diff options
Diffstat (limited to 'PAPER_PLAN.md')
| -rw-r--r-- | PAPER_PLAN.md | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/PAPER_PLAN.md b/PAPER_PLAN.md index 483630f..cc556d6 100644 --- a/PAPER_PLAN.md +++ b/PAPER_PLAN.md @@ -79,6 +79,10 @@ not imply that no-traffic scaling establishes the necessity of residualization. ResNet-20 versus BP's `91.62%`, but it is one seed. Do not promote this to a robustness or depth-scaling claim until the already frozen paired five-seed D4 confirmation and a separate depth panel pass. + The separate dynamic-depth recovery in `ORAL_A_RECOVERY.md` is the only + permitted depth panel: after oral-B passes, it reuses D4's ResNet-20 cells + and adds BP/DFA/clean-KP/dynamic ResNet-32/56 comparisons under a frozen + positive-depth-benefit and cost gate. ## Figure order in the manuscript @@ -187,6 +191,11 @@ can plausibly claim a rare local-learning method that retains performance and alignment with standard depth under an audited cost budget. Reviewer score should be reassessed from the frozen confirmation only. +The original A3/A4 branch is permanently failed, so this paragraph can now +apply only to the separately frozen dynamic-depth recovery. Its full 60-cell +pass is required before a standard-depth abstract/title claim or a 9/10 score; +D4 alone remains a single-architecture robustness result. + ### If A3 or A4 fails Do not soften the threshold or replace the seed panel. Keep a mechanism paper: |