feat(harness): add Action Recognition training experiment

- PerCategoryPoolStrategy: filter test pool by task_types
- RunConfig: add run_holdout_eval toggle (default true)
- load_config: fix YAML task_types list-to-tuple conversion
- Runner: conditionally skip _holdout_four_way when disabled
- CLI: add --no-run-holdout-eval flag
- New config/train_action_recognition.yaml (3 epochs, per_category)
- New scripts/train_action_recognition.sh (baseline + seed + train)

config/train_action_recognition.yaml

@@ -0,0 +1,63 @@
+# config/train_action_recognition.yaml
+# Action Recognition 单题型首次训练实验
+# 设计文档: research-wiki/designs/2026-07-14-action-recognition-training-design.md
+
+harness:
+  workspace_dir: "workspaces/train-action-recognition"
+  store_dir: store
+  mode: train
+  run_id: train_ar_v1
+  concurrency: 24
+  max_steps: 40
+  skill_mode: auto
+  n_samples: 0
+  questions: "generated-v2-360"
+  skills_version: v1
+  prompts_version: v1
+  epochs: 3
+  # CE-Gate 参数（沿用 default.yaml）
+  gate_e_confirm: 20.0
+  gate_e_provisional: 3.0
+  gate_w_net_min: 2
+  gate_delta_min: 0.02
+  gate_lambda_dir: -0.642
+  gate_e_rollback: 10.0
+  gate_block: 8
+  gate_n_max: 40
+  gate_p_low: 0.05
+  gate_p_high: 0.95
+  gate_probe_quota: 0.2
+  gate_gamma_decay: 0.9
+  gate_cooldown_steps: 2
+  gate_guard_err: 0.10
+  # 进化参数
+  edit_budget_start: 5
+  edit_budget_end: 2
+  skill_update_mode: patch
+  appendix_consolidate_threshold: 6
+  # 池配置 — per_category 单题型
+  pool_split_mode: per_category
+  task_types:
+    - "Action Recognition"
+  train_ratio: 0.667
+  test_questions: "benchmarks/Video-MME"
+  run_holdout_eval: false
+  # mini-batch
+  batch_size: 10
+  min_class_per_batch: 2
+  batch_correct_ratio: 0.5
+  momentum_samples: 20
+  eval_min_per_class: 2
+  early_stop_patience: 4
+  test_size: 63
+  diag_size: 20
+  diag_correct_ratio: 0.5
+  val_size: 10
+  val_correct_ratio: 0.5
+  use_slow_momentum: true
+
+embed:
+  backend: "local"
+  model_name: "BAAI/bge-base-zh-v1.5"
+  embed_dim: 768
+  device: "cuda"