facap.git/notes/38_mnist_real_data_validation.md, branch main Unnamed repository; edit this file 'description' to name the repository. Add MNIST real-data validation of e0 theorem and estimator 2026-06-09T20:28:30+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-06-09T20:28:30+00:00 b246cc878c3db48e6d993a6a293176ee9be97e77 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> 
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>