diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-23 07:09:14 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-23 07:09:14 -0500 |
| commit | 2a6f72e22a814fb4093174a2fb1ca2af56c7e63c (patch) | |
| tree | a3eafc8edeac3cae44de2c0da96ae2db2f075688 /README.md | |
| parent | c8bfa25f597dc2760855b3f71a59549753c9e4a2 (diff) | |
figures: add audited ResNet confirmation panel
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 21 |
1 files changed, 12 insertions, 9 deletions
@@ -125,12 +125,14 @@ and the oral-A depth panel stays sealed. - `ORAL_A_V3.md`: frozen vectorizer-space causal-calibration funnel; - `REVIEW_SCORECARD.md`: adversarial ICLR-style score trajectory; - `results/figs/`: deterministic PDF/PNG main figures, captions, and a source - hash manifest, plus audited RRM failure and dynamic-stability supplements. + hash manifest, including the untouched D4 ResNet-20 confirmation, plus + audited RRM failure and dynamic-stability supplements. -The three current main figures show the local-method Pareto frontier, credit -assignment versus depth, and the load-bearing innovation ablation. Every final -cell has exactly seeds 0--4 and clean git provenance; the strict renderer -refuses missing or protocol-mixed cells. +The current main figures show the local-method Pareto frontier, credit +assignment versus depth, the load-bearing innovation ablation, and the +untouched standard-ResNet confirmation. The first three require exactly seeds +0--4; the ResNet panel requires paired test seeds 10--14. Both strict renderers +refuse missing, dirty, protocol-mixed, or gate-inconsistent cells. ## Verification @@ -138,12 +140,13 @@ The lab environment currently used for audited CPU checks is `/home/yurenh2/miniconda3/envs/ep_pascal`. Run: ```bash -experiments/finalize_claims.sh +experiments/finalize_accept.sh ``` -This regenerates the figures and manifest, enforces the frozen Pareto/scaling -gates, verifies baseline and protocol mechanics, checks the local-rule smoke -tests, evaluates the theory identities, and rebuilds the audited tables. +This regenerates all publication-facing figures and manifests, enforces the +frozen Pareto/scaling and D4 confirmation gates, verifies baseline and protocol +mechanics, checks the local-rule smoke tests, evaluates the theory identities, +re-audits completed oral-B outcomes, and rebuilds the audited tables. The convolutional infrastructure can be checked independently: |