From 2a6f72e22a814fb4093174a2fb1ca2af56c7e63c Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Thu, 23 Jul 2026 07:09:14 -0500 Subject: figures: add audited ResNet confirmation panel --- RESULTS.md | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'RESULTS.md') diff --git a/RESULTS.md b/RESULTS.md index c511d1e..16c7293 100644 --- a/RESULTS.md +++ b/RESULTS.md @@ -1085,6 +1085,11 @@ checks. D4 therefore raises the strict reviewer score from 6 to 7 and establishes the accept bar. It is a ResNet-20 robustness/noninferiority result, not evidence of positive utility from ResNet-20 to ResNet-56 and not evidence for the previously failed desired-velocity or online-control interpretation. +`results/figs/figure4_resnet_confirmation.{pdf,png}` renders the paired +endpoint, layerwise raw-versus-innovation direction, reciprocal-credit +trajectory, and resource audit directly from these ten records. Its strict +source-hash manifest refuses an incomplete seed set, failed D4 check, dirty +provenance, protocol drift, or disagreement between the gate and records. ## How to run `experiments/run.py --mode {bp,fa,dfa,sdil} --dataset {mnist,fmnist,cifar10} --depth D --residual {0,1} --act {tanh,gelu,silu,relu}` @@ -1097,9 +1102,11 @@ canonical d2 comparison: `experiments/ep_depth2_sweep.sh`; near-parameter compar C2 direct causal diagnosis: `experiments/c2_nodepert_validation.sh` followed by `python experiments/analyze_c2_nodepert_validation.py`. Theory checks: `python experiments/verify_theory.py`. -Audited aggregate tables: `experiments/analyze_verified.py`. The claim-locked finalizer is -`experiments/finalize_claims.sh`; it rejects missing/dirty inputs, regenerates both main figures, -their captions, source-hash manifest, and `results/audited_tables.md`, then runs all smoke checks. +Audited aggregate tables: `experiments/analyze_verified.py`. The complete +accept-bar finalizer is `experiments/finalize_accept.sh`; it rejects +missing/dirty or gate-inconsistent inputs, regenerates the four main figures, +their captions and source-hash manifests, rebuilds +`results/audited_tables.md`, and runs all smoke and completed-gate audits. ## Open items @@ -1108,8 +1115,10 @@ their captions, source-hash manifest, and `results/audited_tables.md`, then runs SDIL. - Compare simultaneous calibration at fixed loss-evaluation budgets and sweep directions (4/8/16/32). -- Validate SDIL on a genuinely depth-necessary compositional task and a CNN; flattened CIFAR does - not gain accuracy with depth. +- A genuinely depth-necessary standard-network comparison remains absent. The + frozen ResNet-20/32/56 route is sealed by the failed oral-B prerequisite; any + replacement would require a new, independently preregistered mechanism + branch rather than reusing the untouched panel. - Diagnose why residual FA has high directional cosine but lower accuracy: log update-norm ratios, parameter-space cosine, and serial feedback latency/cost. - Reproduce the d2 EP basin sensitivity in the original Theano revision and/or a strong modern EP -- cgit v1.2.3