 35.0,
"years": 11
},
"pd": {
"end_age": 41.3085,
"lord": "Saturn",
"sign": "Aquarius",
"sign_idx": 10,
"start_age": 41.1835,
"years": 0.125
},
"remaining_years": 4.7
},
"vimshottari": {
"antardasha": "Rahu",
"mahadasha": "Jupiter"
}
},
"expected_label": "career_status",
"matched_expected_label": false,
"name": "Leonardo DiCaprio",
"outcome": "Won the Academy Award for Actor in a Leading Role",
"result_class": "miss",
"rule_version": "v2",
"score": 1,
"signals": [
"Jupiter_occupies_event_house:6"
]
},
{
"actual_label": "legal_marriage",
"birth_time_rating": "AA",
"blocked": false,
"case_id": "markle_marriage_2018",
"domain": "marriage",
"event_date": "2018-05-19",
"evidence": {
"arudha_lord": "Sun",
"ascendant": {
"degree": 0.6845,
"degree_in_sign": 0.6845,
"degree_in_sign_raw": 90.68454836083515,
"degree_raw": 90.6845,
"lon": 90.6845,
"lord": "Moon",
"sign": "Cancer",
"sign_cn": "巨蟹座"
},
"birth_source": {
"evidence_basis": "BC/BR in hand",
"source_grade": "primary",
"time_accuracy_rating": "AA",
"url": "https://www.astro.com/astro-databank/Markle,_Meghan"
},
"domain_varga": {
"birth_info": "1981-08-04 04:46",
"divisional_charts": {
"D9_Navamsa": {
"Jupiter": {
"sign": "Aries",
"sign_cn": "白羊座"
},
"Ketu": {
"sign": "Pisces",
"sign_cn": "双鱼座"
},
"Mars": {
"sign": "Pisces",
"sign_cn": "双鱼座"
},
"Mercury": {
"sign": "Libra",
"sign_cn": "天秤座"
},
"Moon": {
"sign": "Aries",
"sign_cn": "白羊座"
},
"Rahu": {
"sign": "Virgo",
"sign_cn": "处女座"
},
"Saturn": {
"sign": "Aries",
"sign_cn": "白羊座"
},
"Sun": {
"sign": "Sagittarius",
"sign_cn": "射手座"
},
"Venus": {
"sign": "Virgo",
"sign_cn": "处女座"
},
"ascendant": "Cancer"
}
}
},
"double_transit_pac": {
"cl": {
"jupiter": {
"CL_7宫(Pisces)": [
{
"desc": "5宫相位",
"offset": 5,
"type": "Aspect"
}
]
},
"saturn": {
"CL_7宫(Pisces)": [
{
"desc": "3宫相位",
"offset": 3,
"type": "Aspect"
}
]
}
},
"d1": {
"jupiter": {},
"saturn": {}
},
"d9": {
"jupiter": {
"D9_7宫(Capricorn)": [
{
"desc": "9宫相位",
"offset": 9,
"type": "Aspect"
}
]
},
"saturn": {
"D9_7宫(Capricorn)": [
{
"desc": "7宫相位",
"offset": 7,
"type": "Aspect"
}
]
}
},
"double_transit": [
{
"jupiter_pac": [
{
"desc": "9宫相位",
"offset": 9,
"type": "Aspect"
}
],
"layer": "D9",
"saturn_pac": [
{
"desc": "7宫相位",
"offset": 7,
"type": "Aspect"
}
],
"strength": "strong",
"target": "D9_7宫(Capricorn)"
},
{
"jupiter_pac": [
{
"desc": "5宫相位",
"offset": 5,
"type": "Aspect"
}
],
"layer": "CL",
"saturn_pac": [
{
"desc": "3宫相位",
"offset": 3,
"type": "Aspect"
}
],
"strength": "strong",
"target": "CL_7宫(Pisces)"
}
],
"event_house": 7,
"stats": {
"chandra_lagna": "Virgo",
"cl_jupiter_targets": [
"CL_7宫(Pisces)"
],
"cl_overlap": [
"CL_7宫(Pisces)"
],
"cl_saturn_targets": [
"CL_7宫(Pisces)"
],
"d1_jupiter_targets": [],
"d1_overlap": [],
"d1_saturn_targets": [],
"d9_ascendant": "Cancer",
"d9_jupiter_targets": [
"D9_7宫(Capricorn)"
],
"d9_overlap": [
"D9_7宫(Capricorn)"
],
"d9_saturn_targets": [
"D9_7宫(Capricorn)"
],
"event_lord_d9_sign": "Aries"
},
