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)

main.py

@@ -203,6 +203,11 @@ def _build_parser() -> argparse.ArgumentParser:
     )
     parser.add_argument("--train-ratio", type=float, dest="train_ratio")
     parser.add_argument("--test-questions", type=str, dest="test_questions")
+    parser.add_argument(
+        "--no-run-holdout-eval",
+        action="store_true",
+        dest="no_run_holdout_eval",
+    )
     return parser
 
 
@@ -267,6 +272,9 @@ def main() -> None:
     if cli_args.get("task_types") is not None:
         cli_args["task_types"] = tuple(cli_args["task_types"])
     cli_overrides = {k: v for k, v in cli_args.items() if k != "config"}
+    if cli_overrides.get("no_run_holdout_eval"):
+        cli_overrides["run_holdout_eval"] = False
+    cli_overrides.pop("no_run_holdout_eval", None)
     config = load_config(args.config, cli_overrides)
     logger.info("配置加载完成: mode={}, workspace={}", config.mode, config.workspace_dir)