diff --git a/docs/BUG_HISTORY.md b/docs/BUG_HISTORY.md
index bc4bd22a..0d25ff73 100644
--- a/docs/BUG_HISTORY.md
+++ b/docs/BUG_HISTORY.md
@@ -14688,6 +14688,21 @@
 - 复发自：无
 - 修复版本：未修
 
+## BUG-1091 | 生时校正打分只奖不罚、权重未校准、高分辨率信号未计分
+
+- 状态：investigating（2026-09-29 研究单 `TASK-rectification-scoring-research-20260929` 脚手架已落地；判定按任务书须在 v5（≥60 例）上做，v4 上只跑通流水线、所有判定字段写 `pending_v5`）
+- 首次发现 / 最近更新：2026-09-29 / 2026-09-29
+- 影响面：`scripts/active_rectification_event_engine.py::_score_event`（11 条加分规则，权重手拍）、`OBSERVATION_ONLY_LAYERS`（KP 宫头子主每分钟在算但不计分）、`_fine_minute_indices`（Pranapada / Hora / Ghati / Bhava lagna 已算未计分）、计分分盘无 D60。
+- 用户现象：开场说 12 件带年份经历、答约 10 张卡后范围整窗不动；引擎原始分头名簇命中在 v4 上只有 0.35 / 0.15 / 0.10（±10 / ±30 / ±60），约为随机水平的 4–5 倍。
+- 触发条件：任何一次校正。打分对候选「能解释事件」加分，对「预测了没发生的事」不扣分；一条规则对真分钟和错分钟同样常命中时照样 +2。
+- 根因（已确认）：(1) 只奖不罚——负证据只来自选择题答「没有」（`core/build-state.ts::applyProbeOutcome`，±2）；(2) 权重是人拍的，R1–R5 / V1 / V2 / V1n 都是「再拍一个权重看结果」，没有按数据校准；(3) KP / Pranapada / D60 这些分钟级信号没进计分，09-14 KP@默认权重更差是「权重没校准」的另一个症状。
+- 修复：未修。本轮只做离线脚手架：`scripts/research/scoring_research_lib.py`（特征记录 provider 与线上 `score_candidates` 逐分对账、似然比权重、leave-one-case-out、加权 provider、缺席 / 精度追问辅助）、`scripts/research/scoring_research.py`（R-A / R-B / R-C 流水线）、`tests/test_scoring_research.py`。生产代码与冻结文件零改动。
+- 验证：`tests/test_scoring_research.py`（含 v4 公开案例对账 0 差）；v4 全集流水线跑通、`PYTHONHASHSEED=0` 两次复跑 JSON 逐字节一致（见 `docs/tasks/PROGRESS-rectification-scoring-research-20260929.md`）。
+- 防复发：任何计分改动必须先在 v5 上过任务书硬红线（六格真值在区间不降、留一法数字、稳健性三项），再按 ERR-110 重冻结；不得在 v4 上下结论（BUG-1090）。
+- 相关记录：BUG-560、BUG-1048、BUG-1089、BUG-1090
+- 复发自：无
+- 修复版本：未修（研究分支 `codex/rectification-scoring-research-20260929`）
+
 ## BUG-1092 | 报告技术页标题出现「字段」，行星主星表头是看不懂的 RL / NL / SL / SS / SB
 
 - 状态：resolved（代码 + 回归测试；未部署，真机待合入 staging 后复核）
diff --git a/docs/research/ACTIVE_FRONTS.md b/docs/research/ACTIVE_FRONTS.md
index 764a8160..0c8d0aa6 100644
--- a/docs/research/ACTIVE_FRONTS.md
+++ b/docs/research/ACTIVE_FRONTS.md
@@ -121,3 +121,4 @@ Do not open new product surfaces before at least one of these four lanes is clos
 - 定论页（先读这个）：`<repo>/docs/research/rectification_minute_resolution_closure_2026_09_14.md`
 - 两个已被证伪的假设：加权重能拉开候选；簇合并把候选并没了（合并从未触发）。
 - 未解决的只剩「区间内部并列」，目前唯一被证明有效的信息源是用户提供的带年月新经历。
+- 2026-09-29 打分方法研究（脚手架，判定待 v5）：`<repo>/docs/research/rectification_scoring_research_2026_09_29.md`——似然比校准权重 / 缺席证据 / 精度追问三条流水线已在 v4 上跑通，所有判定 `pending_v5`；任务书 `docs/tasks/TASK-rectification-scoring-research-20260929.md`，前置 `TASK-rectification-holdout-expansion-20260929.md`。
diff --git a/docs/research/rectification_minute_resolution_closure_2026_09_14.md b/docs/research/rectification_minute_resolution_closure_2026_09_14.md
index a1293351..231f6a1b 100644
--- a/docs/research/rectification_minute_resolution_closure_2026_09_14.md
+++ b/docs/research/rectification_minute_resolution_closure_2026_09_14.md
@@ -94,3 +94,8 @@
 - 任务书和 BUG-689 邀请语依据里的「1 分钟 ≈ 1.1 天大运边界位移」有误，实测中位 3.8 天（1.3–5.9）。45 天闸门对应 8–34 分钟，不是 40 分钟。
 - 新增答错容错：答错 1 题，真值在区间 98–100%；答错 2 题，±30 / ±60 上 7–10% 的回放会挤出真值（两道反答 = 8 分 = 淘汰线）。
 - 全文见 `docs/research/rectification_offline_research_2026_09_26.md`。
+
+## 9. 后续（2026-09-29 打分方法研究单，脚手架阶段）
+
+- §1.3「加权重类改法全部不过门」说的是**人拍权重**。2026-09-29 研究单换了路线：每条规则的权重由数据估（似然比，leave-one-case-out），允许负权重（只奖不罚是结构性问题），KP / Pranapada / D60 作为特征进入由数据定权重；另测「缺席证据」与「对已说事件追问月份」。
+- 脚手架与 v4 流水线见 `docs/research/rectification_scoring_research_2026_09_29.md`；**判定必须在 v5（≥60 例）上做**，v4 上的数字只是调试参考（BUG-1090 / BUG-1091）。本页 §1–§7 的结论不因此改变。
diff --git a/docs/research/rectification_scoring_research_2026_09_29.md b/docs/research/rectification_scoring_research_2026_09_29.md
new file mode 100644
index 00000000..e3648d75
--- /dev/null
+++ b/docs/research/rectification_scoring_research_2026_09_29.md
@@ -0,0 +1,139 @@
+# 生时校正打分方法研究：似然比权重 / 缺席证据 / 精度追问（脚手架阶段，2026-09-29）
+
+- 任务书：`docs/tasks/TASK-rectification-scoring-research-20260929.md`；进度：`docs/tasks/PROGRESS-rectification-scoring-research-20260929.md`
+- 分支：`codex/rectification-scoring-research-20260929`，基线 `origin/staging` @ `6e393780`（开工时 head；任务书写作时为 `5febb111`，其间只有文档提交）。
+- 性质：**离线测量，不改线上代码、打分、阈值、出题闸门、Skill、冻结文件。** 研究计分器是 `precision_gate_lib.score_event_with_policy`（09-14 / 09-26 已证与线上逐分相同）加上不计分的"额外观察"，通过 `build_event_contribution_matrix(row_provider=…)` 走线上同一条矩阵 / 出题 / 六题回放链。
+- 数据：`references/real_case_calibration/minute_rectification_holdout_v4.json`，20 例公开 Rodden-AA。**这是开放集回放，不是盲测；本页所有数字都是 v4 调试参考，任务书规定判定只能在 v5（≥60 例）上做，所以每一项的判定栏都是 `pending_v5`。**
+- 口径：ayanamsa `raman`，node mode `mean`，步长 2 分钟，半径 ±10 / ±30 / ±60；六题回放（`ASK_COUNT = 6`，按真值作答，题目由线上 G0 出题器按**线上矩阵**出一次、各方案共用）；交付区间 = 未淘汰且落后头名不足 8 分的簇并集。两种先验都报：`raw`（引擎行原始分，09-14 / 09-26 口径）与 `percent`（线上 `relative_support` 百分比口径；似然比方案用带温度的 softmax 后验，见 R-A）。
+- 复跑：`PYTHONHASHSEED=0 python3 scripts/research/scoring_research.py --cache-dir <临时目录>`（约 14 分钟）→ `docs/research/scoring_research_{lr,absence,precision_followup}_2026_09_29.json`。同机两次运行 JSON 逐字节一致（见进度记录）。
+- 判门：`precision_gate_lib.gate_verdict`（头名不降**且**宽度下降、覆盖不降）；JSON 里以 `debug_verdict_v4` 记录，`verdict` 字段一律 `pending_v5`。
+
+## 结论
+
+| 项 | 一句话结论（v4 调试参考） | 判定 |
+| --- | --- | --- |
+| R-0 脚手架 | 研究计分器与线上 `score_candidates` 在 20 例 × 3 档 = 60 个 case-radius 上**逐分对账 0 差**（分数与规则 id 都相同）；每个 (候选, 事件, 采样日期) 记录 42 个特征（线上规则 25 个 + 额外观察 17 个） | 完成 |
+| R-A 似然比权重 | 流水线跑通。v4 上：留一法 `raw` 口径头名 / 覆盖与基线持平或略动（±30 A3 头名 0.55 → 0.65、宽度 33 → 31），引擎自身头名（答题前）±10 0.30 → 0.40–0.45；`percent` 口径的 softmax 后验即使按训练集拟合温度仍过度自信，把真值挤出区间（±10 squeezed 3–5 例）。20 例上 42 个特征里 31–38 个的置信区间跨 0 | `pending_v5` |
+| R-B 缺席证据 | 流水线跑通。v4 上按卡片同等强度（2 分）扣分会大量挤出真值（±60 覆盖 1.00 → 0.40）——**v4 的事件表是传记摘录，不是完整时间线，空白年不等于没发生**；真人口述同样不完整。0.5 分档不挤真值但头名下降 | `pending_v5`（v4 信号明确为负，v5 上若不翻转即关闭） |
+| R-C 精度追问 | 流水线跑通。把日精度经历降成"只记得年"后，**每例平均只有 0.2 / 0.45 / 0.7 件经历在知道月份后能把候选分到两边**（±10 只有 2/20 例有）；对这些例子把那一件恢复到月精度重算先验（`C1_prior`）在 ±30 上 7 例头名 0.71 vs 该 7 例的 C0，其余档位样本太少 | `pending_v5` |
+
+## R-0 · 脚手架与对账
+
+- `scripts/research/scoring_research_lib.py`
+  - `make_recording_provider`：对每个 legacy 单事件请求，用 `score_event_with_policy`（V0 基线）+ 线上的过运 / Ashtakavarga / Shadbala 辅助（取 context 里线上算好的结果）产出**与线上完全相同**的 evidence，同时把该候选在该事件下的额外观察写进 `FeatureStore`：
+    - 线上规则（记为特征）：`vim_{md,ad,pd}_domain_{house,lord,varga}`、`{label}_functional_{benefic,malefic}_auxiliary`、`narayana_{md,ad}_domain_house`、`{label}_arudha_auxiliary`、`controlled_transit_{jupiter,saturn}_domain_house`、`ashtakavarga_target_house_{support,pressure}_auxiliary`、`shadbala_sthana_drik_naisargika_{support,pressure}_auxiliary`。`event_kind:*`、`no_domain_activation`、`*_auxiliary_not_primary` 不作特征。
+    - 额外观察（线上算了没计分）：`kp_target_cusp_{sublord,starlord}_is_vim_{md,ad,pd}`、`kp_asc_sublord_is_vim_{md,ad,pd}`（`feature.kp_cusps.houses`，Placidus + Krishnamurti）、`vim_{md,ad,pd}_domain_varga_d60`（D60 现算）、`{pranapada,hora_lagna,ghati_lagna,bhava_lagna}_in_target_house`（`_fine_minute_indices`）。
+  - `reconcile_rows`：逐分比较分数与规则 id。**60/60 case-radius 差异 0。**
+  - `event_feature_matrix`：特征值 = 该规则在该事件采样日期上命中的比例（年精度 12 个采样日、月 3 个、日 1 个），与线上按采样日平均分数同口径。
+  - 真值标签：候选属于真值所在的**签名簇**（`raw_signature_clusters`）。
+- 测试：`tests/test_scoring_research.py`（10 条：LR 估计、留一法不泄漏、特征矩阵、规则过滤、加权 provider、缩放答案、缺席年、精度升降、百分比、以及 v4 公开案例 ±10 对账 0 差）。
+
+## R-A · 似然比校准权重
+
+**方法。** 对每个特征 f，`log LR_present = log P(f | 真值簇) − log P(f | 非真值簇)`，拉普拉斯平滑 α = 1（`(Σx + 1) / (N + 2)`）；`log LR_absent` 为朴素贝叶斯互补项。每档半径单独估。
+
+| 方案 | 特征 | 权重规则 |
+| --- | --- | --- |
+| A1 | 只用线上 25 条规则 | 只奖不罚：`max(log LR_present, 0)`，不用 absent 项 |
+| A2 | 加 17 个额外观察 | 同上 |
+| A3 | 同 A2 | 朴素贝叶斯：present + absent 两项都用，允许负权重 |
+
+候选分 = Σ 事件 Σ 特征（x·w_present + (1−x)·w_absent），经线上矩阵的事件类型系数、精度权重、采样日平均与大运边界邻近项（后者按线上原样附加，不重加权）。两个只从**训练折**估的标定量：`scale`（研究分的例内极差中位 → 线上极差中位，让 `raw` 回放的 ±2 / 8 分线意义不变）、`temperature`（Platt 单温度，最大化训练例真值簇的对数后验；网格 0.25–256），`percent` 先验 = softmax(分 / T) × 100。**留一法按案例留**（`loo_folds`），全集拟合另报只作参照。
+
+### 六题回放（留一法；括号内为全集拟合）
+
+`raw` 口径：
+
+| 半径 | 方案 | 头名命中 | 真值在区间 | 宽度中位 | 引擎头名（答题前） | 挤出真值 | debug 判定 |
+| --- | --- | ---: | ---: | ---: | ---: | ---: | --- |
+| ±10 | 基线 | 0.80 | 1.00 | 15 | 0.30 | 0 | — |
+| ±10 | A1 | 0.70 (0.75) | 1.00 | 14 | 0.45 | 0 | no_benefit |
+| ±10 | A2 | 0.75 (0.80) | 1.00 | 15 | 0.40 (0.50) | 0 | no_benefit |
+| ±10 | A3 | 0.80 (0.85) | 1.00 | 15 | 0.40 (0.50) | 0 | no_benefit |
+| ±30 | 基线 | 0.55 | 1.00 | 33 | 0.20 | 0 | — |
+| ±30 | A1 | 0.55 (0.70) | 1.00 | 32 | 0.25 | 0 | benefit（宽度 −1） |
+| ±30 | A2 | 0.60 (0.65) | 1.00 | 34 | 0.10 (0.30) | 0 | no_benefit |
+| ±30 | A3 | 0.65 (0.75) | 1.00 | 31 | 0.20 (0.45) | 0 | benefit（宽度 −2） |
+| ±60 | 基线 | 0.40 | 1.00 | 56 | 0.05 | 0 | — |
+| ±60 | A1 | 0.45 (0.50) | 1.00 | 61 | 0.15 (0.20) | 0 | no_benefit |
+| ±60 | A2 | 0.55 (0.60) | 1.00 | 61 | 0.00 (0.10) | 0 | no_benefit |
+| ±60 | A3 | 0.50 (0.70) | **0.95** | 61 | 0.05 (0.30) | 1 | no_benefit |
+
+`percent` 口径（基线 = 线上比例百分比；A* = 拟合温度的 softmax 后验）：
+
+| 半径 | 方案 | 头名命中 | 真值在区间 | 宽度中位 | 挤出真值 | 温度（各折） |
+| --- | --- | ---: | ---: | ---: | ---: | --- |
+| ±10 | 基线 | 0.90 | 1.00 | 11 | 0 | — |
+| ±10 | A1 / A2 / A3 | 0.60 / 0.50 / 0.55 | 0.80 / 0.85 / 0.75 | 7 / 7 / 5 | 4 / 3 / 5 | 1–2 / 1 / 0.5–1 |
+| ±30 | 基线 | 0.85 | 1.00 | 33 | 0 | — |
+| ±30 | A1 / A2 / A3 | 0.65 / 0.55 / 0.55 | 0.95 / 0.80 / 0.90 | 31 / 10 / 13 | 1 / 4 / 2 | 2–4 / 1–2 / 1–2 |
+| ±60 | 基线 | 0.80 | 1.00 | 53 | 0 | — |
+| ±60 | A1 / A2 / A3 | 0.65 / 0.50 / 0.40 | 1.00 / 0.80 / 0.80 | 57 / 32 / 38 | 0 / 4 / 4 | 4–8 / 2–4 / 2 |
+
+**读法（v4，仅供 v5 前设计参考，不是结论）。**
+
+1. 对账通过后，`raw` 口径的留一法数字与基线基本持平：似然比权重没有让真值掉出区间（±60 A3 一例除外），也没有明显收窄；引擎答题前的头名在 ±10 从 0.30 到 0.40–0.45、±60 A1 从 0.05 到 0.15，全集拟合再高一些——**全集与留一法的差距就是 20 例过拟合的量**。
+2. `percent` 口径下 softmax 后验**过度自信**：即使温度按训练折拟合，仍把 15–25% 例子的真值挤出区间。校准曲线（A3 留一法）在 ±10 上 [0.20,0.30) 桶预测 0.24 / 实际 0.40、[0.50,0.70) 预测 0.58 / 实际 0.40、[0.70,1.00) 只有 1 个点且错；±30 / ±60 高桶几乎无样本。要上线必须先解决后验的标定，而不是先验本身。
+3. **42 个特征里 31 / 36 / 38 个（±10 / ±30 / ±60）的 5–95% 置信区间跨 0**（案例级 bootstrap 200 次）。±10 上区间不跨 0 的：`ashtakavarga_target_house_pressure_auxiliary`（+0.41）、`vim_ad_domain_varga`（+0.30）、`vim_md_domain_varga`（+0.27）、`ghati_lagna_in_target_house` / `hora_lagna_in_target_house`（+0.31）、`pranapada_in_target_house`（**−0.36**）、`vim_ad_arudha_auxiliary`（−0.21）、`narayana_ad_domain_house`（−0.21）、`kp_target_cusp_sublord_is_vim_ad`（−0.19）。方向与线上手拍权重相反的几条（Arudha、Narayana AD、KP AD 子主为负）正是 20 例上说不清的地方——这就是任务书要先扩集的原因。
+4. 稳健性（留一法 A3，`raw`）：±7 天抖动与 ±1–3 月平移三档真值在区间 0.95–1.00；答错 1 题 0.96–1.00、答错 2 题 0.91–0.99（与 09-26 基线同量级）。`percent` 口径下三项都更差（0.70–0.90），同样是后验过自信的表现。
+
+## R-B · 缺席证据
+
+**方法。** 只用训练事件（留一件 holdout 不用）。每个领域取第一件与最后一件带年月事件之间的年份，没有该领域事件的年份 = 缺席年。对每个缺席 (领域, 年) 用出题器同一判定函数 `_evaluate_contexts(month=None)` 在代表候选上求"这一年该领域是否激活"的分边；分得开就当作一道答了"没有"的题，按 0.5 / 1.0 / 2.0 分扣（卡片是 2.0；低于卡片强度的扣分不计强冲突、不会淘汰）。之后照常六题。漏说稳健性：随机删掉 1–2 件训练事件再算缺席年（每例 5 次，种子固定）。
+
+`raw` 口径六题回放（`percent` 口径同向，见 JSON）：
+
+| 半径 | 方案 | 头名命中 | 真值在区间 | 宽度中位 | 挤出真值 | 漏说 1 件（100 次回放）真值在区间 | 漏说 2 件 |
+| --- | --- | ---: | ---: | ---: | ---: | ---: | ---: |
+| ±10 | B0 | 0.80 | 1.00 | 15 | 0 | — | — |
+| ±10 | 缺席 @0.5 分 | 0.70 | 1.00 | 15 | 0 | 1.00 | 1.00 |
+| ±10 | 缺席 @1.0 分 | 0.70 | 1.00 | 14 | 0 | 1.00 | 1.00 |
+| ±10 | 缺席 @2.0 分（=卡片） | 0.55 | **0.85** | 13 | 3 | 0.94 | 0.94 |
+| ±30 | B0 | 0.55 | 1.00 | 33 | 0 | — | — |
+| ±30 | 缺席 @0.5 分 | 0.50 | 1.00 | 34 | 0 | 1.00 | 1.00 |
+| ±30 | 缺席 @1.0 分 | 0.45 | 1.00 | 33 | 0 | 1.00 | 1.00 |
+| ±30 | 缺席 @2.0 分 | 0.25 | **0.70** | 19 | 6 | 0.80 | 0.87 |
+| ±60 | B0 | 0.40 | 1.00 | 56 | 0 | — | — |
+| ±60 | 缺席 @0.5 分 | 0.35 | 1.00 | 68 | 0 | 1.00 | 1.00 |
+| ±60 | 缺席 @1.0 分 | 0.25 | 1.00 | 61 | 0 | 1.00 | 1.00 |
+| ±60 | 缺席 @2.0 分 | 0.10 | **0.40** | 9 | 12 | 0.54 | 0.73 |
+
+每例平均缺席年 17.95；能分边的缺席题 2.05 / 4.30 / 6.15 道（有题的例子 12 / 17 / 17）。三档 debug 判定全部 no_benefit。
+
+读法：
+
+1. **按卡片强度扣，真值被大量挤出**（±60 覆盖 1.00 → 0.40）。原因不是方法错，而是 v4 的事件表是传记摘录：那些"空白年"里公众人物多半确有该领域的事，只是没进数据集；扣分等于用不完整的时间线否定真值。真人口述同样不完整（用户不会把每年的事都说全），所以这条在 v5 上大概率也是负的——**若 v5 上不翻转，R-B 关闭**。
+2. 0.5 / 1.0 分档不挤真值（覆盖 1.00）但头名一律下降、宽度不降，等于只加噪声。漏说 1–2 件在低强度下不伤覆盖，在卡片强度下把覆盖压到 0.54–0.94。
+
+## R-C · 精度追问可行性
+
+**方法。** 把每例所有日精度经历降成"只记得年"（v4 没有月精度）作为口述形态 `C0_spoken`，先验按线上重算。对每件训练中的日精度经历，用 `_evaluate_contexts(month=真实月份)` 判断"知道月份后能否把代表候选分到两边"；能分的按信息增益排序取前 1 / 2 件：`C{k}_prior`（那件恢复到月精度重算先验）、`C{k}_probe`（当作答"是"的卡）、`C{k}_both`。
+
+| 半径 | 每例可追问件数均值 | ≥1 件的例子 | ≥2 件的例子 |
+| --- | ---: | ---: | ---: |
+| ±10 | 0.20 | 2 / 20 | 1 / 20 |
+| ±30 | 0.45 | 7 / 20 | 1 / 20 |
+| ±60 | 0.70 | 10 / 20 | 3 / 20 |
+
+| 半径 | 方案 | n | 头名命中（raw） | 真值在区间 | 宽度中位 | 同 n 例的 C0（raw 头名 / 宽度） |
+| --- | --- | ---: | ---: | ---: | ---: | --- |
+| ±10 | C1_prior / C1_probe | 2 | 1.00 / 0.50 | 1.00 | 16 | 见 JSON per-arm（样本太少） |
+| ±30 | C1_prior | 7 | 0.71 | 1.00 | 31 | debug 判定 benefit（percent 口径头名 1.00） |
+| ±30 | C1_probe | 7 | 0.57 | 1.00 | 33 | no_benefit |
+| ±60 | C1_prior / C1_probe | 10 | 0.40 / 0.40 | 1.00 | 58 / 63 | no_benefit |
+
+**读法。** 可追问的经历很少（与 09-29 打字经历研究一致：绝大多数经历落在所有候选都一样的大运段），但在 ±30 上"恢复到月精度重算先验"（走线上已有的打字经历通道，不加卡片）对那 7 例有正向信号；"当作答是的卡"没有。样本太少，只能说值得在 v5 上按同口径重测；产品层实现（只对落在候选分歧点的那一件追问月份，算在定向追问 2 条额度内）要等 v5 判定。
+
+## 给产品的话
+
+- 三条流水线都跑通、与线上对账 0 差，**但没有任何一条在 v4 上能下结论**，20 例上 42 个特征有四分之三分不清正负。这一轮交付的是"能在 v5 上一键复跑的测量工具"，不是新打分。
+- v4 上唯一方向明确的信号是负的：把口述时间线的空白当"没发生"会伤真值（R-B）。
+- v5 交付后的复跑命令：`PYTHONHASHSEED=0 python3 scripts/research/scoring_research.py --holdout references/real_case_calibration/minute_rectification_holdout_v5.json --dataset-label v5 --out-suffix v5_<日期>`。
+
+## 附：复跑命令
+
+```bash
+PYTHONHASHSEED=0 python3 scripts/research/scoring_research.py --cache-dir /tmp/scoring_ctx        # 约 14 分钟，写三份 JSON
+PYTHONHASHSEED=0 python3 scripts/research/scoring_research.py --limit 3 --radii 10 --fast --no-write   # 开发用
+python3 -m pytest tests/test_scoring_research.py -q
+```
diff --git a/docs/research/scoring_research_absence_2026_09_29.json b/docs/research/scoring_research_absence_2026_09_29.json
new file mode 100644
index 00000000..96f0cb2c
--- /dev/null
+++ b/docs/research/scoring_research_absence_2026_09_29.json
@@ -0,0 +1,1314 @@
+{
+ "ask_count": 6,
+ "ayanamsa": "raman",
+ "card_points": 2.0,
+ "case_count": 20,
+ "dataset": "v4",
+ "errors": [],
+ "fast": false,
+ "generated_for": "TASK-rectification-scoring-research-20260929",
+ "holdout": "references/real_case_calibration/minute_rectification_holdout_v4.json",
+ "minute_step": 2,
+ "node_mode": "mean",
+ "omit_repeats": 5,
+ "open_set_not_blind": true,
+ "part": "R-B",
+ "points": [
+  0.5,
+  1.0,
+  2.0
+ ],
+ "probe_today": "2026-09-16",
+ "probes": "production G0 probes generated once per case/radius from the production matrix; reused for every arm",
+ "radii": {
+  "10": {
+   "arms": {
+    "B0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0376,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.9,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0346,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     }
+    },
+    "absence@0.5": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0382,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.75,
+      "truth_eliminated": 0,
+      "width_median": 14.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0342,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.7,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     },
+     "verdict": "pending_v5"
+    },
+    "absence@1.0": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0325,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.75,
+      "truth_eliminated": 0,
+      "width_median": 12.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0266,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.7,
+      "truth_eliminated": 0,
+      "width_median": 14.0
+     },
+     "verdict": "pending_v5"
+    },
+    "absence@2.0": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.85,
+      "engine_top1": 0.3,
+      "entropy": 1.4545,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 3,
+      "tie": 0.05,
+      "top1": 0.6,
+      "truth_eliminated": 4,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 0.85,
+      "engine_top1": 0.3,
+      "entropy": 1.4533,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 3,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 4,
+      "width_median": 13.0
+     },
+     "verdict": "pending_v5"
+    }
+   },
+   "gap_stats": {
+    "cases_with_probes": 12,
+    "mean_absence_probes": 2.05,
+    "mean_absent_years": 17.95
+   },
+   "n": 20,
+   "omission": {
+    "omit_1@0.5": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0382,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.04,
+      "top1": 0.83,
+      "truth_eliminated": 0,
+      "width_median": 13.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0343,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.71,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     }
+    },
+    "omit_1@1.0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0344,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.79,
+      "truth_eliminated": 0,
+      "width_median": 12.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0287,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.71,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     }
+    },
+    "omit_1@2.0": {
+     "percent": {
+      "coverage": 0.94,
+      "engine_top1": 0.3,
+      "entropy": 1.6687,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 6,
+      "tie": 0.05,
+      "top1": 0.7,
+      "truth_eliminated": 10,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 0.94,
+      "engine_top1": 0.3,
+      "entropy": 1.6673,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 6,
+      "tie": 0.0,
+      "top1": 0.62,
+      "truth_eliminated": 10,
+      "width_median": 15.0
+     }
+    },
+    "omit_2@0.5": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0376,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.04,
+      "top1": 0.85,
+      "truth_eliminated": 0,
+      "width_median": 13.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0338,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.74,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     }
+    },
+    "omit_2@1.0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0349,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.81,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0297,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.74,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     }
+    },
+    "omit_2@2.0": {
+     "percent": {
+      "coverage": 0.94,
+      "engine_top1": 0.3,
+      "entropy": 1.7352,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 6,
+      "tie": 0.05,
+      "top1": 0.74,
+      "truth_eliminated": 8,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 0.94,
+      "engine_top1": 0.3,
+      "entropy": 1.7338,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 6,
+      "tie": 0.0,
+      "top1": 0.67,
+      "truth_eliminated": 8,
+      "width_median": 15.0
+     }
+    }
+   }
+  },
+  "30": {
+   "arms": {
+    "B0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.151,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.85,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1646,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     }
+    },
+    "absence@0.5": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1456,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.65,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1641,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 34.0
+     },
+     "verdict": "pending_v5"
+    },
+    "absence@1.0": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1172,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.65,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1567,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.45,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "verdict": "pending_v5"
+    },
+    "absence@2.0": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.7,
+      "engine_top1": 0.2,
+      "entropy": 1.8761,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 6,
+      "tie": 0.05,
+      "top1": 0.4,
+      "truth_eliminated": 6,
+      "width_median": 19.0
+     },
+     "raw": {
+      "coverage": 0.7,
+      "engine_top1": 0.2,
+      "entropy": 1.8822,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 6,
+      "tie": 0.0,
+      "top1": 0.25,
+      "truth_eliminated": 6,
+      "width_median": 19.0
+     },
+     "verdict": "pending_v5"
+    }
+   },
+   "gap_stats": {
+    "cases_with_probes": 17,
+    "mean_absence_probes": 4.3,
+    "mean_absent_years": 17.95
+   },
+   "n": 20,
+   "omission": {
+    "omit_1@0.5": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.147,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.73,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1642,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     }
+    },
+    "omit_1@1.0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1213,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.68,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.159,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.44,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     }
+    },
+    "omit_1@2.0": {
+     "percent": {
+      "coverage": 0.8,
+      "engine_top1": 0.2,
+      "entropy": 2.1629,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 20,
+      "tie": 0.04,
+      "top1": 0.47,
+      "truth_eliminated": 20,
+      "width_median": 27.0
+     },
+     "raw": {
+      "coverage": 0.8,
+      "engine_top1": 0.2,
+      "entropy": 2.1702,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 20,
+      "tie": 0.0,
+      "top1": 0.29,
+      "truth_eliminated": 20,
+      "width_median": 27.0
+     }
+    },
+    "omit_2@0.5": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1489,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.81,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1642,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.52,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     }
+    },
+    "omit_2@1.0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1359,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.78,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1616,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.49,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     }
+    },
+    "omit_2@2.0": {
+     "percent": {
+      "coverage": 0.87,
+      "engine_top1": 0.2,
+      "entropy": 2.4897,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 13,
+      "tie": 0.04,
+      "top1": 0.62,
+      "truth_eliminated": 13,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 0.87,
+      "engine_top1": 0.2,
+      "entropy": 2.4992,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 13,
+      "tie": 0.0,
+      "top1": 0.37,
+      "truth_eliminated": 13,
+      "width_median": 31.0
+     }
+    }
+   }
+  },
+  "60": {
+   "arms": {
+    "B0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9174,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 53.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9537,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.4,
+      "truth_eliminated": 0,
+      "width_median": 56.0
+     }
+    },
+    "absence@0.5": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.8196,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9473,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.35,
+      "truth_eliminated": 0,
+      "width_median": 68.0
+     },
+     "verdict": "pending_v5"
+    },
+    "absence@1.0": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.6772,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.921,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.25,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "verdict": "pending_v5"
+    },
+    "absence@2.0": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.4,
+      "engine_top1": 0.05,
+      "entropy": 1.7866,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 12,
+      "tie": 0.1,
+      "top1": 0.25,
+      "truth_eliminated": 13,
+      "width_median": 9.0
+     },
+     "raw": {
+      "coverage": 0.4,
+      "engine_top1": 0.05,
+      "entropy": 1.8021,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 12,
+      "tie": 0.0,
+      "top1": 0.1,
+      "truth_eliminated": 13,
+      "width_median": 9.0
+     },
+     "verdict": "pending_v5"
+    }
+   },
+   "gap_stats": {
+    "cases_with_probes": 17,
