PROBE recasts MLIP uncertainty quantification as selective classification by training a compact discriminative classifier on frozen per-atom backbone embeddings, yielding a reliability probability that tracks actual error better than ensemble disagreement.
P., Kermode, J.et al.Improved uncertainty quantification for gaussian process regression based interatomic potentials.arXiv preprint arXiv:2206.08744 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Knowing when to trust machine-learned interatomic potentials
PROBE recasts MLIP uncertainty quantification as selective classification by training a compact discriminative classifier on frozen per-atom backbone embeddings, yielding a reliability probability that tracks actual error better than ensemble disagreement.