Proof-Carrying Materials：为机器学习原子间势提供可证伪的安全证书（论文已被撤稿）

This paper has been withdrawn by arXiv Admin

No PDF available, click to view other formats

Abstract:Machine-learned interatomic potentials (MLIPs) are deployed for high-throughput materials screening without formal reliability guarantees. We show that a single MLIP used as a stability filter misses 93% of density functional theory (DFT)-stable materials (recall 0.07) on a 25,000-material benchmark. Proof-Carrying Materials (PCM) closes this gap through three stages: adversarial falsification across compositional space, bootstrap envelope refinement with 95% confidence intervals, and Lean 4 formal certification. Auditing CHGNet, TensorNet and MACE reveals architecture-specific blind spots with near-zero pairwise error correlations (r <= 0.13; n = 5,000), confirmed by independent Quantum ESPRESSO validation (20/20 converged; median DFT/CHGNet force ratio 12x). A risk model trained on PCM-discovered features predicts failures on unseen materials (AUC-ROC = 0.938 +/- 0.004) and transfers across architectures (cross-MLIP AUC-ROC ~ 0.70; feature importance r = 0.877). In a thermoelectric screening case study, PCM-audited protocols discover 62 additional stable materials missed by single-MLIP screening - a 25% improvement in discovery yield.

Comments:	arXiv admin note: This submission has been withdrawn because it does not meet arXiv's research content quality standards
Subjects:	Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
MSC classes:	68T07, 74-04
ACM classes:	I.2.6; J.2
Cite as:	arXiv:2603.12183 [cond-mat.mtrl-sci]
	(or arXiv:2603.12183v3 [cond-mat.mtrl-sci] for this version)
	https://doi.org/10.48550/arXiv.2603.12183 arXiv-issued DOI via DataCite

Submission history

From: arXiv Admin [view email]
[v1] Thu, 12 Mar 2026 17:13:25 UTC (1,111 KB)
[v2] Fri, 13 Mar 2026 15:57:32 UTC (1,113 KB)
[v3] Thu, 29 Oct 2026 20:09:23 UTC (1 KB) (withdrawn)