Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.11246

Assessing the Reliability of Foundational Machine Learning Potentials for Evaluating the Veracity of the Crystallography Open Database

Justinas Šlepavičius·Antanas Vaitkus·Andrius Merkys·Saulius Gražulis·Linas Vilčiauskas
View original source ↗Read source document ↗Export metadata ↓

Abstract

The Crystallography Open Database (COD) contains over half a million experimentally determined crystal structures. Validation of crystallographic data proceeds at three hierarchical levels, the third of which assesses the physical plausibility of structures. This level has typically relied on empirical heuristics or expert judgment, which are slow and error-prone given the size of crystallographic databases and the rate at which new structures are deposited. Here we assess whether universal machine-learning interatomic potentials (MLIPs) can automate this level of validation. Of the 522 086 COD entries, 317 457 (60.8\%) passed a data-quality filter removing disordered structures, formula mismatches and unmodelled solvent. These structures were relaxed with M3GNet, and 314 153 (99.0\%) converged without a large change in cell volume. For most entries the relaxed and deposited volumes are nearly identical. Convergence and volume change thus provide simple criteria for identifying relaxations that do not confirm the deposited structure. A manual inspection of 327 structures showed that no single descriptor threshold (energy, largest force, or atomic displacement) separates valid from invalid structures. A comparison of M3GNet, CHGNet, PET-MAD and PET-OAM on 524 selected structures revealed model-specific failures: M3GNet distorts cyclopentadienyl and other $π$ ligands, and both M3GNet and CHGNet distort thiophene and thiazole rings, whereas the PET models preserve these motifs. All models detected missing hydrogen atoms, and at least some detected spurious hydrogens, incorrectly assigned atom types, and two previously unreported coordinate errors. No single model detected all error types. MLIP relaxation is therefore a useful but model-dependent screening tool, and combining several models is preferable to relying on any single one.

Explore related subjects

cond-mat.mtrl-scicond-mat.other

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Justinas Šlepavičius, Antanas Vaitkus, Andrius Merkys, Saulius Gražulis, Linas Vilčiauskas. 2026-10-08. Assessing the Reliability of Foundational Machine Learning Potentials for Evaluating the Veracity of the Crystallography Open Database. https://arxiv.org/abs/2610.11246

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Predictive Inorganic Synthesis based on Machine Learning using Small Data sets: a case study of Hydrodynamic Diameter-controlled Cu Nanoparticles

Cu NPs have a broad applicability, yet their synthesis is sensitive to subtle changes in reaction parameters. This sensitivity, combined with the time- and resource-intensive nature of experimental optimization, poses a major challenge in achieving reproducible and size-controlled synthesis. While ML shows promise in materials research, its application is often limited by scarcity of large high-quality experimental data sets. This study explores ML to predict the DLS-derived hydrodynamic diameter of Cu NPs using a small data set of 25 syntheses. Latin Hypercube Sampling is used to efficiently cover the parameter space while creating the experimental data set. Ensemble regression models successfully predict hydrodynamic diameters with good predictive performance given the limited dataset. Since quantitative regression requires a unique DLS-derived hydrodynamic diameter, the regression model is restricted to mono-modal DLS distributions, while a complementary classification model identifies synthesis conditions for which quantitative prediction is applicable. Using equivalent out-of-sample validation, the ML and DoE models showed comparable generalization. The final ensemble model achieved an R2=0.74 compared to 0.60 for the DoE model, while retaining the complete synthesis parameter space, making it better suited for synthesis guidance. Additionally, classification models using both random forests and LLMs are evaluated to distinguish between large and small particles. These classification models exhibited only modest predictive performance, indicating that this small dataset is insufficient to fully exploit the capabilities of complex LLMs. Overall, this study demonstrates that carefully curated small data sets, paired with robust classical ML, can effectively support the synthesis of Cu NPs and highlights that for lab-scale studies, complex models like LLMs may offer limited benefits.

cond-mat.mtrl-sci↗
arXiv2026

Discontinuous character of the ultrafast exciton Mott transition in monolayer WS$_2$

There are conflicting predictions and reports on the character of the exciton Mott transition (EMT) in monolayer transition metal dichalcogenides. It could be either a discontinuous or a continuous transition from the excitonic to the plasma phase, with important implications for devices such as photoswitches. To resolve the nature of the transition in monolayer WS$_2$, we study its ultrafast optical response upon resonant photoexcitation of the A exciton across a broad range of photoexcitation densities. In agreement with previously reported measurements we observe that the A exciton quenches gradually with increasing excitation density. However, a detailed lineshape analysis unveils an abrupt red shift in the transient peak positions of the A and B exciton resonances above an excitation density threshold. This is attributed to band gap renormalization arising from the formation of free charge carrier plasma, i.e., the EMT. The plasma phase decays with a time constant of 0.65 ps back into the excitonic state. The abrupt appearance of the plasma phase at the threshold density suggests that the EMT is a discontinuous and not a continuous transition. This work demonstrates how transient optical spectroscopy combined with lineshape analysis of two excitonic resonances simultaneously can be used to investigate the EMT in 2D materials.

cond-mat.mtrl-sci↗
arXiv2026

Crystallisation kinetics of supercooled liquid palladium

In this study, we employ classical molecular dynamics (MD) simulations to investigate the crystallisation kinetics of supercooled liquid palladium and relate the results to time-resolved X-ray diffraction measurements on rapidly quenched Pd thin films. Crystal nucleation and growth rates are determined over the temperature range $700$--$1150~\mathrm{K}$ ($0.38$--$0.65 T_{\mathrm{m}}$) by analysing the evolution of the microstructure during the liquid-to-crystal transition. The self-diffusion coefficient of Pd, obtained from the atomic mean-squared displacement, follows Arrhenius behaviour over the investigated temperature range, with an activation energy of $467(6)~\mathrm{meV/atom}$, consistent with available data for supercooled liquid metals. The steady-state homogeneous nucleation rate exhibits a maximum of approximately $4 \times 10^{35}~\mathrm{m^{-3} s^{-1}}$ near $0.5 T_{\mathrm{m}}$. Crystal growth occurs at velocities of the order of metres per second, with a temperature dependence consistent with diffusion-limited Wilson-Frenkel kinetics rather than the collision-limited regime. Based on multiple statistically independent simulations, a time-temperature-transformation (TTT) diagram for crystallisation onset is constructed. The TTT curve exhibits a nose near $0.5 T_{\mathrm{m}}$ and $100~\mathrm{ps}$, corresponding to a critical cooling rate for vitrification on the order of $10^{13}~\mathrm{K s^{-1}}.$ The simulations reproduce the crystallisation onset time and temperature observed in time-resolved X-ray diffraction experiments on optically molten Pd thin films quenched at $5 \times 10^{11}~\mathrm{K s^{-1}}.$ These results indicate that homogeneous, rather than heterogeneous, nucleation governs the achievable supercooling in the experimentally studied films.

cond-mat.mtrl-sci↗