{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:26:28Z","timestamp":1782995188979,"version":"3.54.5"},"reference-count":90,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100007000","name":"Laboratory Directed Research and Development","doi-asserted-by":"crossref","award":["20230290ER"],"award-info":[{"award-number":["20230290ER"]}],"id":[{"id":"10.13039\/100007000","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100006151","name":"Basic Energy Sciences","doi-asserted-by":"crossref","award":["LANLE3F2"],"award-info":[{"award-number":["LANLE3F2"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The promise of machine learning interatomic potentials (MLIPs) has led to an abundance of public quantum mechanical (QM) training datasets. The quality of an MLIP is directly limited by the accuracy of the energies and atomic forces in the training dataset. Unfortunately, most of these datasets are computed with relatively low-accuracy QM methods, e.g. density functional theory with a moderate basis set. Due to the increased computational cost of more accurate QM methods, e.g. coupled-cluster theory with a complete basis set (CBS) extrapolation, most high-accuracy datasets are much smaller and often do not contain atomic forces. The lack of high-accuracy atomic forces is quite troubling, as training with force data greatly improves the stability and quality of the MLIP compared to training to energy alone. Because most datasets are computed with a unique level of theory, traditional single-fidelity (SF) learning is not capable of leveraging the vast amounts of published QM data. In this study, we apply multi-fidelity learning (MFL) to train an MLIP to multiple QM datasets of different levels of accuracy, i.e. levels of fidelity. Specifically, we perform three test cases to demonstrate that MFL with both low-level forces and high-level energies yields an extremely accurate MLIP\u2014far more accurate than a SF MLIP trained solely to high-level energies and almost as accurate as a SF MLIP trained directly to high-level energies and forces. Therefore, MFL greatly alleviates the need for generating large and expensive datasets containing high-accuracy atomic forces and allows for more effective training to existing high-accuracy energy-only datasets. Indeed, low-accuracy atomic forces and high-accuracy energies are all that are needed to achieve a high-accuracy MLIP with MFL.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae040b","type":"journal-article","created":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T22:55:33Z","timestamp":1757112933000},"page":"035066","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Multi-fidelity learning for interatomic potentials: low-level forces and high-level energies are all you need<sup>*<\/sup>"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3812-5915","authenticated-orcid":false,"given":"Mitchell","family":"Messerly","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5166-2838","authenticated-orcid":false,"given":"Sakib","family":"Matin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8727-8333","authenticated-orcid":false,"given":"Alice E A","family":"Allen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5310-3263","authenticated-orcid":true,"given":"Benjamin","family":"Nebgen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-5972","authenticated-orcid":false,"given":"Kipton","family":"Barros","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7314-7896","authenticated-orcid":false,"given":"Justin S","family":"Smith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9001-9973","authenticated-orcid":false,"given":"Nicholas","family":"Lubbers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1321-4246","authenticated-orcid":true,"given":"Richard","family":"Messerly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"mlstae040bbib1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-648X\/ad9657","type":"journal-article","article-title":"Introduction to machine learning potentials for atomistic simulations","volume":"37","author":"Thiemann","year":"2024","journal-title":"J. Condens. Matter Phys."},{"key":"mlstae040bbib2","doi-asserted-by":"publisher","DOI":"10.1002\/qua.27389","type":"journal-article","article-title":"An overview about neural networks potentials in molecular dynamics simulation","volume":"124","author":"Martin-Barrios","year":"2024","journal-title":"Int. J. Quantum Chem."},{"key":"mlstae040bbib3","doi-asserted-by":"publisher","first-page":"6227","DOI":"10.1021\/acs.jpclett.1c01357","type":"journal-article","article-title":"The rise of neural networks for materials and chemical dynamics","volume":"12","author":"Kulichenko","year":"2021","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstae040bbib4","doi-asserted-by":"publisher","DOI":"10.1063\/1.3553717","type":"journal-article","article-title":"Atom-centered symmetry functions for constructing high-dimensional neural network potentials","volume":"134","author":"Behler","year":"2011","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib5","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1039\/C6SC05720A","type":"journal-article","article-title":"ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost","volume":"8","author":"Smith","year":"2017","journal-title":"Chem. Sci."},{"key":"mlstae040bbib6","first-page":"pp 992","type":"conference-proceedings","article-title":"SchNet: a continuous-filter convolutional neural network for modeling quantum interactions","volume":"vol 30","author":"Sch\u00fctt","year":"2017"},{"key":"mlstae040bbib7","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1038\/s41467-022-29939-5","type":"journal-article","article-title":"E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials","volume":"13","author":"Batzner","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstae040bbib8","doi-asserted-by":"publisher","first-page":"10228","DOI":"10.1039\/D4SC08572H","type":"journal-article","article-title":"AIMNet2: a neural network potential to meet your neutral, charged, organic and elemental-organic needs","volume":"16","author":"Anstine","year":"2025","journal-title":"Chem. Sci."},{"key":"mlstae040bbib9","article-title":"MACE-OFF23: transferable machine learning force fields for organic molecules","author":"Kov\u00e1cs","year":"2023","type":"preprint"},{"key":"mlstae040bbib10","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1021\/acs.jctc.3c00936","type":"journal-article","article-title":"TrIP-Transformer Interatomic Potential predicts realistic energy surface using physical bias","volume":"20","author":"Hedelius","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"mlstae040bbib11","doi-asserted-by":"publisher","first-page":"10142","DOI":"10.1021\/acs.chemrev.0c01111","type":"journal-article","article-title":"Machine learning force fields","volume":"121","author":"Unke","year":"2021","journal-title":"Chem. Rev."},{"key":"mlstae040bbib12","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abfd96","type":"journal-article","article-title":"Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations Mach. Learn.: Sci. Technol.","volume":"2","author":"Miksch","year":"2021"},{"key":"mlstae040bbib13","doi-asserted-by":"publisher","first-page":"e1564","DOI":"10.1002\/wcms.1564","type":"journal-article","article-title":"Learning molecular potentials with neural networks","volume":"12","author":"Gokcan","year":"2022","journal-title":"Wiley Interdiscip. Rev.: Comput. Mol. Sci."},{"key":"mlstae040bbib14","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.193","type":"journal-article","article-title":"ANI-1, a data set of 20 million calculated off-equilibrium conformations for organic molecules","volume":"4","author":"Smith","year":"2017","journal-title":"Sci. Data"},{"key":"mlstae040bbib15","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.22","type":"journal-article","article-title":"Quantum chemistry structures and properties of 134 kilo molecules","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci. Data"},{"key":"mlstae040bbib16","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1038\/s41597-021-00812-2","type":"journal-article","article-title":"QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules","volume":"8","author":"Hoja","year":"2021","journal-title":"Sci. Data"},{"key":"mlstae040bbib17","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1038\/s41597-020-0473-z","type":"journal-article","article-title":"The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules","volume":"7","author":"Smith","year":"2020","journal-title":"Sci. Data"},{"key":"mlstae040bbib18","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1038\/s41597-022-01870-w","type":"journal-article","article-title":"Transition1x - a dataset for building generalizable reactive machine learning potentials","volume":"9","author":"Schreiner","year":"2022","journal-title":"Sci. Data"},{"key":"mlstae040bbib19","first-page":"pp 55036","type":"conference-proceedings","article-title":"Generating QM1B with PySCF IPU","volume":"vol 36","author":"Mathiasen","year":"2023"},{"key":"mlstae040bbib20","article-title":"Open materials 2024 (OMat24) inorganic materials dataset and models","author":"Barroso-Luque","year":"2024","type":"preprint"},{"key":"mlstae040bbib21","article-title":"The open molecules 2025 (OMol25) dataset, evaluations, and models","author":"Levine","year":"2025","type":"preprint"},{"key":"mlstae040bbib22","doi-asserted-by":"publisher","first-page":"13681","DOI":"10.1021\/acs.chemrev.4c00572","type":"journal-article","article-title":"Data generation for machine learning interatomic potentials and beyond","volume":"124","author":"Kulichenko","year":"2024","journal-title":"Chem. Rev."},{"key":"mlstae040bbib23","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aca23e","type":"journal-article","article-title":"NeuralNEB\u2014neural networks can find reaction paths fast","volume":"3","author":"Schreiner","year":"2022","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae040bbib24","doi-asserted-by":"publisher","first-page":"8013","DOI":"10.1039\/D3CP03853J","type":"journal-article","article-title":"Perspective on coupled-cluster theory. The evolution toward simplicity in quantum chemistry","volume":"26","author":"Bartlett","year":"2024","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstae040bbib25","doi-asserted-by":"publisher","first-page":"2193","DOI":"10.1063\/1.455064","type":"journal-article","article-title":"A complete basis set model chemistry. I. The total energies of closed-shell atoms and hydrides of the first-row elements","volume":"89","author":"Petersson","year":"1988","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib26","doi-asserted-by":"publisher","DOI":"10.1063\/5.0004608","type":"journal-article","article-title":"The ORCA quantum chemistry program package","volume":"152","author":"Neese","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib27","article-title":"Gaussian 16 Revision C.01","author":"Frisch","year":"2016","type":"other"},{"key":"mlstae040bbib28","doi-asserted-by":"publisher","DOI":"10.1063\/5.0004997","type":"journal-article","article-title":"NWChem: Past, present and future","volume":"152","author":"Apr\u00e1","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib29","article-title":"Reactive chemistry at unrestricted coupled cluster level: high-throughput calculations for training machine learning potentials","author":"Allen","year":"2025","type":"preprint"},{"key":"mlstae040bbib30","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1038\/s41597-021-00833-x","type":"journal-article","article-title":"Quantum chemical benchmark databases of gold-standard dimer interaction energies","volume":"8","author":"Donchev","year":"2021","journal-title":"Sci. Data"},{"key":"mlstae040bbib31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.129.226001","type":"journal-article","article-title":"Coupled cluster molecular dynamics of condensed phase systems enabled by machine learning potentials: liquid water benchmark","volume":"129","author":"Daru","year":"2022","journal-title":"Phys. Rev. Lett."},{"key":"mlstae040bbib32","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.1039\/D3DD00051F","type":"journal-article","article-title":"Neural network potentials for reactive chemistry: CASPT2 quality potential energy surfaces for bond breaking","volume":"2","author":"Hu","year":"2023","journal-title":"Digit. Discov."},{"key":"mlstae040bbib33","doi-asserted-by":"publisher","first-page":"4902","DOI":"10.1021\/acs.jpclett.1c01142","type":"journal-article","article-title":"Breaking the coupled cluster barrier for machine-learned potentials of large molecules: the case of 15-atom acetylacetone","volume":"12","author":"Qu","year":"2021","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstae040bbib34","doi-asserted-by":"crossref","DOI":"10.2172\/1763572","type":"preprint","article-title":"Simple and efficient algorithms for training machine learning potentials to force data","author":"Smith","year":"2020"},{"key":"mlstae040bbib35","doi-asserted-by":"crossref","DOI":"10.1021\/acs.jctc.5c00402","type":"preprint","article-title":"Does Hessian data improve the performance of machine learning potentials?","author":"Rodriguez","year":"2025"},{"key":"mlstae040bbib36","article-title":"Towards fast, specialized machine learning force fields: distilling foundation models via energy Hessians","author":"Amin","year":"2025","type":"preprint"},{"key":"mlstae040bbib37","doi-asserted-by":"publisher","first-page":"2903","DOI":"10.1038\/s41467-019-10827-4","type":"journal-article","article-title":"Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning","volume":"10","author":"Smith","year":"2019","journal-title":"Nat. Commun."},{"key":"mlstae040bbib38","doi-asserted-by":"publisher","DOI":"10.1063\/5.0142127","type":"journal-article","article-title":"Lightweight and effective tensor sensitivity for atomistic neural networks","volume":"158","author":"Chigaev","year":"2023","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib39","doi-asserted-by":"publisher","first-page":"5383","DOI":"10.1039\/D2CP05793J","type":"journal-article","article-title":"Transfer learning for chemically accurate interatomic neural network potentials","volume":"25","author":"Zaverkin","year":"2023","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstae040bbib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.aichem.2023.100042","type":"journal-article","article-title":"Building a DFT+U machine learning interatomic potential for uranium dioxide","volume":"2","author":"Stippell","year":"2024","journal-title":"Artif. Intell. Chem."