chore(rectification): re-freeze sealed holdout and offset sweep for D30 and Venus roles at scoring-13 (ERR-110, BUG-1560, BUG-1570)

FREEZE / REPORT constants first, --freeze, then replay: d30_venus_2026_11_04.
Contract rotated with previous = audit_wave2_2026_11_04 (kept byte-for-byte);
freshness test and frontend confirmation-gate test updated.

Versus audit_wave2_2026_11_04 (product accepted these costs 2026-11-04, no
tuning):
- sealed 20: 17 identical / 3 changed (case 5 rank 1 -> 3, case 18 12 -> 10,
  case 14 reasons only); top_1 0.50 -> 0.45, MAE 6.65 -> 7.05; top_3 0.50 and
  coverage 0 unchanged. All from the D30 table.
- reported offset 900: 650 identical / 250 changed; top-1 hits at
  +-15/30/60 14/17/15 -> 4/3/0 of 300 (all from Venus roles); top-3 and
  delivery coverage unchanged at every radius; mean minute error
  19.79 -> 19.51 (from D30).
Attribution from single-fix replays on git-archive copies: D30 alone 3 sealed
/ 166 offset trials, Venus alone 0 / 108; they overlap only in case 20.

BUG-1560 and BUG-1570 resolved; ledger and CHANGELOG lines added.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyeZrYn6ryNcSe5Y2Y

CHANGELOG.md

@@ -1,5 +1,11 @@
 # 印度占星 Skill 更新日志
 
+## 2026-11-04 — D30 偶数星座与白羊 / 天蝎上升金星按古典出处改正，生时校正算法升到 scoring-13
+
+- 完整解读分盘表与生时校正用的 D30：偶数星座 12–20° 双鱼、20–25° 摩羯、25–30° 天蝎（BPHS 第 6 章；以前是摩羯 / 天蝎 / 双鱼），与星盘页、Shadbala、D30 专项一致（BUG-1560）。
+- 白羊、天蝎上升的金星改判为功能凶星（BPHS 34.20、34.35；以前判中性），数据卡、报告、星盘页功能角色与瑜伽引擎同步（BUG-1570）。
+- 两项都进生时校正打分，算法身份升到 `rectification-v5-matrix-scoring-13`；旧结果打开为只读并可重新比较。产品知情接受：密封 20 例影子头名率 0.50 → 0.45，报时窗口 900 次回放头名命中 46 → 7，交付覆盖不变；没有调参追回。Skill 版本不变；没有数据库迁移。
+
 ## 2026-11-04 — 分盘 D16、D20、D27、D40、D45 与星盘页 D30 按 BPHS 改正起点
 
 - 十六分盘里 D16、D20、D45 按动 / 定 / 变星座定起点，D27 按火 / 土 / 风 / 水定起点（BPHS 第 6 章）。以前完整解读和星盘页 / 对话分盘谱用的是两套互不相同、且都不符 BPHS 的起点；改后两处一致，与 PyJHora、jyotishganit 同方法逐份一致（BUG-1560、BUG-1561）。

docs/BUG_HISTORY.md

@@ -21368,8 +21368,8 @@
 
 ## BUG-1560 | 全读 / 生时校正用的分盘 D16、D20、D27、D45 起点按奇偶星座算；D30 偶数星座后三段星座错位（D30 待产品决定）
 
-- 状态：D16 / D20 / D27 / D45 resolved（引擎 + 回归测试 + ERR-110 重冻，回放不变；未部署）；`varga.py` 的 D30 偶数星座 blocked（缺陷已证实，修正会改生时校正分数，需要 scoring-13 算法身份与新 memoization golden，待产品决定）
-- 首次发现 / 最近更新：2026-11-04（数据核对第二轮 G：19 张固定样本，Raman 与 Lahiri 两种岁差、平均交点，两边显式传参，对 PyJHora 4.8 与 jyotishganit）/ 2026-11-04
+- 状态：resolved（D16 / D20 / D27 / D45 与 `varga.py` 偶数星座 D30 全部按 BPHS 改正；D30 由产品 2026-11-04 决定入算，校正身份升到 scoring-13、ERR-110 重冻 `d30_venus_2026_11_04`；未部署）
+- 首次发现 / 最近更新：2026-11-04（数据核对第二轮 G：19 张固定样本，Raman 与 Lahiri 两种岁差、平均交点，两边显式传参，对 PyJHora 4.8 与 jyotishganit）/ 2026-11-04（D30 入算）
 - 影响面：`scripts/varga.py::varga_map`（默认 `classical_local` 模式）。读它的有：全读 `modules.varga_full`（报告、PL9 导出、`varga-full` 命令）、`flexible_birth_time_profile`、`rectification_varga_segments_api`、`active_rectification_questions`，以及生时校正打分（`active_rectification_event_engine` 的 `health_pressure` 读 D30，`minute_rectification_feature_facts_v4` 读 D30）。`mode='vedastro'` 不变。
 - 现象：同岁差、同经度下，本仓与 PyJHora「traditional Parasara」（方法 1）的星座一致率：D16 26–27%、D20 26–27%、D27 25%、D45 14%、D30 70–72%；jyotishganit 在前四张上与 PyJHora 100% 一致。19 张盘里 D45 上升 19 张全错，D16 / D20 上升 16 张错。
 - 触发条件：任何一张盘读这几张分盘。
@@ -21377,10 +21377,11 @@
 - 修复：按 BPHS 第 6 章（Santhanam 英译；PVR《Vedic Astrology: An Integrated Approach》第 6 章同表）改 `varga_map`：D16、D45 动白羊 / 定狮子 / 变射手；D20 动白羊 / 定射手 / 变狮子；D27 火白羊 / 土巨蟹 / 风天秤 / 水摩羯。D3、D7、D9、D10、D12、D24、D40、D60 本来就对，未动。D30 偶数星座（应为 12–20° 双鱼、20–25° 摩羯、25–30° 天蝎）这次没有改，代码处加了 KNOWN DEFECT 注释：先改过一次并按 ERR-110 重冻回放，生时校正结果变了（见下），快速门 `test_rectification_engine_memoization` 8 条、`test_rectification_dated_transitions` 1 条 golden 转红，按 BUG-1260 / BUG-1275 先例要升 `rectification-v5-matrix-scoring-13`、新增 memoization golden v6，属于产品决定，故撤回。`references/shodasavarga-complete-guide.md` 里 D4、D10、D24、D27、D30、D40 的起算说明一并改正（D24 写成「从本星座起」、D40 写成「动定变」等，与 BPHS 不符）。
 - 验证：新增 `tests/test_varga_bphs_starts_audit_g.py`（D16/D20/D27/D40/D45 每个星座每一份对独立写出的 BPHS 表，`varga` 与 `divisional_charts_extended` 两处；D30 每 0.1° 对 BPHS，`divisional_charts_extended`、`trimshamsa_d30`、`shadbala` 三处一致；装了 PyJHora 时逐份对 PyJHora 方法 1；`varga.py` 偶数星座 D30 用 strict xfail 锁住这条已知缺陷，修了就必须去掉标记）。在 origin/staging 的代码上，D16/D20/D27/D40/D45 与 D30 的断言都失败。19 张盘复跑：同经度下 D16/D20/D27/D45 190 / 190 与 PyJHora 一致（改前 14–27%）；`varga.py` 的 D30 仍是 70–72%。
 - 冻结身份（ERR-110）：`varga.py` 在生时校正冻结身份里。按 ERR-110 改 FREEZE / REPORT 常量后 `--freeze` 新建记录并回放，标签 `audit_g_2026_11_04`，合同 `references/rectification_sealed_holdout.v1.json` 按 11-04 先例轮换，旧记录逐字节保留。与 `moon_paksha_2026_11_04` 逐条逐字段比：密封 20 条、报时窗口 900 条全部相同，`metrics`、`summary` 不变，相对 09-20 历史报告的 changed_trial_count 仍为 8 / 581（D16/D20/D27/D45 与 `divisional_charts_extended` 都不进校正打分）。撤回前（含 D30 改正）那次回放的结果留作产品决定的依据：密封 20 条里 3 条变（第 5 例 true_rank 1 → 3、minute_error 1 → 9，第 18 例 12 → 10，第 14 例只有 sparse_trial_reasons），top_1_rate 0.50 → 0.45、平均分钟误差 6.65 → 7.05；报时窗口 900 条里 166 条变（true_rank 前移 37、后移 118，top_1_minute_error 29 条），头名命中 46 / 900 与交付覆盖 818 / 900 不变，900 条平均分钟误差 19.79 → 19.51。只把 D30 偶数表换回旧表即与 `moon_paksha_2026_11_04` 逐条相同，变化全部来自 D30。合入 staging 时（分支 `codex/audit-wave2-integration-20261104`）G / H / J 三支一起合并，各支的 `audit_g` / `audit_h` / `audit_j` 记录只对各自分支的代码成立，原样保留为中间记录；在合并后的代码上按 ERR-110 只重冻一次为 `audit_wave2_2026_11_04`，合同上一份指回 `moon_paksha_2026_11_04`。逐条逐字段比：密封 20 条、报时 900 条全部相同，`metrics`、`summary` 不变，changed_trial_count 仍为 8 / 581。
-- 防复发：上述测试与 strict xfail；分盘起点只在 `varga_map` 一处写，`divisional_charts_extended` 的 D16/D20/D27/D40/D45 也改为读它（BUG-1561）。对照外部引擎前先确认两边方法编号（PyJHora 每张分盘有 3–6 种方法，默认方法 1）。动分盘表前先查它是否进校正打分（`active_rectification_event_engine`、`minute_rectification_feature_facts_v4` 读 D2/D3/D4/D5/D7/D9/D10/D12/D24/D30）。
+- 决策与落地（2026-11-04，产品决定）：产品知情接受校正分数下降，决定计算按出处走（与 BUG-1570 同一次变更），按 BUG-1158 红线记录签字：本次头名率下降已经产品明确同意，不调参追回。`varga.py` 偶数星座 D30 改为 12–20° 双鱼、20–25° 摩羯、25–30° 天蝎，KNOWN DEFECT 注释删除，strict xfail 改为普通测试，BPHS 0.1° 扫描覆盖 `varga.py` 全部星座。按 BUG-1181 / BUG-1260 / BUG-1275 先例，生时校正算法身份 `rectification-v5-matrix-scoring-12` → `-13`（策略 v4、输入合同 v5、日期窗合同不变；SQL 守卫 `scoring-(9|[1-9][0-9]+)` 已接受 13，无迁移）；记忆化 golden 新写 v6（`source_commit` 18c685c4），v5 逐字节保留并以 sha256 钉住（该公开请求候选分数不变，只有 D30 特征摩羯 → 双鱼、对应窗口转换行与特征哈希变）；`rectification-dated-transitions.native.json` 的 scan 用真实引擎重生成（D30 段起点摩羯 → 双鱼，保留 CRLF）；跨午夜 scoring-13 golden 由 `midnight_date_anchor_regression.py --golden` 生成，scoring-12 golden 留作历史并在 scoring-13 下只读打开、可重新比较；`v9EngineVersion()` 缺省串同步。ERR-110 重冻为 `d30_venus_2026_11_04`（合同上一份 `audit_wave2_2026_11_04`）。对 `audit_wave2_2026_11_04` 逐条比（两项合计）：密封 20 条 17 同 3 变（第 5 例 true_rank 1 → 3、minute_error 1 → 9；第 18 例 12 → 10；第 14 例只有 sparse_trial_reasons），top_1_rate 0.50 → 0.45、平均分钟误差 6.65 → 7.05，top_3 0.50、确认覆盖 0 不变；报时 900 条 650 同 250 变（9 个案例；true_rank 前移 47、后移 188，头名丢 39、得 0，交付覆盖不变 818 / 900），头名命中 ±15 / ±30 / ±60（每档 300 条）14 / 17 / 15 → 4 / 3 / 0（0.0467 / 0.0567 / 0.0500 → 0.0133 / 0.0100 / 0.0000；窗口内口径 ±15 为 220 条，0.0636 → 0.0182），top-3 0.1364 / 0.1133 / 0.0967 与交付覆盖 0.9955 / 0.9967 / 1.0 三档全部不变，900 条平均分钟误差 19.79 → 19.51；相对 09-20 历史报告 changed_trial_count 8 → 9、581 → 686。归因（在 `git archive` 副本上各单独改一项、各自冻结回放）：D30 单独 = 密封全部 3 条变化与 0.50 → 0.45；报时 166 条（7 案例，true_rank 前移 37 / 后移 118，头名命中不变，平均分钟误差 19.79 → 19.51）。金星单独（BUG-1570）= 密封 0 条；报时 108 条（4 案例），头名命中的全部下降（46 → 7 / 900）。两项只在第 20 例重叠（D30 23 条、金星 24 条，合并后 23 条），其余案例合并结果与单项结果逐条相同。
+- 防复发：上述测试（strict xfail 已转为普通测试）；分盘起点只在 `varga_map` 一处写，`divisional_charts_extended` 的 D16/D20/D27/D40/D45 也改为读它（BUG-1561）。对照外部引擎前先确认两边方法编号（PyJHora 每张分盘有 3–6 种方法，默认方法 1）。动分盘表前先查它是否进校正打分（`active_rectification_event_engine`、`minute_rectification_feature_facts_v4` 读 D2/D3/D4/D5/D7/D9/D10/D12/D24/D30）。
 - 关联记录：BUG-1500（D60）、BUG-1561、BUG-1562。
 - 复发自：无
-- 修复版本：分支 `codex/audit-vargas-20261104`（未推送）。
+- 修复版本：分支 `codex/audit-vargas-20261104`（D16/D20/D27/D45）；D30 偶数星座 + scoring-13 + 重冻：分支 `codex/d30-venus-roles-scoring-20261104`（18c685c4 引擎、9fd3fcd5 身份与 golden、重冻提交见同分支；未推送）。
 
 ## BUG-1561 | 星盘页与咨询分盘谱的 D16、D20、D27、D30、D40、D45 从本星座起算，没有一种已发表的方法这样算
 
@@ -21491,19 +21492,19 @@
 
 ## BUG-1570 | 功能吉凶 profile v2 漏了 BPHS 34 章两条明文：白羊、天蝎上升的金星应判凶，引擎判中性
 
-- 状态：blocked（引擎与它自己引用的出处不一致，已证实；改动会让生时校正头名掉 3～5 个百分点，按 BUG-1158 红线待产品与占星师决定，本单未改）
-- 首次发现 / 最近更新：2026-11-04（数据核对第二波 I：12 上升 × 7 星功能吉凶逐格对照 BPHS 34、Laghu Parashari 总则、PyJHora）/ 2026-11-04
+- 状态：resolved（产品 2026-11-04 决定按 BPHS 34.20 / 34.35 采纳；与 BUG-1560 的 D30 同一次升 scoring-13、ERR-110 重冻 `d30_venus_2026_11_04`；未部署）
+- 首次发现 / 最近更新：2026-11-04（数据核对第二波 I：12 上升 × 7 星功能吉凶逐格对照 BPHS 34、Laghu Parashari 总则、PyJHora）/ 2026-11-04（采纳）
 - 影响面：`scripts/functional_benefics.py` `ROLE_OVERRIDES`；读功能吉凶的所有地方（数据卡 `functional_benefic_malefic`、父母卡 `functional` 标签、Technique Audit、报告、星盘页功能角色表、瑜伽引擎 `functional_malefics()`、生时校正 `*_functional_*_auxiliary` 打分）。
 - 现象：白羊上升金星（2、7 宫主）、天蝎上升金星（7、12 宫主）在 `functional_neutrals`；泰勒、琵雅芙（天蝎上升）数据卡上金星是中性。
 - 触发条件：上升为白羊或天蝎。
 - 根因：profile v2 声明「逐上升明文优先于总则」（`references/functional-role-profile.md`），但 `ROLE_OVERRIDES` 只录了上游反馈涉及的格。BPHS 34.20（白羊）梵文「mandasaumyasitāḥ pāpāḥ」、34.35（天蝎）「sitajñaśanayaḥ pāpāḥ」都点名金星（sita）为凶；jyotishvidya.com/ch34.htm 英译（profile 自己引用的出处）、仓内 10-02 T1 分支的逐颂表（vedpuran 英译 + 梵文逐词）读法相同。金星落到总则（只管角宫 / 2 宫 → 中性）。Laghu Parashari 总则本身对这两格只给「角宫主吉星失吉（Venus 最重）」，不直接判凶，所以是 BPHS 明文与引擎不一致，不是流派差。
 - 试改与回放（未提交）：两格加 `"Venus": "malefic"` 后按 ERR-110 冻结并回放（`audit_i_2026_11_04`，记录留在本轮 scratchpad，未入库）：密封 20 条与 `moon_paksha_2026_11_04` 全同；报时窗口 900 条 108 条变（4 个案例，`true_rank` 105 条、`top_1_hit` 39 条、头名分钟误差 42 条），头名率 ±15 / ±30 / ±60：0.0467 → 0.0133、0.0567 → 0.0100、0.0500 → 0.0000，交付覆盖不变。打分语义变了，按 BUG-1181 还要升 `ALGORITHM_VERSION`。超过 1 个百分点红线，已撤回改动，`functional_benefics.py` 与冻结记录未动。
-- 修复：未改。待决定：①采纳（加两格、升 scoring-13、重冻、改 golden）；②不采纳，在 profile 文档里写明这两格有意按总则；③只在数据卡标注冲突、不进校正打分。
-- 验证：本轮对照表与回放数字见报告（scratchpad `audit-i/report.md`）。
-- 防复发：待决定；建议给 `ROLE_OVERRIDES` 加「12 上升逐颂全表」测试，凡与 34.19–44 明文不同的格必须在 profile 里写原因。
+- 修复：产品 2026-11-04 选方案①（采纳），知情接受校正头名下降，按 BUG-1158 红线记录签字，不调参追回。`ROLE_OVERRIDES` 白羊、天蝎各加 `"Venus": "malefic"`（profile 名不变，`references/functional-role-profile.md` 例外清单补两格）；`role_basis` 为 sign-specific exception。生时校正身份升 scoring-13、记忆化 golden v6、ERR-110 重冻 `d30_venus_2026_11_04` 与 BUG-1560 同一次完成（数字见 BUG-1560「决策与落地」）。本项单独的效果（`git archive` 副本单独冻结回放，对 `audit_wave2_2026_11_04`）：密封 20 条全同；报时 900 条 108 条变（4 案例，true_rank 前移 11 / 后移 94，头名丢 39），头名命中 ±15 / ±30 / ±60 14 / 17 / 15 → 4 / 3 / 0 / 300，top-3 与交付覆盖不变；与 audit-I 当时数字一致。合并后报时头名下降全部来自本项（D30 单独不改头名命中数）。
+- 验证：`tests/test_functional_yogakaraka_kendra_trikona.py::test_venus_is_functional_malefic_for_aries_and_scorpio`（期望独立写出，不读 `ROLE_OVERRIDES`；改前红、改后绿）；`test_functional_roles_are_part_of_the_production_identity` 照旧锁功能吉凶文件在冻结身份里。遗留：前端捕获 golden（`consult-evidence-card-golden.json` 第 3 张盘、`consult-biography-backtest-golden.json` 两张天蝎盘）仍是改前的「金星中性」快照，`consult-upstream-functional-v2-20261002.test.ts` 读的是快照不是现算，未重生成（快照同时落后于 BUG-1571 等其他引擎变化，重生成另开单）。
+- 防复发：上述测试；仍建议给 `ROLE_OVERRIDES` 加「12 上升逐颂全表」测试，凡与 34.19–44 明文不同的格必须在 profile 里写原因（未做）。
 - 关联记录：BUG-1158（profile v2 采纳）、BUG-1181（功能吉凶进校正打分须升算法身份）。
 - 复发自：无
-- 修复版本：无（blocked）。
+- 修复版本：分支 `codex/d30-venus-roles-scoring-20261104`（18c685c4 引擎、9fd3fcd5 scoring-13，重冻提交见同分支；未推送）。
 