+    "mean_absence_probes": 6.15,
+    "mean_absent_years": 17.95
+   },
+   "n": 20,
+   "omission": {
+    "omit_1@0.5": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.8369,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.61,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9481,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.37,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     }
+    },
+    "omit_1@1.0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.7299,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.6,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9258,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.28,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     }
+    },
+    "omit_1@2.0": {
+     "percent": {
+      "coverage": 0.54,
+      "engine_top1": 0.05,
+      "entropy": 2.101,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 46,
+      "tie": 0.16,
+      "top1": 0.41,
+      "truth_eliminated": 51,
+      "width_median": 25.0
+     },
+     "raw": {
+      "coverage": 0.54,
+      "engine_top1": 0.05,
+      "entropy": 2.1191,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 46,
+      "tie": 0.0,
+      "top1": 0.18,
+      "truth_eliminated": 51,
+      "width_median": 25.0
+     }
+    },
+    "omit_2@0.5": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.8802,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.67,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9523,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.41,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     }
+    },
+    "omit_2@1.0": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.8027,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.66,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9444,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.33,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     }
+    },
+    "omit_2@2.0": {
+     "percent": {
+      "coverage": 0.73,
+      "engine_top1": 0.05,
+      "entropy": 2.7068,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 27,
+      "tie": 0.15,
+      "top1": 0.53,
+      "truth_eliminated": 28,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 0.73,
+      "engine_top1": 0.05,
+      "entropy": 2.725,
+      "n": 100,
+      "refresh_mean": 0.0,
+      "squeezed": 27,
+      "tie": 0.0,
+      "top1": 0.28,
+      "truth_eliminated": 28,
+      "width_median": 39.0
+     }
+    }
+   }
+  }
+ },
+ "reconciliation": {
+  "cases": 60,
+  "rows": [
+   {
+    "candidates": 11,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   }
+  ],
+  "unreconciled": 0
+ },
+ "seed": 20260929,
+ "verdict": "pending_v5"
+}
diff --git a/docs/research/scoring_research_lr_2026_09_29.json b/docs/research/scoring_research_lr_2026_09_29.json
new file mode 100644
index 00000000..9a6c7bd9
--- /dev/null
+++ b/docs/research/scoring_research_lr_2026_09_29.json
@@ -0,0 +1,3837 @@
+{
+ "alpha": 1.0,
+ "ask_count": 6,
+ "ayanamsa": "raman",
+ "case_count": 20,
+ "dataset": "v4",
+ "errors": [],
+ "fast": false,
+ "generated_for": "TASK-rectification-scoring-research-20260929",
+ "holdout": "references/real_case_calibration/minute_rectification_holdout_v4.json",
+ "minute_step": 2,
+ "node_mode": "mean",
+ "open_set_not_blind": true,
+ "part": "R-A",
+ "probe_today": "2026-09-16",
+ "probes": "production G0 probes generated once per case/radius from the production matrix; reused for every arm",
+ "radii": {
+  "10": {
+   "baseline": {
+    "percent": {
+     "coverage": 1.0,
+     "engine_top1": 0.3,
+     "entropy": 2.0376,
+     "n": 20,
+     "refresh_mean": 0.0,
+     "squeezed": 0,
+     "tie": 0.0,
+     "top1": 0.9,
+     "truth_eliminated": 0,
+     "width_median": 11.0
+    },
+    "raw": {
+     "coverage": 1.0,
+     "engine_top1": 0.3,
+     "entropy": 2.0346,
+     "n": 20,
+     "refresh_mean": 0.0,
+     "squeezed": 0,
+     "tie": 0.0,
+     "top1": 0.8,
+     "truth_eliminated": 0,
+     "width_median": 15.0
+    }
+   },
+   "calibration": [
+    {
+     "bin": "[0.00,0.05)",
+     "n": 19,
+     "observed_rate": 0.1053,
+     "predicted_mean": 0.0226
+    },
+    {
+     "bin": "[0.05,0.10)",
+     "n": 32,
+     "observed_rate": 0.0938,
+     "predicted_mean": 0.0675
+    },
+    {
+     "bin": "[0.10,0.20)",
+     "n": 37,
+     "observed_rate": 0.0811,
+     "predicted_mean": 0.1514
+    },
+    {
+     "bin": "[0.20,0.30)",
+     "n": 15,
+     "observed_rate": 0.4,
+     "predicted_mean": 0.24
+    },
+    {
+     "bin": "[0.30,0.50)",
+     "n": 12,
+     "observed_rate": 0.3333,
+     "predicted_mean": 0.3692
+    },
+    {
+     "bin": "[0.50,0.70)",
+     "n": 5,
+     "observed_rate": 0.4,
+     "predicted_mean": 0.578
+    },
+    {
+     "bin": "[0.70,1.00)",
+     "n": 1,
+     "observed_rate": 0.0,
+     "predicted_mean": 0.89
+    }
+   ],
+   "full_fit": {
+    "A1": {
+     "percent": {
+      "coverage": 0.8,
+      "engine_top1": 0.45,
+      "entropy": 1.9993,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 4,
+      "tie": 0.0,
+      "top1": 0.65,
+      "truth_eliminated": 0,
+      "width_median": 6.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.45,
+      "entropy": 1.9733,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.75,
+      "truth_eliminated": 0,
+      "width_median": 14.0
+     },
+     "scale": 1.972191,
+     "temperature": 2.0
+    },
+    "A2": {
+     "percent": {
+      "coverage": 0.9,
+      "engine_top1": 0.5,
+      "entropy": 1.8004,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 2,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 6.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.5,
+      "entropy": 1.9875,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     },
+     "scale": 1.379186,
+     "temperature": 1.0
+    },
+    "A3": {
+     "percent": {
+      "coverage": 0.8,
+      "engine_top1": 0.5,
+      "entropy": 1.791,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 4,
+      "tie": 0.0,
+      "top1": 0.6,
+      "truth_eliminated": 0,
+      "width_median": 5.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.5,
+      "entropy": 1.5786,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.85,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     },
+     "scale": 1.118947,
+     "temperature": 1.0
+    }
+   },
+   "loo": {
+    "A1": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.8,
+      "engine_top1": 0.45,
+      "entropy": 1.9847,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 4,
+      "tie": 0.0,
+      "top1": 0.6,
+      "truth_eliminated": 0,
+      "width_median": 7.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.45,
+      "entropy": 1.9797,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.7,
+      "truth_eliminated": 0,
+      "width_median": 14.0
+     },
+     "temperatures": [
+      1.0,
+      2.0
+     ],
+     "verdict": "pending_v5"
+    },
+    "A2": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.85,
+      "engine_top1": 0.4,
+      "entropy": 1.8745,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 3,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 7.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.4,
+      "entropy": 1.9935,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.75,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     },
+     "temperatures": [
+      1.0
+     ],
+     "verdict": "pending_v5"
+    },
+    "A3": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.75,
+      "engine_top1": 0.4,
+      "entropy": 1.8429,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 5,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 5.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.4,
+      "entropy": 1.5789,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     },
+     "temperatures": [
+      0.5,
+      1.0
+     ],
+     "verdict": "pending_v5"
+    }
+   },
+   "lr_table": {
+    "ashtakavarga_target_house_pressure_auxiliary": {
+     "draws": 198,
+     "extra": false,
+     "fires_other": 27.0,
+     "fires_truth": 12.0,
+     "log_lr_absent": -0.01392,
+     "log_lr_present": 0.406865,
+     "p05": 0.1883,
+     "p95": 0.9269,
+     "p_other": 0.026794,
+     "p_truth": 0.040248
+    },
+    "ashtakavarga_target_house_support_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 642.0,
+     "fires_truth": 207.0,
+     "log_lr_absent": -0.0774,
+     "log_lr_present": 0.045513,
+     "p05": 0.0077,
+     "p95": 0.0835,
+     "p_other": 0.615311,
+     "p_truth": 0.643963
+    },
+    "bhava_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 197.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": 0.004573,
+     "log_lr_present": -0.019803,
+     "p05": -0.2314,
+     "p95": 0.1766,
+     "p_other": 0.189474,
+     "p_truth": 0.185759
+    },
+    "controlled_transit_jupiter_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 193.6667,
+     "fires_truth": 59.3333,
+     "log_lr_absent": -0.000623,
+     "log_lr_present": 0.002716,
+     "p05": -0.1072,
+     "p95": 0.1176,
+     "p_other": 0.186284,
+     "p_truth": 0.18679
+    },
+    "controlled_transit_saturn_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 153.5833,
+     "fires_truth": 51.3333,
+     "log_lr_absent": -0.016682,
+     "log_lr_present": 0.09102,
+     "p05": -0.0718,
+     "p95": 0.246,
+     "p_other": 0.147927,
+     "p_truth": 0.162023
+    },
+    "ghati_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 142.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": -0.058341,
+     "log_lr_present": 0.30562,
+     "p05": 0.0233,
+     "p95": 0.5434,
+     "p_other": 0.136842,
+     "p_truth": 0.185759
+    },
+    "hora_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 142.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": -0.058341,
+     "log_lr_present": 0.30562,
+     "p05": 0.0233,
+     "p95": 0.5434,
+     "p_other": 0.136842,
+     "p_truth": 0.185759
+    },
+    "kp_asc_sublord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 115.3333,
+     "fires_truth": 38.1667,
+     "log_lr_absent": -0.011243,
+     "log_lr_present": 0.085486,
+     "p05": -0.2308,
+     "p95": 0.3943,
+     "p_other": 0.111324,
+     "p_truth": 0.121259
+    },
+    "kp_asc_sublord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 120.1667,
+     "fires_truth": 60.3333,
+     "log_lr_absent": -0.08734,
+     "log_lr_present": 0.493276,
+     "p05": -0.0258,
+     "p95": 0.8263,
+     "p_other": 0.115949,
+     "p_truth": 0.189886
+    },
+    "kp_asc_sublord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 149.75,
+     "fires_truth": 47.4167,
+     "log_lr_absent": -0.006611,
+     "log_lr_present": 0.038341,
+     "p05": -0.2252,
+     "p95": 0.2252,
+     "p_other": 0.144258,
+     "p_truth": 0.149897
+    },
+    "kp_target_cusp_starlord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 200.5833,
+     "fires_truth": 60.6667,
+     "log_lr_absent": 0.002455,
+     "log_lr_present": -0.010339,
+     "p05": -0.1118,
+     "p95": 0.0662,
+     "p_other": 0.192903,
+     "p_truth": 0.190918
+    },
+    "kp_target_cusp_starlord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 233.0,
+     "fires_truth": 68.0,
+     "log_lr_absent": 0.013186,
+     "log_lr_present": -0.047095,
+     "p05": -0.21,
+     "p95": 0.1178,
+     "p_other": 0.223923,
+     "p_truth": 0.213622
+    },
+    "kp_target_cusp_starlord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 134.4167,
+     "fires_truth": 43.1667,
+     "log_lr_absent": -0.008253,
+     "log_lr_present": 0.053734,
+     "p05": -0.0906,
+     "p95": 0.1935,
+     "p_other": 0.129585,
+     "p_truth": 0.136739
+    },
+    "kp_target_cusp_sublord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 231.3333,
+     "fires_truth": 58.1667,
+     "log_lr_absent": 0.049116,
+     "log_lr_present": -0.193695,
+     "p05": -0.3737,
+     "p95": -0.0597,
+     "p_other": 0.222329,
+     "p_truth": 0.183179
+    },
+    "kp_target_cusp_sublord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 217.75,
+     "fires_truth": 77.6667,
+     "log_lr_absent": -0.044244,
+     "log_lr_present": 0.15141,
+     "p05": -0.1676,
+     "p95": 0.3785,
+     "p_other": 0.20933,
+     "p_truth": 0.24355
+    },
+    "kp_target_cusp_sublord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 201.25,
+     "fires_truth": 68.0833,
+     "log_lr_absent": -0.025544,
+     "log_lr_present": 0.099929,
+     "p05": -0.1017,
+     "p95": 0.2437,
+     "p_other": 0.193541,
+     "p_truth": 0.21388
+    },
+    "narayana_ad_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 140.5,
+     "fires_truth": 34.5,
+     "log_lr_absent": 0.029067,
+     "log_lr_present": -0.208647,
+     "p05": -0.4929,
+     "p95": -0.0116,
+     "p_other": 0.135407,
+     "p_truth": 0.109907
+    },
+    "narayana_md_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 171.75,
+     "fires_truth": 50.0,
+     "log_lr_absent": 0.008846,
+     "log_lr_present": -0.0459,
+     "p05": -0.1656,
+     "p95": 0.0157,
+     "p_other": 0.165311,
+     "p_truth": 0.157895
+    },
+    "pranapada_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 157.0,
+     "fires_truth": 33.0,
+     "log_lr_absent": 0.052702,
+     "log_lr_present": -0.362115,
+     "p05": -0.8036,
+     "p95": -0.0695,
+     "p_other": 0.151196,
+     "p_truth": 0.105263
+    },
+    "shadbala_sthana_drik_naisargika_pressure_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 639.6667,
+     "fires_truth": 198.5,
+     "log_lr_absent": -0.011879,
+     "log_lr_present": 0.007425,
+     "p05": -0.0508,
+     "p95": 0.0587,
+     "p_other": 0.613078,
+     "p_truth": 0.617647
+    },
+    "shadbala_sthana_drik_naisargika_support_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 397.1667,
+     "fires_truth": 121.0833,
+     "log_lr_absent": 0.004921,
+     "log_lr_present": -0.008047,
+     "p05": -0.0934,
+     "p95": 0.0795,
+     "p_other": 0.381021,
+     "p_truth": 0.377967
+    },
+    "vim_ad_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 109.75,
+     "fires_truth": 26.6667,
+     "log_lr_absent": 0.02248,
+     "log_lr_present": -0.212927,
+     "p05": -0.351,
+     "p95": -0.075,
+     "p_other": 0.105981,
+     "p_truth": 0.085655
+    },
+    "vim_ad_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 159.5833,
+     "fires_truth": 52.1667,
+     "log_lr_absent": -0.013004,
+     "log_lr_present": 0.068738,
+     "p05": -0.0373,
+     "p95": 0.1944,
+     "p_other": 0.153668,
+     "p_truth": 0.164603
+    },
+    "vim_ad_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 229.9167,
+     "fires_truth": 69.8333,
+     "log_lr_absent": 0.002147,
+     "log_lr_present": -0.007607,
+     "p05": -0.0983,
+     "p95": 0.0669,
+     "p_other": 0.220973,
+     "p_truth": 0.219298
+    },
+    "vim_ad_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 207.0,
+     "fires_truth": 86.1667,
+     "log_lr_absent": -0.092579,
+     "log_lr_present": 0.304404,
+     "p05": 0.1603,
+     "p95": 0.4577,
+     "p_other": 0.199043,
+     "p_truth": 0.269866
+    },
+    "vim_ad_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 153.6667,
+     "fires_truth": 45.0,
+     "log_lr_absent": 0.006541,
+     "log_lr_present": -0.038511,
+     "p05": -0.3581,
+     "p95": 0.2665,
+     "p_other": 0.148006,
+     "p_truth": 0.142415
+    },
+    "vim_ad_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 404.1667,
+     "fires_truth": 116.1667,
+     "log_lr_absent": 0.039979,
+     "log_lr_present": -0.066581,
+     "p05": -0.127,
+     "p95": 0.0065,
+     "p_other": 0.387719,
+     "p_truth": 0.362745
+    },
+    "vim_ad_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 371.1667,
+     "fires_truth": 124.4167,
+     "log_lr_absent": -0.051217,
+     "log_lr_present": 0.08642,
+     "p05": -0.0198,
+     "p95": 0.1959,
+     "p_other": 0.35614,
+     "p_truth": 0.388287
+    },
+    "vim_md_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 80.0,
+     "fires_truth": 25.0,
+     "log_lr_absent": -0.003239,
+     "log_lr_present": 0.037767,
+     "p05": -0.1267,
+     "p95": 0.3235,
+     "p_other": 0.077512,
+     "p_truth": 0.080495
+    },
+    "vim_md_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 140.0,
+     "fires_truth": 45.6667,
+     "log_lr_absent": -0.011102,
+     "log_lr_present": 0.06839,
+     "p05": -0.055,
+     "p95": 0.232,
+     "p_other": 0.134928,
+     "p_truth": 0.144479
+    },
+    "vim_md_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 276.5,
+     "fires_truth": 87.0,
+     "log_lr_absent": -0.009433,
+     "log_lr_present": 0.025636,
+     "p05": -0.0708,
+     "p95": 0.1151,
+     "p_other": 0.26555,
+     "p_truth": 0.272446
+    },
+    "vim_md_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 216.0833,
+     "fires_truth": 86.6667,
+     "log_lr_absent": -0.08379,
+     "log_lr_present": 0.26738,
+     "p05": 0.091,
+     "p95": 0.4654,
+     "p_other": 0.207735,
+     "p_truth": 0.271414
+    },
+    "vim_md_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 159.6667,
+     "fires_truth": 54.0,
+     "log_lr_absent": -0.019727,
+     "log_lr_present": 0.102121,
+     "p05": -0.2417,
+     "p95": 0.4246,
+     "p_other": 0.153748,
+     "p_truth": 0.170279
+    },
+    "vim_md_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 214.5,
+     "fires_truth": 64.3333,
+     "log_lr_absent": 0.004963,
+     "log_lr_present": -0.019339,
+     "p05": -0.4451,
+     "p95": 0.2187,
+     "p_other": 0.20622,
+     "p_truth": 0.20227
+    },
+    "vim_md_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 564.3333,
+     "fires_truth": 187.1667,
+     "log_lr_absent": -0.094932,
+     "log_lr_present": 0.074032,
+     "p05": -0.0263,
+     "p95": 0.1856,
+     "p_other": 0.540989,
+     "p_truth": 0.582559
+    },
+    "vim_pd_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 82.0,
+     "fires_truth": 25.3333,
+     "log_lr_absent": -0.002285,
+     "log_lr_present": 0.026115,
+     "p05": -0.2546,
+     "p95": 0.264,
+     "p_other": 0.079426,
+     "p_truth": 0.081527
+    },
+    "vim_pd_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 153.5833,
+     "fires_truth": 50.75,
+     "log_lr_absent": -0.014529,
+     "log_lr_present": 0.079811,
+     "p05": -0.0906,
+     "p95": 0.2171,
+     "p_other": 0.147927,
+     "p_truth": 0.160217
+    },
+    "vim_pd_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 249.0833,
+     "fires_truth": 82.9167,
+     "log_lr_absent": -0.027305,
+     "log_lr_present": 0.08215,
+     "p05": -0.0075,
+     "p95": 0.1658,
+     "p_other": 0.239314,
+     "p_truth": 0.259804
+    },
+    "vim_pd_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 217.9167,
+     "fires_truth": 71.1667,
+     "log_lr_absent": -0.017787,
+     "log_lr_present": 0.064407,
+     "p05": -0.1377,
+     "p95": 0.2605,
+     "p_other": 0.20949,
+     "p_truth": 0.223426
+    },
+    "vim_pd_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 151.25,
+     "fires_truth": 50.9167,
+     "log_lr_absent": -0.01776,
+     "log_lr_present": 0.098236,
+     "p05": -0.1431,
+     "p95": 0.3184,
+     "p_other": 0.145694,
+     "p_truth": 0.160733
+    },
+    "vim_pd_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 357.5,
+     "fires_truth": 101.25,
+     "log_lr_absent": 0.039544,
+     "log_lr_present": -0.080388,
+     "p05": -0.1672,
+     "p95": -0.0122,
+     "p_other": 0.343062,
+     "p_truth": 0.316563
+    },
+    "vim_pd_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 332.8333,
+     "fires_truth": 106.5833,
+     "log_lr_absent": -0.020213,
+     "log_lr_present": 0.041744,
+     "p05": -0.0329,
+     "p95": 0.1148,
+     "p_other": 0.319458,
+     "p_truth": 0.333075
+    }
+   },
+   "n": 20,
+   "noise_features": [
+    "bhava_lagna_in_target_house",
+    "controlled_transit_jupiter_domain_house",
+    "controlled_transit_saturn_domain_house",
+    "kp_asc_sublord_is_vim_ad",
+    "kp_asc_sublord_is_vim_md",
+    "kp_asc_sublord_is_vim_pd",
+    "kp_target_cusp_starlord_is_vim_ad",
+    "kp_target_cusp_starlord_is_vim_md",
+    "kp_target_cusp_starlord_is_vim_pd",
+    "kp_target_cusp_sublord_is_vim_md",
+    "kp_target_cusp_sublord_is_vim_pd",
+    "narayana_md_domain_house",
+    "shadbala_sthana_drik_naisargika_pressure_auxiliary",
+    "shadbala_sthana_drik_naisargika_support_auxiliary",
+    "vim_ad_domain_house",
+    "vim_ad_domain_lord",
+    "vim_ad_domain_varga_d60",
+    "vim_ad_functional_benefic_auxiliary",
+    "vim_ad_functional_malefic_auxiliary",
+    "vim_md_arudha_auxiliary",
+    "vim_md_domain_house",
+    "vim_md_domain_lord",
+    "vim_md_domain_varga_d60",
+    "vim_md_functional_benefic_auxiliary",
+    "vim_md_functional_malefic_auxiliary",
+    "vim_pd_arudha_auxiliary",
+    "vim_pd_domain_house",
+    "vim_pd_domain_lord",
+    "vim_pd_domain_varga",
+    "vim_pd_domain_varga_d60",
+    "vim_pd_functional_malefic_auxiliary"
+   ],
+   "robustness": {
+    "A1": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.8588,
+       "engine_top1": 0.4824,
+       "entropy": 1.7366,
+       "n": 85,
+       "refresh_mean": 0.0,
+       "squeezed": 12,
+       "tie": 0.0,
+       "top1": 0.5529,
+       "truth_eliminated": 0,
+       "width_median": 11.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.4824,
+       "entropy": 1.7439,
+       "n": 85,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.5529,
+       "truth_eliminated": 0,
+       "width_median": 13.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.8467,
+       "engine_top1": 0.4667,
+       "entropy": 1.4509,
+       "n": 150,
+       "refresh_mean": 0.0,
+       "squeezed": 23,
+       "tie": 0.0333,
+       "top1": 0.4667,
+       "truth_eliminated": 0,
+       "width_median": 7.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.4667,
+       "entropy": 1.4626,
+       "n": 150,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.3067,
+       "truth_eliminated": 0,
+       "width_median": 11.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 0.85,
+       "engine_top1": 0.4,
+       "entropy": 1.9845,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 3,
+       "tie": 0.0,
+       "top1": 0.7,
+       "truth_eliminated": 0,
+       "width_median": 7.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.4,
+       "entropy": 1.9769,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.75,
+       "truth_eliminated": 0,
+       "width_median": 12.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 0.8833,
+       "engine_top1": 0.3667,
+       "entropy": 1.9998,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 7,
+       "tie": 0.0,
+       "top1": 0.65,
+       "truth_eliminated": 0,
+       "width_median": 10.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.3667,
+       "entropy": 1.984,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.75,
+       "truth_eliminated": 0,
+       "width_median": 13.0
+      }
+     }
+    },
+    "A2": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.7294,
+       "engine_top1": 0.4824,
+       "entropy": 1.6357,
+       "n": 85,
+       "refresh_mean": 0.0,
+       "squeezed": 23,
+       "tie": 0.0,
+       "top1": 0.6118,
+       "truth_eliminated": 0,
+       "width_median": 5.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.4824,
+       "entropy": 1.7522,
+       "n": 85,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.6706,
+       "truth_eliminated": 0,
+       "width_median": 13.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.6533,
+       "engine_top1": 0.4667,
+       "entropy": 1.3626,
+       "n": 150,
+       "refresh_mean": 0.0,
+       "squeezed": 52,
+       "tie": 0.0,
+       "top1": 0.5467,
+       "truth_eliminated": 0,
+       "width_median": 5.0
+      },
+      "raw": {
+       "coverage": 0.9867,
+       "engine_top1": 0.4667,
+       "entropy": 1.4771,
+       "n": 150,
+       "refresh_mean": 0.0,
+       "squeezed": 2,
+       "tie": 0.0,
+       "top1": 0.38,
+       "truth_eliminated": 0,
+       "width_median": 11.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 0.75,
