faeval.git/results/confirmatory/clean_grads/dfa_s42.json, branch master Unnamed repository; edit this file 'description' to name the repository. Add clean gradient check: independent Python process per method, GPU 1 2026-04-01T17:56:24+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-01T17:56:24+00:00 d5326053a2e9ce37dd61606aa37fa8f563481f44 Clean results (each method in fresh Python process): BP: mean_norm=2.58e-04, s(1e-6)=98% — CONFIRMED DFA: layer 0 = 2.86e-07 (1.2%), layers 1-3 ≈ 2.4e-09 (0%) SB: layer 0 = 6.13e-06 (86%), layers 1-3 ≈ 1e-09 (0%) CB: layer 0 = 6.33e-07 (18%), layers 1-3 ≈ 5e-10 (0%) Method A (autograd.grad) and Method B (retain_grad) give identical results. Previous 1e-12 results were caused by Python process state pollution in combined scripts. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
Clean results (each method in fresh Python process):
BP: mean_norm=2.58e-04, s(1e-6)=98% — CONFIRMED
DFA: layer 0 = 2.86e-07 (1.2%), layers 1-3 ≈ 2.4e-09 (0%)
SB: layer 0 = 6.13e-06 (86%), layers 1-3 ≈ 1e-09 (0%)
CB: layer 0 = 6.33e-07 (18%), layers 1-3 ≈ 5e-10 (0%)

Method A (autograd.grad) and Method B (retain_grad) give identical results.
Previous 1e-12 results were caused by Python process state pollution in combined scripts.

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