"summary": "✅ Double Transit PAC 确认: D9+CL 多层激活7宫主题",
"transit_date": "2018-05-19"
},
"event_source": {
"source_grade": "primary",
"url": "https://www.royal.uk/wedding-duke-and-duchess-sussex"
},
"functional_benefic_malefic": {
"ascendant": "Cancer",
"effect_on_confidence": "高严谨模式下必须叠加功能性宫主吉凶与自然吉凶；若功能属性与自然属性冲突，应降低置信度或显式标记冲突。",
"functional_benefics": [
"Jupiter",
"Mars",
"Moon"
],
"functional_malefics": [
"Mercury",
"Saturn",
"Venus"
],
"functional_neutrals": [
"Sun"
],
"owned_houses": {
"Jupiter": [
6,
9
],
"Mars": [
5,
10
],
"Mercury": [
3,
12
],
"Moon": [
1
],
"Saturn": [
7,
8
],
"Sun": [
2
],
"Venus": [
4,
11
]
},
"source": "strict_functional_benefic_malefic_v1",
"status": "used",
"yogakarakas": [
"Mars"
]
},
"narayana": {
"ad": {
"end_age": 36.8684,
"lord": "Venus",
"sign": "Taurus",
"sign_idx": 1,
"start_age": 36.5921,
"years": 0.2763
},
"md": {
"end_age": 40.0,
"lord": "Mars",
"sign": "Scorpio",
"sign_idx": 7,
"start_age": 33.0,
"years": 7
},
"pd": {
"end_age": 36.8139,
"lord": "Saturn",
"sign": "Capricorn",
"sign_idx": 9,
"start_age": 36.7848,
"years": 0.0291
},
"remaining_years": 3.21
},
"vimshottari": {
"antardasha": "Saturn",
"mahadasha": "Jupiter"
}
},
"expected_label": "legal_marriage",
"matched_expected_label": true,
"name": "Meghan Markle",
"outcome": "Married Prince Harry at St George's Chapel",
"result_class": "strong_hit",
"rule_version": "v2",
"score": 7,
"signals": [
"Jupiter_domain_karaka",
"Saturn_owns_event_houses:[7]",
"active_dasha_matches_D9_7L:Saturn",
"narayana_lord_owns_event_house:Mars",
"double_transit_pac_strong"
]
}
],
"external_oracle_boundary": {
"JHora": "manual_oracle_not_automated",
"PyJHora": "blocked_or_benchmark_only_until_dependency_available",
"VedAstro": "diagnostic_only_unless_official_raw_present",
"jyotishganit": "parity_contract_separate_from_this_event_replay"
},
"method": {
"boundary": "Positive-event technical activation replay; not scientific predictive accuracy.",
"pre_registered_layers": [
"D1",
"D9_or_D10",
"UL_or_A10",
"Functional Benefic/Malefic",
"Vimshottari MD/AD",
"Narayana Dasha",
"Double Transit PAC",
"Rahu/Ketu dispositor",
"D9/D10 Lagna and primary-house lord",
"Amatyakaraka/Darakaraka"
],
"score_thresholds": {
"miss": "<4",
"strong_hit": ">=7",
"weak_hit": "4-6"
},
"selection": "Rodden A/AA public figures with independently dated public events"
},
"rule_version": "v2",
"strict_workflow_batch": {
"blocked_reason": "single_case_strict_workflow_timeout_120s",
"status": "blocked"
},
"summary": {
"balanced_accuracy": null,
"balanced_accuracy_blocked_reason": "no_verified_negative_control_dates",
"blocked_events": 0,
"blocked_rate": 0.0,
"evaluated_events": 3,
"exact_label_rate": 0.3333333333333333,
"misses": 2,
"positive_event_recall": 0.3333333333333333,
"strong_hits": 1,
"total_events": 3,
"weak_hits": 0
}
}
docs/research/pre_work_error_ledger.md
+6
View File
@@ -102,6 +102,12 @@ For large architecture or release work, also read:
| ERR-069 | Yoga validation tests and helper runner still imported rules from a `.workbuddy` mirror, so full pytest could fail or silently validate a divergent checkout. | mitigated 2026-07-15 | Resolve repo root from each file location; retain runtime-boundary and focused Yoga regressions. |
| ERR-070 | PyJHora parity for D2/D4/BAV/SAV can pass while Shadbala total virupas still mismatch, so a row-filled Shadbala oracle packet can be mistaken for absolute-value parity. | active external formula blocker | Keep `docs/research/pyjhora_d2_d4_ashtakavarga_shadbala_parity_2026_07_15.md`; do not claim Shadbala external absolute closure until component-level formulas reconcile with PyJHora/JHora raw values. |
| ERR-071 | `runtime-truth` required an untracked `scratch/local/pdf_review_123456` JHora packet, so a clean public checkout failed before it could report the actual external-oracle boundary. | resolved 2026-07-16 | Release truth reads `references/evidence_manifests/jhora_master_evidence_manifest.json`; scratch is optional and may be repaired only through explicit `sync_final_evidence_packet_status.py --sync-local`. Manifest must retain `external_raw_required_for_official_verified=true`. |
| ERR-072 | The 2026-07-14 sweep did not enumerate two `.workbuddy/backups` Jyotish Git snapshots, a Codex `audit_tmp` extraction, or the Kimi training archive, so a later window could mistake them for undiscovered production truth. | active 2026-07-16 | Read `whole_machine_fragment_sweep_2026_07_16.md`; classify every candidate by Git ancestry, relative-path diff, content, privacy, and supersession before any import. Never bulk-copy a backup or archive. |
| ERR-073 | The external article warehouse contains 50 Jyotish source artifacts whose techniques can be absent from the repo even when broad labels such as Jaimini, Arudha, or Tajika are already marked covered. | active 2026-07-16 | Before technique expansion, build a source-ingestion manifest with hashes, provenance, extracted formula IDs, variant identity, copyright boundary, production coverage, and validation state. Broad registry labels must not imply article-level coverage. |
| ERR-074 | Absent local-only quarantined drafts were counted as missing runtime references, causing clean strict workflows to degrade despite all production sources being present. | resolved 2026-07-16 | Keep quarantined paths as declared audit inventory, exclude non-runtime absence from readiness, and never promote them into runtime source refs. |
| ERR-075 | `real_case_calibration_catalog()` unconditionally opened an untracked holdout manifest, so clean installs could silently lose the MCP runtime evidence log. | resolved 2026-07-16 | Missing optional holdout assets return structured `blocked` metadata instead of raising. |
| ERR-076 | Fragment/inventory tests required machine-local drafts, workspace residue, or a fixed minimum file count. | resolved 2026-07-16 | Assert count invariants and stable tracked classifications; validate optional local categories only when present. |
