diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-30 16:40:15 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-30 16:40:15 -0500 |
| commit | a04c9054cd690c8333baed1c2d757570b60a3c9c (patch) | |
| tree | 87ce4f051c84cf85808e046b449320c944df4d21 /README.md | |
| parent | 901315d2c141d44c716395bc97568268c23b6639 (diff) | |
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 9 |
1 files changed, 6 insertions, 3 deletions
@@ -192,9 +192,12 @@ complete validation-only selectors. The current main figures show the local-method Pareto frontier, credit assignment versus depth, the load-bearing innovation ablation, and the untouched standard-ResNet confirmations, including positive ResNet-20-to-56 -scaling. The first three require exactly seeds 0--4; the ResNet panels require -paired test seeds 10--14. Strict renderers refuse missing, dirty, -protocol-mixed, source-drifted, or gate-inconsistent cells. +scaling. The audited complete Plain-CNN crossover is rendered separately in +`results/figs/figure7_plain_cnn_pareto.{pdf,png}`, with local-only and +BP-inclusive frontiers kept distinct. The first three main figures require +exactly seeds 0--4; the ResNet panels require paired test seeds 10--14. Strict +renderers refuse missing, dirty, protocol-mixed, source-drifted, or +gate-inconsistent cells. ## Verification |