},{"key":"mlstae040bbib41","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.1021\/acs.jctc.5b00099","type":"journal-article","article-title":"Big data meets quantum chemistry approximations: the \u0394-machine learning approach","volume":"11","author":"Ramakrishnan","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"mlstae040bbib42","doi-asserted-by":"publisher","first-page":"8807","DOI":"10.1021\/acs.jctc.4c00977","type":"journal-article","article-title":"\u0394-Machine learning to elevate DFT-based potentials and a force field to the CCSD(T) level illustrated for ethanol","volume":"20","author":"Nandi","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"mlstae040bbib43","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1021\/acs.jctc.4c00858","type":"journal-article","article-title":"MLTB: enhancing transferability and extensibility of density functional tight-binding theory with many-body interaction corrections","volume":"21","author":"Burrill","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"mlstae040bbib44","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41524-024-01339-x","type":"journal-article","article-title":"Learning together: towards foundation models for machine learning interatomic potentials with meta-learning","volume":"10","author":"Allen","year":"2024","journal-title":"npj Comput. Mater."},{"key":"mlstae040bbib45","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2023-8n737","type":"other","article-title":"Leveraging multitask learning to improve the transferability of machine learned force fields","author":"Jacobson","year":"2023"},{"key":"mlstae040bbib46","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/adc222","type":"journal-article","article-title":"Multi-fidelity transfer learning for quantum chemical data using a robust density functional tight binding baseline","volume":"6","author":"Cui","year":"2025","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae040bbib47","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.1021\/jacs.4c14455","type":"journal-article","article-title":"Data-efficient multifidelity training for high-fidelity machine learning interatomic potentials","volume":"147","author":"Kim","year":"2025","journal-title":"J. Am. Chem. Soc."},{"key":"mlstae040bbib48","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1038\/s41597-023-02690-2","type":"journal-article","article-title":"MultiXC-QM9: large dataset of molecular and reaction energies from multi-level quantum chemical methods","volume":"10","author":"Nandi","year":"2023","journal-title":"Sci. Data"},{"key":"mlstae040bbib49","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad4ae5","type":"journal-article","article-title":"Reducing training data needs with minimal multilevel machine learning (M3L)","volume":"5","author":"Heinen","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae040bbib50","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s43588-024-00747-9","type":"journal-article","article-title":"Approaching coupled-cluster accuracy for molecular electronic structures with multi-task learning","volume":"5","author":"Tang","year":"2024","journal-title":"Nat. Comput. Sci."},{"key":"mlstae040bbib51","doi-asserted-by":"publisher","first-page":"3678","DOI":"10.1021\/acs.jctc.9b00181","type":"journal-article","article-title":"PhysNet: a neural network for predicting energies, forces, dipole moments and partial charges","volume":"15","author":"Unke","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"mlstae040bbib52","article-title":"From molecules to materials: pre-training large generalizable models for atomic property prediction","author":"Shoghi","year":"2023","type":"preprint"},{"key":"mlstae040bbib53","article-title":"Scalable training of graph foundation models for atomistic materials modeling: a case study with HydraGNN","author":"Pasini","year":"2024","type":"preprint"},{"key":"mlstae040bbib54","doi-asserted-by":"publisher","DOI":"10.1063\/1.5011181","type":"journal-article","article-title":"Hierarchical modeling of molecular energies using a deep neural network","volume":"148","author":"Lubbers","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib55","article-title":"Learning small molecule energies and interatomic forces with an equivariant transformer on the ANI-1x dataset","author":"Hedelius","year":"2022","type":"preprint"},{"key":"mlstae040bbib56","doi-asserted-by":"publisher","DOI":"10.1063\/5.0196232","type":"journal-article","article-title":"Global machine learning potentials for molecular crystals","volume":"160","author":"\u017dugec","year":"2024","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib57","first-page":"pp 37334","type":"conference-proceedings","article-title":"Tensornet: Cartesian tensor representations for efficient learning of molecular potentials","volume":"vol 36","author":"Simeon","year":"2024"},{"key":"mlstae040bbib58","doi-asserted-by":"publisher","first-page":"4367","DOI":"10.1021\/acs.jcim.5c00341","type":"journal-article","article-title":"Including physics-informed atomization constraints in neural networks for reactive chemistry","volume":"65","author":"Zhang","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"mlstae040bbib59","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2024.113155","type":"journal-article","article-title":"Adaptive loss weighting for machine learning interatomic potentials","volume":"244","author":"Ocampo","year":"2024","journal-title":"Comput. Mater. Sci."