analiza aiqbench
This paper introduces a formal OWL ontology to standardize metadata for machine learning interatomic potentials, addressing the critical need for reproducibility in computational materials science. By linking methods, training datasets with DFT provenance, and benchmarks into a unified knowledge graph, it enables systematic comparison of models that approximate quantum-mechanical forces at reduced cost. This infrastructure advancement directly supports the scalability and reliability of AI-driven simulations within high-performance computing environments.
An Ontology for Machine Learning Interatomic Potentials
arXiv:2607.23219v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) approximate quantum-mechanical energies and forces---conventionally computed by density functional theory (DFT) or wave-function methods---at a fraction of the cost. The field encompasses a growing ecosystem of algorithms, training datasets, hyperparameters, and target materials, yet the metadata needed to systematically compare, reproduce, and build upon MLIP studies remains scattered across papers, scripts, and ad-hoc file formats. We present the MLIPs ontology, an OWL 2 DL ontology that captures the concepts needed to describe MLIP methods, their hyperparameters, training datasets with DFT provenance, and published benchmarks. The ontology is organized into three modules---Method, Training Data, and Benchmark---and connects existing ontologies in materials science (MDO, CMSO/ASMO) and machine learning (ML-Schema), complementing dataset-side schemas such as Croissant. It declares 27 formal axioms enforcing data completeness and consistency, including property chains that link trained models to their methods and training data. We demonstrate the ontology through a running example based on Moment Tensor Potentials and evaluate it through competency-question execution on a 20-paper seeded knowledge graph, OWL reasoning, and comparison with existing ontologies.
Abstract:Machine learning interatomic potentials (MLIPs) approximate quantum-mechanical energies and forces---conventionally computed by density functional theory (DFT) or wave-function methods---at a fraction of the cost. The field encompasses a growing ecosystem of algorithms, training datasets, hyperparameters, and target materials, yet the metadata needed to systematically compare, reproduce, and build upon MLIP studies remains scattered across papers, scripts, and ad-hoc file formats. We present the MLIPs ontology, an OWL 2 DL ontology that captures the concepts needed to describe MLIP methods, their hyperparameters, training datasets with DFT provenance, and published benchmarks. The ontology is organized into three modules---Method, Training Data, and Benchmark---and connects existing ontologies in materials science (MDO, CMSO/ASMO) and machine learning (ML-Schema), complementing dataset-side schemas such as Croissant. It declares 27 formal axioms enforcing data completeness and consistency, including property chains that link trained models to their methods and training data. We demonstrate the ontology through a running example based on Moment Tensor Potentials and evaluate it through competency-question execution on a 20-paper seeded knowledge graph, OWL reasoning, and comparison with existing ontologies.
Artificial Intelligence (cs.AI); Databases (cs.DB); Digital Libraries (cs.DL)
arXiv:2607.23219 [cs.AI]
(or arXiv:2607.23219v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.23219 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 196 cuvinte
Subiecte conexe
Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
arXiv · 5 iun. 2026
Quantum machine learning interatomic potential: Application of variational quantum algorithm
arXiv · 31 iul. 2026
Distilling latent electrostatics from foundation machine learning interatomic potentials
arXiv · 16 iun. 2026
HIP: Hessian Interatomic Potentials without derivatives
arXiv · 24 aug. 2026