Preserve proof that cap64 hybrid advanced into evaluation before results landed

Constraint: The cap64 run is still incomplete, so only verified hybrid index-complete and evaluation-running evidence can be recorded safely now
Rejected: Wait for hybrid eval.json before checkpointing | Would lose the verified handoff that hybrid indexing finished and evaluate.py is already running
Confidence: high
Scope-risk: narrow
Directive: Keep cap64 high_energy and hybrid checkpoints symmetric so the final comparison can be written from docs alone if needed
Tested: Verified hybrid reference_progress.json shows 64 refs, 657 windows, 192-d embeddings, and complete status; verified active process is evaluate.py on /tmp/ab_smoke_seg_cap64_top2/hybrid/fma/manifests; verified hybrid eval.json and report.json are still absent
Not-tested: Final hybrid cap64 metrics, final report.json, and any cap64 winner conclusion

+## 2026-06-02 cap64 hybrid 索引完成并进入评测 checkpoint
+
+完成项：
+- 已确认 cap64 的 `hybrid` reference index 构建完成。
+- 已确认流程从 `hybrid build-index` 推进到 `hybrid evaluate.py`。
+
+验证证据：
+- `hybrid/fma_index_smoke/reference_progress.json`：
+  - `status=complete`
+  - `refs_done=64`
+  - `windows_done=657`
+  - `embedding_shape=[657, 192]`
+  - `elapsed_sec=107.228`
+- 进程树显示：
+  - `evaluate.py --data /tmp/ab_smoke_seg_cap64_top2/hybrid/fma/manifests ... --seed 42 --max-queries 32`
+- 截至本 checkpoint：
+  - `hybrid eval.json` 尚未生成
+  - 总 `report.json` 尚未生成
+
 ## 2026-06-02 cap64 hybrid 训练完成证据 checkpoint
 ## 2026-06-02 cap64 hybrid 训练完成证据 checkpoint
 
 
 完成项：
 完成项：

@@ -76,3 +76,5 @@ cd /workspace/acr-engine
 - 已补充 cap64 阶段推进：`hybrid` 已完成训练并进入 build-index。
 - 已补充 cap64 阶段推进：`hybrid` 已完成训练并进入 build-index。
 
 
 - 已补充 cap64 新鲜证据：从运行会话确认 `hybrid` 的 `Epoch 1/1` 已完整跑完。
 - 已补充 cap64 新鲜证据：从运行会话确认 `hybrid` 的 `Epoch 1/1` 已完整跑完。
+
+- 已补充 cap64 新鲜证据：`hybrid` reference index 完成（`64 refs / 657 windows / 192-d`）并进入 `evaluate.py`。

@@ -61,5 +61,5 @@ test -f /tmp/ab_smoke_seg_cap48_top2_seed999/report.json && cat /tmp/ab_smoke_se
 
 
 - 新 benchmark：`/tmp/ab_smoke_seg_cap64_top2`
 - 新 benchmark：`/tmp/ab_smoke_seg_cap64_top2`
 - 当前阶段：`high_energy` 已完成评测，结果为 `top1=0.625 / topk=1.0 / num_queries=32`
 - 当前阶段：`high_energy` 已完成评测，结果为 `top1=0.625 / topk=1.0 / num_queries=32`
-- 当前 `hybrid` 训练已完成，现处于 build-index 阶段
+- 当前 `hybrid` 索引已完成，现处于 evaluate 阶段
 - 下一 session 应优先检查 `hybrid` 结果与 `report.json` 是否生成
 - 下一 session 应优先检查 `hybrid` 结果与 `report.json` 是否生成

@@ -676,7 +676,7 @@ seed123 最终结论：
 - 配置：`subset_size=64`, `max_test_queries=32`, `seed=42`
 - 配置：`subset_size=64`, `max_test_queries=32`, `seed=42`
 - 当前最新证据：
 - 当前最新证据：
   - `high_energy` 已完成评测：`num_queries=32, top1=0.625, topk=1.0`
   - `high_energy` 已完成评测：`num_queries=32, top1=0.625, topk=1.0`
-  - 已从运行会话确认 `hybrid` 的 `Epoch 1/1` 完整跑完（`32/32`）
-  - 当前处于 `run_demo.py build-index`
+  - `hybrid` reference index 已完成：`64 refs / 657 windows / 192-d`
+  - `hybrid` 当前已进入 `evaluate.py`
   - 总 `report.json` 尚未生成
   - 总 `report.json` 尚未生成