physics.chem-phNov 16, 2026

Out-of-training properties in frozen interatomic potential embeddings are decodable and ordered by physical scale

Authors: Natalija Stepurko, Joonatan E. M. Laulainen

Organizations: Altrove, 25 rue de Ponthieu, 75008 Paris, France

Abstract

Machine-learned interatomic potentials (MLIPs) are trained on energies, forces and stresses, yet their frozen representations can predict other materials properties. We probe ORB-v3 and UMA-S across layers, read-outs and equivariant channels for nine properties of 154,875 Materials Project crystals. Both models outperform composition-only descriptors on all targets, including five outside their training objectives; errors in physical units help assess potential screening applications. Optimal depth varies by property, consistent with a physical-scale ordering. Random-weight controls reveal strongly property-dependent benefits of pretraining. UMA-S's rotation-invariant angular channels improve crystal-system classification, while higher scores from its full tensor disappear under rotation; matched-model controls do not isolate equivariance as the explanation. Accuracy varies across different probes, but nearest-neighbour prediction often approaches XGBoost performance, even though materials do not form distinct clusters according to their properties. We also test whether a linear predictor trained on one model's embeddings can predict properties using the other model's embeddings after a learned linear transformation. Predictive accuracy is largely preserved, despite differences in which atoms the two models place close together. These results guide the reuse of frozen MLIP representations for materials prediction.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interatomic Potentials

    Mar 2, 2026Yuanchang Zhou, Siyu Hu, Xiangyu Zhang +3Machine Learning Interatomic PotentialsComputational Materials Science

  2. Knowing when to trust machine-learned interatomic potentials

    May 1, 2026Shams Mehdi, Ilkwon Cho, Olexandr IsayevMachine Learning Interatomic PotentialsSelective Prediction