diff options
Diffstat (limited to 'RESULTS.md')
| -rw-r--r-- | RESULTS.md | 31 |
1 files changed, 26 insertions, 5 deletions
@@ -1091,6 +1091,28 @@ 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. +The separately authorized oral-A-v2 confirmation subsequently reuses those ten +D4 records verbatim and adds exactly 50 preregistered endpoints. Its complete +60-record, five-seed panel passes every accuracy, paired depth-gain, alignment, +mechanism, query, MAC, memory, provenance, and test-isolation check: + +| depth | BP test acc. | DFA test acc. | clean KP test acc. | dynamic SDIL test acc. | SDIL early alignment | SDIL/BP MACs | +|--:|--:|--:|--:|--:|--:|--:| +| 20 | 91.624% | 31.878% | 91.388% | 91.584% | 0.999687 | 1.326x | +| 32 | 92.302% | 32.684% | 92.332% | 92.254% | 0.999613 | 1.329x | +| 56 | 92.632% | 30.850% | 92.670% | **92.760%** | 0.999423 | 1.331x | + +Dynamic SDIL gains `1.176` accuracy points from ResNet-20 to ResNet-56 on +average, and all five paired seeds improve. Its ResNet-56 advantage over DFA is +`61.910` points, while its mean endpoint differs from BP and clean KP by only +`+0.128` and `+0.090` points. The passed gate establishes positive +standard-depth scaling and raises the internal milestone from 8 to 9. It does +not assign the clean-task gain uniquely to residualization: the inherited clean +KP substrate scales equally well, so SDIL's method-specific evidence remains +its survival under the four-times-RMS mixed-traffic intervention. +`results/figs/figure6_standard_depth_scaling.{pdf,png}` is regenerated from all +60 records and verifies their hashes plus the historical training source. + ## 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}` Batteries: `experiments/run_v2.sh <ds> "<depths>" <res> <act> "<seeds>" <ep> <pfx>`. @@ -1104,7 +1126,7 @@ C2 direct causal diagnosis: `experiments/c2_nodepert_validation.sh` followed by Theory checks: `python experiments/verify_theory.py`. 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, +missing/dirty or gate-inconsistent inputs, regenerates the six main figures, their captions and source-hash manifests, rebuilds `results/audited_tables.md`, and runs all smoke and completed-gate audits. @@ -1115,10 +1137,9 @@ their captions and source-hash manifests, rebuilds SDIL. - Compare simultaneous calibration at fixed loss-evaluation budgets and sweep directions (4/8/16/32). -- 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. +- Complete the registered 81-cell crossover: all nine methods at each of + miniCNN/VGGlike/VGG16, ResNet-20/32/56, and Transformer-4/8/12. No depth, + width, or context extension counts unless all nine method cells are added. - 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 |