ProCreations/repro-nonlinear-autoencoder-hidden-structure

A Solvable High-Dimensional Model Where Nonlinear Autoencoders Learn Structure Invisible to PCA While Test Loss Misaligns With Generalization

Five claim-matched executions using the authors' pinned autoencoder and AMP code, exact population-loss quadrature, destructive controls, and two warning-strict byte-identical replays.

Run python reproduce.py --output-dir replay and python validate_evidence.py.