| ERR-077 | VedAstro request previews serialized the live `x-api-key` header, allowing logs and failed test output to expose credentials. | resolved; credential rotation required 2026-07-16 | Preview/metadata profiles never contain authentication headers. Inject `VEDASTRO_API_KEY` only immediately before network execution; rotate any key exposed before this fix. |
## Fragment Sweep Command Set
docs/research/public_real_case_20_case_closure_2026_07_11.md
+113
View File
@@ -0,0 +1,113 @@
# 20 个公开真实案例回放与技法闭环（2026-07-11）
## 结论
本轮新增 10 个独立 holdout 案例，与首批 10 案例合并为 20 个公开事件。V2 规则在查看 holdout 结果前冻结，只增加三层通用技术：Rahu/Ketu 定位星、D9/D10 上升主与主题宫主、Amatyakaraka/Darakaraka。
holdout 上，V1 正事件激活召回从 `0.70` 升至 `0.80`，精确标签率保持 `0.30`，blocked 保持 `0`。按预注册门槛，V2 可以进入主链。这个 `0.80` 不是科学预测准确率：样本全是已发生的正事件，没有负样本，无法计算 specificity、false-positive rate 或 balanced accuracy。
机器报告：
- `docs/benchmark/public_real_case_holdout_v1_2026_07_11.json`
- `docs/benchmark/public_real_case_holdout_v2_2026_07_11.json`
- `docs/benchmark/public_real_case_holdout_comparison_2026_07_11.json`
- `docs/benchmark/public_real_case_20_case_closure_2026_07_11.json`
## 样本设计
- 出生时间：Astro-Databank Rodden `A/AA`。
- 事件：事业公开成就或法律婚姻的明确日期。
- 事件来源：官方机构优先；官方资料缺失时使用已核验二手资料。
- 域平衡：事业 10，婚姻 10。
- holdout 平衡：事业 5，婚姻 5；A 5，AA 5。
- 隐私：只使用公众人物公开资料，不含用户出生信息或个人反馈。
## 20 案例结果
| # | 人物 | 事件域 | 日期 | V2 分数 | 结果 |
|---|---|---|---|---:|---|
| 1 | Steve Jobs | career | 2007-01-09 | 7 | strong_hit |
| 2 | Barack Obama | career | 2008-11-04 | 1 | miss |
| 3 | Arnold Schwarzenegger | career | 2003-10-07 | 2 | miss |
| 4 | Meryl Streep | career | 1983-04-11 | 6 | weak_hit |
| 5 | Jennifer Aniston | career | 2002-09-22 | 7 | strong_hit |
| 6 | William, Prince of Wales | marriage | 2011-04-29 | 6 | weak_hit |
| 7 | Angelina Jolie | marriage | 2014-08-23 | 6 | weak_hit |
| 8 | Frida Kahlo | marriage | 1929-08-21 | 7 | strong_hit |
| 9 | Snoop Dogg | marriage | 1997-06-14 | 10 | strong_hit |
| 10 | Walt Disney | marriage | 1925-07-13 | 10 | strong_hit |
| 11 | Albert II, Prince of Monaco | career | 2005-04-06 | 9 | strong_hit |
| 12 | Boy George | career | 1984-02-28 | 6 | weak_hit |
| 13 | Ingrid Bergman | career | 1945-03-15 | 8 | strong_hit |
| 14 | Alanis Morissette | career | 1996-02-28 | 4 | weak_hit |
| 15 | Celine Dion | career | 1988-04-30 | 5 | weak_hit |
| 16 | Paul McCartney | marriage | 1969-03-12 | 7 | strong_hit |
| 17 | Johnny Depp | marriage | 2015-02-03 | 6 | weak_hit |
| 18 | Nicole Kidman | marriage | 2006-06-25 | 3 | miss |
| 19 | Demi Moore | marriage | 1987-11-21 | 0 | miss |
| 20 | Chelsea Clinton | marriage | 2010-07-31 | 5 | weak_hit |
合并结果：`8 strong + 8 weak + 4 miss + 0 blocked`。事业与婚姻两域各自都是 `0.80` 正事件激活召回、`0.40` 精确标签率。
## V2 带来的可复现变化
- 首批训练集：正事件召回仍为 `0.80`，精确标签率由 `0.30` 升至 `0.50`。Jobs 和 Aniston 从 weak 升为 strong。
- 未见 holdout：Celine Dion 从 `3/miss` 升为 `5/weak_hit`，依据为 Mercury 同时成为 D10 上升主与 Amatyakaraka。
