faeval.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
2026-04-01	Add BP support sparsity analysis: threshold sweep + gradient histograms	YurenHao0426
	A1 Synthetic: all methods have >93% support at τ=1e-6 (gradients rarely zero) A2 CIFAR: massive gap — BP 98.4% vs DFA 0.4% vs SB 21% vs CB 3% DFA-trained CIFAR networks have near-zero BP gradients for 99.6% of samples This explains why Gamma is unreliable for CIFAR non-BP methods Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>