Add Phase 6.5A: same-batch linesearch REVISES Phase 6A conclusion

Phase 6A's "better credit → worse loss" was a protocol artifact caused by:
1. Credit normalization (inflated DFA, suppressed Vec magnitude ordering)
2. Held-out evaluation (measured generalization failure, not exploitability)
3. Gradient clamping

With strict same-batch evaluation:
- Oracle BP: dL_same = -0.406 (strongest descent)
- Vec_M4: dL_same = -0.135
- ScalarCB: dL_same = -0.025
- DFA: dL_same = -0.003
Same-batch loss decrease is MONOTONIC with credit quality.

But held-out loss INCREASES for all non-DFA methods (Case D: overfitting).
The bottleneck is batch-level generalization, not surrogate exploitability.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

1 files changed, 46 insertions, 1 deletions

diff --git a/NOTE.md b/NOTE.md
index 6242a41..a57fd30 100644
--- a/NOTE.md
+++ b/NOTE.md
@@ -5,7 +5,7 @@
 - **pilot**: Controlled iteration (commits 0b9ebb2, 7baf7ae)
 - **frozen**: Code at commit 0b9ebb2 for all reported results
 
-## Status: PHASE 6 EXPLOITABILITY DISSECTION COMPLETE
+## Status: PHASE 6.5 PROTOCOL AUDIT — PHASE 6A CONCLUSION REVISED
 
 ---
 
@@ -373,3 +373,48 @@ Better credit does NOT lead to better snapshot loss decrease.
 ### Experiment IDs (Phase 6)
 - `snapshot_exploit/`: Phase 6A snapshot exploitability
 - `update_swap/`: Phase 6C local update rule comparison
+
+---
+
+## Phase 6.5: Protocol Audit (REVISES Phase 6A conclusion)
+
+### Phase 6.5A: Same-Batch Linesearch
+
+**CRITICAL REVISION**: Phase 6A's "better credit → worse loss" was a protocol artifact.
+
+Phase 6A used: normalized credit + held-out evaluation + gradient clamping.
+Phase 6.5A uses: raw + norm credit, same-batch + held-out eval, no clamping, eta sweep.
+
+**With same-batch evaluation, better credit DOES produce more loss decrease:**
+
+| Method | Gamma | dL_same (norm, all, best eta) | dL_held |
+|--------|-------|-------------------------------|---------|
+| DFA | 0.01 | -0.003 | +0.004 |
+| ScalarCB | 0.12 | -0.025 | +0.027 |
+| Vec_M4 | 0.38 | **-0.135** | +0.045 |
+| Oracle BP | 1.00 | **-0.406** | +0.094 |
+
+Same-batch loss decrease is MONOTONIC with credit quality.
+But held-out loss INCREASES for all non-DFA methods.
+
+**This is Case D: the local surrogate exploits credit correctly on training data,
+but the update overfits to the batch. Better credit = more effective overfitting.**
+
+### Key confounds identified in Phase 6A:
+1. **Normalization** inflated DFA's weak credits to same magnitude as Vec's
+2. **Held-out evaluation** showed generalization failure, not exploitability failure
+3. **Gradient clamping** distorted the natural credit quality ordering
+
+### Raw vs Norm:
+- Raw credit: tiny updates (BP grad RMS ≈ 0.00004). Vec raw best dL_same=-0.005
+- Norm credit: amplifies to useful magnitude but also amplifies overfitting
+
+### Revised diagnosis:
+The bottleneck is NOT "surrogate can't exploit credit" (Phase 6A was wrong).
+It IS "local surrogate with good credit overfits to mini-batch."
+This suggests: regularization of local updates (larger batches, weight decay,
+gradient noise) could make better credit usable.
+
+### Experiment IDs (Phase 6.5)
+- `exploit_linesearch/`: Phase 6.5A smoke test (Oracle + Vec, last1, raw)
+- `exploit_linesearch_full/`: Phase 6.5A full sweep (all methods, ranges, norm modes)