 ## BUG-1571 | 2026-06-27 改了瑜伽表达式的辅助函数名，规则表没跟着改：9 条瑜伽（含 Matru Sneha、Bhratruvriddhi）四个月从未成立
 

docs/research/pre_work_error_ledger.md

@@ -23,6 +23,7 @@ Purpose: read this file before substantial project work. It exists to stop repea
 - 数据核对第二波 I 瑜伽与功能吉凶（worktree `/workspace/wt-i`，`codex/audit-yoga-roles-20261104`）：`pre_work_check.py` exit 0。两边显式 Raman + 平均交点，19 张盘上升与行星星座 0 差。BUG-1571：规则表里的 custom 表达式还在调 06-27 改名前的 `pyjhora_*` 辅助函数，NameError 被吞，9 条瑜伽从未成立；BUG-1572：`_eval_parivartana` 不解析 any_pair 的 "$a"。教训：yoga 引擎「表达式出错 = 不成立」，改名 / 改签名后必须跑全表静态扫描（新测试已加），「某条瑜伽 19 张盘 0 次」先当成检测器坏了查。BUG-1570：白羊 / 天蝎金星按 BPHS 34.20 / 34.35 应判凶，试改后报时窗口头名掉 3～5 个百分点（108 / 900 条变），按红线撤回，待产品决定；只动 `yoga_engine.py` / `yoga_rules.json`（不在冻结身份里）时，密封 20 条、报时 900 条与 `moon_paksha_2026_11_04` 逐条相同，未重冻。`run_yoga_accuracy.py` 只用手写星座 / 宫位，不排盘，不涉及岁差。
 - 数据核对 J：Sthana / Dig / Drik（worktree `/workspace/wt-j`，`codex/audit-shadbala-rest-20261104`）：`pre_work_check.py` exit 0。本仓与 PyJHora 在 19 张盘加乔布斯盘上 Dig 140 / 140「一致」，但两边用的是同一个没折回的函数（PyJHora `_dig_bala`；它自己的 `_dig_bala_another` 是折回的）。这是第二次出现「两家一致 = 两家同错」（BUG-1546 之后）。BUG-1270 已按 BPHS 27.7 和 Raman GBB 例 14–15 修好。同一份经度两次复算，Drik 差了 0.01：求和顺序跟着 PYTHONHASHSEED 变，记为 BUG-1576，已修。两个修复一起重冻为 `audit_j_2026_11_04`。比较前后两次运行时，要固定 PYTHONHASHSEED，或者先确认被比较的函数本身是确定的。教训：对照某个外部引擎时，先查这个引擎有没有同一分量的多种写法，几种都跑一遍，再拿原书的例题核对。Sthana 和 Drik 用 Raman 标准盘例 13、例 55 逐项吻合。jyotishganit 在本机跑需要 Hipparcos 星表，下载被 SSL 拦截，改用 Spica 的 J2000 星表值替代；七星经度与 Lahiri 相差不超过 0.022°。jyotishganit 的上升点比我们晚约 1.08°，Piaf 和 Kahlo 两张盘的上升换了星座，不要把它的 Kendra / Dig 当对照。`jyotish_engine.MOOLATRIKONA` 里月亮写成金牛 0–3°，记为 BUG-1575，未修。全量 Shadbala 相关测试在负载 69 的机器上很慢，基线放在独立的干净 worktree（`/workspace/wt-j-base`）里跑，不占用改动中的 worktree。
 - 数据核对第二波合并（worktree `/workspace/wt-int2`，`codex/audit-wave2-integration-20261104`，基于 staging 8f15745c）：G、H、I、J 依次 `--no-ff` 合并。G / H / J 各自的 `audit_g` / `audit_h` / `audit_j` 冻结记录只对各自分支的代码成立，合并后的代码上哪一份都不是当前记录；合并时合同、FREEZE / REPORT 常量与两份门测试先保持 G 的状态，最后按 ERR-110 只重冻一次为 `audit_wave2_2026_11_04`，合同上一份指回 `moon_paksha_2026_11_04`，三份分支记录逐字节保留为中间记录。与 `moon_paksha_2026_11_04` 逐条逐字段比：密封 20 / 20、报时 900 / 900 全同，`metrics`、`summary` 不变，changed_trial_count 仍为 8 / 581。冲突只在文档（BUG_HISTORY、台账、CHANGELOG 全部保留）、冻结合同与 `run_chara_dasha_compare.py`（G、H 都改了岁差传参，取 H 的写法）。注意：`tests/test_narayana_rath_book_tables.py::test_rath_profile_is_display_only` 在 staging 8f15745c 上就失败（`scripts/annual_service/package.py` 也引用 `narayana_rath`），不是本轮造成。
+- BUG-1560 D30 + BUG-1570 金星功能凶入算（worktree `/workspace/wt-sc`，`codex/d30-venus-roles-scoring-20261104`，基于 staging 607a48b6；产品 2026-11-04 决定）：`pre_work_check.py` exit 0。两项一起升 `rectification-v5-matrix-scoring-13`、记忆化 golden v6（v5 逐字节保留）、跨午夜 scoring-13 golden、dated-transitions scan 重生成，ERR-110 只重冻一次为 `d30_venus_2026_11_04`。对 `audit_wave2_2026_11_04`：密封 3 / 20 条变（头名率 0.50 → 0.45，全部来自 D30），报时 250 / 900 条变（头名命中 46 → 7，全部来自金星；覆盖不变）。归因用 `git archive` 副本各改一项各自冻结回放（冻结记录放副本内、传绝对路径）。教训：①`midnight_date_anchor_regression.py --golden` 先断言 baseline 与当前同日 A/B 不变，分数变化的升版里 baseline 只能传当前树（只证明独立进程可复现），不能传旧树；②记忆化公开请求（1990-01-01 北京）候选分数这次没变，变的是 D30 特征与哈希，「golden 红」不等于「这张盘分数变了」；③两项在同一案例（第 20 例）上有交互，合并结果不是单项变化条数之和（166 + 108 − 15 重叠 ≠ 250），归因要逐条比对。前端捕获 golden（咨询卡、名人回测）仍是改前的金星中性快照，未重生成。
 
 ## 2026-11-03 · 输入框单行起步（方案 2，worktree `/workspace/wt-composer`）
 

docs/research/reported_offset_d30_venus_2026_11_04.freeze.json

@@ -0,0 +1,118 @@
+{
+  "record_version": "reported-offset-native-candidate-date-v3",
+  "frozen_at_utc": "2026-11-04T09:36:21.630661+00:00",
+  "ayanamsa": "raman",
+  "node_mode": "mean",
+  "radii_minutes": [
+    15,
+    30,
+    60
+  ],
+  "offsets_minutes": [
+    -30,
+    -20,
+    -15,
+    -10,
+    -8,
+    -5,
+    -3,
+    0,
+    3,
+    5,
+    8,
+    10,
+    15,
+    20,
+    30
+  ],
+  "minute_step": 1,
+  "dataset": "references/real_case_calibration/minute_rectification_holdout_v3.json",
+  "dataset_sha256": "45aa76ab79dfc6c6404b6252083e1aa5c7e2e2b7de811fc11042a8ad2da3f0ea",
+  "dataset_benchmark_id": "minute_rectification_fact_ranker_v4_holdout_v3",
+  "implementation_sha256": "894867c7290a63a2eef11a657a773bb0954ff1e399e095c7decbc77fd27df150",
+  "implementation_sha256_prefix": "894867c7290a63a2",
+  "historical_artifacts_manifest_sha256": "6102a26a840be207b5858b3a4c0509274468ae9071e86d308cbbac7371d6864e",
+  "production_scoring_files": [
+    "scripts/active_rectification_event_engine.py",
+    "scripts/active_rectification_events.py",
+    "scripts/ashtakavarga.py",
+    "scripts/dasha_analyzer.py",
+    "scripts/divisional_charts_extended.py",
+    "scripts/domain_calculation_service.py",
+    "scripts/functional_benefics.py",
+    "scripts/jaimini.py",
+    "scripts/minute_rectification_fact_ranker_v4.py",
+    "scripts/minute_rectification_feature_facts_v4.py",
+    "scripts/narayana_dasha.py",
+    "scripts/rectification/api_service.py",
+    "scripts/rectification/candidate_contrast.py",
+    "scripts/rectification/candidate_window.py",
+    "scripts/rectification/case_holdout.py",
+    "scripts/rectification/contracts.py",
+    "scripts/rectification/dasha_transition_proximity.py",
+    "scripts/rectification/decision_policy.py",
+    "scripts/rectification/event_probes.py",
+    "scripts/rectification/refinement_packet.py",
+    "scripts/rectification/scoring_service.py",
+    "scripts/shadbala.py",
+    "scripts/varga.py"
+  ],
+  "production_scoring_sha256": "9ba1c80f211c36ed5232e0f39c0192a4adc48a38a3e54c87e0cab7eba619609c",
+  "research_files": [
+    "scripts/research/reported_offset_sweep.py",
+    "scripts/research/cluster_width_lib.py",
+    "scripts/research/probe_supply_after_six.py",
+    "scripts/research/sealed_holdout_rerun.py",
+    "scripts/minute_rectification_blind_eval.py",
+    "scripts/minute_rectification_fact_blind_eval_v4.py",
+    "scripts/minute_rectification_holdout_validator.py"
+  ],
+  "research_implementation_sha256": "d89d1261ba4e0ddb064a4a7ffab90beceec1f19129a3c6a801a4f496c25e31f0",
+  "file_sha256": {
+    "scripts/active_rectification_event_engine.py": "dced0b398ad90bdec59c743a55ffe01613306127c17a1e44c8c9cfb569c57841",
+    "scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
+    "scripts/ashtakavarga.py": "c524da3f54b2ed9c080b78b33854854a0ca3d5d79b7e536bb1c3bc2be3e02852",
+    "scripts/dasha_analyzer.py": "3949b96813217fe624899856afec9f0b787c4cb0fea3a9a0d961990dbd11943a",
+    "scripts/divisional_charts_extended.py": "6050ee6706d0f27b8c406b1c06ac5b49cf6f13814a3f930d944598892650ed92",
+    "scripts/domain_calculation_service.py": "66923a2bc69daf65c965d2973c4b9234edbec5147909eaf3609b6b377ce3c7ca",
+    "scripts/functional_benefics.py": "f2c0b25cf0b112584ed54dada3c1403eb2f73760a9935719f023a17fb17ee867",
+    "scripts/jaimini.py": "706d20dcff89079063fd1857a36f19419604ef81c80227921c7a2ced60011ac9",
+    "scripts/minute_rectification_blind_eval.py": "07aa30d8bad3278669495d5fea8be937aaf6367c8af980ff4f2fe9aa84ccc6ff",
+    "scripts/minute_rectification_fact_blind_eval_v4.py": "bdf460e3467208e8b87345c5beb2128f3e22de7eeffd68f72b281b3ad9affc92",
+    "scripts/minute_rectification_fact_ranker_v4.py": "f1a0d8d2482cd754d2e7f253a9606b0373519435a2bf58cfc3753e2b9ae0fb76",
+    "scripts/minute_rectification_feature_facts_v4.py": "3d899a2cdd4825b8e32062443d487edcd2173a4ea55a36eb9f3abe587c0faf0f",
+    "scripts/minute_rectification_holdout_validator.py": "b60b1c752e58672beaee8b36eb3b2348169726cda070ec969db0f13e7ed715af",
+    "scripts/narayana_dasha.py": "9a847d3b8d05f90d4f275079c97af1f71e83a74f930e14bd8f3f37b293d91d1e",
+    "scripts/rectification/api_service.py": "089730097d3872a4f7b5d7dd5574bb7e9ab4d2e246d4a380800bc824d7979b95",
+    "scripts/rectification/candidate_contrast.py": "eee7da71c0574a08876404b78ca111153fa95fb83ace82b9fdca141d1992e273",
+    "scripts/rectification/candidate_window.py": "2fbc5058b12049b15fca375cdc125b8283e19f9f3e4bedcc291e344501891bef",
+    "scripts/rectification/case_holdout.py": "fe0e699b617d9e216acdfeff87af4221c1d6f4c101bf33e1dbf14e2bcd75a8b5",
+    "scripts/rectification/contracts.py": "c6dc6bd230e38f9f2126c224aae9ddbd6415304c15340f8c7cd3f06f6ef3160f",
+    "scripts/rectification/dasha_transition_proximity.py": "5ce4ed27b0f06c681abc34e5fd998fafb10c153a0070aa36c99ddfa869a2cbf2",
+    "scripts/rectification/decision_policy.py": "80e8de4680d19a052213bb821d2a9c94143a2962235aeb27f6ad81374d2e60d5",
+    "scripts/rectification/event_probes.py": "f5ca9d54501f67a1546fcf5b01da0c1277dec2e2c6df481884e8900d14909a7c",
+    "scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
+    "scripts/rectification/scoring_service.py": "07f8a04d6ff2a6ce7cd4e5bd42a848c3aedcbff8ec8f49668b4817993b8a6eb0",
+    "scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
+    "scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
+    "scripts/research/reported_offset_sweep.py": "34b06eaf95eaec492039ab546ede9dc473f11081e08669fc247855493d851c2e",
+    "scripts/research/sealed_holdout_rerun.py": "0d069a6cc6c31a37646c319476a94df3cec3b0bd2c358554aaacd133c9a38e57",
+    "scripts/shadbala.py": "6a586b504b45d96acf593393051b878b12068e80f2799fe0ebbea2d433658192",
+    "scripts/varga.py": "05ea7711dea8cce11f5b831eac70d9f694b9230c641ba4bdc3e62e3bc1cc5416"
+  },
+  "hash_scope": "explicit_identity_file_sets_not_a_transitive_dependency_lock",
+  "scorer": "native_event_contribution_matrix_not_shadow_fact_ranker",
+  "delivery": "initial_signature_clusters_peak_gap_lt_8_envelope_no_answers_no_elimination",
+  "rank": "score_desc_then_sha256(benchmark_id:case_id:candidate_time)",
+  "grid": "every_minute_inclusive_not_production_two_minute_sampling",
+  "cross_midnight": "date_aware_candidates_distance_and_native_single_matrix",
+  "evaluator_sha256": "34b06eaf95eaec492039ab546ede9dc473f11081e08669fc247855493d851c2e",
+  "replay_revision": "native_candidate_date_v3",
+  "supersedes": "candidate_date_grouped_v2_identity_and_path_not_assumed_numerically_wrong",
+  "is_blind_evaluation": false,
+  "truth_hidden_from_ranker": true,
+  "official_valid_independent_blind": false,
+  "official_blind_trial_count": 0,
+  "results_previously_seen": true,
+  "must_not_use_for_tuning": true
+}

docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.freeze.json

@@ -0,0 +1,116 @@
+{
+  "record_version": "exposed-v3-fixed-protocol-cross-midnight-rerun-v2",
+  "extended_identity": {
+    "historical_artifacts_manifest_sha256": "6102a26a840be207b5858b3a4c0509274468ae9071e86d308cbbac7371d6864e",
+    "production_scoring_files": [
+      "scripts/active_rectification_event_engine.py",
+      "scripts/active_rectification_events.py",
+      "scripts/ashtakavarga.py",
+      "scripts/dasha_analyzer.py",
+      "scripts/divisional_charts_extended.py",
+      "scripts/domain_calculation_service.py",
+      "scripts/functional_benefics.py",
+      "scripts/jaimini.py",
+      "scripts/minute_rectification_fact_ranker_v4.py",
+      "scripts/minute_rectification_feature_facts_v4.py",
+      "scripts/narayana_dasha.py",
+      "scripts/rectification/api_service.py",
+      "scripts/rectification/candidate_contrast.py",
+      "scripts/rectification/candidate_window.py",
+      "scripts/rectification/case_holdout.py",
+      "scripts/rectification/contracts.py",
+      "scripts/rectification/dasha_transition_proximity.py",
+      "scripts/rectification/decision_policy.py",
+      "scripts/rectification/event_probes.py",
+      "scripts/rectification/refinement_packet.py",
+      "scripts/rectification/scoring_service.py",
+      "scripts/shadbala.py",
+      "scripts/varga.py"
+    ],
+    "production_scoring_sha256": "9ba1c80f211c36ed5232e0f39c0192a4adc48a38a3e54c87e0cab7eba619609c",
+    "research_files": [
+      "scripts/research/reported_offset_sweep.py",
+      "scripts/research/cluster_width_lib.py",
+      "scripts/research/probe_supply_after_six.py",
+      "scripts/research/sealed_holdout_rerun.py",
+      "scripts/minute_rectification_blind_eval.py",
+      "scripts/minute_rectification_fact_blind_eval_v4.py",
+      "scripts/minute_rectification_holdout_validator.py"
+    ],
+    "research_implementation_sha256": "d89d1261ba4e0ddb064a4a7ffab90beceec1f19129a3c6a801a4f496c25e31f0",
+    "file_sha256": {
+      "scripts/active_rectification_event_engine.py": "dced0b398ad90bdec59c743a55ffe01613306127c17a1e44c8c9cfb569c57841",
+      "scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
+      "scripts/ashtakavarga.py": "c524da3f54b2ed9c080b78b33854854a0ca3d5d79b7e536bb1c3bc2be3e02852",
+      "scripts/dasha_analyzer.py": "3949b96813217fe624899856afec9f0b787c4cb0fea3a9a0d961990dbd11943a",
+      "scripts/divisional_charts_extended.py": "6050ee6706d0f27b8c406b1c06ac5b49cf6f13814a3f930d944598892650ed92",
+      "scripts/domain_calculation_service.py": "66923a2bc69daf65c965d2973c4b9234edbec5147909eaf3609b6b377ce3c7ca",
+      "scripts/functional_benefics.py": "f2c0b25cf0b112584ed54dada3c1403eb2f73760a9935719f023a17fb17ee867",
+      "scripts/jaimini.py": "706d20dcff89079063fd1857a36f19419604ef81c80227921c7a2ced60011ac9",
+      "scripts/minute_rectification_blind_eval.py": "07aa30d8bad3278669495d5fea8be937aaf6367c8af980ff4f2fe9aa84ccc6ff",
+      "scripts/minute_rectification_fact_blind_eval_v4.py": "bdf460e3467208e8b87345c5beb2128f3e22de7eeffd68f72b281b3ad9affc92",
+      "scripts/minute_rectification_fact_ranker_v4.py": "f1a0d8d2482cd754d2e7f253a9606b0373519435a2bf58cfc3753e2b9ae0fb76",
+      "scripts/minute_rectification_feature_facts_v4.py": "3d899a2cdd4825b8e32062443d487edcd2173a4ea55a36eb9f3abe587c0faf0f",
+      "scripts/minute_rectification_holdout_validator.py": "b60b1c752e58672beaee8b36eb3b2348169726cda070ec969db0f13e7ed715af",
+      "scripts/narayana_dasha.py": "9a847d3b8d05f90d4f275079c97af1f71e83a74f930e14bd8f3f37b293d91d1e",
+      "scripts/rectification/api_service.py": "089730097d3872a4f7b5d7dd5574bb7e9ab4d2e246d4a380800bc824d7979b95",
+      "scripts/rectification/candidate_contrast.py": "eee7da71c0574a08876404b78ca111153fa95fb83ace82b9fdca141d1992e273",
+      "scripts/rectification/candidate_window.py": "2fbc5058b12049b15fca375cdc125b8283e19f9f3e4bedcc291e344501891bef",
+      "scripts/rectification/case_holdout.py": "fe0e699b617d9e216acdfeff87af4221c1d6f4c101bf33e1dbf14e2bcd75a8b5",
+      "scripts/rectification/contracts.py": "c6dc6bd230e38f9f2126c224aae9ddbd6415304c15340f8c7cd3f06f6ef3160f",
+      "scripts/rectification/dasha_transition_proximity.py": "5ce4ed27b0f06c681abc34e5fd998fafb10c153a0070aa36c99ddfa869a2cbf2",
+      "scripts/rectification/decision_policy.py": "80e8de4680d19a052213bb821d2a9c94143a2962235aeb27f6ad81374d2e60d5",
+      "scripts/rectification/event_probes.py": "f5ca9d54501f67a1546fcf5b01da0c1277dec2e2c6df481884e8900d14909a7c",
+      "scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
+      "scripts/rectification/scoring_service.py": "07f8a04d6ff2a6ce7cd4e5bd42a848c3aedcbff8ec8f49668b4817993b8a6eb0",
+      "scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
+      "scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
+      "scripts/research/reported_offset_sweep.py": "34b06eaf95eaec492039ab546ede9dc473f11081e08669fc247855493d851c2e",
+      "scripts/research/sealed_holdout_rerun.py": "0d069a6cc6c31a37646c319476a94df3cec3b0bd2c358554aaacd133c9a38e57",
+      "scripts/shadbala.py": "6a586b504b45d96acf593393051b878b12068e80f2799fe0ebbea2d433658192",
+      "scripts/varga.py": "05ea7711dea8cce11f5b831eac70d9f694b9230c641ba4bdc3e62e3bc1cc5416"
+    },
+    "hash_scope": "explicit_identity_file_sets_not_a_transitive_dependency_lock"
+  },
+  "production_identity_scope": "context_only_shadow_scorer_does_not_call_transition_proximity",
+  "frozen_at_utc": "2026-11-04T09:36:21.533123+00:00",
+  "dataset_path": "references/real_case_calibration/minute_rectification_holdout_v3.json",
+  "dataset_sha256": "45aa76ab79dfc6c6404b6252083e1aa5c7e2e2b7de811fc11042a8ad2da3f0ea",
+  "algorithm_version": "birth-time-event-fact-ranker-v4-shadow",
+  "implementation_sha256": "894867c7290a63a2eef11a657a773bb0954ff1e399e095c7decbc77fd27df150",
+  "files": [
+    "scripts/active_rectification_event_engine.py",
+    "scripts/active_rectification_events.py",
+    "scripts/ashtakavarga.py",
+    "scripts/dasha_analyzer.py",
+    "scripts/divisional_charts_extended.py",
+    "scripts/domain_calculation_service.py",
+    "scripts/jaimini.py",
+    "scripts/minute_rectification_fact_ranker_v4.py",
+    "scripts/minute_rectification_feature_facts_v4.py",
+    "scripts/narayana_dasha.py",
+    "scripts/shadbala.py",
+    "scripts/varga.py"
+  ],
+  "historical_frozen_sha256": "f41c298dd6cdcebe7a93e632f7191954be7987f6012ca2a34cecb6e447fbf196",
+  "evaluator_sha256": "0d069a6cc6c31a37646c319476a94df3cec3b0bd2c358554aaacd133c9a38e57",
+  "ayanamsa": "raman",
+  "node_mode": "mean",
+  "candidate_radius_minutes": [
+    10
+  ],
+  "minute_step": 1,
+  "release_metrics": {
+    "top_1_rate_minimum": 0.6,
+    "top_3_rate_minimum": 0.85,
+    "mean_absolute_minute_error_maximum": 2.0,
+    "false_confirmation_rate_maximum": 0.05,
+    "correct_insufficient_evidence_rejection_rate_minimum": 0.9
+  },
+  "results_previously_seen": true,
+  "official_valid_independent_blind": false,
+  "must_not_use_for_tuning": true,
+  "tie_breaker": "sha256(benchmark_id:case_id:candidate_time); published minute is never passed to the ranker",
+  "metric_rank_definition": "competition_rank_1_plus_strictly_higher_scores_legacy_protocol",
+  "extra_metric_rank_definition": "score_desc_then_existing_opaque_sha256_total_order"
+}

frontend/tests/rectification-confirmation-gate.test.ts

@@ -126,8 +126,11 @@ const diagnosticReport = JSON.parse(readFileSync(
 // 原值(15)：docs/research/sealed_holdout_rerun_moon_paksha_2026_11_04.json
 // 新值(15)：docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.json
 // 原因(15)：数据核对第二波合并（BUG-1560 / BUG-1561 varga.py、divisional_charts_extended.py；BUG-1566 / BUG-1567 jaimini.py；BUG-1270 / BUG-1576 shadbala.py）改了冻结身份文件，20 条回放不变，ERR-110 在合并后的代码上另存新记录；各分支的 audit_g / audit_h / audit_j 是中间记录。确认门行为与阈值不变。
+// 原值(16)：docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.json
+// 新值(16)：docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.json
+// 原因(16)：产品 2026-11-04 决定按出处改算法：BUG-1560 varga.py 偶数星座 D30 按 BPHS、BUG-1570 白羊 / 天蝎上升金星判功能凶，scoring-13；冻结身份变了、20 条回放 3 条变（影子头名率 0.50 → 0.45），ERR-110 另存新记录。影子重跑不是发布指标，确认门行为与阈值不变。
 const currentTreeRerun = JSON.parse(readFileSync(
-  new URL("../../docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.json", import.meta.url),
+  new URL("../../docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.json", import.meta.url),
   "utf8",
 )) as {
   frozen_record: { implementation_sha256: string };
@@ -280,9 +283,10 @@ test("sealed holdout aggregates match the v3 report and still block confirmation
   // 原值(12)：…d60_mapping_2026_10_29.json / 新值(12)：…data_audit_2026_11_04.json / 原因(12)：BUG-1545 / BUG-1546 改了冻结身份文件，输出不变，ERR-110 另存新记录。
   // 原值(13)：…data_audit_2026_11_04.json / 新值(13)：…moon_paksha_2026_11_04.json / 原因(13)：BUG-1557 改了冻结身份里的 shadbala.py，输出不变，ERR-110 另存新记录。
   // 原值(14)：…moon_paksha_2026_11_04.json / 新值(14)：…audit_wave2_2026_11_04.json / 原因(14)：数据核对第二波 BUG-1560 / 1561、1566 / 1567、1270 / 1576 改了冻结身份文件，输出不变，ERR-110 在合并后的代码上另存新记录（audit_g / h / j 为中间记录）。
+  // 原值(15)：…audit_wave2_2026_11_04.json / 新值(15)：…d30_venus_2026_11_04.json / 原因(15)：BUG-1560 / BUG-1570 与 scoring-13 重新冻结（ERR-110，产品 2026-11-04 决定），影子回放 3 / 20 条变。
   assert.equal(
     productHoldout.current_tree_scorer.source_report,
-    "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.json",
+    "docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.json",
   );
   assert.equal(currentTreeRerun.official_valid_independent_blind, false);
   assert.equal(productHoldout.current_tree_scorer.matches_metrics_scorer, false);

