feat: Module C v5/v6 training complete, ablations, SOTA baselines, paper updates

- Module C: BC+PPO training v5/v6 done; eval results in experiments/eval_intervention_v{5,6}.json
- Reward: v5 label-aligned constrained reward (code/src/rl/reward.py)
- Ablations: Module B (history_r, response_only, full) + Module C (wo_category_reward)
- SOTA baselines: WildGuard and ShieldGemma2b eval scripts and results
- Paper: update sections 05–08 (Module B/C description, experiments table, discussion)
- Docs: add record.md (change log), update state.md and exp.md; retire change.md
- Tools: add html-to-ppt utilities and run_shieldgemma2b.sh
- Configs: add ablation YAML configs for Module B and C
- Cleanup: remove stale reference/ PNG screenshots

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

code/configs/intervention_config.yaml

@@ -1,7 +1,6 @@
 detector:
   checkpoint: "checkpoints/detector/best.pt"
-  # Server 2 path — update this when running on server 2
-  model_name: "/root/siton-data-740d234e02d749f08fe5347b0c74c49f/zsy/macbert-large"
+  model_name: "/root/siton-data-2849d4ce327c4ccfb233ce33868fe7fe/zsy/macbert-large"
   hidden_size: 1024
 
 agent: