发表机构
ICAMS, Ruhr-Universität Bochum（波鸿鲁尔大学综合数学与应用中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出内置于GRACE基础势的CALM外推等级γ，通过潜在空间Mahalanobis距离检测外推，以低成本引导数据收集并提升模型可靠性。
AI 中文摘要
基础机器学习原子间势覆盖了广泛的构型和化学空间，但其可靠性在模拟过程中遇到的原子环境中可能有所不同。在此，我们引入了校准的Mahalanobis（CALM）外推等级γ，这是一个逐原子分段可微的量，集成在GRACE基础模型中，并在单次模型传递中与能量和力一起评估。我们根据潜在特征空间中的最近簇Mahalanobis距离定义γ，分别针对每个元素和簇从训练距离分布中设置γ=1。受控测试表明，不变多体基的归一化随机投影能够检测结构和化学外推。在不同的基础数据集OMat24和SMAX上，γ与原子力误差相关，并区分具有不同误差分布的结构。CALM等级增加了百分比级别的计算成本，其空间梯度引导不确定性偏置的数据收集朝向具有较大绝对力误差的构型。
英文摘要
Foundation machine-learning interatomic potentials cover broad configurational and chemical spaces, but their reliability can vary across the atomic environments encountered during a simulation. Here we introduce the calibrated Mahalanobis (CALM) extrapolation grade $γ$, a piecewise differentiable per-atom quantity integrated into GRACE foundation models and evaluated alongside energies and forces in a single model pass. We define $γ$ from nearest-cluster Mahalanobis distances in latent feature space, setting $γ=1$ from the training-distance distribution separately for each element and cluster. Controlled tests show that a normalized random projection of the invariant many-body basis detects structural and chemical extrapolation. On different foundation datasets, OMat24 and SMAX, $γ$ correlates with atomic force errors and separates structures with different error distributions. The CALM grade adds percent-level computational cost, and its spatial gradient guides uncertainty-biased data collection toward configurations with larger absolute force errors.
Comments48 pages, 8 figures and 1 table in the main text; supplementary information with 12 figures and 8 tables
