faeval.git/report_explore/MEMO_6_exploitability.md, branch master Unnamed repository; edit this file 'description' to name the repository. Add Phase 6: snapshot exploitability reveals local update rule is the bottleneck 2026-03-25T01:07:03+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-03-25T01:07:03+00:00 825d973428450cb24d8cccc8c2604235ef974b7c Phase 6A: Better credit is ANTI-CORRELATED with loss decrease on fixed snapshot. DFA (Gamma=0.01) → dL=-0.0001 (only method that decreases loss) Vec_M4 (Gamma=0.38) → dL=+0.057 (increases loss most) Oracle BP (Gamma=1.0) → dL=+0.011 (still increases loss) Phase 6C: Target-shift rule reduces damage but cannot make non-DFA credits productive. The inner-product surrogate <F_l(h), a_l> is fundamentally mismatched with directional credit. Conclusion: Case B — the primary bottleneck is the local update paradigm itself, not the credit estimator quality or tracking/co-adaptation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
Phase 6A: Better credit is ANTI-CORRELATED with loss decrease on fixed snapshot.
  DFA (Gamma=0.01) → dL=-0.0001 (only method that decreases loss)
  Vec_M4 (Gamma=0.38) → dL=+0.057 (increases loss most)
  Oracle BP (Gamma=1.0) → dL=+0.011 (still increases loss)

Phase 6C: Target-shift rule reduces damage but cannot make non-DFA credits productive.
  The inner-product surrogate <F_l(h), a_l> is fundamentally mismatched with directional credit.

Conclusion: Case B — the primary bottleneck is the local update paradigm itself,
not the credit estimator quality or tracking/co-adaptation.

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