fix(m5): eval pipeline — anomaly_regions schema + nested JSON + pure-LLM baseline

Critical eval-pipeline bugs found while running the stage-2 model:

1. parse_anomaly_segments only recognized {"segments\:[[s,e]]}; the training
   data (data/instruct.py) emits {"anomaly_regions":[{"start","end"}]}.
   The model learned the correct format but scored 0 → VUS-PR=0. Now accepts
   both schemas + a balanced-brace JSON scanner (the flat regex could not
   match nested objects the model emits).
2. qa_judge._extract_json had the same nesting bug — reuse the scanner.
3. Generation truncated at 64-96 tokens (too short for stats JSON) → bumped
   to 192 in report + instruct_check.

Report enhancements:
- wire the pure-LLM baseline (series-as-text, no TS modality) so design §5.4
  'model vs pure LLM' is actually computed. Heavy predictors built/evaluated
  one at a time with GPU cleanup (single 12GB card).
- add QA-judge table across all 6 categories (design §6.5 问答均分).
- add --pure_llm / --max_per_cat flags.

Results (reports/eval-2026-06-30.md): model QA-judge mean 2.45 vs pure_llm
0.88 (2.8x); anomaly localization (VUS-PR) is the weak point — neither
model nor pure_llm localize well; TS-modality ablation change_rate 0.98.

src/tsmm/eval/qa_judge.py

@@ -16,7 +16,7 @@ import json
 import re
 from typing import Any, Callable, Dict, List, Optional, Tuple
 
-from .parse_answer import parse_anomaly_segments
+from .parse_answer import _extract_balanced_json, parse_anomaly_segments
 
 
 _JSON_RE = re.compile(r"\{[^{}]*\}", re.DOTALL)
@@ -25,6 +25,15 @@ _JSON_RE = re.compile(r"\{[^{}]*\}", re.DOTALL)
 def _extract_json(pred: str) -> Optional[dict]:
     if pred is None:
         return None
+    # prefer balanced (nested-capable) extraction first
+    for blob in _extract_balanced_json(pred):
+        try:
+            obj = json.loads(blob)
+            if isinstance(obj, dict):
+                return obj
+        except json.JSONDecodeError:
+            continue
+    # fallback to flat blobs
     for blob in _JSON_RE.findall(pred):
         try:
             return json.loads(blob)