references/rectification_sealed_holdout.v1.json

@@ -24,7 +24,7 @@
     "evaluated_on": "2026-07-21"
   },
   "current_tree_scorer": {
-    "implementation_sha256": "6911e686575d0b4ea1a6b17682c4557811ac79366e59ccaecaea504892043dad",
+    "implementation_sha256": "894867c7290a63a2eef11a657a773bb0954ff1e399e095c7decbc77fd27df150",
     "extended_identity": {
       "historical_artifacts_manifest_sha256": "6102a26a840be207b5858b3a4c0509274468ae9071e86d308cbbac7371d6864e",
       "production_scoring_files": [
@@ -52,7 +52,7 @@
         "scripts/shadbala.py",
         "scripts/varga.py"
       ],
-      "production_scoring_sha256": "c67128293d994c55f99d1c0dc444261fd828182d9bf6f098a371403037524ab2",
+      "production_scoring_sha256": "9ba1c80f211c36ed5232e0f39c0192a4adc48a38a3e54c87e0cab7eba619609c",
       "research_files": [
         "scripts/research/reported_offset_sweep.py",
         "scripts/research/cluster_width_lib.py",
@@ -62,7 +62,7 @@
         "scripts/minute_rectification_fact_blind_eval_v4.py",
         "scripts/minute_rectification_holdout_validator.py"
       ],
-      "research_implementation_sha256": "27107a247e1fab7d4e2148f8105a20fa040ab4ec2767f3ca40e63772cc7165f5",
+      "research_implementation_sha256": "d89d1261ba4e0ddb064a4a7ffab90beceec1f19129a3c6a801a4f496c25e31f0",
       "file_sha256": {
         "scripts/active_rectification_event_engine.py": "dced0b398ad90bdec59c743a55ffe01613306127c17a1e44c8c9cfb569c57841",
         "scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
@@ -70,7 +70,7 @@
         "scripts/dasha_analyzer.py": "3949b96813217fe624899856afec9f0b787c4cb0fea3a9a0d961990dbd11943a",
         "scripts/divisional_charts_extended.py": "6050ee6706d0f27b8c406b1c06ac5b49cf6f13814a3f930d944598892650ed92",
         "scripts/domain_calculation_service.py": "66923a2bc69daf65c965d2973c4b9234edbec5147909eaf3609b6b377ce3c7ca",
-        "scripts/functional_benefics.py": "cbaac3b8c09b97f8724b5300e9a402cbf77089af6c7db8788550d40fd35ac57b",
+        "scripts/functional_benefics.py": "f2c0b25cf0b112584ed54dada3c1403eb2f73760a9935719f023a17fb17ee867",
         "scripts/jaimini.py": "706d20dcff89079063fd1857a36f19419604ef81c80227921c7a2ced60011ac9",
         "scripts/minute_rectification_blind_eval.py": "07aa30d8bad3278669495d5fea8be937aaf6367c8af980ff4f2fe9aa84ccc6ff",
         "scripts/minute_rectification_fact_blind_eval_v4.py": "bdf460e3467208e8b87345c5beb2128f3e22de7eeffd68f72b281b3ad9affc92",
@@ -87,26 +87,26 @@
         "scripts/rectification/decision_policy.py": "80e8de4680d19a052213bb821d2a9c94143a2962235aeb27f6ad81374d2e60d5",
         "scripts/rectification/event_probes.py": "f5ca9d54501f67a1546fcf5b01da0c1277dec2e2c6df481884e8900d14909a7c",
         "scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
-        "scripts/rectification/scoring_service.py": "fa056fa30d9e6ffa4b75295fc49c793e35b26ebeca64ca843d26c8abef3050f2",
+        "scripts/rectification/scoring_service.py": "07f8a04d6ff2a6ce7cd4e5bd42a848c3aedcbff8ec8f49668b4817993b8a6eb0",
         "scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
         "scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
-        "scripts/research/reported_offset_sweep.py": "fde2e27595546d6c607ba804dafe9e9f4a2a33f4ea67684c7aefc3cbe1caa4be",
-        "scripts/research/sealed_holdout_rerun.py": "97fdb9e30d7fc697439a692e1115b9e8ddaca6619788bb1654a7b8f4ecfb720d",
+        "scripts/research/reported_offset_sweep.py": "34b06eaf95eaec492039ab546ede9dc473f11081e08669fc247855493d851c2e",
+        "scripts/research/sealed_holdout_rerun.py": "0d069a6cc6c31a37646c319476a94df3cec3b0bd2c358554aaacd133c9a38e57",
         "scripts/shadbala.py": "6a586b504b45d96acf593393051b878b12068e80f2799fe0ebbea2d433658192",
-        "scripts/varga.py": "37813c5da7b619439880808c0c69cfedf5c4d2c5cedd0dd2296ed7ffa7282e13"
+        "scripts/varga.py": "05ea7711dea8cce11f5b831eac70d9f694b9230c641ba4bdc3e62e3bc1cc5416"
       },
       "hash_scope": "explicit_identity_file_sets_not_a_transitive_dependency_lock"
     },
     "matches_metrics_scorer": false,
     "official_eval_implementation_hash_matches": false,
     "official_eval_trial_count": 0,
-    "source_report": "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.json",
+    "source_report": "docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.json",
     "fixed_protocol_rerun_trial_count": 20,
     "fixed_protocol_rerun_hash_matches": true,
     "metrics": {
-      "top_1_rate": 0.5,
+      "top_1_rate": 0.45,
       "top_3_rate": 0.5,
-      "mean_absolute_minute_error": 6.65,
+      "mean_absolute_minute_error": 7.05,
       "false_confirmation_rate": 0.0,
       "correct_insufficient_evidence_rejection_rate": 1.0,
       "confirmation_coverage_rate": 0.0
@@ -114,9 +114,9 @@
   },
   "current_tree_fixed_protocol_rerun": {
     "evaluated_on": "2026-11-04",
-    "report_path": "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.json",
-    "freeze_record_path": "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.freeze.json",
-    "implementation_sha256": "6911e686575d0b4ea1a6b17682c4557811ac79366e59ccaecaea504892043dad",
+    "report_path": "docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.json",
+    "freeze_record_path": "docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.freeze.json",
+    "implementation_sha256": "894867c7290a63a2eef11a657a773bb0954ff1e399e095c7decbc77fd27df150",
     "extended_identity": {
       "historical_artifacts_manifest_sha256": "6102a26a840be207b5858b3a4c0509274468ae9071e86d308cbbac7371d6864e",
       "production_scoring_files": [
@@ -144,7 +144,7 @@
         "scripts/shadbala.py",
         "scripts/varga.py"
       ],
-      "production_scoring_sha256": "c67128293d994c55f99d1c0dc444261fd828182d9bf6f098a371403037524ab2",
+      "production_scoring_sha256": "9ba1c80f211c36ed5232e0f39c0192a4adc48a38a3e54c87e0cab7eba619609c",
       "research_files": [
         "scripts/research/reported_offset_sweep.py",
         "scripts/research/cluster_width_lib.py",
@@ -154,7 +154,7 @@
         "scripts/minute_rectification_fact_blind_eval_v4.py",
         "scripts/minute_rectification_holdout_validator.py"
       ],
-      "research_implementation_sha256": "27107a247e1fab7d4e2148f8105a20fa040ab4ec2767f3ca40e63772cc7165f5",
+      "research_implementation_sha256": "d89d1261ba4e0ddb064a4a7ffab90beceec1f19129a3c6a801a4f496c25e31f0",
       "file_sha256": {
         "scripts/active_rectification_event_engine.py": "dced0b398ad90bdec59c743a55ffe01613306127c17a1e44c8c9cfb569c57841",
         "scripts/active_rectification_events.py": "03e333ccf1103caf685dfe50fe890ab1793e945037085f50ce834a4a3b232222",
@@ -162,7 +162,7 @@
         "scripts/dasha_analyzer.py": "3949b96813217fe624899856afec9f0b787c4cb0fea3a9a0d961990dbd11943a",
         "scripts/divisional_charts_extended.py": "6050ee6706d0f27b8c406b1c06ac5b49cf6f13814a3f930d944598892650ed92",
         "scripts/domain_calculation_service.py": "66923a2bc69daf65c965d2973c4b9234edbec5147909eaf3609b6b377ce3c7ca",
-        "scripts/functional_benefics.py": "cbaac3b8c09b97f8724b5300e9a402cbf77089af6c7db8788550d40fd35ac57b",
+        "scripts/functional_benefics.py": "f2c0b25cf0b112584ed54dada3c1403eb2f73760a9935719f023a17fb17ee867",
         "scripts/jaimini.py": "706d20dcff89079063fd1857a36f19419604ef81c80227921c7a2ced60011ac9",
         "scripts/minute_rectification_blind_eval.py": "07aa30d8bad3278669495d5fea8be937aaf6367c8af980ff4f2fe9aa84ccc6ff",
         "scripts/minute_rectification_fact_blind_eval_v4.py": "bdf460e3467208e8b87345c5beb2128f3e22de7eeffd68f72b281b3ad9affc92",
@@ -179,13 +179,13 @@
         "scripts/rectification/decision_policy.py": "80e8de4680d19a052213bb821d2a9c94143a2962235aeb27f6ad81374d2e60d5",
         "scripts/rectification/event_probes.py": "f5ca9d54501f67a1546fcf5b01da0c1277dec2e2c6df481884e8900d14909a7c",
         "scripts/rectification/refinement_packet.py": "dbeea5aa780889785ce850f3881e8b7f67bb44594e9bc382c65b2e730884a2f4",
-        "scripts/rectification/scoring_service.py": "fa056fa30d9e6ffa4b75295fc49c793e35b26ebeca64ca843d26c8abef3050f2",
+        "scripts/rectification/scoring_service.py": "07f8a04d6ff2a6ce7cd4e5bd42a848c3aedcbff8ec8f49668b4817993b8a6eb0",
         "scripts/research/cluster_width_lib.py": "1d8f2ffa7795d62069deebb2de8e16749317037d4ed3f24a2c0092676e5cfcc6",
         "scripts/research/probe_supply_after_six.py": "098a5b4398d6f8d996917d809c2fc922ad64031d3b70660f8ef7c876aba92438",
-        "scripts/research/reported_offset_sweep.py": "fde2e27595546d6c607ba804dafe9e9f4a2a33f4ea67684c7aefc3cbe1caa4be",
-        "scripts/research/sealed_holdout_rerun.py": "97fdb9e30d7fc697439a692e1115b9e8ddaca6619788bb1654a7b8f4ecfb720d",
+        "scripts/research/reported_offset_sweep.py": "34b06eaf95eaec492039ab546ede9dc473f11081e08669fc247855493d851c2e",
+        "scripts/research/sealed_holdout_rerun.py": "0d069a6cc6c31a37646c319476a94df3cec3b0bd2c358554aaacd133c9a38e57",
         "scripts/shadbala.py": "6a586b504b45d96acf593393051b878b12068e80f2799fe0ebbea2d433658192",