+       "engine_top1": 0.3,
+       "entropy": 1.8711,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 5,
+       "tie": 0.0,
+       "top1": 0.5,
+       "truth_eliminated": 0,
+       "width_median": 6.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.3,
+       "entropy": 1.9924,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.75,
+       "truth_eliminated": 0,
+       "width_median": 15.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 0.7,
+       "engine_top1": 0.25,
+       "entropy": 1.8559,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 18,
+       "tie": 0.0,
+       "top1": 0.5333,
+       "truth_eliminated": 0,
+       "width_median": 5.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.25,
+       "entropy": 1.9943,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.7333,
+       "truth_eliminated": 0,
+       "width_median": 15.0
+      }
+     }
+    },
+    "A3": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.7647,
+       "engine_top1": 0.4118,
+       "entropy": 1.5963,
+       "n": 85,
+       "refresh_mean": 0.0,
+       "squeezed": 20,
+       "tie": 0.0,
+       "top1": 0.6353,
+       "truth_eliminated": 0,
+       "width_median": 5.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.4118,
+       "entropy": 1.6416,
+       "n": 85,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.6706,
+       "truth_eliminated": 0,
+       "width_median": 13.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.6667,
+       "engine_top1": 0.4,
+       "entropy": 1.326,
+       "n": 150,
+       "refresh_mean": 0.0,
+       "squeezed": 50,
+       "tie": 0.0,
+       "top1": 0.5667,
+       "truth_eliminated": 0,
+       "width_median": 5.0
+      },
+      "raw": {
+       "coverage": 0.9867,
+       "engine_top1": 0.4,
+       "entropy": 1.3898,
+       "n": 150,
+       "refresh_mean": 0.0,
+       "squeezed": 2,
+       "tie": 0.0,
+       "top1": 0.38,
+       "truth_eliminated": 0,
+       "width_median": 11.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 0.75,
+       "engine_top1": 0.3,
+       "entropy": 1.8436,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 5,
+       "tie": 0.0,
+       "top1": 0.55,
+       "truth_eliminated": 0,
+       "width_median": 5.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.3,
+       "entropy": 1.5768,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.75,
+       "truth_eliminated": 0,
+       "width_median": 15.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 0.7333,
+       "engine_top1": 0.3333,
+       "entropy": 1.8368,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 16,
+       "tie": 0.0,
+       "top1": 0.6,
+       "truth_eliminated": 0,
+       "width_median": 5.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.3333,
+       "entropy": 1.5645,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.7833,
+       "truth_eliminated": 0,
+       "width_median": 15.0
+      }
+     }
+    }
+   }
+  },
+  "30": {
+   "baseline": {
+    "percent": {
+     "coverage": 1.0,
+     "engine_top1": 0.2,
+     "entropy": 3.151,
+     "n": 20,
+     "refresh_mean": 0.0,
+     "squeezed": 0,
+     "tie": 0.0,
+     "top1": 0.85,
+     "truth_eliminated": 0,
+     "width_median": 33.0
+    },
+    "raw": {
+     "coverage": 1.0,
+     "engine_top1": 0.2,
+     "entropy": 3.1646,
+     "n": 20,
+     "refresh_mean": 0.0,
+     "squeezed": 0,
+     "tie": 0.0,
+     "top1": 0.55,
+     "truth_eliminated": 0,
+     "width_median": 33.0
+    }
+   },
+   "calibration": [
+    {
+     "bin": "[0.00,0.05)",
+     "n": 163,
+     "observed_rate": 0.0307,
+     "predicted_mean": 0.0257
+    },
+    {
+     "bin": "[0.05,0.10)",
+     "n": 124,
+     "observed_rate": 0.0484,
+     "predicted_mean": 0.0668
+    },
+    {
+     "bin": "[0.10,0.20)",
+     "n": 40,
+     "observed_rate": 0.175,
+     "predicted_mean": 0.1285
+    },
+    {
+     "bin": "[0.20,0.30)",
+     "n": 3,
+     "observed_rate": 0.6667,
+     "predicted_mean": 0.21
+    },
+    {
+     "bin": "[0.30,0.50)",
+     "n": 3,
+     "observed_rate": 0.0,
+     "predicted_mean": 0.41
+    },
+    {
+     "bin": "[0.50,0.70)",
+     "n": 1,
+     "observed_rate": 0.0,
+     "predicted_mean": 0.5
+    },
+    {
+     "bin": "[0.70,1.00)",
+     "n": 0,
+     "observed_rate": null,
+     "predicted_mean": null
+    }
+   ],
+   "full_fit": {
+    "A1": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.25,
+      "entropy": 3.133,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.25,
+      "entropy": 3.1392,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.7,
+      "truth_eliminated": 0,
+      "width_median": 32.0
+     },
+     "scale": 3.375292,
+     "temperature": 4.0
+    },
+    "A2": {
+     "percent": {
+      "coverage": 0.85,
+      "engine_top1": 0.3,
+      "entropy": 3.004,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 3,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 7.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 3.1301,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.65,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "scale": 1.84633,
+     "temperature": 2.0
+    },
+    "A3": {
+     "percent": {
+      "coverage": 0.9,
+      "engine_top1": 0.45,
+      "entropy": 2.9852,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 2,
+      "tie": 0.0,
+      "top1": 0.65,
+      "truth_eliminated": 0,
+      "width_median": 12.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.45,
+      "entropy": 2.9242,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.75,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "scale": 1.506452,
+     "temperature": 2.0
+    }
+   },
+   "loo": {
+    "A1": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "benefit"
+     },
+     "percent": {
+      "coverage": 0.95,
+      "engine_top1": 0.25,
+      "entropy": 3.1307,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 1,
+      "tie": 0.0,
+      "top1": 0.65,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.25,
+      "entropy": 3.1414,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 32.0
+     },
+     "temperatures": [
+      2.0,
+      4.0
+     ],
+     "verdict": "pending_v5"
+    },
+    "A2": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.8,
+      "engine_top1": 0.1,
+      "entropy": 3.0138,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 4,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 10.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.1,
+      "entropy": 3.1341,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.6,
+      "truth_eliminated": 0,
+      "width_median": 34.0
+     },
+     "temperatures": [
+      1.0,
+      2.0
+     ],
+     "verdict": "pending_v5"
+    },
+    "A3": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "benefit"
+     },
+     "percent": {
+      "coverage": 0.9,
+      "engine_top1": 0.2,
+      "entropy": 3.0,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 2,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 13.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 2.9259,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.65,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "temperatures": [
+      1.0,
+      2.0
+     ],
+     "verdict": "pending_v5"
+    }
+   },
+   "lr_table": {
+    "ashtakavarga_target_house_pressure_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 100.0,
+     "fires_truth": 12.0,
+     "log_lr_absent": -0.012009,
+     "log_lr_present": 0.339812,
+     "p05": 0.0424,
+     "p95": 0.7324,
+     "p_other": 0.028652,
+     "p_truth": 0.040248
+    },
+    "ashtakavarga_target_house_support_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 2177.0,
+     "fires_truth": 207.0,
+     "log_lr_absent": -0.07072,
+     "log_lr_present": 0.041359,
+     "p05": -0.0024,
+     "p95": 0.0763,
+     "p_other": 0.617872,
+     "p_truth": 0.643963
+    },
+    "bhava_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 605.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": -0.016859,
+     "log_lr_present": 0.077448,
+     "p05": -0.1477,
+     "p95": 0.2646,
+     "p_other": 0.171915,
+     "p_truth": 0.185759
+    },
+    "controlled_transit_jupiter_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 646.8333,
+     "fires_truth": 59.3333,
+     "log_lr_absent": -0.003692,
+     "log_lr_present": 0.016235,
+     "p05": -0.0804,
+     "p95": 0.1187,
+     "p_other": 0.183782,
+     "p_truth": 0.18679
+    },
+    "controlled_transit_saturn_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 548.1666,
+     "fires_truth": 51.3333,
+     "log_lr_absent": -0.007408,
+     "log_lr_present": 0.039215,
+     "p05": -0.1024,
+     "p95": 0.1725,
+     "p_other": 0.155792,
+     "p_truth": 0.162023
+    },
+    "ghati_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 511.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": -0.048554,
+     "log_lr_present": 0.246003,
+     "p05": -0.0058,
+     "p95": 0.4429,
+     "p_other": 0.145248,
+     "p_truth": 0.185759
+    },
+    "hora_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 511.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": -0.048554,
+     "log_lr_present": 0.246003,
+     "p05": -0.0058,
+     "p95": 0.4429,
+     "p_other": 0.145248,
+     "p_truth": 0.185759
+    },
+    "kp_asc_sublord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 453.0,
+     "fires_truth": 38.1667,
+     "log_lr_absent": 0.008612,
+     "log_lr_present": -0.060288,
+     "p05": -0.4385,
+     "p95": 0.2757,
+     "p_other": 0.128794,
+     "p_truth": 0.121259
+    },
+    "kp_asc_sublord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 382.6667,
+     "fires_truth": 60.3333,
+     "log_lr_absent": -0.095348,
+     "log_lr_present": 0.556533,
+     "p05": -0.104,
+     "p95": 1.0984,
+     "p_other": 0.108842,
+     "p_truth": 0.189886
+    },
+    "kp_asc_sublord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 467.0,
+     "fires_truth": 47.4167,
+     "log_lr_absent": -0.019951,
+     "log_lr_present": 0.121359,
+     "p05": -0.2428,
+     "p95": 0.3892,
+     "p_other": 0.132766,
+     "p_truth": 0.149897
+    },
+    "kp_target_cusp_starlord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 660.25,
+     "fires_truth": 60.6667,
+     "log_lr_absent": -0.004107,
+     "log_lr_present": 0.017595,
+     "p05": -0.1232,
+     "p95": 0.1206,
+     "p_other": 0.187589,
+     "p_truth": 0.190918
+    },
+    "kp_target_cusp_starlord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 770.0833,
+     "fires_truth": 68.0,
+     "log_lr_absent": 0.006538,
+     "log_lr_present": -0.023707,
+     "p05": -0.2418,
+     "p95": 0.1482,
+     "p_other": 0.218747,
+     "p_truth": 0.213622
+    },
+    "kp_target_cusp_starlord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 499.8333,
+     "fires_truth": 43.1667,
+     "log_lr_absent": 0.006207,
+     "log_lr_present": -0.03832,
+     "p05": -0.2111,
+     "p95": 0.1437,
+     "p_other": 0.14208,
+     "p_truth": 0.136739
+    },
+    "kp_target_cusp_sublord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 728.9167,
+     "fires_truth": 58.1667,
+     "log_lr_absent": 0.029684,
+     "log_lr_present": -0.122589,
+     "p05": -0.4276,
+     "p95": 0.0569,
+     "p_other": 0.207069,
+     "p_truth": 0.183179
+    },
+    "kp_target_cusp_sublord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 656.75,
+     "fires_truth": 77.6667,
+     "log_lr_absent": -0.072592,
+     "log_lr_present": 0.266378,
+     "p05": -0.0871,
+     "p95": 0.5337,
+     "p_other": 0.186596,
+     "p_truth": 0.24355
+    },
+    "kp_target_cusp_sublord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 717.0834,
+     "fires_truth": 68.0833,
+     "log_lr_absent": -0.012852,
+     "log_lr_present": 0.048711,
+     "p05": -0.1908,
+     "p95": 0.213,
+     "p_other": 0.203712,
+     "p_truth": 0.21388
+    },
+    "narayana_ad_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 463.75,
+     "fires_truth": 34.5,
+     "log_lr_absent": 0.024954,
+     "log_lr_present": -0.181984,
+     "p05": -0.4537,
+     "p95": 0.0052,
+     "p_other": 0.131844,
+     "p_truth": 0.109907
+    },
+    "narayana_md_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 569.5834,
+     "fires_truth": 50.0,
+     "log_lr_absent": 0.004729,
+     "log_lr_present": -0.02485,
+     "p05": -0.143,
+     "p95": 0.0549,
+     "p_other": 0.161868,
+     "p_truth": 0.157895
+    },
+    "pranapada_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 501.0,
+     "fires_truth": 33.0,
+     "log_lr_absent": 0.042405,
+     "log_lr_present": -0.302256,
+     "p05": -0.7297,
+     "p95": -0.0528,
+     "p_other": 0.142411,
+     "p_truth": 0.105263
+    },
+    "shadbala_sthana_drik_naisargika_pressure_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 2190.5833,
+     "fires_truth": 198.5,
+     "log_lr_absent": 0.010725,
+     "log_lr_present": -0.006582,
+     "p05": -0.0612,
+     "p95": 0.0496,
+     "p_other": 0.621726,
+     "p_truth": 0.617647
+    },
+    "shadbala_sthana_drik_naisargika_support_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1305.8333,
+     "fires_truth": 121.0833,
+     "log_lr_absent": -0.011563,
+     "log_lr_present": 0.019325,
+     "p05": -0.0825,
+     "p95": 0.1008,
+     "p_other": 0.370733,
+     "p_truth": 0.377967
+    },
+    "vim_ad_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 353.3333,
+     "fires_truth": 26.6667,
+     "log_lr_absent": 0.016391,
+     "log_lr_present": -0.160026,
+     "p05": -0.2859,
+     "p95": -0.0381,
+     "p_other": 0.10052,
+     "p_truth": 0.085655
+    },
+    "vim_ad_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 540.1667,
+     "fires_truth": 52.1667,
+     "log_lr_absent": -0.013176,
+     "log_lr_present": 0.069688,
+     "p05": -0.0289,
+     "p95": 0.1841,
+     "p_other": 0.153522,
+     "p_truth": 0.164603
+    },
+    "vim_ad_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 815.3333,
+     "fires_truth": 69.8333,
+     "log_lr_absent": 0.015862,
+     "log_lr_present": -0.05451,
+     "p05": -0.1664,
+     "p95": 0.0185,
+     "p_other": 0.231584,
+     "p_truth": 0.219298
+    },
+    "vim_ad_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 682.1667,
+     "fires_truth": 86.1667,
+     "log_lr_absent": -0.099096,
+     "log_lr_present": 0.331067,
+     "p05": 0.1427,
+     "p95": 0.5103,
+     "p_other": 0.193806,
+     "p_truth": 0.269866
+    },
+    "vim_ad_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 534.9167,
+     "fires_truth": 45.0,
+     "log_lr_absent": 0.011279,
+     "log_lr_present": -0.065354,
+     "p05": -0.3476,
+     "p95": 0.1848,
+     "p_other": 0.152033,
+     "p_truth": 0.142415
+    },
+    "vim_ad_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1361.5,
+     "fires_truth": 116.1667,
+     "log_lr_absent": 0.03803,
+     "log_lr_present": -0.063496,
+     "p05": -0.1448,
+     "p95": 0.0135,
+     "p_other": 0.386525,
+     "p_truth": 0.362745
+    },
+    "vim_ad_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1246.8333,
+     "fires_truth": 124.4167,
+     "log_lr_absent": -0.054543,
+     "log_lr_present": 0.092461,
+     "p05": -0.0273,
+     "p95": 0.1918,
+     "p_other": 0.353995,
+     "p_truth": 0.388287
+    },
+    "vim_md_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 270.0,
+     "fires_truth": 25.0,
+     "log_lr_absent": -0.003925,
+     "log_lr_present": 0.045961,
+     "p05": -0.0973,
+     "p95": 0.2954,
+     "p_other": 0.076879,
+     "p_truth": 0.080495
+    },
+    "vim_md_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 479.6667,
+     "fires_truth": 45.6667,
+     "log_lr_absent": -0.009446,
+     "log_lr_present": 0.057839,
+     "p05": -0.0811,
+     "p95": 0.1992,
+     "p_other": 0.136359,
+     "p_truth": 0.144479
+    },
+    "vim_md_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 921.3333,
+     "fires_truth": 87.0,
+     "log_lr_absent": -0.014723,
+     "log_lr_present": 0.040414,
+     "p05": -0.0639,
+     "p95": 0.1361,
+     "p_other": 0.261655,
+     "p_truth": 0.272446
+    },
+    "vim_md_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 724.75,
+     "fires_truth": 86.6667,
+     "log_lr_absent": -0.08612,
+     "log_lr_present": 0.27632,
+     "p05": 0.0548,
+     "p95": 0.4848,
+     "p_other": 0.205887,
+     "p_truth": 0.271414
+    },
+    "vim_md_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 514.1667,
+     "fires_truth": 54.0,
+     "log_lr_absent": -0.02867,
+     "log_lr_present": 0.152826,
+     "p05": -0.1199,
+     "p95": 0.3922,
+     "p_other": 0.146147,
+     "p_truth": 0.170279
+    },
+    "vim_md_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 730.25,
+     "fires_truth": 64.3333,
+     "log_lr_absent": 0.00651,
+     "log_lr_present": -0.02527,
+     "p05": -0.436,
+     "p95": 0.224,
+     "p_other": 0.207447,
+     "p_truth": 0.20227
+    },
+    "vim_md_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1920.1667,
+     "fires_truth": 187.1667,
+     "log_lr_absent": -0.086129,
+     "log_lr_present": 0.066624,
+     "p05": -0.0489,
+     "p95": 0.1718,
+     "p_other": 0.545012,
+     "p_truth": 0.582559
+    },
+    "vim_pd_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 251.9167,
+     "fires_truth": 25.3333,
+     "log_lr_absent": -0.01059,
+     "log_lr_present": 0.127759,
+     "p05": -0.1884,
+     "p95": 0.3812,
+     "p_other": 0.071749,
+     "p_truth": 0.081527
+    },
+    "vim_pd_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 528.4167,
+     "fires_truth": 50.75,
+     "log_lr_absent": -0.01187,
+     "log_lr_present": 0.064632,
+     "p05": -0.1211,
+     "p95": 0.2197,
+     "p_other": 0.150189,
+     "p_truth": 0.160217
+    },
+    "vim_pd_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 817.25,
+     "fires_truth": 82.9167,
+     "log_lr_absent": -0.036708,
+     "log_lr_present": 0.11264,
+     "p05": -0.0431,
+     "p95": 0.2536,
+     "p_other": 0.232128,
+     "p_truth": 0.259804
+    },
+    "vim_pd_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 754.1667,
+     "fires_truth": 71.1667,
+     "log_lr_absent": -0.01177,
+     "log_lr_present": 0.042023,
+     "p05": -0.1441,
+     "p95": 0.229,
+     "p_other": 0.214232,
+     "p_truth": 0.223426
+    },
+    "vim_pd_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 536.3333,
+     "fires_truth": 50.9167,
+     "log_lr_absent": -0.009838,
+     "log_lr_present": 0.053005,
+     "p05": -0.1492,
+     "p95": 0.2272,
+     "p_other": 0.152435,
+     "p_truth": 0.160733
+    },
+    "vim_pd_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1289.0833,
+     "fires_truth": 101.25,
+     "log_lr_absent": 0.075055,
+     "log_lr_present": -0.145058,
+     "p05": -0.2501,
+     "p95": -0.0447,
+     "p_other": 0.365981,
+     "p_truth": 0.316563
+    },
+    "vim_pd_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1196.4167,
+     "fires_truth": 106.5833,
+     "log_lr_absent": 0.009972,
+     "log_lr_present": -0.019673,
+     "p05": -0.1355,
+     "p95": 0.1012,
+     "p_other": 0.339693,
+     "p_truth": 0.333075
+    }
+   },
+   "n": 20,
+   "noise_features": [
+    "ashtakavarga_target_house_support_auxiliary",
+    "bhava_lagna_in_target_house",
+    "controlled_transit_jupiter_domain_house",
+    "controlled_transit_saturn_domain_house",
+    "ghati_lagna_in_target_house",
+    "hora_lagna_in_target_house",
+    "kp_asc_sublord_is_vim_ad",
+    "kp_asc_sublord_is_vim_md",
+    "kp_asc_sublord_is_vim_pd",
+    "kp_target_cusp_starlord_is_vim_ad",
+    "kp_target_cusp_starlord_is_vim_md",
+    "kp_target_cusp_starlord_is_vim_pd",
+    "kp_target_cusp_sublord_is_vim_ad",
+    "kp_target_cusp_sublord_is_vim_md",
+    "kp_target_cusp_sublord_is_vim_pd",
+    "narayana_ad_domain_house",
+    "narayana_md_domain_house",
+    "shadbala_sthana_drik_naisargika_pressure_auxiliary",
+    "shadbala_sthana_drik_naisargika_support_auxiliary",
+    "vim_ad_domain_house",
+    "vim_ad_domain_lord",
+    "vim_ad_domain_varga_d60",
+    "vim_ad_functional_benefic_auxiliary",
+    "vim_ad_functional_malefic_auxiliary",
+    "vim_md_arudha_auxiliary",
+    "vim_md_domain_house",
+    "vim_md_domain_lord",
+    "vim_md_domain_varga_d60",
+    "vim_md_functional_benefic_auxiliary",
+    "vim_md_functional_malefic_auxiliary",
+    "vim_pd_arudha_auxiliary",
+    "vim_pd_domain_house",
+    "vim_pd_domain_lord",
+    "vim_pd_domain_varga",
+    "vim_pd_domain_varga_d60",
+    "vim_pd_functional_malefic_auxiliary"
+   ],
+   "robustness": {
+    "A1": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.9444,
+       "engine_top1": 0.2778,
+       "entropy": 3.0241,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 6,
+       "tie": 0.0185,
+       "top1": 0.5093,
+       "truth_eliminated": 0,
+       "width_median": 32.0
+      },
+      "raw": {
+       "coverage": 0.9907,
+       "engine_top1": 0.2778,
+       "entropy": 3.0397,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 1,
+       "tie": 0.0,
+       "top1": 0.3889,
+       "truth_eliminated": 0,
+       "width_median": 35.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.8778,
+       "engine_top1": 0.2778,
+       "entropy": 2.752,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 22,
+       "tie": 0.0056,
+       "top1": 0.1778,
+       "truth_eliminated": 0,
+       "width_median": 31.0
+      },
+      "raw": {
+       "coverage": 0.9778,
+       "engine_top1": 0.2778,
+       "entropy": 2.7682,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 4,
+       "tie": 0.0,
+       "top1": 0.1167,
+       "truth_eliminated": 0,
+       "width_median": 35.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 0.95,
+       "engine_top1": 0.2,
+       "entropy": 3.1348,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 1,
+       "tie": 0.0,
+       "top1": 0.7,
+       "truth_eliminated": 0,
+       "width_median": 31.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.2,
+       "entropy": 3.1419,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.6,
+       "truth_eliminated": 0,
+       "width_median": 32.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 0.9833,
+       "engine_top1": 0.2,
+       "entropy": 3.1341,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 1,
+       "tie": 0.0,
+       "top1": 0.7,
+       "truth_eliminated": 0,
+       "width_median": 31.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.2,
+       "entropy": 3.1418,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.6833,
+       "truth_eliminated": 0,
+       "width_median": 33.0
+      }
+     }
+    },
+    "A2": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.8519,
+       "engine_top1": 0.1111,
+       "entropy": 2.9474,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 16,
+       "tie": 0.0,
+       "top1": 0.5278,
+       "truth_eliminated": 0,
+       "width_median": 19.0
+      },
+      "raw": {
+       "coverage": 0.9815,
+       "engine_top1": 0.1111,
+       "entropy": 3.0352,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 2,
+       "tie": 0.0,
+       "top1": 0.4074,
+       "truth_eliminated": 0,
+       "width_median": 35.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.8611,
+       "engine_top1": 0.1111,
+       "entropy": 2.6772,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 25,
+       "tie": 0.0111,
+       "top1": 0.4,
+       "truth_eliminated": 0,
+       "width_median": 27.0
+      },
+      "raw": {
+       "coverage": 0.9444,
+       "engine_top1": 0.1111,
+       "entropy": 2.7639,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 10,
+       "tie": 0.0,
+       "top1": 0.1222,
+       "truth_eliminated": 0,
+       "width_median": 35.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 0.85,
+       "engine_top1": 0.05,
+       "entropy": 3.0233,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 3,
+       "tie": 0.0,
+       "top1": 0.55,
+       "truth_eliminated": 0,
+       "width_median": 18.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.05,
+       "entropy": 3.1348,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.65,
+       "truth_eliminated": 0,
+       "width_median": 34.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 0.8167,
+       "engine_top1": 0.1333,
+       "entropy": 3.0269,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 11,
+       "tie": 0.0,
+       "top1": 0.5167,
+       "truth_eliminated": 0,
+       "width_median": 12.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.1333,
+       "entropy": 3.1354,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.7,
+       "truth_eliminated": 0,
+       "width_median": 33.0
+      }
+     }
+    },
+    "A3": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.8796,
+       "engine_top1": 0.2222,
+       "entropy": 2.9498,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 13,
+       "tie": 0.0,
+       "top1": 0.5185,
+       "truth_eliminated": 0,
+       "width_median": 23.0
+      },
+      "raw": {
+       "coverage": 0.9722,
+       "engine_top1": 0.2222,
+       "entropy": 2.9319,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 3,
+       "tie": 0.0,
+       "top1": 0.5093,
+       "truth_eliminated": 0,
+       "width_median": 35.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.8222,
+       "engine_top1": 0.2222,
+       "entropy": 2.6728,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 32,
+       "tie": 0.0,
+       "top1": 0.4,
+       "truth_eliminated": 0,
+       "width_median": 21.0
+      },
+      "raw": {
+       "coverage": 0.9444,
+       "engine_top1": 0.2222,
+       "entropy": 2.6317,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 10,
+       "tie": 0.0,
+       "top1": 0.1778,
+       "truth_eliminated": 0,
+       "width_median": 35.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 0.9,
+       "engine_top1": 0.15,
+       "entropy": 3.0061,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 2,
+       "tie": 0.0,
+       "top1": 0.5,
+       "truth_eliminated": 0,
+       "width_median": 18.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.15,
+       "entropy": 2.9277,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.6,
+       "truth_eliminated": 0,
+       "width_median": 32.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 0.85,
+       "engine_top1": 0.2167,
+       "entropy": 3.0173,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 9,
+       "tie": 0.0,
+       "top1": 0.5667,
+       "truth_eliminated": 0,
+       "width_median": 17.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.2167,
+       "entropy": 2.9176,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.7,
+       "truth_eliminated": 0,
+       "width_median": 32.0
+      }
+     }
+    }
+   }
+  },
+  "60": {
+   "baseline": {
+    "percent": {
+     "coverage": 1.0,
+     "engine_top1": 0.05,
+     "entropy": 3.9174,
+     "n": 20,
+     "refresh_mean": 0.0,
+     "squeezed": 0,
+     "tie": 0.0,
+     "top1": 0.8,
+     "truth_eliminated": 0,
+     "width_median": 53.0
+    },
+    "raw": {
+     "coverage": 1.0,
+     "engine_top1": 0.05,
+     "entropy": 3.9537,
+     "n": 20,
+     "refresh_mean": 0.0,
+     "squeezed": 0,
+     "tie": 0.0,
+     "top1": 0.4,
+     "truth_eliminated": 0,
+     "width_median": 56.0
+    }
+   },
+   "calibration": [
+    {
+     "bin": "[0.00,0.05)",
+     "n": 541,
+     "observed_rate": 0.0259,
+     "predicted_mean": 0.0204
+    },
+    {
+     "bin": "[0.05,0.10)",
+     "n": 89,
+     "observed_rate": 0.0674,
+     "predicted_mean": 0.0596
+    },
+    {
+     "bin": "[0.10,0.20)",
+     "n": 14,
+     "observed_rate": 0.0,
+     "predicted_mean": 0.1329
+    },
+    {
+     "bin": "[0.20,0.30)",
+     "n": 7,
+     "observed_rate": 0.0,
+     "predicted_mean": 0.2443
+    },
+    {
+     "bin": "[0.30,0.50)",
+     "n": 0,
+     "observed_rate": null,
+     "predicted_mean": null
+    },
+    {
+     "bin": "[0.50,0.70)",
+     "n": 0,
+     "observed_rate": null,
+     "predicted_mean": null
+    },
+    {
+     "bin": "[0.70,1.00)",
+     "n": 0,
+     "observed_rate": null,
+     "predicted_mean": null
+    }
+   ],
+   "full_fit": {
+    "A1": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.9069,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.75,
+      "truth_eliminated": 0,
+      "width_median": 54.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.9317,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "scale": 3.74725,
+     "temperature": 4.0
+    },
+    "A2": {
+     "percent": {
+      "coverage": 0.85,
+      "engine_top1": 0.1,
+      "entropy": 3.8143,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 3,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 28.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.1,
+      "entropy": 3.9313,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.6,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "scale": 2.400103,
+     "temperature": 2.0
+    },
+    "A3": {
+     "percent": {
+      "coverage": 0.8,
+      "engine_top1": 0.3,
+      "entropy": 3.7963,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 4,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 19.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 3.6958,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.7,
+      "truth_eliminated": 0,
+      "width_median": 56.0
+     },
+     "scale": 1.790734,
+     "temperature": 2.0
+    }
+   },
+   "loo": {
+    "A1": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.15,
+      "entropy": 3.9106,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.65,
+      "truth_eliminated": 0,
+      "width_median": 57.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.15,
+      "entropy": 3.9344,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.45,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "temperatures": [
+      4.0,
+      8.0
+     ],
+     "verdict": "pending_v5"
+    },
+    "A2": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.8,
+      "engine_top1": 0.0,
+      "entropy": 3.8427,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 4,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 32.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.9353,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "temperatures": [
+      2.0,
+      4.0
+     ],
+     "verdict": "pending_v5"
+    },
+    "A3": {
+     "debug_verdict_v4": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 0.8,
+      "engine_top1": 0.05,
+      "entropy": 3.8133,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 4,
+      "tie": 0.0,
+      "top1": 0.4,
+      "truth_eliminated": 0,
+      "width_median": 38.0
+     },
+     "raw": {
+      "coverage": 0.95,
+      "engine_top1": 0.05,
+      "entropy": 3.703,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 1,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "temperatures": [
+      2.0
+     ],
+     "verdict": "pending_v5"
+    }
+   },
+   "lr_table": {
+    "ashtakavarga_target_house_pressure_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 200.0,
+     "fires_truth": 12.0,
+     "log_lr_absent": -0.012945,
+     "log_lr_present": 0.372059,
+     "p05": -0.0234,
+     "p95": 0.7343,
+     "p_other": 0.027743,
+     "p_truth": 0.040248
+    },
+    "ashtakavarga_target_house_support_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 4437.0,
+     "fires_truth": 207.0,
+     "log_lr_absent": -0.084525,
+     "log_lr_present": 0.049994,
+     "p05": 0.0051,
+     "p95": 0.0811,
+     "p_other": 0.61256,
+     "p_truth": 0.643963
+    },
+    "bhava_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1121.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": -0.037239,
+     "log_lr_present": 0.181891,
+     "p05": -0.0095,
+     "p95": 0.362,
+     "p_other": 0.154865,
+     "p_truth": 0.185759
+    },
+    "controlled_transit_jupiter_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1301.9166,
+     "fires_truth": 59.3333,
+     "log_lr_absent": -0.008515,
+     "log_lr_present": 0.037939,
+     "p05": -0.0689,
+     "p95": 0.1491,
+     "p_other": 0.179837,
+     "p_truth": 0.18679
+    },
+    "controlled_transit_saturn_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1123.25,
+     "fires_truth": 51.3333,
+     "log_lr_absent": -0.008137,
+     "log_lr_present": 0.043177,
+     "p05": -0.1232,
+     "p95": 0.1808,
+     "p_other": 0.155176,
+     "p_truth": 0.162023
+    },
+    "ghati_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1115.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": -0.038218,
+     "log_lr_present": 0.187253,
+     "p05": -0.1753,
+     "p95": 0.4423,
+     "p_other": 0.154037,
+     "p_truth": 0.185759
+    },
+    "hora_lagna_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1115.0,
+     "fires_truth": 59.0,
+     "log_lr_absent": -0.038218,
+     "log_lr_present": 0.187253,
+     "p05": -0.1753,
+     "p95": 0.4423,
+     "p_other": 0.154037,
+     "p_truth": 0.185759
+    },
+    "kp_asc_sublord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 968.3333,
+     "fires_truth": 38.1667,
+     "log_lr_absent": 0.014367,
+     "log_lr_present": -0.098368,
+     "p05": -0.461,
+     "p95": 0.2379,
+     "p_other": 0.133793,
+     "p_truth": 0.121259
+    },
+    "kp_asc_sublord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 890.25,
+     "fires_truth": 60.3333,
+     "log_lr_absent": -0.079315,
+     "log_lr_present": 0.434113,
+     "p05": -0.1927,
+     "p95": 0.9596,
+     "p_other": 0.123016,
+     "p_truth": 0.189886
+    },
+    "kp_asc_sublord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 947.1667,
+     "fires_truth": 47.4167,
+     "log_lr_absent": -0.022133,
+     "log_lr_present": 0.135728,
+     "p05": -0.2531,
+     "p95": 0.4058,
+     "p_other": 0.130872,
+     "p_truth": 0.149897
+    },
+    "kp_target_cusp_starlord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1399.5,
+     "fires_truth": 60.6667,
+     "log_lr_absent": 0.002955,
+     "log_lr_present": -0.012427,
+     "p05": -0.2017,
+     "p95": 0.1241,
+     "p_other": 0.193306,
+     "p_truth": 0.190918
+    },
+    "kp_target_cusp_starlord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1587.0833,
+     "fires_truth": 68.0,
+     "log_lr_absent": 0.007115,
+     "log_lr_present": -0.025762,
+     "p05": -0.3339,
+     "p95": 0.2173,
+     "p_other": 0.219197,
+     "p_truth": 0.213622
+    },
+    "kp_target_cusp_starlord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1120.8334,
+     "fires_truth": 43.1667,
+     "log_lr_absent": 0.021194,
+     "log_lr_present": -0.124335,
+     "p05": -0.3359,
+     "p95": 0.0417,
+     "p_other": 0.154842,
+     "p_truth": 0.136739
+    },
+    "kp_target_cusp_sublord_is_vim_ad": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1510.5833,
+     "fires_truth": 58.1667,
+     "log_lr_absent": 0.031665,
+     "log_lr_present": -0.13014,
+     "p05": -0.3839,
+     "p95": 0.0282,
+     "p_other": 0.208638,
+     "p_truth": 0.183179
+    },
+    "kp_target_cusp_sublord_is_vim_md": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1432.5,
+     "fires_truth": 77.6667,
+     "log_lr_absent": -0.058646,
+     "log_lr_present": 0.20776,
+     "p05": -0.114,
+     "p95": 0.4384,
+     "p_other": 0.197861,
+     "p_truth": 0.24355
+    },
+    "kp_target_cusp_sublord_is_vim_pd": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1492.0834,
+     "fires_truth": 68.0833,
+     "log_lr_absent": -0.009868,
+     "log_lr_present": 0.037129,
+     "p05": -0.1873,
+     "p95": 0.2145,
+     "p_other": 0.206085,
+     "p_truth": 0.21388
+    },
+    "narayana_ad_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 980.4167,
+     "fires_truth": 34.5,
+     "log_lr_absent": 0.02913,
+     "log_lr_present": -0.20905,
+     "p05": -0.5102,
+     "p95": 0.0,
+     "p_other": 0.135461,
+     "p_truth": 0.109907
+    },
+    "narayana_md_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1163.8334,
+     "fires_truth": 50.0,
+     "log_lr_absent": 0.003429,
+     "log_lr_present": -0.018093,
+     "p05": -0.1467,
+     "p95": 0.0852,
+     "p_other": 0.160778,
+     "p_truth": 0.157895
+    },
+    "pranapada_in_target_house": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1088.0,
+     "fires_truth": 33.0,
+     "log_lr_absent": 0.051659,
+     "log_lr_present": -0.35624,
+     "p05": -0.8298,
+     "p95": -0.0547,
+     "p_other": 0.150311,
+     "p_truth": 0.105263
+    },
+    "shadbala_sthana_drik_naisargika_pressure_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 4507.5,
+     "fires_truth": 198.5,
+     "log_lr_absent": 0.012221,
+     "log_lr_present": -0.007491,
+     "p05": -0.0736,
+     "p95": 0.0625,
+     "p_other": 0.622291,
+     "p_truth": 0.617647
+    },
+    "shadbala_sthana_drik_naisargika_support_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 2684.0833,
+     "fires_truth": 121.0833,
+     "log_lr_absent": -0.011755,
+     "log_lr_present": 0.019651,
+     "p05": -0.1107,
+     "p95": 0.1179,
+     "p_other": 0.370612,
+     "p_truth": 0.377967
+    },
+    "vim_ad_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 646.6667,
+     "fires_truth": 26.6667,
+     "log_lr_absent": 0.004098,
+     "log_lr_present": -0.042733,
+     "p05": -0.2608,
+     "p95": 0.0895,
+     "p_other": 0.089395,
+     "p_truth": 0.085655
+    },
+    "vim_ad_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1134.3333,
+     "fires_truth": 52.1667,
+     "log_lr_absent": -0.009408,
+     "log_lr_present": 0.049165,
+     "p05": -0.1036,
+     "p95": 0.1541,
+     "p_other": 0.156706,
+     "p_truth": 0.164603
+    },
+    "vim_ad_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1690.5833,
+     "fires_truth": 69.8333,
+     "log_lr_absent": 0.018336,
+     "log_lr_present": -0.062676,
+     "p05": -0.25,
+     "p95": 0.0477,
+     "p_other": 0.233483,
+     "p_truth": 0.219298
+    },
+    "vim_ad_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1587.5833,
+     "fires_truth": 86.1667,
+     "log_lr_absent": -0.067006,
+     "log_lr_present": 0.207639,
+     "p05": 0.0249,
+     "p95": 0.3774,
+     "p_other": 0.219266,
+     "p_truth": 0.269866
+    },
+    "vim_ad_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1101.8333,
+     "fires_truth": 45.0,
+     "log_lr_absent": 0.011499,
+     "log_lr_present": -0.066582,
+     "p05": -0.3334,
+     "p95": 0.1863,
+     "p_other": 0.15222,
+     "p_truth": 0.142415
+    },
+    "vim_ad_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 2757.5,
+     "fires_truth": 116.1667,
+     "log_lr_absent": 0.028653,
+     "log_lr_present": -0.04843,
+     "p05": -0.1616,
+     "p95": 0.0351,
+     "p_other": 0.380745,
+     "p_truth": 0.362745
+    },
+    "vim_ad_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 2521.3333,
+     "fires_truth": 124.4167,
+     "log_lr_absent": -0.063554,
+     "log_lr_present": 0.109116,
+     "p05": -0.0164,
+     "p95": 0.2197,
+     "p_other": 0.348148,
+     "p_truth": 0.388287
+    },
+    "vim_md_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 560.0,
+     "fires_truth": 25.0,
+     "log_lr_absent": -0.003325,
+     "log_lr_present": 0.03879,
+     "p05": -0.1978,
+     "p95": 0.2129,
+     "p_other": 0.077433,
+     "p_truth": 0.080495
+    },
+    "vim_md_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 965.6667,
+     "fires_truth": 45.6667,
+     "log_lr_absent": -0.012837,
+     "log_lr_present": 0.079591,
+     "p05": -0.0629,
+     "p95": 0.1899,
+     "p_other": 0.133425,
+     "p_truth": 0.144479
+    },
+    "vim_md_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1887.75,
+     "fires_truth": 87.0,
+     "log_lr_absent": -0.016019,
+     "log_lr_present": 0.044081,
+     "p05": -0.0756,
+     "p95": 0.1651,
+     "p_other": 0.260697,
+     "p_truth": 0.272446
+    },
+    "vim_md_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1529.25,
+     "fires_truth": 86.6667,
+     "log_lr_absent": -0.079388,
+     "log_lr_present": 0.25077,
+     "p05": 0.0124,
+     "p95": 0.4643,
+     "p_other": 0.211215,
+     "p_truth": 0.271414
+    },
+    "vim_md_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1072.9167,
+     "fires_truth": 54.0,
+     "log_lr_absent": -0.026228,
+     "log_lr_present": 0.13868,
+     "p05": -0.1143,
+     "p95": 0.3613,
+     "p_other": 0.148229,
+     "p_truth": 0.170279
+    },
+    "vim_md_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1661.6667,
+     "fires_truth": 64.3333,
+     "log_lr_absent": 0.034719,
+     "log_lr_present": -0.126261,
+     "p05": -0.5659,
+     "p95": 0.137,
+     "p_other": 0.229492,
+     "p_truth": 0.20227
+    },
+    "vim_md_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 3854.25,
+     "fires_truth": 187.1667,
+     "log_lr_absent": -0.114057,
+     "log_lr_present": 0.090551,
+     "p05": -0.0316,
+     "p95": 0.2159,
+     "p_other": 0.532126,
+     "p_truth": 0.582559
+    },
+    "vim_pd_arudha_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 537.6667,
+     "fires_truth": 25.3333,
+     "log_lr_absent": -0.007784,
+     "log_lr_present": 0.092153,
+     "p05": -0.2921,
+     "p95": 0.3608,
+     "p_other": 0.07435,
+     "p_truth": 0.081527
+    },
+    "vim_pd_domain_house": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1072.0833,
+     "fires_truth": 50.75,
+     "log_lr_absent": -0.014309,
+     "log_lr_present": 0.078548,
+     "p05": -0.1158,
+     "p95": 0.2466,
+     "p_other": 0.148114,
+     "p_truth": 0.160217
+    },
+    "vim_pd_domain_lord": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1615.0833,
+     "fires_truth": 82.9167,
+     "log_lr_absent": -0.048446,
+     "log_lr_present": 0.152478,
+     "p05": -0.0105,
+     "p95": 0.3008,
+     "p_other": 0.223062,
+     "p_truth": 0.259804
+    },
+    "vim_pd_domain_varga": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 1596.0833,
+     "fires_truth": 71.1667,
+     "log_lr_absent": -0.003839,
+     "log_lr_present": 0.013459,
+     "p05": -0.1839,
+     "p95": 0.2082,
+     "p_other": 0.220439,
+     "p_truth": 0.223426
+    },
+    "vim_pd_domain_varga_d60": {
+     "draws": 200,
+     "extra": true,
+     "fires_other": 1102.9167,
+     "fires_truth": 50.9167,
+     "log_lr_absent": -0.009916,
+     "log_lr_present": 0.053435,
+     "p05": -0.124,
+     "p95": 0.2272,
+     "p_other": 0.152369,
+     "p_truth": 0.160733
+    },
+    "vim_pd_functional_benefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 2581.5833,
+     "fires_truth": 101.25,
+     "log_lr_absent": 0.060156,
+     "log_lr_present": -0.11871,
+     "p05": -0.2421,
+     "p95": 0.0026,
+     "p_other": 0.356464,
+     "p_truth": 0.316563
+    },
+    "vim_pd_functional_malefic_auxiliary": {
+     "draws": 200,
+     "extra": false,
+     "fires_other": 2563.5833,
+     "fires_truth": 106.5833,
+     "log_lr_absent": 0.031846,
+     "log_lr_present": -0.060871,
+     "p05": -0.2179,
+     "p95": 0.0682,
+     "p_other": 0.35398,
+     "p_truth": 0.333075
+    }
+   },
+   "n": 20,
+   "noise_features": [
+    "ashtakavarga_target_house_pressure_auxiliary",
+    "bhava_lagna_in_target_house",
+    "controlled_transit_jupiter_domain_house",
+    "controlled_transit_saturn_domain_house",
+    "ghati_lagna_in_target_house",
+    "hora_lagna_in_target_house",
+    "kp_asc_sublord_is_vim_ad",
+    "kp_asc_sublord_is_vim_md",
+    "kp_asc_sublord_is_vim_pd",
+    "kp_target_cusp_starlord_is_vim_ad",
+    "kp_target_cusp_starlord_is_vim_md",
+    "kp_target_cusp_starlord_is_vim_pd",
+    "kp_target_cusp_sublord_is_vim_ad",
+    "kp_target_cusp_sublord_is_vim_md",
+    "kp_target_cusp_sublord_is_vim_pd",
+    "narayana_ad_domain_house",
+    "narayana_md_domain_house",
+    "shadbala_sthana_drik_naisargika_pressure_auxiliary",
+    "shadbala_sthana_drik_naisargika_support_auxiliary",
+    "vim_ad_arudha_auxiliary",
+    "vim_ad_domain_house",
+    "vim_ad_domain_lord",
+    "vim_ad_domain_varga_d60",
+    "vim_ad_functional_benefic_auxiliary",
+    "vim_ad_functional_malefic_auxiliary",
+    "vim_md_arudha_auxiliary",
+    "vim_md_domain_house",
+    "vim_md_domain_lord",
+    "vim_md_domain_varga_d60",
+    "vim_md_functional_benefic_auxiliary",
+    "vim_md_functional_malefic_auxiliary",
+    "vim_pd_arudha_auxiliary",
+    "vim_pd_domain_house",
+    "vim_pd_domain_lord",
+    "vim_pd_domain_varga",
+    "vim_pd_domain_varga_d60",
+    "vim_pd_functional_benefic_auxiliary",
+    "vim_pd_functional_malefic_auxiliary"
+   ],
+   "robustness": {
+    "A1": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.9907,
+       "engine_top1": 0.1667,
+       "entropy": 3.8947,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 1,
+       "tie": 0.0,
+       "top1": 0.3889,
+       "truth_eliminated": 0,
+       "width_median": 75.0
+      },
+      "raw": {
+       "coverage": 0.9907,
+       "engine_top1": 0.1667,
+       "entropy": 3.9126,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 1,
+       "tie": 0.0,
+       "top1": 0.287,
+       "truth_eliminated": 0,
+       "width_median": 77.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.8944,
+       "engine_top1": 0.1667,
+       "entropy": 3.6107,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 19,
+       "tie": 0.0111,
+       "top1": 0.1,
+       "truth_eliminated": 0,
+       "width_median": 69.0
+      },
+      "raw": {
+       "coverage": 0.9278,
+       "engine_top1": 0.1667,
+       "entropy": 3.6264,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 13,
+       "tie": 0.0,
+       "top1": 0.0611,
+       "truth_eliminated": 0,
+       "width_median": 71.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 1.0,
+       "engine_top1": 0.1,
+       "entropy": 3.9109,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.7,
+       "truth_eliminated": 0,
+       "width_median": 54.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.1,
+       "entropy": 3.9347,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.45,
+       "truth_eliminated": 0,
+       "width_median": 73.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 1.0,
+       "engine_top1": 0.0667,
+       "entropy": 3.9114,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.7833,
+       "truth_eliminated": 0,
+       "width_median": 61.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.0667,
+       "entropy": 3.9338,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.4,
+       "truth_eliminated": 0,
+       "width_median": 61.0
+      }
+     }
+    },
+    "A2": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.7963,
+       "engine_top1": 0.0,
+       "entropy": 3.8452,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 22,
+       "tie": 0.0093,
+       "top1": 0.3704,
+       "truth_eliminated": 0,
+       "width_median": 62.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.0,
+       "entropy": 3.9115,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.3333,
+       "truth_eliminated": 0,
+       "width_median": 77.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.7611,
+       "engine_top1": 0.0,
+       "entropy": 3.5592,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 43,
+       "tie": 0.0,
+       "top1": 0.1333,
+       "truth_eliminated": 0,
+       "width_median": 61.0
+      },
+      "raw": {
+       "coverage": 0.9111,
+       "engine_top1": 0.0,
+       "entropy": 3.6239,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 16,
+       "tie": 0.0,
+       "top1": 0.0833,
+       "truth_eliminated": 0,
+       "width_median": 71.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 0.85,
+       "engine_top1": 0.0,
+       "entropy": 3.8459,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 3,
+       "tie": 0.0,
+       "top1": 0.5,
+       "truth_eliminated": 0,
+       "width_median": 37.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.0,
+       "entropy": 3.9356,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.5,
+       "truth_eliminated": 0,
+       "width_median": 61.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 0.8667,
+       "engine_top1": 0.0833,
+       "entropy": 3.8484,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 8,
+       "tie": 0.0,
+       "top1": 0.55,
+       "truth_eliminated": 0,
