faeval.git/results/fa_dfa_d256_L8_seed4/results_cifar10.json, branch master Unnamed repository; edit this file 'description' to name the repository. d=256 deep scan: FA+DFA at L=8 and L=12 (5 seeds each) 2026-04-26T20:05:13+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-26T20:05:13+00:00 c4bd8d321b3cb2e77a6727ecfc2c2ae999065c4a FA does NOT drop below frozen 0.349 at deeper L on d=256: L=8: FA mean 0.394, min 0.386 (gap +3.7pp) L=12: FA mean 0.391, min 0.368 (gap +1.9pp) FA accuracy is essentially depth-invariant (~0.39) even though FA deep cosine drops from +0.13 (L=8) to +0.09 (L=12). DFA is always below frozen (~0.27-0.30). Conclusion: on CIFAR-10 with d=256 ResMLP, FA is too good at L≥4 to fail the frozen baseline. The only qualifying setting at deeper L would require ~20+ seeds to find a rare 2σ outlier. The d=512 L=2 setting (seeds 1,2,5) remains the cleanest qualifying case. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
FA does NOT drop below frozen 0.349 at deeper L on d=256:
  L=8:  FA mean 0.394, min 0.386 (gap +3.7pp)
  L=12: FA mean 0.391, min 0.368 (gap +1.9pp)

FA accuracy is essentially depth-invariant (~0.39) even though FA
deep cosine drops from +0.13 (L=8) to +0.09 (L=12). DFA is always
below frozen (~0.27-0.30).

Conclusion: on CIFAR-10 with d=256 ResMLP, FA is too good at L≥4
to fail the frozen baseline. The only qualifying setting at deeper L
would require ~20+ seeds to find a rare 2σ outlier. The d=512 L=2
setting (seeds 1,2,5) remains the cleanest qualifying case.

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