Work

Pseudo-Rank Leakage: How Inhomogeneous Physical Conservation Laws and Row-Wise Nonlinear Scaling Break Standard SVD Least Squares in Chemical Machine Learning

Year: 2026
Type: preprint
Abstract: Mathematical proof and reproducible empirical benchmark identifying Pseudo-Rank Leakage: a numerical failure mode in chemical and physics-informed machine learning where an inhomogeneous linear conservation law (such as the Euler valency-cycle identity) interacts with smooth row-wise nonlinear scaling to bend an exact zero singular value into an unpruned intermediate mode, triggering catastrophic cross-validation variance explosion under standard SVD solvers across public EPA OPERA datasets.
Source: Figshare
Author: Shoji Fujita
Language: English
Open Access status: green
OpenAlex ID: W7236625626
Cites:
Cited by:
Related to: 10