+       "width_median": 40.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.0833,
+       "entropy": 3.935,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.55,
+       "truth_eliminated": 0,
+       "width_median": 61.0
+      }
+     }
+    },
+    "A3": {
+     "flip_1": {
+      "percent": {
+       "coverage": 0.787,
+       "engine_top1": 0.0556,
+       "entropy": 3.8303,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 23,
+       "tie": 0.0093,
+       "top1": 0.3241,
+       "truth_eliminated": 0,
+       "width_median": 57.0
+      },
+      "raw": {
+       "coverage": 0.963,
+       "engine_top1": 0.0556,
+       "entropy": 3.7475,
+       "n": 108,
+       "refresh_mean": 0.0,
+       "squeezed": 4,
+       "tie": 0.0,
+       "top1": 0.2685,
+       "truth_eliminated": 0,
+       "width_median": 77.0
+      }
+     },
+     "flip_2": {
+      "percent": {
+       "coverage": 0.7111,
+       "engine_top1": 0.0556,
+       "entropy": 3.5437,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 52,
+       "tie": 0.0,
+       "top1": 0.1167,
+       "truth_eliminated": 0,
+       "width_median": 59.0
+      },
+      "raw": {
+       "coverage": 0.9056,
+       "engine_top1": 0.0556,
+       "entropy": 3.457,
+       "n": 180,
+       "refresh_mean": 0.0,
+       "squeezed": 17,
+       "tie": 0.0,
+       "top1": 0.0556,
+       "truth_eliminated": 0,
+       "width_median": 71.0
+      }
+     },
+     "jitter_7d": {
+      "percent": {
+       "coverage": 0.7,
+       "engine_top1": 0.05,
+       "entropy": 3.8116,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 6,
+       "tie": 0.0,
+       "top1": 0.3,
+       "truth_eliminated": 0,
+       "width_median": 32.0
+      },
+      "raw": {
+       "coverage": 0.95,
+       "engine_top1": 0.05,
+       "entropy": 3.6992,
+       "n": 20,
+       "refresh_mean": 0.0,
+       "squeezed": 1,
+       "tie": 0.0,
+       "top1": 0.4,
+       "truth_eliminated": 0,
+       "width_median": 61.0
+      }
+     },
+     "shift_1_3_months": {
+      "percent": {
+       "coverage": 0.7833,
+       "engine_top1": 0.15,
+       "entropy": 3.8162,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 13,
+       "tie": 0.0,
+       "top1": 0.45,
+       "truth_eliminated": 0,
+       "width_median": 33.0
+      },
+      "raw": {
+       "coverage": 1.0,
+       "engine_top1": 0.15,
+       "entropy": 3.6825,
+       "n": 60,
+       "refresh_mean": 0.0,
+       "squeezed": 0,
+       "tie": 0.0,
+       "top1": 0.5,
+       "truth_eliminated": 0,
+       "width_median": 61.0
+      }
+     }
+    }
+   }
+  }
+ },
+ "reconciliation": {
+  "cases": 60,
+  "rows": [
+   {
+    "candidates": 11,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   }
+  ],
+  "unreconciled": 0
+ },
+ "seed": 20260929,
+ "variants": [
+  "A1",
+  "A2",
+  "A3"
+ ],
+ "verdict": "pending_v5"
+}
diff --git a/docs/research/scoring_research_precision_followup_2026_09_29.json b/docs/research/scoring_research_precision_followup_2026_09_29.json
new file mode 100644
index 00000000..a2ab15f5
--- /dev/null
+++ b/docs/research/scoring_research_precision_followup_2026_09_29.json
@@ -0,0 +1,1206 @@
+{
+ "ask_count": 6,
+ "ayanamsa": "raman",
+ "case_count": 20,
+ "dataset": "v4",
+ "errors": [],
+ "fast": false,
+ "generated_for": "TASK-rectification-scoring-research-20260929",
+ "holdout": "references/real_case_calibration/minute_rectification_holdout_v4.json",
+ "minute_step": 2,
+ "node_mode": "mean",
+ "open_set_not_blind": true,
+ "part": "R-C",
+ "probe_today": "2026-09-16",
+ "probes": "production G0 probes generated once per case/radius from the production matrix; reused for every arm",
+ "radii": {
+  "10": {
+   "arms": {
+    "B0_true_precision": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0376,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.9,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0346,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     }
+    },
+    "C0_spoken": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0396,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.9,
+      "truth_eliminated": 0,
+      "width_median": 12.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3,
+      "entropy": 2.0286,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.75,
+      "truth_eliminated": 0,
+      "width_median": 15.0
+     }
+    },
+    "C1_both": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.5,
+      "entropy": 1.7906,
+      "n": 2,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 16.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.5,
+      "entropy": 1.7428,
+      "n": 2,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 16.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C1_prior": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.5,
+      "entropy": 1.7905,
+      "n": 2,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 16.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.5,
+      "entropy": 1.7799,
+      "n": 2,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 1.0,
+      "truth_eliminated": 0,
+      "width_median": 16.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C1_probe": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.5,
+      "entropy": 1.7908,
+      "n": 2,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 16.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.5,
+      "entropy": 1.7395,
+      "n": 2,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5,
+      "truth_eliminated": 0,
+      "width_median": 16.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_both": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 1.5789,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 1.5743,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_prior": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "benefit",
+      "raw": "benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 1.5848,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 1.0,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 1.5849,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 1.0,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_probe": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 1.0,
+      "entropy": 1.5808,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 1.0,
+      "entropy": 1.5755,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 11.0
+     },
+     "verdict": "pending_v5"
+    }
+   },
+   "askable_per_case": {
+    "cases_with_at_least_one": 2,
+    "cases_with_at_least_two": 1,
+    "distribution": {
+     "0": 18,
+     "1": 1,
+     "3": 1
+    },
+    "mean": 0.2
+   },
+   "n": 20
+  },
+  "30": {
+   "arms": {
+    "B0_true_precision": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.151,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.85,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.2,
+      "entropy": 3.1646,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.55,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     }
+    },
+    "C0_spoken": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.25,
+      "entropy": 3.1519,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.05,
+      "top1": 0.9,
+      "truth_eliminated": 0,
+      "width_median": 34.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.25,
+      "entropy": 3.1585,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.6,
+      "truth_eliminated": 0,
+      "width_median": 35.0
+     }
+    },
+    "C1_both": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "benefit",
+      "raw": "benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.1429,
+      "entropy": 3.0509,
+      "n": 7,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 1.0,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.1429,
+      "entropy": 3.0578,
+      "n": 7,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.7143,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C1_prior": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "benefit",
+      "raw": "benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.1429,
+      "entropy": 3.0781,
+      "n": 7,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 1.0,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.1429,
+      "entropy": 3.0875,
+      "n": 7,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.7143,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C1_probe": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.1429,
+      "entropy": 3.0526,
+      "n": 7,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8571,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.1429,
+      "entropy": 3.0565,
+      "n": 7,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.5714,
+      "truth_eliminated": 0,
+      "width_median": 33.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_both": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.3139,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.3175,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_prior": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "benefit",
+      "raw": "benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.3103,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 1.0,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.317,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 1.0,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_probe": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 1.0,
+      "entropy": 3.3137,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 1.0,
+      "entropy": 3.318,
+      "n": 1,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 31.0
+     },
+     "verdict": "pending_v5"
+    }
+   },
+   "askable_per_case": {
+    "cases_with_at_least_one": 7,
+    "cases_with_at_least_two": 1,
+    "distribution": {
+     "0": 13,
+     "1": 6,
+     "3": 1
+    },
+    "mean": 0.45
+   },
+   "n": 20
+  },
+  "60": {
+   "arms": {
+    "B0_true_precision": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9174,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 53.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.05,
+      "entropy": 3.9537,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.4,
+      "truth_eliminated": 0,
+      "width_median": 56.0
+     }
+    },
+    "C0_spoken": {
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.15,
+      "entropy": 3.9174,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.9,
+      "truth_eliminated": 0,
+      "width_median": 55.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.15,
+      "entropy": 3.9471,
+      "n": 20,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.45,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     }
+    },
+    "C1_both": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.5108,
+      "n": 10,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.7,
+      "truth_eliminated": 0,
+      "width_median": 53.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.5319,
+      "n": 10,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.3,
+      "truth_eliminated": 0,
+      "width_median": 58.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C1_prior": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.6783,
+      "n": 10,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 44.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.7156,
+      "n": 10,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.4,
+      "truth_eliminated": 0,
+      "width_median": 58.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C1_probe": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.1,
+      "entropy": 3.5111,
+      "n": 10,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.8,
+      "truth_eliminated": 0,
+      "width_median": 53.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.1,
+      "entropy": 3.5316,
+      "n": 10,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.4,
+      "truth_eliminated": 0,
+      "width_median": 63.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_both": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.9205,
+      "n": 3,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.3333,
+      "truth_eliminated": 0,
+      "width_median": 83.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 3.9302,
+      "n": 3,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.3333,
+      "truth_eliminated": 0,
+      "width_median": 91.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_prior": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 4.0118,
+      "n": 3,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.6667,
+      "truth_eliminated": 0,
+      "width_median": 61.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.0,
+      "entropy": 4.036,
+      "n": 3,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.6667,
+      "truth_eliminated": 0,
+      "width_median": 91.0
+     },
+     "verdict": "pending_v5"
+    },
+    "C2_probe": {
+     "debug_verdict_v4_vs_C0": {
+      "percent": "no_benefit",
+      "raw": "no_benefit"
+     },
+     "percent": {
+      "coverage": 1.0,
+      "engine_top1": 0.3333,
+      "entropy": 3.9219,
+      "n": 3,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.3333,
+      "truth_eliminated": 0,
+      "width_median": 83.0
+     },
+     "raw": {
+      "coverage": 1.0,
+      "engine_top1": 0.3333,
+      "entropy": 3.9294,
+      "n": 3,
+      "refresh_mean": 0.0,
+      "squeezed": 0,
+      "tie": 0.0,
+      "top1": 0.0,
+      "truth_eliminated": 0,
+      "width_median": 91.0
+     },
+     "verdict": "pending_v5"
+    }
+   },
+   "askable_per_case": {
+    "cases_with_at_least_one": 10,
+    "cases_with_at_least_two": 3,
+    "distribution": {
+     "0": 10,
+     "1": 7,
+     "2": 2,
+     "3": 1
+    },
+    "mean": 0.7
+   },
+   "n": 20
+  }
+ },
+ "reconciliation": {
+  "cases": 60,
+  "rows": [
+   {
+    "candidates": 11,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "barack_obama_1961_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "angelina_jolie_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "tiger_woods_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "elizabeth_taylor_1932_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "pablo_picasso_1881_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "sigmund_freud_1856_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "salma_hayek_1966_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "steve_reich_1936_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "albert_brooks_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "paul_ryan_1970_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "tom_kennedy_1927_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "andrew_windsor_1960_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "sean_lennon_1975_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "kurt_cobain_1967_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "john_robbins_1947_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "chad_everett_1937_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "bernd_eichinger_1949_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   },
+   {
+    "candidates": 11,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 10
+   },
+   {
+    "candidates": 31,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 30
+   },
+   {
+    "candidates": 61,
+    "case_id": "iwao_takamoto_1925_aa_v4_holdout",
+    "changed": 0,
+    "details": [],
+    "radius": 60
+   }
+  ],
+  "unreconciled": 0
+ },
+ "seed": 20260929,
+ "verdict": "pending_v5"
+}
diff --git a/docs/tasks/PROGRESS-rectification-scoring-research-20260929.md b/docs/tasks/PROGRESS-rectification-scoring-research-20260929.md
new file mode 100644
index 00000000..531cf095
--- /dev/null
+++ b/docs/tasks/PROGRESS-rectification-scoring-research-20260929.md
@@ -0,0 +1,66 @@
+# PROGRESS · 生时校正打分方法研究：似然比权重 / 缺席证据 / 精度追问（脚手架阶段，2026-09-29）
+
+- 任务书：`docs/tasks/TASK-rectification-scoring-research-20260929.md`
+- 执行：Claude（直接执行模式，fork 子代理），分支 `codex/rectification-scoring-research-20260929`，基线 `origin/staging` @ `6e393780`（任务书写作时 `5febb111`，其间只有文档提交）。**未推送。**
+- 研究报告：`docs/research/rectification_scoring_research_2026_09_29.md` + `scoring_research_{lr,absence,precision_followup}_2026_09_29.json`
+- 本轮范围（按调度方指令）：在 v4 上完成 R-0 脚手架并把 R-A / R-B / R-C 流水线跑通；**所有判定字段写 `pending_v5`**，v4 数字只作调试参考。v5 交付后在 v5 上跑判定（复跑命令见研究报告末尾）。
+
+## 开工
+
+- `git fetch origin --prune` → worktree `.worktrees/rectification-scoring-research-20260929` 基于 `origin/staging`；任何 git 操作前 `git status -sb` 核对分支。
+- 先读：定论页（含 §7 勘误）、`rectification_offline_research_2026_09_26.md`、`rectification_typed_event_scoring_2026_09_29.md`、ERR-110 / ERR-111。
+- 环境：本机没有 `.venv`（所有 worktree 的 `.venv` 软链都指向不存在的 `/workspace/Jyotisha/.venv`），全部用系统 `python3` 3.13.5（swisseph 9.1.1、pytest、timezonefinder 齐）。快速门的前端步需要 Node 22：`frontend/node_modules` 软链到主检出，`npm` 用 `/exec-daemon/node` + `/exec-daemon/lib/node_modules/npm` 的 shim（系统 `node` 是 20.19，`/usr/bin/npm` 跑的 `tsx` 不在 PATH）。`PYTHONHASHSEED=0`（ERR-111）。
+- 另一子代理并行做 v5 扩集（`.worktrees/rectification-holdout-expansion-20260929`），未触碰。
+
+## 交付物
+
+| 文件 | 内容 |
+| --- | --- |
+| `scripts/research/scoring_research_lib.py` | R-0：特征记录 provider（线上同源 evidence + 额外观察）、逐分对账、特征矩阵、似然比估计（α = 1）、案例级 bootstrap、加权 provider、leave-one-case-out、缩放答案、Platt 温度、缺席年 / 精度升降 / 月份平移辅助 |
+| `scripts/research/scoring_research.py` | R-A / R-B / R-C 流水线；`--limit / --radii / --parts / --fast / --cache-dir / --holdout / --dataset-label / --out-suffix` |
+| `tests/test_scoring_research.py` | 10 条：纯函数 9 条 + v4 公开案例 ±10 对账 0 差 1 条 |
+| `docs/research/rectification_scoring_research_2026_09_29.md` | 报告（结构按任务书 R-D；结论栏全部 `pending_v5`；复跑命令） |
+| `docs/research/scoring_research_*_2026_09_29.json` | 三份结果（`dataset: v4, verdict: pending_v5`） |
+| `docs/BUG_HISTORY.md` | BUG-1091 `investigating`（开工核对最大号 1089；1090 由扩集单占用，未冲突） |
+| `docs/research/ACTIVE_FRONTS.md`、定论页 §9、`docs/tasks/README.md` | 索引与状态板 |
+
+生产代码、`sealed_holdout_rerun.py::PRODUCTION_FILES` 的 10 个冻结文件、任何常数：**零改动**（`git status` 只有上表文件）。
+
+## R-0 · 对账（任务书硬红线 4）
+
+- 研究计分器 vs 线上 `score_candidates`（经 `build_event_contribution_matrix` 同一条矩阵链）：**20 例 × 3 档 = 60 个 case-radius，分数差 0、规则 id 差 0**（`reconciliation.unreconciled = 0`，三份 JSON 均记录）。
+- 做法：provider 用 `precision_gate_lib.score_event_with_policy`（V0）+ 线上 `_controlled_transit_rules`（带缓存）/ `_ashtakavarga_auxiliary` / `_shadbala_verified_components_auxiliary`（取 context 里线上算好的结果），返回与 `_candidate_row` 相同的 evidence；额外观察只进 `FeatureStore`，不进 rule_ids / points，所以矩阵、`event_kind` 系数、`technique_layers`、出题都与线上一致。
+- 特征 42 个：线上规则 25 + 额外观察 17（KP 宫头子主 / 星主 × MD/AD/PD、KP 上升子主、D60 × MD/AD/PD、Pranapada / Hora / Ghati / Bhava lagna 落领域宫）。特征值 = 该规则在该事件采样日期上命中的比例。真值标签 = 候选属于真值所在签名簇。
+- 留一法按**案例**留（`loo_folds`），`scale` 与 `temperature` 也只从训练折估。
+
+## R-A / R-B / R-C · 流水线状态
+
+| 项 | 状态 | v4 调试参考（`raw` 口径，留一法） | 判定 |
+| --- | --- | --- | --- |
+| R-A A1 / A2 / A3 | 跑通（留一法 + 全集、六题回放、引擎头名、校准曲线、稳健性四项、LR 表 + 案例级 bootstrap 区间） | 头名 ±10 0.70 / 0.75 / 0.80（基线 0.80）；±30 0.55 / 0.60 / 0.65（0.55）；±60 0.45 / 0.55 / 0.50（0.40）。真值在区间除 ±60 A3 0.95 外全 1.00。`percent` 口径 softmax 后验过自信，挤出 3–5 例 | `pending_v5` |
+| R-B 缺席 @0.5 / 1.0 / 2.0 分 | 跑通（含漏说 1–2 件 × 5 次） | 2.0 分（=卡片）把覆盖压到 0.85 / 0.70 / 0.40；0.5 / 1.0 分覆盖 1.00 但头名一律降 | `pending_v5`（v4 信号为负） |
+| R-C C1 / C2 × prior / probe / both | 跑通 | 可追问件数每例均值 0.20 / 0.45 / 0.70；±30 上 C1_prior 7 例头名 0.71 | `pending_v5`（样本太少） |
+
+各特征在 v4 上的 LR 与「LR≈1」名单在报告 R-A 第 3 条与 JSON `radii.*.lr_table` / `noise_features`：**42 个特征里 31 / 36 / 38 个（±10 / ±30 / ±60）的 5–95% 区间跨 0**。
+
+## 复跑与确定性（任务书硬红线 5）
+
+- `PYTHONHASHSEED=0 python3 scripts/research/scoring_research.py --cache-dir <scratch>` 连跑两次（758 s / 748 s，静态 context 走磁盘缓存），三份 JSON `cmp` **逐字节一致**；`--out-suffix rerun` 的副本比对后删除，不入库。
+- JSON 不写耗时字段，`sort_keys=True`；随机（漏说抽样、月份平移、答错抽样、bootstrap）全部按 `f"{SEED}:{case_id}:{radius}:…"` 种子。
+
+## 快速门
+
+- 开工基线（`origin/staging` @ `6e393780`，未改任何文件）与改后各跑一次 `python3 scripts/run_quality_gate.py --profile quick`（PATH 带 Node 22 shim）：
+  - Python：**1001 passed, 1 skipped** 两次相同（改后含新增的 10 条 `test_scoring_research.py`——门禁的 pytest 集合按清单收集，新文件不在清单里，计数没变；定向 `python3 -m pytest tests/test_scoring_research.py -q` 10 passed）。
+  - 前端 `npm test`：基线 4357 / pass 4301 / fail 25；改后 4357 / pass **4302** / fail **24**、cancelled 0。失败清单逐条比对：改后 24 条是基线 25 条的子集（少的一条 `D3 · the first stage line shows on send…` 是基线那次偶发红、改后绿，前端零改动）；24 条全是需要 Docker / PostgreSQL / 部署环境的套件（Better Auth / billing / migration / staging sync 等），与 09-29 上一单验收记录的 24 条环境失败一致。
+  - 门禁整体 exit 1 = 该 24 条环境失败所致，基线同样 exit 1；**无新增失败**。
+- 隐私：`tests/test_repo_privacy_markers.py` 在快速门 Python 步内通过（1001 passed 含之）。
+
+## 缺口与说明
+
+- **判定未做**：按任务书，R-A / R-B / R-C 的有无收益只能在 v5 上判；本轮 JSON 的 `debug_verdict_v4` 只是 `gate_verdict` 的机械输出，不作结论。
+- R-A 的 `percent` 口径需要先解决后验标定（单温度 Platt 不够，校准曲线高桶过自信）；v5 上若仍过自信，考虑按训练折做等分位标定或直接用 `raw` 口径（缩放到线上极差）。
+- 六道题由线上矩阵出一次、各方案共用（隔离先验的影响）；若某方案在 v5 上过门，实现前还应按方案矩阵重新出题再测一次。
+- 大运边界邻近项（`merge_transition_proximity`）按线上原样附加、未重加权。
+- R-B 的缺席年在 v4 上不可靠（传记摘录不是完整时间线）；这条限制在真人口述上同样存在，报告已写明。
+- 未做：R-C 的产品层实现、任何实现单；`CHANGELOG.md` 无用户可见变化，未改。
diff --git a/docs/tasks/README.md b/docs/tasks/README.md
index ec9247de..0c70bf01 100644
--- a/docs/tasks/README.md
+++ b/docs/tasks/README.md
@@ -256,7 +256,7 @@
 | `TASK-mobile-chart-and-confirmed-edit-20260929.md` | `PROGRESS-mobile-chart-confirmed-edit-20260929.md` | **手机星盘 + 确认时间可改 + 天空定格**：iPhone 星盘被宽表撑出屏幕（BUG-1083）；confirmed 状态改声明字段也重置排盘时间（推翻 BUG-264 约定）；「那一刻的天空」改为重放汇聚→定格→右上角分享；去掉报告星图封面 | 已验收（Claude 2026-09-29），已推 staging | BUG-1083 |
 | `TASK-rectification-futile-collect-stop-20260929.md` | `PROGRESS-rectification-futile-collect-stop-20260929.md` | **生时校正停掉无效补经历循环（止血）**：打字经历不收窄（BUG-560 后果），流程却一路索要，真机 22 件整窗不动；采集只为开闸、门开后只问点选卡问完即出卡；交付正文去吻合率；多段时旁白误报「范围没变」；交付轮带采集题 | 已验收（Claude 2026-09-29 合并验收：全量前端 4302/24 与基线同 24 条环境失败、tsc 0、lint 0 error、`/` Static、gzip +0.16%、快速门 pytest 1001 passed、两份回放复跑一致），待部署核对 | BUG-1084～1087 |
 | `TASK-rectification-holdout-expansion-20260929.md` | — | **开放评价集扩到 ≥60 例（v5）**：所有打分判定都在 20 例上做，1 例 = 5pp，KP / 精度闸 / V1n 的 no_benefit 都只差 1–3 例。只用 Rodden AA 公开名人，事件人工核对出处，分层（年代 / 纬度 / 南半球 / 跨午夜 / UTC+8），v4 不动；基线成绩单 v4 子集须与已发布数字逐格一致。研究单的判定以 v5 为准 | 待领取 | — |
-| `TASK-rectification-scoring-research-20260929.md` | — | **打分方法研究（离线）**：R-A 似然比校准权重（leave-one-case-out，KP / Pranapada / D60 作为特征由数据定权重、允许负权重）、R-B 缺席证据（口述时间线覆盖时段内的空白年扣分，必测漏说稳健性）、R-C 精度追问可行性（对已说事件追问月份，算在定向追问 2 条额度内）。判定必须在 v5 上做；有收益才立实现单并按 ERR-110 重冻结 | 待领取（脚手架可先在 v4 上开发） | — |
+| `TASK-rectification-scoring-research-20260929.md` | `PROGRESS-rectification-scoring-research-20260929.md` | **打分方法研究（离线）**：R-A 似然比校准权重（leave-one-case-out，KP / Pranapada / D60 作为特征由数据定权重、允许负权重）、R-B 缺席证据（口述时间线覆盖时段内的空白年扣分，必测漏说稳健性）、R-C 精度追问可行性（对已说事件追问月份，算在定向追问 2 条额度内）。判定必须在 v5 上做；有收益才立实现单并按 ERR-110 重冻结 | 已实现待验收（Claude fork 2026-09-29：R-0 脚手架 + R-A / R-B / R-C 流水线在 v4 上跑通，对账 0 差，判定全部 `pending_v5`；生产代码零改动） | 分支 `codex/rectification-scoring-research-20260929`（BUG-1091 investigating） |
 | `TASK-rectification-typed-event-scoring-research-20260929.md` | `PROGRESS-rectification-typed-event-research-20260929.md` | **打字经历按选择题规则计分（离线研究，不上线）**：计分通道不对称 + 已入账年份挡题；R0 学业质量题措辞 / 年精度显示成 1 月（冻结文件，需重新冻结） | 已验收（Claude 2026-09-29 合并验收：全量前端 4302/24 与基线同 24 条环境失败、tsc 0、lint 0 error、`/` Static、gzip +0.16%、快速门 pytest 1001 passed、两份回放复跑一致），待部署核对 | BUG-1088、1089 |
 | `TASK-report-reader-polish-20260929.md` | `PROGRESS-report-reader-polish-20260929.md` | **报告页打磨**：生成入口挪进页面主体（删标题栏按钮）、详情页到底部按钮（懒渲染一次到底）、导出按钮带文字、目录一级/二级分层、去掉「字段」与 RL/NL 缩写表头、状态列同义重复去重、报告表格淡底色、分块导出显示真实文件大小 | Claude 直接执行并自验（tsc 0、lint 0 error、全量 fail 与基线同 24 条、`/` Static、gzip +7 B、快速门 Python 1000 passed），已推 staging，真机欠 | BUG-1092～1094 |
 | `TASK-report-english-edition-20260929.md` | — | **报告中英两版**：同一次引擎计算渲染 zh/en 两遍（不用模型翻译），瑜伽库 406 条补英文、模板与前端表头英文化；中文逐字节不变、英文零汉字、两版数字序列一致；阅读页 `?lang=en` 切换，导出当前语言 + 「问 AI 建议导出英文版」提示；旧报告不补英文 | 待领取（依赖 reader-polish 合入） | — |
diff --git a/scripts/research/scoring_research.py b/scripts/research/scoring_research.py
new file mode 100644
index 00000000..bf2487c0
--- /dev/null
+++ b/scripts/research/scoring_research.py
@@ -0,0 +1,529 @@
+#!/usr/bin/env python3
+"""Offline research runner for TASK-rectification-scoring-research-20260929.
+
+R-0  research scorer reconciled per minute against the production scorer, then
+     per-(candidate, event) rule features recorded (eleven production rules,
+     auxiliary rules, and unscored extras: KP cusp sub/star lords, Pranapada /
+     Hora / Ghati / Bhava lagna, D60).
+R-A  likelihood-ratio weights (Laplace α = 1) per radius, leave-one-CASE-out
+     and full-fit; variants A1 (production features, reward only), A2 (+extras,
+     reward only), A3 (+extras, naive-Bayes present/absent, negative allowed);
+     six-probe replay, engine top1, calibration curve, robustness (±7-day and
+     ±1–3-month date shifts, 1–2 flipped answers).
+R-B  absence evidence: gap years inside a domain's spoken span answered "no"
+     at 0.5 / 1.0 / 2.0 points (a card is 2.0), plus "user omitted 1–2 events"
+     robustness.
+R-C  precision follow-up: with all day events degraded to year ("spoken"
+     form), how many events would split candidates if the month were known,
+     and the gain from asking 1 / 2 of them (as a prior recompute and as an
+     answered probe).
+
+Every verdict field is written as ``pending_v5``: the task brief allows a
+verdict only on the v5 open set. v4 numbers are debugging references.
+
+Run:
+    PYTHONHASHSEED=0 python3 scripts/research/scoring_research.py --limit 2 --radii 10 --no-write
+    PYTHONHASHSEED=0 python3 scripts/research/scoring_research.py
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import pickle
+import sys
+import time as clock_module
+import traceback
+from collections import defaultdict
+from pathlib import Path
+from random import Random
+from typing import Any, Sequence
+
+ROOT = Path(__file__).resolve().parents[2]
+if str(ROOT) not in sys.path:
+    sys.path.insert(0, str(ROOT))
+
+from scripts.active_rectification_event_engine import AYANAMSA, NODE_MODE, compute_candidate_static_contexts  # noqa: E402
+from scripts.rectification.scoring_service import build_event_contribution_matrix, score_from_matrix, scoreable_request  # noqa: E402
+from scripts.research.minute_resolution_sweep import MINUTE_STEP, scoring_request_for  # noqa: E402
+from scripts.research.offline_research_20260926_lib import exhaustive_flip_sets, flipped_answers, sample_flip_sets  # noqa: E402
+from scripts.research.precision_gate_lib import gate_verdict, jitter_day_events  # noqa: E402
+from scripts.research.probe_supply_after_six import ASK_COUNT, optimal_answer  # noqa: E402
+import scripts.research.scoring_research_lib as lib  # noqa: E402
+
+HOLDOUT_V4 = ROOT / "references" / "real_case_calibration" / "minute_rectification_holdout_v4.json"
+OUT_DIR = ROOT / "docs" / "research"
+RADII = (10, 30, 60)
+PRIORS = ("raw", "percent")
+ABSENCE_POINTS = (0.5, 1.0, 2.0)  # score points per "no"; a card is 2.0
+CARD_POINTS = 2.0
+OMIT_REPEATS = 5
+SHIFT_REPEATS = 3
+FLIP_REPEATS = 10
+SEED = 20260929
+ABSENCE_SOURCE = "absence_research"
+FOLLOWUP_SOURCE = "precision_followup_research"
+
+
+# ---------------------------------------------------------------------------
+# per-case data
+# ---------------------------------------------------------------------------
+
+class CaseData:
+    def __init__(self, case: dict[str, Any], radius: int, cache_dir: Path | None) -> None:
+        self.case = case
+        self.case_id = str(case["case_id"])
+        self.radius = radius
+        self.true_time = str(case["birth"]["time"])[:5]
+        self.request = scoring_request_for({**case, "candidate_radius_minutes": radius}, radius)
+        self.contexts = self._contexts(cache_dir)
+        self.times = [ctx["candidate_at"].strftime("%H:%M") for ctx in self.contexts]
+        self.truth_times = lib.truth_cluster_times(self.contexts, self.true_time)
+        self.d60 = lib.d60_charts(self.contexts)
+        # production
+        prod_built = build_event_contribution_matrix(self.request, static_contexts=self.contexts)
+        self.prod_rows = score_from_matrix(self.request, prod_built)
+        self.prod_built = prod_built
+        self.probes = lib.production_probes(self.request, prod_built, self.times, self.true_time)
+        self.prod_public = lib.public_for(self.prod_rows, self.contexts)
+        # research recording pass (must reconcile to production)
+        self.store = lib.FeatureStore()
+        built = build_event_contribution_matrix(
+            self.request, row_provider=lib.make_recording_provider(self.contexts, self.store, self.d60),
+            static_contexts=self.contexts,
+        )
+        rows = score_from_matrix(self.request, built)
+        self.reconciliation = lib.reconcile_rows(self.prod_rows, rows)
+        self.training_ids = lib.training_event_ids(self.request)
+        self.representatives = lib.representatives_for(self.contexts)
+        self.events_by_id = {str(e["id"]): e for e in self.request["events"]}
+
+    def _contexts(self, cache_dir: Path | None) -> list[dict[str, Any]]:
+        if cache_dir is not None:
+            path = cache_dir / f"{self.case_id}_{self.radius}.pkl"
+            if path.exists():
+                with path.open("rb") as handle:
+                    return pickle.load(handle)
+        contexts = compute_candidate_static_contexts(self.request)
+        if cache_dir is not None:
+            cache_dir.mkdir(parents=True, exist_ok=True)
+            with (cache_dir / f"{self.case_id}_{self.radius}.pkl").open("wb") as handle:
+                pickle.dump(contexts, handle)
+        return contexts
+
+    # features -------------------------------------------------------------
+    def examples(self, *, include_extras: bool) -> list[tuple[dict[str, float], bool]]:
+        out: list[tuple[dict[str, float], bool]] = []
+        truth = set(self.truth_times)
+        for event_id in self.training_ids:
+            matrix = lib.event_feature_matrix(self.store, event_id, self.times, include_extras=include_extras)
+            for time in self.times:
+                out.append((matrix.get(time, {}), time in truth))
+        return out
+
+    # scoring with a weight table ------------------------------------------
+    def weighted_rows(
+        self, table: lib.LRTable, variant: str, scale: float,
+        store: lib.FeatureStore | None = None, request: dict[str, Any] | None = None,
+    ) -> tuple[list[dict[str, Any]], dict[str, Any]]:
+        request = request or self.request
+        built = build_event_contribution_matrix(
+            request,
+            row_provider=lib.make_weighted_provider(store or self.store, table, variant=variant, scale=scale),
+            static_contexts=self.contexts,
+        )
+        return score_from_matrix(request, built), built
+
+    def rescored_store(self, events: Sequence[dict[str, Any]]) -> tuple[lib.FeatureStore, dict[str, Any], list[dict[str, Any]]]:
+        """Re-record features for an altered event list (date shifts): (store, request, production rows)."""
+        request = scoring_request_for({**self.case, "events": list(events), "candidate_radius_minutes": self.radius}, self.radius)
+        store = lib.FeatureStore()
+        built = build_event_contribution_matrix(
+            request, row_provider=lib.make_recording_provider(self.contexts, store, self.d60), static_contexts=self.contexts,
+        )
+        return store, request, score_from_matrix(request, built)
+
+    def production_rows_for(self, events: Sequence[dict[str, Any]]) -> list[dict[str, Any]]:
+        request = scoring_request_for({**self.case, "events": list(events), "candidate_radius_minutes": self.radius}, self.radius)
+        built = build_event_contribution_matrix(request, static_contexts=self.contexts)
+        return score_from_matrix(request, built)
+
+
+def evaluate(data: CaseData, rows: Sequence[dict[str, Any]], *, softmax_prior: bool, pre_answers=(), answers=None, temperature: float = 1.0) -> dict[str, dict[str, Any]]:
+    public = lib.public_for(rows, data.contexts)
+    out: dict[str, dict[str, Any]] = {}
+    for mode in PRIORS:
+        prior = lib.prior_for(public, mode=mode, softmax=softmax_prior, temperature=temperature)
+        result = lib.replay(
+            public=public, prior=prior, probes=data.probes, true_time=data.true_time,
+            window_times=data.times, pre_answers=pre_answers, answers=answers,
+        )
+        result["engine_top1"] = lib.engine_top1(public, data.true_time)
+        out[mode] = result
+    return out
+
+
+# ---------------------------------------------------------------------------
+# R-A
+# ---------------------------------------------------------------------------
+
+def fit_prior(training: Sequence[CaseData], table: lib.LRTable, variant: str) -> tuple[float, float]:
+    """(scale, temperature) from training cases only.
+
+    scale: research within-case score range matched to the production median
+    range (so the raw-prior replay's ±2 / 8-lead constants mean the same);
+    temperature: single Platt temperature for the percent (softmax) prior.
+    """
+    prod = [lib.within_case_range(d.prod_rows) for d in training]
+    rows_by_case = {d.case_id: d.weighted_rows(table, variant, 1.0)[0] for d in training}
+    research = [lib.within_case_range(rows) for rows in rows_by_case.values()]
+    p_med, r_med = lib.median(prod), lib.median(research)
+    scale = round(p_med / r_med, 6) if p_med and r_med else 1.0
+    publics = [
+        (lib.public_for([{**r, "score": float(r["score"]) * scale} for r in rows_by_case[d.case_id]], d.contexts), d.truth_times)
+        for d in training
+    ]
+    return scale, lib.fit_temperature(publics)
+
+
+def run_ra(by_radius: dict[int, list[CaseData]], *, fast: bool) -> dict[str, Any]:
+    out: dict[str, Any] = {"variants": list(lib.VARIANTS), "alpha": lib.LAPLACE_ALPHA, "radii": {}}
+    for radius, cases in sorted(by_radius.items()):
+        block: dict[str, Any] = {"n": len(cases), "baseline": {}, "full_fit": {}, "loo": {}, "robustness": {}, "calibration": {}, "lr_table": {}, "noise_features": {}}
+        baseline_rows = []
+        for data in cases:
+            row = evaluate(data, data.prod_rows, softmax_prior=False)
+            baseline_rows.append({"case_id": data.case_id, **{f"{m}": row[m] for m in PRIORS}})
+        block["baseline"] = {m: lib.summarize([r[m] for r in baseline_rows]) for m in PRIORS}
+        per_case_examples = {
+            include: {d.case_id: d.examples(include_extras=include) for d in cases} for include in (False, True)
+        }
+        altered_stores: dict[tuple[str, str, int], tuple[lib.FeatureStore, dict[str, Any]]] = {}
+        for variant in lib.VARIANTS:
+            include_extras, _neg = lib.VARIANT_SPEC[variant]
+            examples = per_case_examples[include_extras]
+            # full fit -------------------------------------------------------
+            full_table = lib.estimate_lr([ex for rows in examples.values() for ex in rows])
+            full_scale, full_temperature = fit_prior(cases, full_table, variant)
+            full_rows = []
+            for data in cases:
+                rows, _ = data.weighted_rows(full_table, variant, full_scale)
+                full_rows.append(evaluate(data, rows, softmax_prior=True, temperature=full_temperature))
+            block["full_fit"][variant] = {
+                "scale": full_scale,
+                "temperature": full_temperature,
+                **{m: lib.summarize([r[m] for r in full_rows]) for m in PRIORS},
+            }
+            if variant == "A3":
+                block["lr_table"] = {
+                    name: {
+                        "log_lr_present": full_table.present[name],
+                        "log_lr_absent": full_table.absent[name],
+                        **full_table.support[name],
+                        "extra": lib.is_extra_feature(name),
+                    }
+                    for name in sorted(full_table.present)
+                }
+                ci = lib.bootstrap_lr(examples, resamples=50 if fast else 200)
+                for name, interval in ci.items():
+                    block["lr_table"].setdefault(name, {}).update(interval)
+                block["noise_features"] = sorted(
+                    name for name, row in block["lr_table"].items()
+                    if row.get("p05") is not None and row["p05"] <= 0.0 <= row["p95"]
+                )
+            # leave-one-case-out -------------------------------------------
+            loo_rows = []
+            robustness = defaultdict(list)
+            calibration_points: list[tuple[float, bool]] = []
+            temperatures: list[float] = []
+            for held in cases:
+                training = [d for d in cases if d.case_id != held.case_id]
+                table = lib.estimate_lr([ex for d in training for ex in examples[d.case_id]])
+                scale, temperature = fit_prior(training, table, variant)
+                temperatures.append(temperature)
+                rows, _ = held.weighted_rows(table, variant, scale)
+                result = evaluate(held, rows, softmax_prior=True, temperature=temperature)
+                loo_rows.append(result)
+                if variant == "A3":
+                    public = lib.public_for(rows, held.contexts)
+                    posterior = lib.percent_softmax({str(r["time"])[:5]: float(r["score"]) for r in public}, temperature)
+                    truth = set(held.truth_times)
+                    for rep in public:
+                        stamp = str(rep["time"])[:5]
+                        members = {str(t)[:5] for t in (rep.get("cluster_times") or [stamp])}
+                        calibration_points.append((posterior.get(stamp, 0.0) / 100.0, bool(members & truth)))
+                # robustness: date shifts (features re-recorded with fold weights)
+                if not fast or variant == "A3":
+                    events = list(held.case.get("events") or [])
+                    shifted_sets = {
+                        "jitter_7d": [jitter_day_events(events, 7, case_id=held.case_id)],
+                        "shift_1_3_months": [
+                            lib.shift_day_events_by_months(events, seed=f"{SEED}:{held.case_id}:{radius}:{k}")
+                            for k in range(1 if fast else SHIFT_REPEATS)
+                        ],
+                    }
+                    for label, variants_of_events in shifted_sets.items():
+                        for index, altered in enumerate(variants_of_events):
+                            cache_key = (held.case_id, label, index)
+                            if cache_key not in altered_stores:
+                                altered_stores[cache_key] = held.rescored_store(altered)[:2]
+                            store, request_alt = altered_stores[cache_key]
+                            rows_alt, _ = held.weighted_rows(table, variant, scale, store=store, request=request_alt)
+                            robustness[label].append(evaluate(held, rows_alt, softmax_prior=True, temperature=temperature))
+                    # answer flips on the LOO rows
+                    asked = list(held.probes)[:ASK_COUNT]
+                    optimal = [optimal_answer(p, held.true_time) for p in asked]
+                    for k in (1, 2):
+                        sets = exhaustive_flip_sets(optimal, k) if k == 1 else sample_flip_sets(
+                            optimal, k, 3 if fast else FLIP_REPEATS, case_id=held.case_id, radius=radius,
+                        )
+                        for picked in sets:
+                            robustness[f"flip_{k}"].append(evaluate(
+                                held, rows, softmax_prior=True, answers=flipped_answers(optimal, picked), temperature=temperature,
+                            ))
+            block["loo"][variant] = {m: lib.summarize([r[m] for r in loo_rows]) for m in PRIORS}
+            block["loo"][variant]["temperatures"] = sorted(set(temperatures))
+            block["loo"][variant]["debug_verdict_v4"] = {
+                m: gate_verdict(block["baseline"][m], block["loo"][variant][m]) for m in PRIORS
+            }
+            block["loo"][variant]["verdict"] = "pending_v5"
+            if robustness:
+                block["robustness"][variant] = {
+                    label: {m: lib.summarize([r[m] for r in rows_]) for m in PRIORS}
+                    for label, rows_ in robustness.items()
+                }
+            if variant == "A3":
+                block["calibration"] = lib.calibration_bins(calibration_points)
+        out["radii"][str(radius)] = block
+    return out
+
+
+# ---------------------------------------------------------------------------
+# R-B
+# ---------------------------------------------------------------------------
+
+def absence_probes(data: CaseData, events: Sequence[dict[str, Any]]) -> tuple[list[dict[str, Any]], dict[str, list[int]]]:
+    gaps = lib.absent_years(events)
+    probes: list[dict[str, Any]] = []
+    for domain, years in gaps.items():
+        for year in years:
+            probe = lib.split_probe(
+                data.representatives, birth_date=str(data.request["birth_date"]), domain=domain,
+                year=year, month=None, source=ABSENCE_SOURCE,
+            )
+            if probe is not None:
+                probes.append(probe)
+    return probes, gaps
+
+
+def run_rb(by_radius: dict[int, list[CaseData]], *, fast: bool) -> dict[str, Any]:
+    out: dict[str, Any] = {"points": list(ABSENCE_POINTS), "card_points": CARD_POINTS, "omit_repeats": OMIT_REPEATS, "radii": {}}
+    for radius, cases in sorted(by_radius.items()):
+        rows_by_arm: dict[str, list[dict[str, Any]]] = defaultdict(list)
+        gap_stats = []
+        omit_rows: dict[str, list[dict[str, Any]]] = defaultdict(list)
+        for data in cases:
+            training = [data.events_by_id[i] for i in data.training_ids]
+            spoken = [{**e, "date": e.get("date_start"), "domain": e["domain"]} for e in training]
+            probes, gaps = absence_probes(data, spoken)
+            gap_stats.append({
+                "case_id": data.case_id, "absent_years": sum(len(v) for v in gaps.values()),
+                "domains_with_gaps": len(gaps), "absence_probes": len(probes),
+            })
+            base = evaluate(data, data.prod_rows, softmax_prior=False)
+            rows_by_arm["B0"].append(base)
+            for points in ABSENCE_POINTS:
+                pre = [(probe, "no", points / CARD_POINTS) for probe in probes]
+                rows_by_arm[f"absence@{points}"].append(evaluate(data, data.prod_rows, softmax_prior=False, pre_answers=pre))
+            # omission robustness: user did not mention 1–2 of the training events
+            for k in (1, 2):
+                for rep in range(1 if fast else OMIT_REPEATS):
+                    kept = lib.drop_events(spoken, k, seed=f"{SEED}:{data.case_id}:{radius}:{k}:{rep}")
+                    probes_k, _ = absence_probes(data, kept)
+                    for points in ABSENCE_POINTS:
+                        pre = [(probe, "no", points / CARD_POINTS) for probe in probes_k]
+                        omit_rows[f"omit_{k}@{points}"].append(evaluate(data, data.prod_rows, softmax_prior=False, pre_answers=pre))
+        block: dict[str, Any] = {
+            "n": len(cases),
+            "gap_stats": {
+                "mean_absent_years": round(sum(g["absent_years"] for g in gap_stats) / len(gap_stats), 2),
+                "mean_absence_probes": round(sum(g["absence_probes"] for g in gap_stats) / len(gap_stats), 2),
+                "cases_with_probes": sum(1 for g in gap_stats if g["absence_probes"]),
+            },
+            "arms": {arm: {m: lib.summarize([r[m] for r in rows]) for m in PRIORS} for arm, rows in rows_by_arm.items()},
+            "omission": {arm: {m: lib.summarize([r[m] for r in rows]) for m in PRIORS} for arm, rows in omit_rows.items()},
+        }
+        for arm in block["arms"]:
+            if arm == "B0":
+                continue
+            block["arms"][arm]["debug_verdict_v4"] = {m: gate_verdict(block["arms"]["B0"][m], block["arms"][arm][m]) for m in PRIORS}
+            block["arms"][arm]["verdict"] = "pending_v5"
+        out["radii"][str(radius)] = block
+    return out
+
+
+# ---------------------------------------------------------------------------
+# R-C
+# ---------------------------------------------------------------------------
+
+def run_rc(by_radius: dict[int, list[CaseData]], *, fast: bool) -> dict[str, Any]:
+    out: dict[str, Any] = {"radii": {}}
+    for radius, cases in sorted(by_radius.items()):
+        rows_by_arm: dict[str, list[dict[str, Any]]] = defaultdict(list)
+        askable_counts = []
+        for data in cases:
+            originals = {str(e["id"]): e for e in data.case.get("events") or []}
+            raw_events = list(data.case.get("events") or [])
+            spoken = lib.degrade_to_year(raw_events)
+            spoken_rows = data.production_rows_for(spoken)
+            rows_by_arm["B0_true_precision"].append(evaluate(data, data.prod_rows, softmax_prior=False))
+            rows_by_arm["C0_spoken"].append(evaluate(data, spoken_rows, softmax_prior=False))
+            # which spoken (year) events would split candidates if the month were known?