-        "scripts/varga.py": "37813c5da7b619439880808c0c69cfedf5c4d2c5cedd0dd2296ed7ffa7282e13"
+        "scripts/varga.py": "05ea7711dea8cce11f5b831eac70d9f694b9230c641ba4bdc3e62e3bc1cc5416"
       },
       "hash_scope": "explicit_identity_file_sets_not_a_transitive_dependency_lock"
     },
@@ -201,15 +201,15 @@
     "verified_minute_claim_allowed": false,
     "metric_gates_passed": false,
     "events_per_case": 3,
-    "boundary": "Previously exposed v3 shadow fixed-protocol rerun after the data audit wave 2 merge: BUG-1560 / BUG-1561 (scripts/varga.py, scripts/divisional_charts_extended.py: D16/D20/D27/D30/D40/D45 starting signs per BPHS ch. 6), BUG-1566 / BUG-1567 (scripts/jaimini.py: K.N. Rao Chara Dasha co-lord and antardasha order), BUG-1270 / BUG-1576 (scripts/shadbala.py: Dig Bala arc fold, deterministic Drik rounding) (ERR-110). Trials and metrics match the 2026-11-04 moon_paksha_2026_11_04 report on every field. Versus the 2026-09-20 historical report, changed_trial_count stays 8. Not a release metric. Prior reports and freezes preserved byte-for-byte.",
-    "report_sha256": "6cc1b9a80f86cf8c4768a224a19ceccda7a2e672a5531f9d29f064c53f585298",
-    "freeze_record_sha256": "219856490a73e0a0331a17253179b8556e557b78c251a318fc442cdb1ec79809",
-    "replay_started_at_utc": "2026-11-04T09:06:17.646138+00:00",
-    "replay_finished_at_utc": "2026-11-04T09:06:19.899116+00:00",
+    "boundary": "Previously exposed v3 shadow fixed-protocol rerun after the Product decision 2026-11-04 (BUG-1560 / BUG-1570): scripts/varga.py even-sign D30 follows BPHS ch. 6 (12-20 Pisces, 20-25 Capricorn, 25-30 Scorpio) and scripts/functional_benefics.py makes Venus a functional malefic for Aries / Scorpio (BPHS 34.20 / 34.35); scoring identity rectification-v5-matrix-scoring-13 (ERR-110). Versus the 2026-11-04 audit_wave2_2026_11_04 report, 3 of 20 trials changed (all from the D30 table; the Venus roles alone change none); top_1_rate 0.5 -> 0.45, mean_absolute_minute_error 6.65 -> 7.05. Versus the 2026-09-20 historical report, changed_trial_count is 9. Not a release metric. No tuning. Prior reports and freezes preserved byte-for-byte.",
+    "report_sha256": "d334a1f8dce584cd3372ebffdfe45984db1951ed918e2daf45059b460427fc3f",
+    "freeze_record_sha256": "c2a25e00a860ea1c727bfa895488a56f6c2f236c79895645687c5105cdde2f68",
+    "replay_started_at_utc": "2026-11-04T09:36:23.965501+00:00",
+    "replay_finished_at_utc": "2026-11-04T09:36:26.152976+00:00",
     "previous_fixed_protocol_rerun": {
-      "report_path": "docs/research/sealed_holdout_rerun_moon_paksha_2026_11_04.json",
-      "freeze_record_path": "docs/research/sealed_holdout_rerun_moon_paksha_2026_11_04.freeze.json",
-      "superseded_reason": "The data audit wave 2 merge: BUG-1560 / BUG-1561 (scripts/varga.py, scripts/divisional_charts_extended.py: D16/D20/D27/D30/D40/D45 starting signs per BPHS ch. 6), BUG-1566 / BUG-1567 (scripts/jaimini.py: K.N. Rao Chara Dasha co-lord and antardasha order), BUG-1270 / BUG-1576 (scripts/shadbala.py: Dig Bala arc fold, deterministic Drik rounding) changed frozen identity files. Output is unchanged, so ERR-110 stored one new record for the merged tree. The per-branch records audit_g_2026_11_04, audit_h_2026_11_04 and audit_j_2026_11_04 were frozen on the individual branches, match only those branch trees, and are kept byte-for-byte as intermediate history; none was current on the merged tree. Prior moon_paksha_2026_11_04 report and freeze preserved byte-for-byte."
+      "report_path": "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.json",
+      "freeze_record_path": "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.freeze.json",
+      "superseded_reason": "Product decision 2026-11-04 (BUG-1560 / BUG-1570): scripts/varga.py even-sign D30 follows BPHS ch. 6 (12-20 Pisces, 20-25 Capricorn, 25-30 Scorpio) and scripts/functional_benefics.py makes Venus a functional malefic for Aries / Scorpio (BPHS 34.20 / 34.35); scoring identity rectification-v5-matrix-scoring-13 changed frozen identity files and the replay output, so ERR-110 stored a new record. Prior audit_wave2_2026_11_04 report and freeze preserved byte-for-byte."
     }
   },
   "previous_fixed_protocol_rerun": {
@@ -330,25 +330,25 @@
     "verified_minute_claim_allowed": false
   },
   "current_tree_reported_offset_replay": {
-    "report_path": "docs/research/reported_offset_audit_wave2_2026_11_04.json",
-    "report_sha256": "4832ce11ab096dd55b04ee00c04b7020eee2a3ba2e73fb3b5b565b995a56e059",
-    "freeze_record_path": "docs/research/reported_offset_audit_wave2_2026_11_04.freeze.json",
-    "freeze_record_sha256": "dedaaf7a29ba8cd122c100075bac71b5836c5097cb47a443e230592a5e6bef4f",
+    "report_path": "docs/research/reported_offset_d30_venus_2026_11_04.json",
+    "report_sha256": "d67cd503ca51d519ddfd7b2a924055131cc9c95a71cedcd512f0843103441b1a",
+    "freeze_record_path": "docs/research/reported_offset_d30_venus_2026_11_04.freeze.json",
+    "freeze_record_sha256": "5d584c71a94b9139fe95b7c9083a07b65b93285dd72384d77802f93a0fb08c69",
     "scope": "reported_offset_sensitivity_not_product_accuracy",
     "trial_count": 900,
     "official_valid_independent_blind": false,
     "official_blind_trial_count": 0,
     "must_not_use_for_tuning": true,
     "must_not_claim_as_release_metrics": true,
-    "replay_started_at_utc": "2026-11-04T09:06:20.135348+00:00",
-    "replay_finished_at_utc": "2026-11-04T09:08:59.718147+00:00",
-    "boundary": "Previously exposed reported-offset sensitivity after the data audit wave 2 merge: BUG-1560 / BUG-1561 (scripts/varga.py, scripts/divisional_charts_extended.py: D16/D20/D27/D30/D40/D45 starting signs per BPHS ch. 6), BUG-1566 / BUG-1567 (scripts/jaimini.py: K.N. Rao Chara Dasha co-lord and antardasha order), BUG-1270 / BUG-1576 (scripts/shadbala.py: Dig Bala arc fold, deterministic Drik rounding) (ERR-110). Summary and all 900 trials match the 2026-11-04 moon_paksha_2026_11_04 report on every field. Versus the 2026-09-20 historical report, changed_trial_count stays 581 of 900. Not a release metric. No tuning. Prior reports and freezes preserved byte-for-byte.",
+    "replay_started_at_utc": "2026-11-04T09:36:26.246986+00:00",
+    "replay_finished_at_utc": "2026-11-04T09:38:56.940901+00:00",
+    "boundary": "Previously exposed reported-offset sensitivity after the Product decision 2026-11-04 (BUG-1560 / BUG-1570): scripts/varga.py even-sign D30 follows BPHS ch. 6 (12-20 Pisces, 20-25 Capricorn, 25-30 Scorpio) and scripts/functional_benefics.py makes Venus a functional malefic for Aries / Scorpio (BPHS 34.20 / 34.35); scoring identity rectification-v5-matrix-scoring-13 (ERR-110). Versus the 2026-11-04 audit_wave2_2026_11_04 report, 250 of 900 trials changed. Versus the 2026-09-20 historical report, changed_trial_count is 686 of 900. Not a release metric. No tuning. Prior reports and freezes preserved byte-for-byte.",
     "previous_reported_offset_replay": {
-      "report_path": "docs/research/reported_offset_moon_paksha_2026_11_04.json",
-      "report_sha256": "f0b602a0477d5913d4befcdf888f3687062c3e62e0b11e6ea3bc69303f0f02cb",
-      "freeze_record_path": "docs/research/reported_offset_moon_paksha_2026_11_04.freeze.json",
-      "freeze_record_sha256": "9728da404c736a85179dfbbd62ac551550ff8590494f4da62df874cac5ffbd49",
-      "superseded_reason": "The data audit wave 2 merge: BUG-1560 / BUG-1561 (scripts/varga.py, scripts/divisional_charts_extended.py: D16/D20/D27/D30/D40/D45 starting signs per BPHS ch. 6), BUG-1566 / BUG-1567 (scripts/jaimini.py: K.N. Rao Chara Dasha co-lord and antardasha order), BUG-1270 / BUG-1576 (scripts/shadbala.py: Dig Bala arc fold, deterministic Drik rounding) changed frozen identity files. Summary and all 900 trials are unchanged, so ERR-110 stored one new record for the merged tree. The per-branch records audit_g_2026_11_04, audit_h_2026_11_04 and audit_j_2026_11_04 were frozen on the individual branches, match only those branch trees, and are kept byte-for-byte as intermediate history; none was current on the merged tree. Prior moon_paksha_2026_11_04 report and freeze preserved byte-for-byte."
+      "report_path": "docs/research/reported_offset_audit_wave2_2026_11_04.json",
+      "report_sha256": "4832ce11ab096dd55b04ee00c04b7020eee2a3ba2e73fb3b5b565b995a56e059",
+      "freeze_record_path": "docs/research/reported_offset_audit_wave2_2026_11_04.freeze.json",
+      "freeze_record_sha256": "dedaaf7a29ba8cd122c100075bac71b5836c5097cb47a443e230592a5e6bef4f",
+      "superseded_reason": "Product decision 2026-11-04 (BUG-1560 / BUG-1570): scripts/varga.py even-sign D30 follows BPHS ch. 6 (12-20 Pisces, 20-25 Capricorn, 25-30 Scorpio) and scripts/functional_benefics.py makes Venus a functional malefic for Aries / Scorpio (BPHS 34.20 / 34.35); scoring identity rectification-v5-matrix-scoring-13 changed frozen identity files and the replay output, so ERR-110 stored a new record. Prior audit_wave2_2026_11_04 report and freeze preserved byte-for-byte."
     }
   },
   "previous_reported_offset_replay": {