- Boy George、Ingrid Bergman、Johnny Depp、Chelsea Clinton 得分增加，但未跨越结果等级或只增强已有等级。
- V2 没有增加 blocked，也没有改变阈值。
## 四个剩余漏判揭示的技法债
### 1. Obama 与 Schwarzenegger：普通事业层不足以覆盖政治身份跃迁
当前回放把所有事业事件统一映射到 `10/6/9/11 + D10/A10`。总统当选、州长当选属于公众权力与国家身份跃迁，还需要独立审计：D10 Raja Yoga、D10 宫主相位、A10/AL 联动、Sun/AmK/政治权力指标、年度 Varshaphala。不能为两个 miss 临时提高通用事业分数。
### 2. Kidman 与 Demi Moore：Narayana 只审计 MD，遗漏 AD/PD 语义
两案事件时的 Narayana 包中都出现 Venus 主导的下级周期，但 V2 只对 Narayana MD 的主题星座和宫主加分。完整 MD/AD/PD 主题收敛是明确的 V3 候选；它必须在第三批新 holdout 上验证后才能进入生产评分，不能用当前两案反向调参。
### 3. PD/PrAD 已能展开，但尚非外部验证闭环
`scripts/vimshottari_subperiod_timeline.py` 可从本仓 AD 边界按标准比例展开 PD/PrAD。它适合提供月/周级候选窗，不应在没有 JHora/PyJHora/VedAstro 同盘原始输出时当作已验证 oracle。
### 4. 年度层与 KP 仍是 partial
- `Varshaphala/Muntha` 可运行，但年主裁决仍有简化实现，外部 Tajika oracle 未闭环。
- 本地 KP 可算 sub-lord/significator，但宫位层仍含“星座中点代替精确 cusp”的近似，不能称为完整 KP 事件裁决。
- 本轮修复了 `scripts/muntha.py` 独立导入时遗漏 `List` 导致的崩溃，并新增回归测试；这只是恢复可运行性，不等于年度预测精度已验证。
## Technique Audit Table
| Technique | 状态 | 说明 |
|---|---|---|
| D1 + Functional Benefic/Malefic | used | 20/20 |
| D9 + UL + Darakaraka | used | 10 个婚姻事件 |
| D10 + A10 + Amatyakaraka | used | 10 个事业事件 |
| Vimshottari MD/AD | used | 20/20 |
| Narayana Dasha | used | 20/20；AD/PD 完整语义仍待 V3 |
| Double Transit PAC | used | 20/20 |
| Rahu/Ketu dispositor | used | V2 正式评分层 |
| Vimshottari PD/PrAD | partial | 比例展开可用，外部同盘未验证 |
| Tajika/Varshaphala/Muntha | partial | 本地简化层；外部 oracle 未闭环 |
| KP exact cusp/significators | partial | sub-lord 可用；精确 cusp 闭环不足 |
| VedAstro official raw | blocked | `official_snapshot_budget_exhausted` |
| PyJHora/JHora/jyotishganit parity | blocked | canonical raw comparison 未完成 |
| MEVG / Global Web Evidence | used | 20 组公开出生/事件来源 |
| Real Case Calibration | used | 10 discovery + 10 frozen holdout |
| Negative controls | blocked | 无已核验“不发生事件”日期 |
## 新增 holdout 主要来源
- 出生时间：Astro-Databank VIP 页面，逐案 URL 已保存在 `references/real_case_calibration/replay_manifest_holdout_v2.json`。
- 事业事件：[Monaco Palace](https://www.palais.mc/en/princely-family/h-s-h-prince-albert-ii/biography-1-9.html)、[Oscars 1945](https://www.oscars.org/oscars/ceremonies/1945)、[Eurovision 1988](https://eurovision.tv/event/dublin-1988)。
- 婚姻事件：[Variety - Johnny Depp](https://variety.com/2016/biz/news/johnny-depp-amber-heard-divorce-settlement-1201837685/)、其余核验二手来源逐案保存在 holdout manifest。
## 已落地优化
1. V2 通过 holdout 门槛，统一 orchestrator 改读 20 案例合并报告。
2. 新增 V1/V2 纯比较模式，禁止比较命令重复跑两遍底层引擎导致超时。
3. 合并报告自动输出 domain summary、holdout promotion、Technique Audit 与 technique debt。
4. 修复 Muntha 独立模块导入错误并加测试。
5. 保留四个 miss，不用事后调参掩盖。
下一次真正提高可信度的最小方案：第三批 10 案例冻结 holdout，其中加入政治/公众身份事件与经核验负样本；只验证 Narayana AD/PD、D10 Raja Yoga/相位和年度层，不再扩展更多名称。
docs/research/public_real_case_benchmark_2026_07_11.md
+82
View File
@@ -0,0 +1,82 @@
# Public Real-Case Jyotish Benchmark - 2026-07-11
## Result
Ten public cases with Astro-Databank Rodden `A/AA` birth times were replayed through the local evidence stack. No user birth data or private feedback was used.
