{"paper":{"title":"Heterogeneous Ensemble Enables a Universal Uncertainty Metric for Atomistic Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Fei Shuang, Kai Liu, Marcel H.F. Sluiter, Poulumi Dey, Wei Gao, Zixiong Wei","submitted_at":"2025-07-28T19:32:25Z","abstract_excerpt":"Universal machine learning interatomic potentials (uMLIPs) are reshaping atomistic simulation as foundation models, delivering near \\textit{ab initio} accuracy at a fraction of the cost. Yet the lack of reliable, general uncertainty quantification limits their safe, wide-scale use. Here we introduce a unified, scalable uncertainty metric \\(U\\) based on a heterogeneous model ensemble with reuse of pretrained uMLIPs. Across chemically and structurally diverse datasets, \\(U\\) shows a strong correlation with the true prediction errors and provides a robust ranking of configuration-level risk. Leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21297","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.21297/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}