scripts/research/reported_offset_sweep.py

@@ -45,8 +45,11 @@ MINUTE_STEP = 1
 # 原值: docs/research/reported_offset_moon_paksha_2026_11_04.{freeze.json,json}
 # 新值: docs/research/reported_offset_audit_wave2_2026_11_04.{freeze.json,json}
 # 原因: 数据核对第二波合并（BUG-1560 / BUG-1561 varga.py、divisional_charts_extended.py；BUG-1566 / BUG-1567 jaimini.py；BUG-1270 / BUG-1576 shadbala.py）改了冻结身份文件，ERR-110 在合并后的代码上另存新记录；各分支自己的 audit_g / audit_h / audit_j 记录只对各自分支成立，作为中间记录原样保留
-FREEZE = ROOT / "docs/research/reported_offset_audit_wave2_2026_11_04.freeze.json"
-REPORT = ROOT / "docs/research/reported_offset_audit_wave2_2026_11_04.json"
+# 原值: docs/research/reported_offset_audit_wave2_2026_11_04.{freeze.json,json}
+# 新值: docs/research/reported_offset_d30_venus_2026_11_04.{freeze.json,json}
+# 原因: 产品 2026-11-04 决定按出处改算法：BUG-1560 varga.py 偶数星座 D30 按 BPHS 第 6 章、BUG-1570 白羊 / 天蝎上升金星判功能凶（BPHS 34.20 / 34.35），校正身份升到 scoring-13；冻结身份文件变了且回放结果变了，ERR-110 另存新记录
+FREEZE = ROOT / "docs/research/reported_offset_d30_venus_2026_11_04.freeze.json"
+REPORT = ROOT / "docs/research/reported_offset_d30_venus_2026_11_04.json"
 LEGACY_REPORT = ROOT / "docs/research/reported_offset_2026_09_20.json"
 
 

scripts/research/sealed_holdout_rerun.py

@@ -42,8 +42,11 @@ DATASET = ROOT / "references/real_case_calibration/minute_rectification_holdout_
 # 原值: docs/research/sealed_holdout_rerun_moon_paksha_2026_11_04.{freeze.json,json}
 # 新值: docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.{freeze.json,json}
 # 原因: 数据核对第二波合并（BUG-1560 / BUG-1561 varga.py、divisional_charts_extended.py；BUG-1566 / BUG-1567 jaimini.py；BUG-1270 / BUG-1576 shadbala.py）改了冻结身份文件，ERR-110 在合并后的代码上另存新记录；各分支自己的 audit_g / audit_h / audit_j 记录只对各自分支成立，作为中间记录原样保留
-FREEZE = ROOT / "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.freeze.json"
-REPORT = ROOT / "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.json"
+# 原值: docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04.{freeze.json,json}
+# 新值: docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.{freeze.json,json}
+# 原因: 产品 2026-11-04 决定按出处改算法：BUG-1560 varga.py 偶数星座 D30 按 BPHS 第 6 章、BUG-1570 白羊 / 天蝎上升金星判功能凶（BPHS 34.20 / 34.35），校正身份升到 scoring-13；冻结身份文件变了且回放结果变了，ERR-110 另存新记录
+FREEZE = ROOT / "docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.freeze.json"
+REPORT = ROOT / "docs/research/sealed_holdout_rerun_d30_venus_2026_11_04.json"
 LEGACY_REPORT = ROOT / "docs/research/sealed_holdout_rerun_2026_09_20.json"
 ARCHIVE = ROOT / "docs/research/history/rectification_pre_cross_midnight_2026_09_20"
 PRODUCTION_FILES = [

tests/test_sealed_holdout_contract_freshness.py

@@ -84,6 +84,11 @@ IDENTITY_FORBIDDEN_PREFIXES = (
     "docs/research/reported_offset_audit_j_2026_11_04",
     "docs/research/sealed_holdout_rerun_audit_wave2_2026_11_04",
     "docs/research/reported_offset_audit_wave2_2026_11_04",
+    # 原值: 排除到 audit_wave2_2026_11_04
+    # 新值: 再排除 d30_venus_2026_11_04 两份冻结路径（追加，不替换上面的）
+    # 原因: 产品 2026-11-04 决定 BUG-1560（varga.py 偶数星座 D30）与 BUG-1570（白羊 / 天蝎金星功能凶）入算、scoring-13，冻结身份与回放结果都变了，ERR-110 另存新记录
+    "docs/research/sealed_holdout_rerun_d30_venus_2026_11_04",
+    "docs/research/reported_offset_d30_venus_2026_11_04",
     "docs/research/history/",
     "artifacts/",
 )