| Metric | Result | Boundary |
|---|---:|---|
| Cases / dated events | 10 / 10 | 5 career, 5 marriage |
| Positive-event activation recall | 80% | 8 of 10 known events reached weak or strong activation |
| Strong hits | 30% | 3 of 10 |
| Exact-label rate | 30% | Weak domain activation is not exact event classification |
| Blocked local replays | 0% | All lightweight local evidence packets completed |
| Balanced accuracy / specificity | blocked | No independently verified negative-control dates |
This is not scientific predictive accuracy. It is a positive-event technical activation replay. Full machine output: [`docs/benchmark/public_real_case_benchmark_2026_07_11.json`](../benchmark/public_real_case_benchmark_2026_07_11.json).
## Cases
| Case | Event | Domain | Rodden | Result | Score |
|---|---|---|---|---|---:|
| Steve Jobs | iPhone introduction, 2007-01-09 | career | AA | weak | 5 |
| Barack Obama | presidential election, 2008-11-04 | career | AA | miss | 1 |
| Arnold Schwarzenegger | California recall election, 2003-10-07 | career | A | miss | 2 |
| Meryl Streep | Best Actress Oscar, 1983-04-11 | career | AA | weak | 5 |
| Jennifer Aniston | lead-actress Emmy, 2002-09-22 | career | AA | weak | 5 |
| Prince William | legal marriage, 2011-04-29 | marriage | AA | weak | 6 |
| Angelina Jolie | legal marriage, 2014-08-23 | marriage | AA | weak | 4 |
| Frida Kahlo | legal marriage, 1929-08-21 | marriage | AA | strong | 7 |
| Snoop Dogg | legal marriage, 1997-06-14 | marriage | AA | strong | 10 |
| Walt Disney | legal marriage, 1925-07-13 | marriage | A | strong | 8 |
## Sources
Birth times: [Jobs](https://www.astro.com/adbvip/adbvip_02_24.htm), [Obama](https://www.astro.com/adbvip/adbvip_08_04.htm), [Schwarzenegger](https://www.astro.com/adbvip/adbvip_07_30.htm), [Streep](https://www.astro.com/adbvip/adbvip_06_22.htm), [Aniston](https://www.astro.com/adbvip/adbvip_02_11.htm), [Prince William](https://www.astro.com/adbvip/adbvip_06_21.htm), [Jolie](https://www.astro.com/adbvip/adbvip_06_04.htm), [Kahlo](https://www.astro.com/adbvip/adbvip_07_06.htm), [Snoop Dogg](https://www.astro.com/adbvip/adbvip_10_20.htm), [Disney](https://www.astro.com/adbvip/adbvip_12_05.htm).
Event dates: [Apple Newsroom](https://www.apple.com/newsroom/2007/01/09Apple-Reinvents-the-Phone-with-iPhone/), [FEC Federal Elections 2008](https://www.fec.gov/introduction-campaign-finance/election-results-and-voting-information/federal-elections-2008/), [California Secretary of State](https://elections.cdn.sos.ca.gov/sov/2003-special/sov-complete.pdf), [Oscars 1983](https://www.oscars.org/oscars/ceremonies/1983), [Television Academy 2002](https://www.televisionacademy.com/awards/nominees-winners/2002/outstanding-lead-actress-in-a-comedy-series), [Royal Family wedding record](https://www.royal.uk/wedding-prince-william-and-miss-catherine-middleton), [Angelina Jolie biography](https://en.wikipedia.org/wiki/Angelina_Jolie), [Frida Kahlo biography](https://en.wikipedia.org/wiki/Frida_Kahlo), [Snoop Dogg biography](https://en.wikipedia.org/wiki/Snoop_Dogg), [Walt Disney Family Museum](https://www.waltdisney.org/blog/who-did-walt-disney-marry).
## Pre-Registered Replay Logic
- D1 event-house ownership and occupation.
- D10 for career; D9 for marriage.
- A10 for career; UL for marriage.
- Functional Benefic/Malefic by Lagna.
- Vimshottari Mahadasha and Antardasha at the event date.
- Narayana Dasha at event age.
- Jupiter-Saturn Double Transit PAC for house 10 or 7.
Thresholds were frozen before the batch run: `>=7 strong`, `4-6 weak`, `<4 miss`.
