diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 06:25:06 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 06:25:06 -0500 |
| commit | 94fc8471c515fb0baacc0aa79d4a47f539858e57 (patch) | |
| tree | 39236544cef50f50559669a4bbf5bebd231c1b2e /ORAL_A.md | |
| parent | 931273085034d48db5d93b71669ba9bc30b8bc4d (diff) | |
experiments: freeze oral A confirmation gates
Diffstat (limited to 'ORAL_A.md')
| -rw-r--r-- | ORAL_A.md | 4 |
1 files changed, 3 insertions, 1 deletions
@@ -118,7 +118,9 @@ No recovery branch follows an A3 failure. Only after A3 passes, run exact BP, selected DFA, and selected SDIL at depths 20, 32, and 56 for model/data-loader seeds 10--14. Hyperparameters and epoch -budgets are copied without depth-specific tuning. The CIFAR-10 test set is +budgets are copied without depth-specific tuning. Confirmation refits on all +50,000 original training examples (`val_examples=0`) after development has +closed. The CIFAR-10 test set is evaluated exactly once at the end of every run; no intermediate test metric is logged or used for selection. |
