AI RESEARCH

Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization

arXiv CS.AI

ArXi:2603.28040v1 Announce Type: cross is non-deterministic: identical code with different random seeds produces models that agree on aggregate metrics but disagree on individual predictions, with per-class AUC swings exceeding 20%age points on rare clinical classes. We present a framework for verified bit-identical