## Findings
1. Marriage timing is stronger in this sample: `5/5` activation recall, including three strong hits.
2. Career timing is weaker: `3/5` activation recall and no strong hit. Public-office elevation is not captured well by direct 10/6/9/11 ownership alone.
3. General missing career layers: D10 Lagna/10L hierarchy, A10 sign activation, Amatyakaraka, Raja-yoga activation, Rahu/Ketu dispositor results, and Varshaphala/Tajika annual confirmation.
4. Double Transit is confirmation, not a standalone verdict.
5. `80%` must not be advertised as predictive accuracy: five hits are weak, exact-label rate is `30%`, and no negative controls were tested.
6. Do not tune thresholds on these same ten cases. Freeze v2 rules, then validate on a new holdout batch.
## Technique Audit
| Technique | Status | Notes |
|---|---|---|
| D1 | used | All 10 cases |
| D9 / D10 | used | Domain-specific |
| UL / A10 | used | Lord linkage included |
| Functional Benefic/Malefic | used | Lagna-specific roles retained |
| Vimshottari MD/AD | used | Event-date boundaries |
| Narayana Dasha | used | Event-age sign/lord |
| Double Transit PAC | used | House 7 or 10 |
| MEVG / Global Web Evidence | used | Astro-Databank plus independent event sources |
| Real Case Calibration | used | 10 structured cases; positive events only |
| VedAstro official raw | blocked | `official_snapshot_budget_exhausted` |
| PyJHora / JHora parity | blocked | Missing canonical fixture; JHora automation absent |
| jyotishganit | partial | Importable readiness only; not event-timing oracle |
## Next Holdout Design
- Add 10 new cases not used here: 5 public-status career events and 5 marriages.
- Add sourced negative-control windows to estimate specificity and balanced accuracy.
- Freeze v2 career rules before holdout: node dispositor, D10 10L, A10 transit/dasha, AmK, Raja yoga, annual chart.
- Keep v1 and v2 reports side by side; reject rules that improve training cases but fail holdout.
docs/research/public_real_case_probe3_2026_07_11.md
+44
View File
@@ -0,0 +1,44 @@
# 3 个独立公开案例补充检测（2026-07-11）
## 设计
沿用冻结 V2，不修改阈值、不先看星盘选人。三案全部为 Astro-Databank Rodden AA，且与前 20 人不重复：
| 人物 | 领域 | 公开事件 | 来源 |
|---|---|---|---|
| Donald Trump | career/public power | 2017-01-20 就任美国总统 | [美国国会就职委员会](https://www.inaugural.senate.gov/58th-inaugural-ceremonies/) |
| Leonardo DiCaprio | career/award | 2016-02-28 获奥斯卡最佳男主角 | [Academy Awards](https://www.oscars.org/oscars/ceremonies/2016) |
| Meghan Markle | legal marriage | 2018-05-19 与 Prince Harry 结婚 | [The Royal Family](https://www.royal.uk/wedding-duke-and-duchess-sussex) |
出生资料逐案保存在 `references/real_case_calibration/replay_manifest_probe3_v2.json`。
## 结果
| 人物 | 分数 | 判定 | 主要命中证据 |
|---|---:|---|---|
| Donald Trump | 3 | miss | Narayana lord 事业宫关联；Double Transit strong |
| Leonardo DiCaprio | 1 | miss | Jupiter 落事业事件宫 6 |
| Meghan Markle | 7 | strong_hit | Jupiter 婚姻 karaka；Saturn 为 7L；D9 7L；Double Transit strong |
补充样本：`1 strong + 0 weak + 2 miss`，正事件激活召回和精确标签率均为 `1/3`。样本太小，不能据此晋级或降级规则，但必须作为 V2 泛化反证公开。
合并 23 案例后：
- 总体：`9 strong + 8 weak + 6 miss`，正事件激活召回 `17/23 = 0.7391`，精确标签率 `9/23 = 0.3913`。
- 事业：`8/12 = 0.6667` 激活召回，`4/12 = 0.3333` 精确标签率。
- 婚姻：`9/11 = 0.8182` 激活召回，`5/11 = 0.4545` 精确标签率。
- balanced accuracy 仍 blocked：没有负事件控制样本。
## 新发现
1. 事业缺口不只限政治身份。DiCaprio 的明确奖项事件同样漏判，说明当前 D10/A10 层只检查活动大运星是否等于上升主、10L、AmK 或落 10 宫，覆盖不足。
2. Trump 的 Jupiter/Jupiter 与强双重过境仍未跨阈值，证明通用宫位加分不能替代 D10 Raja Yoga、行星相位、AL-A10、年度盘及公众权力专项裁决。
3. Meghan 的婚姻事件完整命中，支持现有 D1 功能宫主 + D9 7L + karaka + Double Transit 的婚姻组合，但单案不能证明整体准确率。
4. 不应按这三案立即新增分数。下一步应先冻结 V3 候选：D10 宫主相位/Raja Yoga、Narayana AD/PD、Varshaphala；再用新的至少 10 案例验证。
机器报告：
- `docs/benchmark/public_real_case_probe3_v2_2026_07_11.json`
- `docs/benchmark/public_real_case_23_case_observation_2026_07_11.json`
边界：全部是正事件回放，不是科学预测准确率；VedAstro official raw 与三引擎 parity 未因此闭环。
docs/superpowers/plans/2026-07-11-real-case-holdout-v2.md
+61
View File
@@ -0,0 +1,61 @@
# Real-Case Holdout V2 Implementation Plan
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** Add ten new research-grade holdout cases, compare frozen v1/v2 Jyotish replay logic across twenty cases, and promote only improvements that generalize to holdout data.
**Architecture:** Keep batch 1 immutable as discovery/training evidence. Store batch 2 separately, run both rule versions through one benchmark runner, and generate batch/combined comparison reports. Production orchestration receives only the promoted rule version plus explicit external-oracle and specificity boundaries.
**Tech Stack:** Python 3, Swiss Ephemeris-backed local CLI, JSON manifests/schemas, pytest, public Astro-Databank and independently sourced event records.
## Global Constraints
- Batch 2 must contain ten new people: five career events and five legal marriages.
- Birth time must be Rodden A or AA; event date must have primary or verified-secondary source.
- Freeze v2 before observing batch-2 results.
- V2 additions: node dispositor, D10/D9 Lagna-lord and domain-house lord, A10/UL lord, Amatyakaraka/Darakaraka, and annual-layer audit when available.
- Do not change score thresholds after batch-2 results.
- No user birth data or private conversation feedback.
- No scientific accuracy claim without sourced negative controls.
### Task 1: Freeze V2 Contract
**Files:**
- Modify: `tests/test_public_real_case_benchmark.py`
- Modify: `scripts/public_real_case_benchmark.py`
- [ ] Add failing tests for explicit `v1` and `v2` rule versions.
- [ ] Add deterministic v2 signal helpers and preserve v1 output.
- [ ] Verify v1 batch-1 results remain unchanged.
### Task 2: Add Holdout Manifest
**Files:**
- Create: `references/real_case_calibration/replay_manifest_holdout_v2.json`
- Modify: `tests/test_real_case_replay_validator.py`
- [ ] Add failing validation test for ten new A/AA cases and 5/5 domain split.
- [ ] Research and import birth/event sources.
- [ ] Validate no person overlaps batch 1.
### Task 3: Run V1/V2 Holdout Comparison
**Files:**
- Modify: `scripts/public_real_case_benchmark.py`
- Create: `docs/benchmark/public_real_case_holdout_v2_2026_07_11.json`
- [ ] Add batch comparison summary and rule-promotion decision.
- [ ] Run v1 and frozen v2 on batch 2.
- [ ] Run combined twenty-case summary.
- [ ] Promote v2 only if holdout recall/exact-label improve without more blocked cases.
### Task 4: Integrate and Document
**Files:**
- Modify: `scripts/unified_consultation_orchestrator.py`
- Create: `docs/research/public_real_case_20_case_closure_2026_07_11.md`
- Modify: `docs/research/pre_work_error_ledger.md`
- [ ] Expose promoted benchmark summary and remaining gaps.
- [ ] Document misses, conflicts, external-engine states, and next negative-control design.
- [ ] Run focused tests, privacy scan, diff check, and pre-work gate.