faeval.git/results/confirmatory/C2_energy_concentration.csv, branch master Unnamed repository; edit this file 'description' to name the repository. Add extended sparsity analysis: A4 per-layer, B1 snapshots, B2 active subset, C1/C2 2026-04-01T14:59:39+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-01T14:59:39+00:00 6315e18de1b8640ddf4a818c767f3fc14cc5001e A4: Per-layer support — DFA/SB/CB layers 1-3 have 0% support at τ=1e-6 Only BP has ~95% support; only SB layer 0 has 53% B1: Snapshot evolution — old snapshot checkpoints have near-zero grads (data issue) B2: Active subset — with τ=1e-6, no active samples for non-BP methods C1: Active vs inactive cosine — only inactive subset exists for non-BP C2: Energy concentration — near-zero for non-BP methods Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
A4: Per-layer support — DFA/SB/CB layers 1-3 have 0% support at τ=1e-6
    Only BP has ~95% support; only SB layer 0 has 53%
B1: Snapshot evolution — old snapshot checkpoints have near-zero grads (data issue)
B2: Active subset — with τ=1e-6, no active samples for non-BP methods
C1: Active vs inactive cosine — only inactive subset exists for non-BP
C2: Energy concentration — near-zero for non-BP methods

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