Local topology hallucinations in universal machine-learned interatomic potentials

Predicting metastable states with universal machine-learned interatomic potentials requires that they preserve the minima and saddles of the reference potential-energy surface. Here we identify local topology hallucination, in which distinct model minima relax into the same reference basin. This failure arises from mode-selective curvature-sign errors shared by MACE, CHGNet and M3GNet. Curvature signs predicted by two of the three models agreed with density-functional calculations in 55 of 57 positive but only 5 of 56 negative cases. In LiGe$_2$S, two MACE minima connected by a verified saddle relaxed into one density-functional basin. Reference relaxation likewise returned nine of ten selected model minima to their reference basins. A directional test with two displaced reference calculations rejected 9 of 12 prospectively tested model instabilities. Model agreement alone therefore cannot establish that predicted minima are distinct metastable states.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.21489
Primary Topic
Machine Learning in Materials Science
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Local topology hallucinations in universal machine-learned interatomic potentials

Xiaoqing Liu, Lei Shen, Yangshuai Wang
arXiv (Cornell University)
Machine Learning in Materials Science
preprint

Local topology hallucinations in universal machine-learned interatomic potentials

Xiaoqing Liu, Lei Shen, Yangshuai Wang
preprint en

Abstract

Predicting metastable states with universal machine-learned interatomic potentials requires that they preserve the minima and saddles of the reference potential-energy surface. Here we identify local topology hallucination, in which distinct model minima relax into the same reference basin. This failure arises from mode-selective curvature-sign errors shared by MACE, CHGNet and M3GNet. Curvature signs predicted by two of the three models agreed with density-functional calculations in 55 of 57 positive but only 5 of 56 negative cases. In LiGe$_2$S, two MACE minima connected by a verified saddle relaxed into one density-functional basin. Reference relaxation likewise returned nine of ten selected model minima to their reference basins. A directional test with two displaced reference calculations rejected 9 of 12 prospectively tested model instabilities. Model agreement alone therefore cannot establish that predicted minima are distinct metastable states.

arXiv (Cornell University)
Machine Learning in Materials Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon