faeval.git/results/confirmatory/T1_cifar_full_metrics.csv, branch master Unnamed repository; edit this file 'description' to name the repository. Add confirmatory supplement: T1-T4 from checkpoints (no retraining) 2026-04-01T15:54:40+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-01T15:54:40+00:00 ff91444879a7035c88b2c3c48859f36fb560c660 WARNING: All methods (including BP) show near-zero BP hidden gradients (~1e-12-1e-14) when computed via manual forward with detached hidden states. This is inconsistent with the earlier first-priority analysis which showed BP at 2.86e-04. Investigation needed. T1: 40 rows (4 methods × 10 seeds) - full metrics T2: 800 rows (support sparsity, 5 thresholds × 4 methods × 10 seeds × 4 layers) T3: 48 rows (gradient norm distributions, 3 seeds × 4 methods × 4 layers) T4: 100 rows (active-subset Gamma, 5 thresholds × 2 methods × 10 seeds) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
WARNING: All methods (including BP) show near-zero BP hidden gradients (~1e-12-1e-14)
when computed via manual forward with detached hidden states. This is inconsistent with
the earlier first-priority analysis which showed BP at 2.86e-04. Investigation needed.

T1: 40 rows (4 methods × 10 seeds) - full metrics
T2: 800 rows (support sparsity, 5 thresholds × 4 methods × 10 seeds × 4 layers)
T3: 48 rows (gradient norm distributions, 3 seeds × 4 methods × 4 layers)
T4: 100 rows (active-subset Gamma, 5 thresholds × 2 methods × 10 seeds)

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