Checkpoint the second cap48 seed while the rerun is still building

Preserve the second-seed cap48 entry point and current build-index phase so later sessions can validate whether the cap48 reversal was stable or a seed artifact.

Constraint: The second-seed run has not produced scores yet, so only execution-state evidence is available
Rejected: Wait for the seed123 scores before recording anything | Risks losing the multi-seed validation checkpoint if the session ends first
Confidence: high
Scope-risk: narrow
Directive: Replace the seed123 running-state section with measured scores once hybrid eval.json or report.json land
Tested: Verified active cap48 seed123 processes; verified handoff records work-root, seed, subset size, query cap, and current build-index phase
Not-tested: cap48 seed123 strategy scores because the run is still in progress

@@ -2,6 +2,28 @@
 
 ## 2026-06-02
 
+### Stage: 启动 cap48 第二个 seed 复核反转结果
+
+完成项：
+- 启动第二个 seed 的 cap48 top2 benchmark：
+  - `work_root = /tmp/ab_smoke_seg_cap48_top2_seed123`
+  - `subset_size = 48`
+  - `max_test_queries = 24`
+  - `seed = 123`
+  - 策略：`hybrid` vs `high_energy`
+- 更新 [session-handoff.md](./session-handoff.md)
+
+当前 fresh evidence：
+- 第二个 seed 已启动
+- 当前 first lane 为：
+  - `hybrid`
+- 当前已进入：
+  - `run_demo.py build-index --resume --checkpoint-every-refs 100`
+
+结论：
+- 已经从“单轮 cap48 反转”升级为“开始做多 seed 复核”
+- 即使当前 session 结束，新 session 也可直接从 handoff 中的 `cap48_top2_seed123` 入口继续
+
 ### Stage: 收尾 cap48 top2 真实 FMA 对照并发现 high_energy 反超
 
 完成项：

@@ -503,6 +503,46 @@ cap48 top2 最终结论：
   1. 更大 subset（如 64+）
   2. 多 seed 复跑
   3. style-aware bucket benchmark
+
+---
+
+## 13. cap48 top2 第二个 seed（进行中）
+
+为验证 cap48 的“high_energy 反超”是否稳定，已启动第二个 seed：
+
+```bash
+cd /workspace/acr-engine
+/usr/local/miniconda3/bin/python scripts/ab_smoke_segmentation.py \
+  --dataset fma \
+  --input-dir data/raw/fma_small_audio \
+  --work-root /tmp/ab_smoke_seg_cap48_top2_seed123 \
+  --subset-size 48 \
+  --query-duration 8 \
+  --train-epochs 1 \
+  --batch-size 2 \
+  --device cpu \
+  --strategies hybrid high_energy \
+  --max-test-queries 24 \
+  --seed 123 \
+  --output-json /tmp/ab_smoke_seg_cap48_top2_seed123/report.json
+```
+
+当前 fresh evidence：
+
+| 项目 | 状态 |
+|---|---|
+| `subset_size` | `48` |
+| `max_test_queries` | `24` |
+| `seed` | `123` |
+| 首个运行策略 | `hybrid` |
+| 当前阶段 | `run_demo.py build-index --resume --checkpoint-every-refs 100` |
+| `report.json` | 尚未生成 |
+
+恢复检查命令：
+
+```bash
+pgrep -af 'ab_smoke_seg_cap48_top2_seed123|external_adapters.py smoke-local fma /tmp/ab_smoke_seg_cap48_top2_seed123|evaluate.py --data /tmp/ab_smoke_seg_cap48_top2_seed123|run_demo.py build-index --data /tmp/ab_smoke_seg_cap48_top2_seed123|train.py --data /tmp/ab_smoke_seg_cap48_top2_seed123'
+```
 - `b766c74` Make open-dataset manifests trainable end to end
 - `fa23144` Add a single-page open dataset workflow for training prep
 - `af33be3` Condense docs and add manifest validation before training