+            training = set(data.training_ids)
+            id_map = {str(e["id"]): str(rid) for rid, e in zip(
+                [str(x["id"]) for x in data.request["events"]], data.case.get("events") or [],
+            )}
+            candidates = []
+            for event in raw_events:
+                if str(event.get("precision")) != "day":
+                    continue
+                request_id = id_map.get(str(event["id"]))
+                if request_id not in training:
+                    continue
+                year, month = int(str(event["date"])[:4]), int(str(event["date"])[5:7])
+                probe = lib.split_probe(
+                    data.representatives, birth_date=str(data.request["birth_date"]), domain=str(event["domain"]),
+                    year=year, month=month, source=FOLLOWUP_SOURCE,
+                )
+                if probe is None:
+                    continue
+                candidates.append((float(probe.get("information_gain") or 0), str(event["id"]), probe))
+            candidates.sort(key=lambda item: (-item[0], item[1]))
+            askable_counts.append(len(candidates))
+            for k in (1, 2):
+                picked = candidates[:k]
+                if len(picked) < k:
+                    continue
+                ids = {item[1] for item in picked}
+                upgraded = lib.upgrade_to_month(spoken, ids, originals)
+                rows_by_arm[f"C{k}_prior"].append(evaluate(data, data.production_rows_for(upgraded), softmax_prior=False))
+                pre = [(item[2], "yes", 1.0) for item in picked]
+                rows_by_arm[f"C{k}_probe"].append(evaluate(data, spoken_rows, softmax_prior=False, pre_answers=pre))
+                rows_by_arm[f"C{k}_both"].append(evaluate(data, data.production_rows_for(upgraded), softmax_prior=False, pre_answers=pre))
+        block: dict[str, Any] = {
+            "n": len(cases),
+            "askable_per_case": {
+                "mean": round(sum(askable_counts) / len(askable_counts), 2) if askable_counts else None,
+                "distribution": {str(k): askable_counts.count(k) for k in sorted(set(askable_counts))},
+                "cases_with_at_least_one": sum(1 for c in askable_counts if c >= 1),
+                "cases_with_at_least_two": sum(1 for c in askable_counts if c >= 2),
+            },
+            "arms": {arm: {m: lib.summarize([r[m] for r in rows]) for m in PRIORS} for arm, rows in rows_by_arm.items()},
+        }
+        for arm in block["arms"]:
+            if arm.startswith("C0") or arm.startswith("B0"):
+                continue
+            block["arms"][arm]["debug_verdict_v4_vs_C0"] = {m: gate_verdict(block["arms"]["C0_spoken"][m], block["arms"][arm][m]) for m in PRIORS}
+            block["arms"][arm]["verdict"] = "pending_v5"
+        out["radii"][str(radius)] = block
+    return out
+
+
+# ---------------------------------------------------------------------------
+# main
+# ---------------------------------------------------------------------------
+
+def load_cases(path: Path) -> tuple[dict[str, Any], list[dict[str, Any]]]:
+    payload = json.loads(path.read_text(encoding="utf-8"))
+    return payload, list(payload["cases"])
+
+
+def write_json(path: Path, payload: dict[str, Any]) -> None:
+    path.write_text(json.dumps(payload, ensure_ascii=False, indent=1, sort_keys=True) + "\n", encoding="utf-8")
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--holdout", default=str(HOLDOUT_V4))
+    parser.add_argument("--dataset-label", default="v4")
+    parser.add_argument("--limit", type=int, default=0)
+    parser.add_argument("--radii", nargs="+", type=int, default=list(RADII))
+    parser.add_argument("--parts", nargs="+", default=["ra", "rb", "rc"])
+    parser.add_argument("--cache-dir", default="")
+    parser.add_argument("--fast", action="store_true", help="fewer repeats (development)")
+    parser.add_argument("--no-write", action="store_true")
+    parser.add_argument("--out-suffix", default="2026_09_29")
+    args = parser.parse_args()
+    started = clock_module.time()
+    holdout_path = Path(args.holdout)
+    meta, cases = load_cases(holdout_path)
+    if args.limit:
+        cases = cases[: args.limit]
+    cache_dir = Path(args.cache_dir) if args.cache_dir else None
+    by_radius: dict[int, list[CaseData]] = defaultdict(list)
+    errors: list[dict[str, Any]] = []
+    reconciliation: list[dict[str, Any]] = []
+    for case in cases:
+        for radius in args.radii:
+            try:
+                data = CaseData(case, radius, cache_dir)
+            except Exception as exc:  # noqa: BLE001
+                errors.append({"case_id": case.get("case_id"), "radius": radius, "error": f"{type(exc).__name__}: {exc}", "trace": traceback.format_exc()})
+                continue
+            reconciliation.append({"case_id": data.case_id, "radius": radius, **data.reconciliation})
+            by_radius[radius].append(data)
+        print(f"loaded {case.get('case_id')} ({clock_module.time() - started:.0f}s)", flush=True)
+    unreconciled = [row for row in reconciliation if row["changed"]]
+    header = {
+        "generated_for": "TASK-rectification-scoring-research-20260929",
+        "dataset": args.dataset_label,
+        "holdout": str(holdout_path.relative_to(ROOT)) if holdout_path.is_relative_to(ROOT) else str(holdout_path),
+        "case_count": len(cases),
+        "radii": list(args.radii),
+        "minute_step": MINUTE_STEP,
+        "ayanamsa": AYANAMSA,
+        "node_mode": NODE_MODE,
+        "ask_count": ASK_COUNT,
+        "probe_today": lib.TODAY.isoformat(),
+        "probes": "production G0 probes generated once per case/radius from the production matrix; reused for every arm",
+        "open_set_not_blind": True,
+        "verdict": "pending_v5",
+        "reconciliation": {"cases": len(reconciliation), "unreconciled": len(unreconciled), "rows": reconciliation},
+        "errors": errors,
+        "seed": SEED,
+        "fast": bool(args.fast),
+    }
+    if unreconciled:
+        print(json.dumps({"UNRECONCILED": unreconciled}, ensure_ascii=False, indent=1))
+        return 2
+    results: dict[str, dict[str, Any]] = {}
+    if "ra" in args.parts:
+        results["lr"] = {**header, "part": "R-A", **run_ra(by_radius, fast=args.fast)}
+        print("R-A done", f"{clock_module.time() - started:.0f}s", flush=True)
+    if "rb" in args.parts:
+        results["absence"] = {**header, "part": "R-B", **run_rb(by_radius, fast=args.fast)}
+        print("R-B done", f"{clock_module.time() - started:.0f}s", flush=True)
+    if "rc" in args.parts:
+        results["precision_followup"] = {**header, "part": "R-C", **run_rc(by_radius, fast=args.fast)}
+        print("R-C done", f"{clock_module.time() - started:.0f}s", flush=True)
+    for key, payload in results.items():
+        payload["elapsed_seconds"] = round(clock_module.time() - started, 1)
+        if not args.no_write:
+            write_json(OUT_DIR / f"scoring_research_{key}_{args.out_suffix}.json", {k: v for k, v in payload.items() if k != "elapsed_seconds"})
+    brief: dict[str, Any] = {"reconciliation_unreconciled": len(unreconciled), "errors": len(errors)}
+    for key, payload in results.items():
+        brief[key] = {}
+        for radius, block in payload["radii"].items():
+            if key == "lr":
+                brief[key][radius] = {
+                    "baseline": {m: (block["baseline"][m]["top1"], block["baseline"][m]["coverage"], block["baseline"][m]["width_median"], block["baseline"][m]["engine_top1"]) for m in PRIORS},
+                    **{v: {m: (block["loo"][v][m]["top1"], block["loo"][v][m]["coverage"], block["loo"][v][m]["width_median"], block["loo"][v][m]["engine_top1"]) for m in PRIORS} for v in lib.VARIANTS},
+                }
+            else:
+                brief[key][radius] = {arm: {m: (s[m]["top1"], s[m]["coverage"], s[m]["width_median"]) for m in PRIORS} for arm, s in block["arms"].items()}
+    print(json.dumps(brief, ensure_ascii=False, indent=1))
+    return 0 if not errors else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())
diff --git a/scripts/research/scoring_research_lib.py b/scripts/research/scoring_research_lib.py
new file mode 100644
index 00000000..b1d824c5
--- /dev/null
+++ b/scripts/research/scoring_research_lib.py
@@ -0,0 +1,820 @@
+"""Scaffold (R-0) for TASK-rectification-scoring-research-20260929.
+
+Offline only. Nothing here changes a production default or a frozen scoring
+file. The module records, for every (case, candidate minute, event, sample
+date), which scoring rules fire — the eleven production rules from
+`active_rectification_event_engine._score_event` plus the auxiliary
+transit / Ashtakavarga / Shadbala rules — and a set of *extra* observations
+that production computes but does not score (KP cusp sub-lords, Pranapada /
+Hora / Ghati / Bhava lagna, D60). Likelihood-ratio weights are estimated per
+feature with leave-one-**case**-out folds, and a weighted row provider feeds
+the same contribution-matrix / probe / six-question replay machinery that the
+09-14 / 09-26 / 09-29 studies used.
+
+Recording provider vs production: the provider returns exactly the production
+evidence (same rule ids, same points), so `build_event_contribution_matrix`
+yields the same matrix as the production path. `reconcile_rows` asserts that
+per case before any experiment (task hard line 4).
+"""
+
+from __future__ import annotations
+
+import math
+import statistics
+import sys
+from collections import defaultdict
+from dataclasses import dataclass, field
+from datetime import date, datetime
+from pathlib import Path
+from random import Random
+from typing import Any, Callable, Sequence
+
+ROOT = Path(__file__).resolve().parents[2]
+if str(ROOT) not in sys.path:
+    sys.path.insert(0, str(ROOT))
+
+from scripts.active_rectification_event_engine import (  # noqa: E402
+    DOMAIN_CONFIG,
+    OBSERVATION_ONLY_LAYERS,
+    _active_narayana,
+    _active_vimshottari,
+    _ashtakavarga_auxiliary,
+    _controlled_transit_rules,
+    _event_datetime,
+    _relative_house,
+    _shadbala_verified_components_auxiliary,
+    _varga_chart,
+    _varga_house,
+)
+import scripts.rectification.event_probes as event_probes  # noqa: E402
+from scripts.rectification.candidate_contrast import cluster_contexts_by_signature  # noqa: E402
+from scripts.rectification.case_holdout import holdout_event_ids  # noqa: E402
+from scripts.rectification.contracts import is_scoreable_event  # noqa: E402
+from scripts.rectification.refinement_packet import window_scan  # noqa: E402
+from scripts.rectification.scoring_service import (  # noqa: E402
+    build_event_contribution_matrix,
+    score_from_matrix,
+)
+from scripts.research.cluster_width_lib import (  # noqa: E402
+    SEPARATION_LEAD,
+    delivery_from_public,
+    merge_adjacent_traced,
+    metrics_bundle,
+    public_from_clusters,
+    raw_signature_clusters,
+    shannon_entropy,
+    still_valid_public,
+)
+from scripts.research.precision_gate_lib import (  # noqa: E402
+    VargaPolicy,
+    score_event_with_policy,
+)
+from scripts.research.probe_supply_after_six import (  # noqa: E402
+    ASK_COUNT,
+    SCORE_DELTA,
+    apply_answer,
+    inherit_direction,
+    optimal_answer,
+    outcome_groups,
+)
+import varga  # noqa: E402
+
+TODAY = date(2026, 9, 16)  # same probe "today" as the 09-16 / 09-29 replays
+LAPLACE_ALPHA = 1.0
+EPS = 1e-9
+EXTRA_PREFIXES = ("kp_", "pranapada_", "hora_lagna_", "ghati_lagna_", "bhava_lagna_")
+D60_SUFFIX = "_domain_varga_d60"
+IGNORED_RULE_PREFIXES = ("event_kind:", "event_kind_profile:", "no_domain_activation")
+CONSTANT_RULES = frozenset({"occupation_auxiliary_not_primary", "appearance_auxiliary_not_primary"})
+VARIANTS = ("A1", "A2", "A3")
+VARIANT_SPEC = {
+    # (uses extra features, allows negative / absence weights)
+    "A1": (False, False),
+    "A2": (True, False),
+    "A3": (True, True),
+}
+
+
+# ---------------------------------------------------------------------------
+# small helpers
+# ---------------------------------------------------------------------------
+
+def hhmm(value: object) -> str | None:
+    text = str(value or "")[:5]
+    return text if len(text) == 5 and text[2] == ":" else None
+
+
+def clock(value: str) -> int:
+    return int(value[:2]) * 60 + int(value[3:5])
+
+
+def is_extra_feature(name: str) -> bool:
+    return name.startswith(EXTRA_PREFIXES) or name.endswith(D60_SUFFIX)
+
+
+def is_scoring_rule(name: str) -> bool:
+    if name.startswith(IGNORED_RULE_PREFIXES) or name in CONSTANT_RULES:
+        return False
+    return not is_extra_feature(name)
+
+
+def median(values: Sequence[float]) -> float | None:
+    items = [float(item) for item in values if item is not None]
+    return statistics.median(items) if items else None
+
+
+# ---------------------------------------------------------------------------
+# R-0 · feature recording provider (production-identical evidence + extras)
+# ---------------------------------------------------------------------------
+
+@dataclass
+class FeatureStore:
+    """(event_id, sample_date) -> HH:MM -> {rules, extras}."""
+
+    rows: dict[tuple[str, str], dict[str, dict[str, Any]]] = field(default_factory=dict)
+
+    def put(self, event_id: str, sample: str, time: str, rules: Sequence[str], extras: Sequence[str]) -> None:
+        self.rows.setdefault((event_id, sample), {})[time] = {
+            "rules": sorted(set(rules)),
+            "extras": sorted(set(extras)),
+        }
+
+    def samples_for(self, event_id: str) -> list[str]:
+        return sorted(sample for (item, sample) in self.rows if item == event_id)
+
+
+def d60_charts(contexts: Sequence[dict[str, Any]]) -> dict[str, dict[str, Any] | None]:
+    out: dict[str, dict[str, Any] | None] = {}
+    for context in contexts:
+        stamp = context["candidate_at"].strftime("%H:%M")
+        try:
+            computed = varga.calc_all_vargas(
+                context["planet_longitudes"], float(context["ascendant_longitude"]), divisions=[60],
+            )
+            out[stamp] = _varga_chart(computed, "D60")
+        except (KeyError, TypeError, ValueError):
+            out[stamp] = None
+    return out
+
+
+def extra_features(
+    context: dict[str, Any],
+    target_houses: tuple[int, ...],
+    vimshottari: tuple[str, str, str],
+    d60: dict[str, Any] | None,
+) -> list[str]:
+    feature = context.get("feature") if isinstance(context.get("feature"), dict) else {}
+    ascendant_index = int(context["ascendant_index"])
+    kp_houses = ((feature.get("kp_cusps") or {}).get("houses") or {})
+    target_sub = {str((kp_houses.get(str(h)) or {}).get("sub_lord") or "") for h in target_houses}
+    target_star = {str((kp_houses.get(str(h)) or {}).get("nakshatra_lord") or "") for h in target_houses}
+    asc_sub = str((kp_houses.get("1") or {}).get("sub_lord") or "")
+    out: list[str] = []
+    for lord, label in zip(vimshottari, ("md", "ad", "pd")):
+        if lord in target_sub:
+            out.append(f"kp_target_cusp_sublord_is_vim_{label}")
+        if lord in target_star:
+            out.append(f"kp_target_cusp_starlord_is_vim_{label}")
+        if asc_sub and lord == asc_sub:
+            out.append(f"kp_asc_sublord_is_vim_{label}")
+        if isinstance(d60, dict) and _varga_house(d60, lord) in target_houses:
+            out.append(f"vim_{label}{D60_SUFFIX}")
+    for key, name in (
+        ("pranapada_sign_index", "pranapada"),
+        ("hora_sign_index", "hora_lagna"),
+        ("ghati_sign_index", "ghati_lagna"),
+        ("bhava_sign_index", "bhava_lagna"),
+    ):
+        index = feature.get(key)
+        if isinstance(index, int) and _relative_house(index, ascendant_index) in target_houses:
+            out.append(f"{name}_in_target_house")
+    return out
+
+
+def recorded_row(
+    request: dict[str, Any],
+    context: dict[str, Any],
+    *,
+    store: FeatureStore,
+    transit_cache: dict[tuple[Any, ...], dict[str, Any]],
+    d60_by_time: dict[str, dict[str, Any] | None],
+) -> dict[str, Any]:
+    """Production `_candidate_row` for one legacy (single event, one date) request, plus extras."""
+    candidate_at = context["candidate_at"]
+    chart = context["chart"]
+    planet_longitudes = context["planet_longitudes"]
+    ascendant_index = context["ascendant_index"]
+    arudha_padas = context["arudha_padas"]
+    varga_charts = context["varga_charts"]
+    moon_longitude = planet_longitudes["Moon"]
+    stamp = candidate_at.strftime("%H:%M")
+    policy = VargaPolicy(name="V0", window_minutes=0.0)
+    evidence: list[dict[str, Any]] = []
+    missing: list[str] = []
+    for event in request["events"]:
+        event_at = _event_datetime(event)
+        prefixes, target_houses = DOMAIN_CONFIG[event["domain"]]
+        selected = {prefix: varga_charts.get(prefix) for prefix in prefixes}
+        if any(item is None for item in selected.values()):
+            missing.extend(prefixes)
+            continue
+        try:
+            vimshottari = _active_vimshottari(
+                candidate_at.date().isoformat(), moon_longitude, event_at, context.get("vimshottari_timeline"),
+            )
+        except (KeyError, TypeError, ValueError):
+            missing.append("Vimshottari_MD_AD_PD")
+            continue
+        try:
+            narayana = _active_narayana(
+                ascendant_index, planet_longitudes, candidate_at, event_at, context.get("narayana_periods"),
+            )
+        except (KeyError, TypeError, ValueError):
+            missing.append("Narayana_MD_AD")
+            continue
+        if narayana[0] is None or narayana[1] is None:
+            missing.append("Narayana_MD_AD")
+            continue
+        row = score_event_with_policy(
+            candidate_time=stamp, event=event, natal_chart=chart,
+            varga_by_prefix={k: v for k, v in selected.items() if isinstance(v, dict)},
+            vimshottari=vimshottari, narayana=narayana, arudha_padas=arudha_padas, policy=policy,
+        )
+        weight = 1.0  # legacy requests carry precision "day"; the matrix applies the real weight
+        transit_rules = _controlled_transit_rules(
+            request, event, ascendant_index, target_houses, transit_cache,
+        )
+        if transit_rules:
+            row["rule_ids"].extend(transit_rules)
+            row["points"] = round(row["points"] + 0.25 * len(transit_rules) * weight, 4)
+        av_rules, av_points = _ashtakavarga_auxiliary(
+            chart, ascendant_index, target_houses, context.get("ashtakavarga_result"),
+        )
+        if av_rules:
+            row["rule_ids"].extend(av_rules)
+            row["points"] = round(row["points"] + av_points * weight, 4)
+        sb_rules, sb_points = _shadbala_verified_components_auxiliary(
+            chart, candidate_at.hour + candidate_at.minute / 60, vimshottari, context.get("shadbala_result"),
+        )
+        if sb_rules:
+            row["rule_ids"].extend(sb_rules)
+            row["points"] = round(row["points"] + sb_points * weight, 4)
+        evidence.append(row)
+        store.put(
+            str(event["id"]), str(event["date"]), stamp, row["rule_ids"],
+            extra_features(context, target_houses, vimshottari, d60_by_time.get(stamp)),
+        )
+    return {
+        "time": stamp,
+        "score": round(sum(item["points"] for item in evidence), 4),
+        "evidence": evidence,
+        "missing_layers": sorted(set(
+            missing + [layer for layer in context["feature"]["blocked_layers"] if layer not in OBSERVATION_ONLY_LAYERS]
+        )),
+    }
+
+
+def make_recording_provider(
+    contexts: Sequence[dict[str, Any]],
+    store: FeatureStore,
+    d60_by_time: dict[str, dict[str, Any] | None],
+) -> Callable[[dict[str, Any]], list[dict[str, Any]]]:
+    transit_cache: dict[tuple[Any, ...], dict[str, Any]] = {}
+
+    def provider(request: dict[str, Any]) -> list[dict[str, Any]]:
+        return [
+            recorded_row(request, context, store=store, transit_cache=transit_cache, d60_by_time=d60_by_time)
+            for context in contexts
+        ]
+
+    return provider
+
+
+def score_map(rows: Sequence[dict[str, Any]]) -> dict[str, float]:
+    return {str(row["time"])[:5]: float(row.get("score") or 0) for row in rows}
+
+
+def reconcile_rows(production: Sequence[dict[str, Any]], research: Sequence[dict[str, Any]]) -> dict[str, Any]:
+    """Per-minute score and rule-id comparison. `changed == 0` is the R-0 gate."""
+    prod = {str(r["time"])[:5]: r for r in production}
+    rese = {str(r["time"])[:5]: r for r in research}
+    changed: list[dict[str, Any]] = []
+    for time, row in prod.items():
+        other = rese.get(time)
+        if other is None:
+            changed.append({"time": time, "reason": "missing"})
+            continue
+        if abs(float(row.get("score") or 0) - float(other.get("score") or 0)) > EPS:
+            changed.append({"time": time, "reason": "score", "production": row.get("score"), "research": other.get("score")})
+            continue
+        prod_rules = {
+            (item["event_id"], tuple(sorted(item["rule_ids"]))) for item in row.get("evidence") or []
+        }
+        rese_rules = {
+            (item["event_id"], tuple(sorted(item["rule_ids"]))) for item in other.get("evidence") or []
+        }
+        if prod_rules != rese_rules:
+            changed.append({"time": time, "reason": "rule_ids"})
+    return {"candidates": len(prod), "changed": len(changed), "details": changed[:5]}
+
+
+# ---------------------------------------------------------------------------
+# feature matrices and likelihood-ratio weights
+# ---------------------------------------------------------------------------
+
+def event_feature_matrix(
+    store: FeatureStore,
+    event_id: str,
+    times: Sequence[str],
+    *,
+    include_extras: bool,
+) -> dict[str, dict[str, float]]:
+    """HH:MM -> feature -> fraction of sample dates on which it fired."""
+    samples = store.samples_for(event_id)
+    out: dict[str, dict[str, float]] = {}
+    if not samples:
+        return {time: {} for time in times}
+    for time in times:
+        counts: dict[str, int] = defaultdict(int)
+        for sample in samples:
+            cell = store.rows.get((event_id, sample), {}).get(time)
+            if not cell:
+                continue
+            names = [name for name in cell["rules"] if is_scoring_rule(name)]
+            if include_extras:
+                names += list(cell["extras"])
+            for name in names:
+                counts[name] += 1
+        out[time] = {name: round(count / len(samples), 6) for name, count in counts.items()}
+    return out
+
+
+def training_event_ids(request: dict[str, Any]) -> list[str]:
+    holdout = holdout_event_ids(request["events"])
+    return [str(e["id"]) for e in request["events"] if is_scoreable_event(e) and str(e["id"]) not in holdout]
+
+
+@dataclass
+class LRTable:
+    alpha: float
+    positives: float
+    negatives: float
+    present: dict[str, float]   # log LR of the feature firing
+    absent: dict[str, float]    # log LR of the feature not firing (naive Bayes complement)
+    support: dict[str, dict[str, float]]
+
+    def weight(self, name: str, *, allow_negative: bool) -> tuple[float, float]:
+        """(present weight, absent weight) under the variant policy."""
+        present = self.present.get(name, 0.0)
+        absent = self.absent.get(name, 0.0)
+        if allow_negative:
+            return present, absent
+        return max(present, 0.0), 0.0
+
+
+def estimate_lr(examples: Sequence[tuple[dict[str, float], bool]], *, alpha: float = LAPLACE_ALPHA) -> LRTable:
+    """Per-feature log likelihood ratios from (feature fractions, is-truth-cluster) examples."""
+    positives = float(sum(1 for _values, truth in examples if truth))
+    negatives = float(sum(1 for _values, truth in examples if not truth))
+    names: set[str] = set()
+    pos_sum: dict[str, float] = defaultdict(float)
+    neg_sum: dict[str, float] = defaultdict(float)
+    for values, truth in examples:
+        for name, value in values.items():
+            names.add(name)
+            if truth:
+                pos_sum[name] += float(value)
+            else:
+                neg_sum[name] += float(value)
+    present: dict[str, float] = {}
+    absent: dict[str, float] = {}
+    support: dict[str, dict[str, float]] = {}
+    for name in sorted(names):
+        p_pos = (pos_sum[name] + alpha) / (positives + 2 * alpha)
+        p_neg = (neg_sum[name] + alpha) / (negatives + 2 * alpha)
+        present[name] = round(math.log(p_pos / p_neg), 6)
+        absent[name] = round(math.log((1 - p_pos) / (1 - p_neg)), 6)
+        support[name] = {
+            "fires_truth": round(pos_sum[name], 4),
+            "fires_other": round(neg_sum[name], 4),
+            "p_truth": round(p_pos, 6),
+            "p_other": round(p_neg, 6),
+        }
+    return LRTable(alpha=alpha, positives=positives, negatives=negatives, present=present, absent=absent, support=support)
+
+
+def bootstrap_lr(
+    per_case_examples: dict[str, list[tuple[dict[str, float], bool]]],
+    *,
+    resamples: int = 200,
+    seed: int = 20260929,
+    alpha: float = LAPLACE_ALPHA,
+) -> dict[str, dict[str, float]]:
+    """Case-level bootstrap 5–95 % interval of the present-log-LR per feature."""
+    ids = sorted(per_case_examples)
+    rng = Random(f"{seed}:lr-bootstrap")
+    draws: dict[str, list[float]] = defaultdict(list)
+    for _ in range(resamples):
+        picked = [rng.choice(ids) for _ in ids]
+        table = estimate_lr([ex for cid in picked for ex in per_case_examples[cid]], alpha=alpha)
+        for name, value in table.present.items():
+            draws[name].append(value)
+    out: dict[str, dict[str, float]] = {}
+    for name, values in draws.items():
+        ordered = sorted(values)
+        lo = ordered[int(0.05 * (len(ordered) - 1))]
+        hi = ordered[int(0.95 * (len(ordered) - 1))]
+        out[name] = {"p05": round(lo, 4), "p95": round(hi, 4), "draws": len(ordered)}
+    return out
+
+
+def weighted_points(values: dict[str, float], table: LRTable, *, allow_negative: bool, universe: Sequence[str]) -> float:
+    total = 0.0
+    for name in universe:
+        present, absent = table.weight(name, allow_negative=allow_negative)
+        x = float(values.get(name, 0.0))
+        total += x * present + (1.0 - x) * absent
+    return total
+
+
+def make_weighted_provider(
+    store: FeatureStore,
+    table: LRTable,
+    *,
+    variant: str,
+    scale: float = 1.0,
+    baseline_rows_by_sample: dict[tuple[str, str], dict[str, dict[str, Any]]] | None = None,
+) -> Callable[[dict[str, Any]], list[dict[str, Any]]]:
+    """Row provider that scores each (event, sample date) as Σ feature weights.
+
+    Production rule ids are kept on the evidence so the matrix's kind factor
+    and technique layers behave as in production; only the points change.
