uMOF: A Universal Database, Benchmark, and Machine Learning Interatomic Potentials for Metal-Organic Frameworks
Abstract
Foundation machine learning interatomic potentials (MLIPs) deliver near-ab-initio accuracy at a fraction of the computational cost, yet their promise for Metal-organic Frameworks (MOFs) remains largely unrealized as large unit cells make first-principles training data expensive to generate, fine-tuned models are scarce, and experimentally grounded benchmarks are scarcer still. We introduce uMOF, a three-part contribution addressing this gap. First, we release the largest and most accurate density functional theory dataset for MOFs to date, computed at the r2SCAN-D4 level of theory across 85524 configurations spanning 19950 unique frameworks and 79 elements, covering empty and gas-loaded structures, geometry optimizations, equations of state, and finite-temperature molecular dynamics. Second, we release a literature-mined benchmark of 3986 verified property values (3146 experimental) extracted from 626 papers by a seven-stage, checkpointed multi-pass large language model pipeline, linked to more than 650 crystallographic information files. Third, we release two universal MLIPs for MOFs, uMOF-MH and uMOF-POLAR, fine-tuned from two architecturally distinct MACE foundation models on the uMOF dataset. On near-equilibrium, ``Tier-1'' properties (bulk modulus, phonon-derived heat capacity) the uMOF models perform comparably to existing foundation and fine-tuned baselines. On harder, dynamics-sensitive properties like gas adsorption enthalpies via Widom insertion and adsorption isotherms, the uMOF models outperform every baseline we test, including MOF-specialized gas-capture models trained on datasets up to three orders of magnitude larger, cutting error by more than 80% to within experimental uncertainty. We trace this advantage to the physical diversity of the training data and to level of theory where a small (1.7%) fraction of MD simulations is decisive for MLIP stability.
Related
- Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides
- MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
- From sparse quantum-computing data to atomistic simulation with universal machine-learning interatomic potentials
- Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models
- Understanding compression-extension error asymmetry in universal machine-learning interatomic potentials
BibTeX
@misc{inizan2026umof,
title = {{uMOF: A Universal Database, Benchmark, and Machine Learning Interatomic Potentials for Metal-Organic Frameworks}},
author = {Théo Jaffrelot Inizan and Prathami Divakar Kamath and Alin Marin Elena and Kristin A. Persson},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.28100},
eprint = {2608.28100},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28100},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - uMOF: A Universal Database, Benchmark, and Machine Learning Interatomic Potentials for Metal-Organic Frameworks
AU - Théo Jaffrelot Inizan
AU - Prathami Divakar Kamath
AU - Alin Marin Elena
AU - Kristin A. Persson
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2608.28100
UR - https://arxiv.org/abs/2608.28100
AB - Foundation machine learning interatomic potentials (MLIPs) deliver near-ab-initio accuracy at a fraction of the computational cost, yet their promise for Metal-organic Frameworks (MOFs) remains largely unrealized as large unit cells make first-principles training data expensive to generate, fine-tuned models are scarce, and experimentally grounded benchmarks are scarcer still. We introduce uMOF, a three-part contribution addressing this gap. First, we release the largest and most accurate density functional theory dataset for MOFs to date, computed at the r^2SCAN-D4 level of theory across 85524 configurations spanning 19950 unique frameworks and 79 elements, covering empty and gas-loaded structures, geometry optimizations, equations of state, and finite-temperature molecular dynamics. Second, we release a literature-mined benchmark of 3986 verified property values (3146 experimental) extracted from 626 papers by a seven-stage, checkpointed multi-pass large language model pipeline, linked to more than 650 crystallographic information files. Third, we release two universal MLIPs for MOFs, uMOF-MH and uMOF-POLAR, fine-tuned from two architecturally distinct MACE foundation models on the uMOF dataset. On near-equilibrium, ``Tier-1'' properties (bulk modulus, phonon-derived heat capacity) the uMOF models perform comparably to existing foundation and fine-tuned baselines. On harder, dynamics-sensitive properties like gas adsorption enthalpies via Widom insertion and adsorption isotherms, the uMOF models outperform every baseline we test, including MOF-specialized gas-capture models trained on datasets up to three orders of magnitude larger, cutting error by more than 80% to within experimental uncertainty. We trace this advantage to the physical diversity of the training data and to level of theory where a small (1.7%) fraction of MD simulations is decisive for MLIP stability.
ER -