Record the first cap48 hybrid score while the larger run continues

Persist the newly finished cap48 hybrid result so the next session can continue the 48-track validation run from measured evidence instead of only a runtime checkpoint.

Constraint: cap48 high_energy and the final report are still pending
Rejected: Wait for the full cap48 report before updating docs | Would leave the largest current real-data checkpoint stale across sessions
Confidence: high
Scope-risk: narrow
Directive: Replace the cap48 partial section with the final two-strategy ranking once high_energy eval and report.json land
Tested: Verified /tmp/ab_smoke_seg_cap48_top2/hybrid/fma_reports_smoke/eval.json; verified docs record hybrid=24/0.7917/1.0 and high_energy still in build-index
Not-tested: Final cap48 comparison because high_energy has not finished yet

@@ -14,10 +14,12 @@
 
 当前 fresh evidence：
 - `scripts/ab_smoke_segmentation.py ... --work-root /tmp/ab_smoke_seg_cap48_top2` 已启动
-- 当前 first lane 为：
-  - `hybrid`
-- 当前已进入：
-  - `evaluate.py --data /tmp/ab_smoke_seg_cap48_top2/hybrid/fma/manifests ... --max-queries 24`
+- `hybrid` 已完成首条评测：
+  - `num_queries = 24`
+  - `top1 = 0.7917`
+  - `topk = 1.0`
+- `high_energy` 已进入：
+  - `run_demo.py build-index --resume --checkpoint-every-refs 100`
 - `report.json` 尚未落盘
 
 结论：

@@ -485,8 +485,8 @@ cd /workspace/acr-engine
 |---|---|
 | `subset_size` | `48` |
 | `max_test_queries` | `24` |
-| 首个运行策略 | `hybrid` |
-| 当前阶段 | `evaluate.py --max-queries 24` |
+| `hybrid` | `num_queries=24`, `top1=0.7917`, `topk=1.0` |
+| `high_energy` | `run_demo.py build-index --resume --checkpoint-every-refs 100` |
 | `report.json` | 尚未生成 |
 
 恢复检查命令：
@@ -496,7 +496,7 @@ pgrep -af 'ab_smoke_seg_cap48_top2|external_adapters.py smoke-local fma /tmp/ab_
 ```
 
 优先等待文件：
-- `/tmp/ab_smoke_seg_cap48_top2/hybrid/fma_reports_smoke/eval.json`
+- `/tmp/ab_smoke_seg_cap48_top2/high_energy/fma_reports_smoke/eval.json`
 - `/tmp/ab_smoke_seg_cap48_top2/report.json`
 - `b766c74` Make open-dataset manifests trainable end to end
 - `fa23144` Add a single-page open dataset workflow for training prep