diff options
| -rw-r--r-- | COLLABORATOR_ONBOARDING.md | 12 | ||||
| -rw-r--r-- | README.md | 9 |
2 files changed, 18 insertions, 3 deletions
diff --git a/COLLABORATOR_ONBOARDING.md b/COLLABORATOR_ONBOARDING.md index 724ae0e..79b1091 100644 --- a/COLLABORATOR_ONBOARDING.md +++ b/COLLABORATOR_ONBOARDING.md @@ -26,6 +26,13 @@ Family-specific semantics and schedules are frozen in [`RESNET_CROSSOVER.md`](RESNET_CROSSOVER.md), and [`TRANSFORMER_CROSSOVER.md`](TRANSFORMER_CROSSOVER.md). +After accepting the private-repository invitation: + +```bash +git clone https://github.com/YurenHao0426/sdil.git +cd sdil +``` + ## What SDIL is SDIL tests a narrow algorithmic reading of the Harnett et al. result: the @@ -66,6 +73,11 @@ below are best validation accuracy; parenthesized values are measured GTX-1080 wall hours. Nonfinite cells remain in the table at their last finite metric. +The audited visual summary is available as +[`figure7_plain_cnn_pareto.png`](results/figs/figure7_plain_cnn_pareto.png) +and a vector +[`PDF`](results/figs/figure7_plain_cnn_pareto.pdf). + | method | miniCNN | VGGlike | VGG16 | |---|---:|---:|---:| | BP | 83.62 (0.08) | 90.52 (0.28) | 92.68 (0.71) | @@ -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 |