כתבה
arXiv cs.AI ·
CrystalJev: חשיבה מהירה ואיטית עם דגמי יסוד אטומיים לגילוי חומרים
CrystalJev: thinking fast and slow with atomistic foundation models for materials discovery
דגמי יסוד אטומיים לגילוי חומרים יכולים לשמש כמחשבים מהירים. הם נבחנו ב-65 דגמי Matbench Discovery והוכיחו עצמם כיעילים.
תקציר מקורי באנגליתarXiv:2610.06985v1 Announce Type: cross Abstract: Atomistic foundation models triage millions of hypothetical materials but are used as slow simulators, their thresholded energies taken at face value. They are better read as fast decision-makers. CrystalJev queries a frozen interatomic potential once per unrelaxed structure and answers typed questions with calibrated probabilities, finite-sample guarantees and a rule for when to think slowly. Across 65 Matbench Discovery models, a 'stable' call is a probability in disguise, explained by a model's errors and the candidate population. Once trained, one forward pass decides nearly as well as a relaxation at a thirtieth of its cost, and a value-of-information theory sends slower computation only where decisions can change. The same layer answe
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית