| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2026-06-09 | Add MNIST real-data validation of e0 theorem and estimator | YurenHao0426 | |
| New script validates both no-fit claims on MNIST-subset MLPs. e0 theorem: 16 configs, hidden share 0.39-0.82, measured E_B[e0] within 0.0001-0.0089 of prediction (512 real-backward draws each). Estimator: 96 trajectories, velocity MAE 0.00196 (3.9% of mean gap), bias -0.0006, beating fixed K(0) everywhere; kernels computed via a layerwise gram identity self-tested against autograd at machine precision. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> | |||