+    """
+    include_extras, allow_negative = VARIANT_SPEC[variant]
+    universe = [
+        name for name in sorted(table.present)
+        if (include_extras or not is_extra_feature(name))
+    ]
+
+    def provider(request: dict[str, Any]) -> list[dict[str, Any]]:
+        rows: list[dict[str, Any]] = []
+        for event in request["events"]:
+            key = (str(event["id"]), str(event["date"]))
+            cells = store.rows.get(key, {})
+            for time in sorted(cells, key=clock):
+                cell = cells[time]
+                names = [name for name in cell["rules"] if is_scoring_rule(name)]
+                if include_extras:
+                    names += list(cell["extras"])
+                values = {name: 1.0 for name in names}
+                points = round(scale * weighted_points(values, table, allow_negative=allow_negative, universe=universe), 4)
+                rows.append({
+                    "time": time,
+                    "score": points,
+                    "evidence": [{
+                        "event_id": event["id"], "domain": event["domain"], "candidate_time": time,
+                        "rule_ids": list(cell["rules"]), "points": points,
+                    }],
+                    "missing_layers": [],
+                })
+        return rows
+
+    return provider
+
+
+def loo_folds(case_ids: Sequence[str]) -> list[tuple[str, list[str]]]:
+    ids = list(case_ids)
+    return [(held, [other for other in ids if other != held]) for held in ids]
+
+
+# ---------------------------------------------------------------------------
+# truth labels, priors, replay
+# ---------------------------------------------------------------------------
+
+def truth_cluster_times(contexts: Sequence[dict[str, Any]], true_time: str) -> list[str]:
+    for cluster in raw_signature_clusters(contexts):
+        times = [str(item)[:5] for item in cluster.get("times") or []]
+        if true_time[:5] in times:
+            return sorted(times, key=clock)
+    return [true_time[:5]]
+
+
+def public_for(rows: Sequence[dict[str, Any]], contexts: Sequence[dict[str, Any]]) -> list[dict[str, Any]]:
+    raw = raw_signature_clusters(contexts)
+    by_time = {stamp: row for row in rows if (stamp := hhmm(row.get("time")))}
+    merged, _trace = merge_adjacent_traced(raw, by_time)
+    public = public_from_clusters(merged, rows)
+    for row in public:
+        row["score"] = float(row.get("score") or 0)
+    return public
+
+
+def percent_proportional(scores: dict[str, float]) -> dict[str, float]:
+    total = sum(max(value, 0.0) for value in scores.values())
+    if total <= 0:
+        return {key: 0.0 for key in scores}
+    return {key: float(round(max(value, 0.0) / total * 100)) for key, value in scores.items()}
+
+
+def softmax_probabilities(scores: dict[str, float], temperature: float = 1.0) -> dict[str, float]:
+    if not scores:
+        return {}
+    temp = float(temperature) if temperature and temperature > 0 else 1.0
+    peak = max(scores.values())
+    weights = {key: math.exp((value - peak) / temp) for key, value in scores.items()}
+    total = sum(weights.values())
+    return {key: weight / total for key, weight in weights.items()}
+
+
+def percent_softmax(scores: dict[str, float], temperature: float = 1.0) -> dict[str, float]:
+    return {key: float(round(p * 100)) for key, p in softmax_probabilities(scores, temperature).items()}
+
+
+TEMPERATURE_GRID = (0.25, 0.5, 1.0, 2.0, 4.0, 8.0, 16.0, 32.0, 64.0, 128.0, 256.0)
+
+
+def truth_mass(public: Sequence[dict[str, Any]], probabilities: dict[str, float], truth_times: Sequence[str]) -> float:
+    truth = {str(t)[:5] for t in truth_times}
+    mass = 0.0
+    for row in public:
+        stamp = str(row["time"])[:5]
+        members = {str(t)[:5] for t in (row.get("cluster_times") or [stamp])}
+        if members & truth:
+            mass += probabilities.get(stamp, 0.0)
+    return mass
+
+
+def fit_temperature(
+    training: Sequence[tuple[Sequence[dict[str, Any]], Sequence[str]]],
+    grid: Sequence[float] = TEMPERATURE_GRID,
+) -> float:
+    """Platt-style single temperature: maximise Σ log P(truth cluster) on training cases only."""
+    best_t, best_ll = 1.0, None
+    for temp in grid:
+        ll = 0.0
+        for public, truth_times in training:
+            base = {str(r["time"])[:5]: float(r.get("score") or 0) for r in public}
+            mass = truth_mass(public, softmax_probabilities(base, temp), truth_times)
+            ll += math.log(max(mass, 1e-9))
+        if best_ll is None or ll > best_ll + 1e-12:
+            best_t, best_ll = float(temp), ll
+    return best_t
+
+
+def prior_for(public: Sequence[dict[str, Any]], *, mode: str, softmax: bool, temperature: float = 1.0) -> dict[str, float]:
+    base = {str(row["time"])[:5]: float(row.get("score") or 0) for row in public}
+    if mode == "raw":
+        return base
+    return percent_softmax(base, temperature) if softmax else percent_proportional(base)
+
+
+def apply_scaled_answer(
+    scores: dict[str, float],
+    conflicts: dict[str, int],
+    eliminated: set[str],
+    probe: dict[str, Any],
+    answer: str,
+    candidate_times: Sequence[str],
+    factor: float,
+) -> tuple[dict[str, float], dict[str, int], set[str]]:
+    """`apply_answer` at card strength (factor == 1); weaker evidence scales the
+    delta and never counts a strong conflict (so it can never eliminate)."""
+    if factor >= 1.0 - EPS:
+        return apply_answer(scores, conflicts, eliminated, probe, answer, candidate_times)
+    yes, no = outcome_groups(probe)
+    next_scores = dict(scores)
+    for time in candidate_times:
+        if time in eliminated:
+            continue
+        if time in yes:
+            raw = "support"
+        elif time in no:
+            raw = "conflict"
+        else:
+            raw = inherit_direction(time, yes, no)
+        if answer == "no":
+            raw = {"support": "conflict", "conflict": "support", "neutral": "neutral"}[raw]
+        next_scores[time] = next_scores.get(time, 0.0) + SCORE_DELTA[raw] * factor
+    return next_scores, dict(conflicts), set(eliminated)
+
+
+def replay(
+    *,
+    public: Sequence[dict[str, Any]],
+    prior: dict[str, float],
+    probes: Sequence[dict[str, Any]],
+    true_time: str,
+    window_times: Sequence[str],
+    pre_answers: Sequence[tuple[dict[str, Any], str, float]] = (),
+    answers: Sequence[str | None] | None = None,
+) -> dict[str, Any]:
+    """Prior → optional pre-answers (probe, answer, factor) → six probes answered from truth."""
+    reps = [str(row["time"])[:5] for row in public]
+    scores = {time: float(prior.get(time, 0.0)) for time in reps}
+    conflicts = {time: 0 for time in reps}
+    eliminated: set[str] = set()
+    for probe, answer, factor in pre_answers:
+        scores, conflicts, eliminated = apply_scaled_answer(scores, conflicts, eliminated, probe, answer, reps, factor)
+    asked = list(probes)[:ASK_COUNT]
+    given = list(answers) if answers is not None else [optimal_answer(p, true_time) for p in asked]
+    answered = 0
+    for probe, answer in zip(asked, given):
+        if answer is None:
+            continue
+        answered += 1
+        scores, conflicts, eliminated = apply_answer(scores, conflicts, eliminated, probe, answer, reps)
+    posterior = [{**row, "score": scores.get(str(row["time"])[:5], row.get("score") or 0)} for row in public]
+    valid = still_valid_public(posterior, scores, eliminated, lead=SEPARATION_LEAD)
+    delivery = delivery_from_public(valid)
+    alive = [row for row in posterior if str(row["time"])[:5] not in eliminated]
+    metrics = metrics_bundle(
+        public=alive, true_time=true_time, window_times=window_times,
+        delivery_times=delivery["times"], delivery_width=delivery["width"], independent=True,
+        entropy_scores=[scores.get(str(row["time"])[:5], 0.0) for row in alive],
+    )
+    truth_eliminated = any(
+        true_time in (row.get("cluster_times") or [str(row.get("time"))[:5]]) and str(row["time"])[:5] in eliminated
+        for row in public
+    )
+    return {
+        "top1": bool(metrics["top1_hit"]),
+        "coverage": bool(metrics["coverage"]),
+        "width": delivery["width"],
+        "tie": bool(metrics["tie"]),
+        "squeezed": bool(metrics["truth_squeezed"]),
+        "eliminated": len(eliminated),
+        "truth_eliminated": bool(truth_eliminated),
+        "questions": answered,
+        "entropy": round(shannon_entropy(max(s, 0.0) for t, s in scores.items() if t not in eliminated), 4),
+    }
+
+
+def engine_top1(public: Sequence[dict[str, Any]], true_time: str) -> bool:
+    from scripts.research.cluster_width_lib import top1_from_public
+    return bool(top1_from_public(public, true_time))
+
+
+def within_case_range(rows: Sequence[dict[str, Any]]) -> float:
+    scores = [float(row.get("score") or 0) for row in rows]
+    return (max(scores) - min(scores)) if scores else 0.0
+
+
+def summarize(rows: Sequence[dict[str, Any]]) -> dict[str, Any]:
+    """Same keys as precision_gate_sweep.summarize so `gate_verdict` can read it."""
+    if not rows:
+        return {"n": 0, "top1": None, "coverage": None, "width_median": None, "tie": None, "squeezed": 0,
+                "engine_top1": None, "refresh_mean": 0.0, "entropy": None, "truth_eliminated": 0}
+    n = len(rows)
+    return {
+        "n": n,
+        "top1": round(sum(1 for r in rows if r.get("top1")) / n, 4),
+        "coverage": round(sum(1 for r in rows if r.get("coverage")) / n, 4),
+        "width_median": median([r.get("width") for r in rows]),
+        "tie": round(sum(1 for r in rows if r.get("tie")) / n, 4),
+        "squeezed": sum(1 for r in rows if r.get("squeezed")),
+        "engine_top1": round(sum(1 for r in rows if r.get("engine_top1")) / n, 4),
+        "refresh_mean": 0.0,
+        "entropy": round(sum(float(r.get("entropy") or 0) for r in rows) / n, 4),
+        "truth_eliminated": sum(1 for r in rows if r.get("truth_eliminated")),
+    }
+
+
+# ---------------------------------------------------------------------------
+# probes on representatives (typed-event convention), absence, precision follow-up
+# ---------------------------------------------------------------------------
+
+def production_probes(request: dict[str, Any], built: dict[str, Any], times: Sequence[str], true_time: str) -> list[dict[str, Any]]:
+    payload = {**request, "refresh_probes": False, "asked_probe_keys": []}
+    return event_probes.discriminating_event_probes(
+        payload, built, scan=window_scan(built), candidate_times=list(times),
+        representative_time=true_time, today=TODAY,
+    )
+
+
+@dataclass
+class Representatives:
+    reps: list[dict[str, Any]]
+    clusters: list[dict[str, Any]]
+    set_version: str
+
+
+def representatives_for(contexts: Sequence[dict[str, Any]]) -> Representatives:
+    full = [item for item in contexts if event_probes._context_time(item)]
+    full.sort(key=lambda item: event_probes._clock(str(event_probes._context_time(item))))
+    clusters = cluster_contexts_by_signature(full)
+    reps = [c["representative"] for c in clusters if event_probes._scoreable(c["representative"])]
+    if len(reps) < 2:
+        reps = [item for item in full if event_probes._scoreable(item)]
+    version = event_probes.candidate_set_version([c["times"] for c in clusters])
+    return Representatives(reps=reps, clusters=clusters, set_version=version)
+
+
+def split_probe(
+    representatives: Representatives,
+    *,
+    birth_date: str,
+    domain: str,
+    year: int,
+    month: int | None,
+    source: str,
+) -> dict[str, Any] | None:
+    canonical = event_probes.canonical_domain(domain)
+    if canonical not in event_probes.DOMAIN_CATALOG:
+        return None
+    return event_probes._evaluate_contexts(
+        representatives.reps, birth_date=birth_date, domain=canonical, year=year, month=month,
+        source=source, clusters=representatives.clusters, set_version=representatives.set_version,
+    )
+
+
+def event_year(event: dict[str, Any]) -> int | None:
+    raw = str(event.get("date_start") or event.get("date") or "")
+    return int(raw[:4]) if raw[:4].isdigit() else None
+
+
+def event_month(event: dict[str, Any]) -> int | None:
+    raw = str(event.get("date_start") or event.get("date") or "")
+    return int(raw[5:7]) if len(raw) >= 7 and raw[4] == "-" else None
+
+
+def absent_years(events: Sequence[dict[str, Any]]) -> dict[str, list[int]]:
+    """Per domain: years strictly inside the span of that domain's dated events with no event."""
+    years: dict[str, set[int]] = defaultdict(set)
+    for event in events:
+        year = event_year(event)
+        if year is None:
+            continue
+        years[str(event.get("domain") or "")].add(year)
+    out: dict[str, list[int]] = {}
+    for domain, known in years.items():
+        if len(known) < 2:
+            continue
+        lo, hi = min(known), max(known)
+        gaps = [year for year in range(lo + 1, hi) if year not in known]
+        if gaps:
+            out[domain] = gaps
+    return dict(sorted(out.items()))
+
+
+def drop_events(events: Sequence[dict[str, Any]], count: int, *, seed: str) -> list[dict[str, Any]]:
+    rng = Random(seed)
+    if count <= 0 or count >= len(events):
+        return list(events)
+    dropped = set(rng.sample(range(len(events)), count))
+    return [event for index, event in enumerate(events) if index not in dropped]
+
+
+def degrade_to_year(events: Sequence[dict[str, Any]]) -> list[dict[str, Any]]:
+    """The 'spoken' form of a case: every day/month event becomes year precision."""
+    out = []
+    for event in events:
+        item = dict(event)
+        if str(item.get("precision")) in {"day", "month"}:
+            item["precision"] = "year"
+            item["date"] = str(item.get("date") or "")[:4]
+        out.append(item)
+    return out
+
+
+def upgrade_to_month(events: Sequence[dict[str, Any]], event_ids: set[str], originals: dict[str, dict[str, Any]]) -> list[dict[str, Any]]:
+    out = []
+    for event in events:
+        item = dict(event)
+        original = originals.get(str(item.get("id")))
+        if str(item.get("id")) in event_ids and original is not None and len(str(original.get("date") or "")) >= 7:
+            item["precision"] = "month"
+            item["date"] = str(original["date"])[:7]
+        out.append(item)
+    return out
+
+
+def shift_day_events_by_months(events: Sequence[dict[str, Any]], *, seed: str, choices: Sequence[int] = (-3, -2, -1, 1, 2, 3)) -> list[dict[str, Any]]:
+    rng = Random(seed)
+    out = []
+    for event in events:
+        item = dict(event)
+        raw = str(item.get("date") or "")
+        if str(item.get("precision")) == "day" and len(raw) >= 10:
+            year, month, day = int(raw[:4]), int(raw[5:7]), int(raw[8:10])
+            index = year * 12 + (month - 1) + rng.choice(list(choices))
+            new_year, new_month = divmod(index, 12)
+            item["date"] = f"{new_year:04d}-{new_month + 1:02d}-{min(day, 28):02d}"
+            item["shift_months"] = index - (year * 12 + month - 1)
+        out.append(item)
+    return out
+
+
+def calibration_bins(points: Sequence[tuple[float, bool]], edges: Sequence[float] = (0.0, 0.05, 0.1, 0.2, 0.3, 0.5, 0.7, 1.0001)) -> list[dict[str, Any]]:
+    out = []
+    for lo, hi in zip(edges, edges[1:]):
+        inside = [(p, t) for p, t in points if lo <= p < hi]
+        out.append({
+            "bin": f"[{lo:.2f},{min(hi, 1.0):.2f})",
+            "n": len(inside),
+            "predicted_mean": round(sum(p for p, _ in inside) / len(inside), 4) if inside else None,
+            "observed_rate": round(sum(1 for _, t in inside if t) / len(inside), 4) if inside else None,
+        })
+    return out
+
+
+__all__ = [name for name in dir() if not name.startswith("__")]
diff --git a/tests/test_scoring_research.py b/tests/test_scoring_research.py
new file mode 100644
index 00000000..1e382742
--- /dev/null
+++ b/tests/test_scoring_research.py
@@ -0,0 +1,159 @@
+"""Regression tests for the 2026-09-29 scoring-method research scaffold.
+
+Pure helpers use fictional inputs. The one integration test reconciles the
+research recording scorer against the production scorer on a public v4 case
+(task hard line 4: zero difference before any experiment).
+"""
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+import pytest
+
+import scripts.research.scoring_research_lib as lib
+
+ROOT = Path(__file__).resolve().parents[1]
+HOLDOUT_V4 = ROOT / "references" / "real_case_calibration" / "minute_rectification_holdout_v4.json"
+
+
+def test_estimate_lr_rewards_discriminating_feature_and_leaves_noise_near_zero() -> None:
+    examples = []
+    for _ in range(20):
+        examples.append(({"good": 1.0, "noise": 1.0}, True))
+        examples.append(({"good": 1.0, "noise": 0.0}, True))
+    for _ in range(80):
+        examples.append(({"noise": 1.0}, False))
+        examples.append(({"noise": 0.0}, False))
+    table = lib.estimate_lr(examples, alpha=1.0)
+    assert table.positives == 40 and table.negatives == 160
+    assert table.present["good"] > 1.5
+    assert table.absent["good"] < -1.5
+    assert abs(table.present["noise"]) < 0.05
+    # reward-only policy clips the negative absent term; naive-Bayes keeps it
+    assert table.weight("good", allow_negative=False) == (table.present["good"], 0.0)
+    assert table.weight("good", allow_negative=True) == (table.present["good"], table.absent["good"])
+
+
+def test_loo_folds_never_contain_the_held_out_case() -> None:
+    folds = lib.loo_folds(["a", "b", "c"])
+    assert [held for held, _ in folds] == ["a", "b", "c"]
+    for held, training in folds:
+        assert held not in training and len(training) == 2
+
+
+def test_event_feature_matrix_is_the_fraction_of_sample_dates() -> None:
+    store = lib.FeatureStore()
+    store.put("e1", "1990-01-15", "10:00", ["vim_md_domain_house", "event_kind:career"], ["pranapada_in_target_house"])
+    store.put("e1", "1990-02-15", "10:00", ["vim_ad_domain_lord"], [])
+    store.put("e1", "1990-01-15", "10:02", ["no_domain_activation"], [])
+    store.put("e1", "1990-02-15", "10:02", ["no_domain_activation"], [])
+    matrix = lib.event_feature_matrix(store, "e1", ["10:00", "10:02"], include_extras=True)
+    assert matrix["10:00"] == {"vim_md_domain_house": 0.5, "vim_ad_domain_lord": 0.5, "pranapada_in_target_house": 0.5}
+    assert matrix["10:02"] == {}
+    without = lib.event_feature_matrix(store, "e1", ["10:00"], include_extras=False)
+    assert "pranapada_in_target_house" not in without["10:00"]
+
+
+def test_scoring_rule_filter_drops_event_kind_and_constant_rules() -> None:
+    assert lib.is_scoring_rule("vim_md_domain_varga")
+    assert lib.is_scoring_rule("controlled_transit_jupiter_domain_house")
+    assert not lib.is_scoring_rule("event_kind:career")
+    assert not lib.is_scoring_rule("event_kind_profile:career:change")
+    assert not lib.is_scoring_rule("no_domain_activation")
+    assert not lib.is_scoring_rule("occupation_auxiliary_not_primary")
+    assert not lib.is_scoring_rule("kp_asc_sublord_is_vim_md")  # extras are a separate namespace
+    assert lib.is_extra_feature("vim_md_domain_varga_d60")
+
+
+def test_weighted_provider_scores_each_sample_from_the_store() -> None:
+    store = lib.FeatureStore()
+    store.put("e1", "1990-01-15", "10:00", ["vim_md_domain_house"], ["kp_asc_sublord_is_vim_md"])
+    store.put("e1", "1990-01-15", "10:02", [], [])
+    table = lib.LRTable(
+        alpha=1.0, positives=1, negatives=1,
+        present={"vim_md_domain_house": 1.0, "kp_asc_sublord_is_vim_md": 0.5},
+        absent={"vim_md_domain_house": -0.25, "kp_asc_sublord_is_vim_md": -0.1},
+        support={},
+    )
+    request = {"events": [{"id": "e1", "date": "1990-01-15", "domain": "career"}]}
+    a1 = lib.make_weighted_provider(store, table, variant="A1")(request)
+    a2 = lib.make_weighted_provider(store, table, variant="A2")(request)
+    a3 = lib.make_weighted_provider(store, table, variant="A3", scale=2.0)(request)
+    assert [(r["time"], r["score"]) for r in a1] == [("10:00", 1.0), ("10:02", 0.0)]
+    assert [(r["time"], r["score"]) for r in a2] == [("10:00", 1.5), ("10:02", 0.0)]
+    assert [(r["time"], r["score"]) for r in a3] == [("10:00", 3.0), ("10:02", -0.7)]
+    assert a1[0]["evidence"][0]["rule_ids"] == ["vim_md_domain_house"]
+
+
+def _probe() -> dict:
+    return {"expected_outcomes": [
+        {"answer_class": "yes", "supports": ["10:00"], "conflicts": ["10:04"]},
+        {"answer_class": "no", "supports": ["10:04"], "conflicts": ["10:00"]},
+    ]}
+
+
+def test_scaled_answer_halves_the_delta_and_never_counts_a_conflict() -> None:
+    scores = {"10:00": 10.0, "10:02": 10.0, "10:04": 10.0}
+    conflicts = {time: 0 for time in scores}
+    weak, weak_conflicts, weak_elim = lib.apply_scaled_answer(scores, conflicts, set(), _probe(), "no", list(scores), 0.5)
+    assert weak == {"10:00": 9.0, "10:02": 10.0, "10:04": 11.0}
+    assert weak_conflicts == conflicts and weak_elim == set()
+    full, full_conflicts, _ = lib.apply_scaled_answer(scores, conflicts, set(), _probe(), "no", list(scores), 1.0)
+    assert full == {"10:00": 8.0, "10:02": 10.0, "10:04": 12.0}
+    assert full_conflicts["10:00"] == 1
+
+
+def test_absent_years_are_gaps_strictly_inside_each_domain_span() -> None:
+    events = [
+        {"domain": "career", "date": "2017-05-01", "precision": "day"},
+        {"domain": "career", "date": "2019", "precision": "year"},
+        {"domain": "career", "date": "2025-02", "precision": "month"},
+        {"domain": "relocation", "date": "2000", "precision": "year"},
+    ]
+    assert lib.absent_years(events) == {"career": [2018, 2020, 2021, 2022, 2023, 2024]}
+
+
+def test_degrade_and_upgrade_precision_helpers() -> None:
+    events = [{"id": "a", "domain": "career", "date": "2017-05-20", "precision": "day"},
+              {"id": "b", "domain": "career", "date": "2019", "precision": "year"}]
+    spoken = lib.degrade_to_year(events)
+    assert spoken[0]["precision"] == "year" and spoken[0]["date"] == "2017"
+    assert spoken[1] == events[1]
+    upgraded = lib.upgrade_to_month(spoken, {"a"}, {e["id"]: e for e in events})
+    assert upgraded[0]["precision"] == "month" and upgraded[0]["date"] == "2017-05"
+    shifted = lib.shift_day_events_by_months(events, seed="fictional")
+    assert shifted[0]["shift_months"] in {-3, -2, -1, 1, 2, 3}
+    assert shifted[1] == events[1]
+    assert lib.drop_events(events, 1, seed="x") != events and len(lib.drop_events(events, 1, seed="x")) == 1
+
+
+def test_softmax_and_proportional_percent_sum_to_about_one_hundred() -> None:
+    scores = {"10:00": 12.0, "10:02": 11.0, "10:04": 9.0}
+    assert abs(sum(lib.percent_proportional(scores).values()) - 100) <= 2
+    soft = lib.percent_softmax(scores)
+    assert abs(sum(soft.values()) - 100) <= 2 and soft["10:00"] > soft["10:02"] > soft["10:04"]
+    assert lib.calibration_bins([(0.9, True), (0.02, False)])[-1]["observed_rate"] == 1.0
+
+
+@pytest.mark.skipif(not HOLDOUT_V4.exists(), reason="v4 open set not present")
+def test_recording_scorer_reconciles_with_production_on_a_public_case() -> None:
+    from scripts.active_rectification_event_engine import compute_candidate_static_contexts
+    from scripts.rectification.scoring_service import build_event_contribution_matrix, score_from_matrix
+    from scripts.research.minute_resolution_sweep import scoring_request_for
+
+    case = json.loads(HOLDOUT_V4.read_text(encoding="utf-8"))["cases"][0]
+    request = scoring_request_for({**case, "candidate_radius_minutes": 10}, 10)
+    contexts = compute_candidate_static_contexts(request)
+    production = score_from_matrix(request, build_event_contribution_matrix(request, static_contexts=contexts))
+    store = lib.FeatureStore()
+    built = build_event_contribution_matrix(
+        request, row_provider=lib.make_recording_provider(contexts, store, lib.d60_charts(contexts)), static_contexts=contexts,
+    )
+    research = score_from_matrix(request, built)
+    outcome = lib.reconcile_rows(production, research)
+    assert outcome["changed"] == 0, outcome
+    assert outcome["candidates"] == len(contexts) == 11
+    # extras were recorded alongside the production rules
+    recorded = {name for cells in store.rows.values() for cell in cells.values() for name in cell["extras"]}
+    assert any(name.startswith("kp_") for name in recorded) or any(name.endswith("_in_target_house") for name in recorded)