Clarify evaluation scope and proof

README.md

@@ -25,11 +25,18 @@ QLoRA adapter for `google/gemma-4-E4B-it`, trained on filtered benign coding ins
 
 ## Proof
 
-- HumanEval subset: first 8 tasks (ran out of GPU hours)
+- HumanEval subset: first 8 tasks
 - Executable pass count before: 5/8
 - Executable pass count after: 7/8
 - Heuristic score before: 0.7688
 - Heuristic score after: 0.7688
+- Relative executable pass-count increase: 40%
+- Absolute executable pass-rate increase: +25 percentage points
+
+The public executable proof is intentionally small because the Kaggle GPU-hour
+budget was exhausted during training, merge preparation, and upload validation.
+`eval_before_after.csv` contains output previews; executable pass/fail proof is
+recorded in `executable_eval.json`.
 
 Artifacts included:
 
@@ -39,5 +46,6 @@ Artifacts included:
 - `summary.json`
 - `proof_summary.json`
 - `nvidia_smi.txt`
+- `evaluation_scope.json`
 
 This adapter is for benign coding assistance only. It was not trained on malware, phishing, exploit, credential theft, evasion, or destructive automation examples.