},{"key":"mlstae040bbib60","article-title":"Ensemble knowledge distillation for machine learning interatomic potentials","author":"Matin","year":"2025","type":"preprint"},{"key":"mlstae040bbib61","doi-asserted-by":"publisher","DOI":"10.1063\/1.5023802","type":"journal-article","article-title":"Less is more: sampling chemical space with active learning","volume":"148","author":"Smith","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib62","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1039\/D2DD00008C","type":"journal-article","article-title":"NewtonNet: a Newtonian message passing network for deep learning of interatomic potentials and forces","volume":"1","author":"Haghighatlari","year":"2022","journal-title":"Digit. Discov."},{"key":"mlstae040bbib63","doi-asserted-by":"publisher","DOI":"10.1063\/5.0155322","type":"journal-article","article-title":"Evaluation of the MACE force field architecture: from medicinal chemistry to materials science","volume":"159","author":"Kov\u00e1cs","year":"2023","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib64","doi-asserted-by":"publisher","DOI":"10.1063\/1.2834918","type":"journal-article","article-title":"Systematic optimization of long-range corrected hybrid density functionals","volume":"128","author":"Chai","year":"2008","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib65","doi-asserted-by":"publisher","first-page":"3297","DOI":"10.1039\/b508541a","type":"journal-article","article-title":"Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: design and assessment of accuracy","volume":"7","author":"Weigend","year":"2005","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstae040bbib66","doi-asserted-by":"publisher","first-page":"12084","DOI":"10.1021\/acs.jpclett.1c03468","type":"journal-article","article-title":"Regularized second-order M\u00f8ller\u2014plesset theory: a more accurate alternative to conventional mp2 for noncovalent interactions and transition metal thermochemistry for the same computational cost","volume":"12","author":"Shee","year":"2021","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstae040bbib67","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1063\/1.456153","type":"journal-article","article-title":"Gaussian basis sets for use in correlated molecular calculations. I. The atoms boron through neon and hydrogen","volume":"90","author":"Dunning","year":"1989","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib68","doi-asserted-by":"publisher","first-page":"6796","DOI":"10.1063\/1.462569","type":"journal-article","article-title":"Electron affinities of the first-row atoms revisited. Systematic basis sets and wave functions","volume":"96","author":"Kendall","year":"1992","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib69","doi-asserted-by":"publisher","DOI":"10.1063\/1.5011798","type":"journal-article","article-title":"Communication: an improved linear scaling perturbative triples correction for the domain based local pair-natural orbital based singles and doubles coupled cluster method [DLPNO-CCSD(T)]","volume":"148","author":"Guo","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib70","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/S0009-2614(99)00179-7","type":"journal-article","article-title":"Basis-set convergence of the energy in molecular Hartree\u2013Fock calculations","volume":"302","author":"Halkier","year":"1999","journal-title":"Chem. Phys. Lett."},{"key":"mlstae040bbib71","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1021\/ct100396y","type":"journal-article","article-title":"Revisiting the atomic natural orbital approach for basis sets: robust systematic basis sets for explicitly correlated and conventional correlated ab initio methods?","volume":"7","author":"Neese","year":"2011","journal-title":"J. Chem. Theory Comput."},{"key":"mlstae040bbib72","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1002\/anie.200462457","type":"journal-article","article-title":"Virtual exploration of the small-molecule chemical Universe below 160 daltons","volume":"44","author":"Fink","year":"2005","journal-title":"Angew. Chem. Int. Ed."},{"key":"mlstae040bbib73","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1021\/ci600423u","type":"journal-article","article-title":"Virtual exploration of the chemical Universe up to 11 atoms of C, N, O, F: assembly of 26.4 million structures (110.9 million stereoisomers) and analysis for new ring systems, stereochemistry, physicochemical properties, compound classes and drug discovery","volume":"47","author":"Fink","year":"2007","journal-title":"J. Chem. Inf. Model."},{"key":"mlstae040bbib74","doi-asserted-by":"publisher","first-page":"8732","DOI":"10.1021\/ja902302h","type":"journal-article","article-title":"970 million druglike small molecules for virtual screening in the chemical Universe database GDB-13","volume":"131","author":"Blum","year":"2009","journal-title":"J. Am. Chem. Soc."},{"key":"mlstae040bbib75","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1021\/acs.jcim.6b00614","type":"journal-article","article-title":"A comparison of quantum and molecular mechanical methods to estimate strain energy in druglike fragments","volume":"57","author":"Sellers","year":"2017","journal-title":"J. Chem. Inf. Model."},{"key":"mlstae040bbib76","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1063\/1.438955","type":"journal-article","article-title":"Self-consistent molecular orbital methods. XX. A basis set for correlated wave functions","volume":"72","author":"Krishnan","year":"1980","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib77","article-title":"QuantumBind-RBFE: accurate relative binding free energy calculations using neural network potentials","author":"Zariquiey","year":"2025","type":"preprint"},{"key":"mlstae040bbib78","doi-asserted-by":"publisher","first-page":"6258","DOI":"10.1021\/acs.jcim.0c00904","type":"journal-article","article-title":"Benchmarking force field and the ANI neural network potentials for the torsional potential energy surface of biaryl drug fragments","volume":"60","author":"Lahey","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"mlstae040bbib79","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1021\/acs.jcim.1c01346","type":"journal-article","article-title":"TorsionNet: a deep neural network to rapidly predict small-molecule torsional energy profiles with the accuracy of quantum mechanics","volume":"62","author":"Rai","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"mlstae040bbib80","article-title":"Egret-1: pretrained neural network potentials for efficient and accurate bioorganic simulation","author":"Mann","year":"2025","type":"preprint"},{"key":"mlstae040bbib81","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1038\/s41524-020-00484-3","type":"journal-article","article-title":"Neural network reactive force field for C, H, N and O systems","volume":"7","author":"Pilsun","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstae040bbib82","doi-asserted-by":"publisher","DOI":"10.1063\/5.0146055","type":"journal-article","article-title":"High-pressure and temperature neural network reactive force field for energetic materials","volume":"158","author":"Hamilton","year":"2023","journal-title":"J. Chem. Phys."},{"key":"mlstae040bbib83","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.106.L180101","type":"journal-article","article-title":"Machine learning interatomic potential for simulations of carbon at extreme conditions","volume":"106","author":"Willman","year":"2022","journal-title":"Phys. Rev. B"},{"key":"mlstae040bbib84","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1002\/wcms.1161","type":"journal-article","article-title":"Semiempirical quantum-chemical methods","volume":"4","author":"Thiel","year":"2014","journal-title":"Wiley Interdiscip. Rev.: Comput. Mol. Sci."},{"key":"mlstae040bbib85","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1039\/D2DD00137C","type":"journal-article","article-title":"Synthetic data enable experiments in atomistic machine learning","volume":"2","author":"Gardner","year":"2023","journal-title":"Digit. Discov."},{"key":"mlstae040bbib86","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad1626","type":"journal-article","article-title":"Synthetic pre-training for neural-network interatomic potentials","volume":"5","author":"Gardner","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae040bbib87","doi-asserted-by":"publisher","first-page":"4797","DOI":"10.1021\/acs.jcim.5c00079","type":"journal-article","article-title":"Atomic energy accuracy of neural network potentials: Harnessing pretraining and transfer learning","volume":"65","author":"Jung","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"mlstae040bbib88","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.1021\/acs.jcim.4c01847","type":"journal-article","article-title":"Improving bond dissociations of reactive machine learning potentials through physics-constrained data augmentation","volume":"65","author":"dos Santos","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"mlstae040bbib89","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1021\/acs.accounts.0c00868","type":"journal-article","article-title":"Development of multimodal machine learning potentials: toward a physics-aware artificial intelligence","volume":"54","author":"Zubatiuk","year":"2021","journal-title":"Acc. Chem. Res."},{"key":"mlstae040bbib90","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2024-ng3ws-v3","type":"journal-article","article-title":"One to rule them all: a universal interatomic potential learning across quantum chemical levels","author":"Chen","year":"2025","journal-title":"ChemRxiv"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T12:34:06Z","timestamp":1759149246000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae040b"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":90,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9,29]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae040b","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"Multi-fidelity learning for interatomic potentials: low-level forces and high-level energies are all you need*","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-05-02","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-09-05","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-09-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}