{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T02:47:00Z","timestamp":1788749220878,"version":"build-2803163510"},"reference-count":138,"publisher":"National Academy of Sciences","issue":"30","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["URF\\R1\\211144"],"award-info":[{"award-number":["URF\\R1\\211144"]}],"id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"UKRI | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/F036884\/1"],"award-info":[{"award-number":["EP\/F036884\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"UKRI | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/X035859"],"award-info":[{"award-number":["EP\/X035859"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2026,7,28]]},"abstract":"<jats:p>Understanding and predicting the behavior of liquid matter across length scales\u2014using only the microscopic interactions encoded in the Schr\u00f6dinger equation\u2014remains a central challenge in the physical sciences. Achieving this goal requires not only an accurate and efficient description of intermolecular forces but also a consistent framework that bridges the micro-, meso-, and macroscales. Here, by combining machine-learned interatomic potentials (MLIPs) with neural classical density functional theory (cDFT), we present such a framework. MLIPs trained on quantum-mechanical energies and forces are used to generate inhomogeneous density profiles, which then serve as the training data for neural cDFT. The resulting ab initio neural cDFT is more computationally efficient than molecular simulations and provides a conceptually transparent route to the thermodynamics of both homogeneous and planar inhomogeneous systems. We demonstrate the approach for both water and carbon dioxide using several exchange\u2013correlation functionals. Beyond accurately reproducing\u2014at the level of the underlying approximate electronic structure\u2014bulk equations of state and liquid\u2013vapor phase diagrams, ab initio neural cDFT predicts, from first principles, how confinement modifies liquid\u2013vapor coexistence in water. It also captures complex behavior in supercritical carbon dioxide such as the Fisher\u2013Widom and Widom lines. While current applications are limited to bulk fluids and planar geometries, this approach establishes a general first-principles route to multiscale modeling of fluids by unifying two independently developed machine-learning paradigms. This work represents an important step toward generalizing cDFT beyond simple empirical potentials to chemically complex systems.<\/jats:p>","DOI":"10.1073\/pnas.2610049123","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T17:38:12Z","timestamp":1784914692000},"update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":2,"title":["A unified machine-learning framework for ab initio multiscale modeling of liquids"],"prefix":"10.1073","volume":"123","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0981-4329","authenticated-orcid":false,"given":"Anna T.","family":"Bui","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/013meh722","id-type":"ROR","asserted-by":"publisher"}],"name":"Yusuf Hamied Department of Chemistry, University of Cambridge","place":["Cambridge, United Kingdom"]},{"id":[{"id":"https:\/\/ror.org\/01v29qb04","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Chemistry, Durham University","place":["Durham, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2708-8711","authenticated-orcid":false,"given":"Stephen J.","family":"Cox","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01v29qb04","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Chemistry, Durham University","place":["Durham, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1056991"},{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2505929122"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50418-6"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1039\/B920571C"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adw6615"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/natrevmats.2017.36"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/aic.17026"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.540110605"},{"key":"e_1_3_4_9_2","doi-asserted-by":"crossref","unstructured":"K. Reuter M. Scheffler First-principles kinetic Monte Carlo simulations for heterogeneous catalysis: Application to the CO oxidation at RuO2(110). Phys. Rev. B 73 045433 (2006).","DOI":"10.1103\/PhysRevB.73.045433"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/nsb0902-646"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41929-019-0298-3"},{"key":"e_1_3_4_12_2","volume-title":"Theory of Simple Liquids: with Applications to Soft Matter","author":"Hansen J.","year":"2013","unstructured":"J. Hansen, I. McDonald, Theory of Simple Liquids: with Applications to Soft Matter (Elsevier Science, 2013)."},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1080\/00018737900101365"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.146401"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.143001"},{"key":"e_1_3_4_16_2","doi-asserted-by":"crossref","unstructured":"I. Batatia D. P. Kovacs G. Simm C. Ortner G. Csanyi \u201cMACE: Higher order equivariant message passing neural networks for fast and accurate force fields\u201d in Advances in Neural Information Processing Systems S. Koyejo Eds. (Curran Associates Inc. 2022) vol. 35 pp. 11423\u201311436.","DOI":"10.52202\/068431-0830"},{"key":"e_1_3_4_17_2","unstructured":"B. M. Wood UMA: A family of universal models for atoms. arXiv [Preprint] (2025). http:\/\/arxiv.org\/abs\/2506.23971 (Accessed 7 July 2026)."},{"key":"e_1_3_4_18_2","unstructured":"B. Rhodes Orb-v3: Atomistic simulation at scale. arXiv [Preprint] (2025). http:\/\/arxiv.org\/abs\/2504.06231 (Accessed 7 July 2026)."},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-65662-7"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2110077118"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1815117116"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0021852"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28538-8"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpcb.3c00610"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-023-01100-w"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18788-9"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-20821-w"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05036-x"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-024-01441-0"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.4c15287"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.71.1253"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.63.980"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/14\/46\/313"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/22\/6\/063102"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.70.011201"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1021\/jz301956b"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.4993175"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0311853"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0248694"},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.134.056103"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.5c00484"},{"key":"e_1_3_4_42_2","doi-asserted-by":"crossref","unstructured":"A. Simon M. Oettel Machine Learning Approaches to Classical Density Functional Theory M. te Vrugt Ed. (Springer Nature Switzerland Cham 2026) pp. 83\u2013113.","DOI":"10.1007\/978-3-032-04129-6_6"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2312484120"},{"key":"e_1_3_4_44_2","first-page":"011013","article-title":"Neural density functional theory of liquid-gas phase coexistence","volume":"15","author":"Samm\u00fcller F.","year":"2025","unstructured":"F. Samm\u00fcller, M. Schmidt, R. Evans, Neural density functional theory of liquid-gas phase coexistence. Phys. Rev. X 15, 011013 (2025).","journal-title":"Phys. Rev. X"},{"key":"e_1_3_4_45_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0290261"},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpcb.6c00640"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.134.148001"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-69482-1"},{"key":"e_1_3_4_49_2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-648X\/ade7e7"},{"key":"e_1_3_4_50_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.3c00495"},{"key":"e_1_3_4_51_2","doi-asserted-by":"publisher","DOI":"10.1103\/7bqn-y2d7"},{"key":"e_1_3_4_52_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.111.055305"},{"key":"e_1_3_4_53_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.115.036402"},{"key":"e_1_3_4_54_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.59.7413"},{"key":"e_1_3_4_55_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.3382344"},{"key":"e_1_3_4_56_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.2121687"},{"key":"e_1_3_4_57_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.77.3865"},{"key":"e_1_3_4_58_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.38.3098"},{"key":"e_1_3_4_59_2","first-page":"041005","article-title":"Versatile van der Waals density functional based on a meta-generalized gradient approximation","volume":"6","author":"Peng H.","year":"2016","unstructured":"H. Peng, Z. H. Yang, J. P. Perdew, J. Sun, Versatile van der Waals density functional based on a meta-generalized gradient approximation. Phys. Rev. X 6, 041005 (2016).","journal-title":"Phys. Rev. X"},{"key":"e_1_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690470719"},{"key":"e_1_3_4_61_2","unstructured":"Y. Li Assessment of first-principles methods in modeling the melting properties of water. arXiv [Preprint] (2025). https:\/\/arxiv.org\/abs\/2512.23940 (Accessed 7th July 2026)."},{"key":"e_1_3_4_62_2","volume-title":"Molecular Theory of Capillarity, Dover Books on Chemistry","author":"Rowlinson J.","year":"2002","unstructured":"J. Rowlinson, B. Widom, Molecular Theory of Capillarity, Dover Books on Chemistry (Dover Publications, 2002)."},{"key":"e_1_3_4_63_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.2215612"},{"key":"e_1_3_4_64_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0144500"},{"key":"e_1_3_4_65_2","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.25123"},{"key":"e_1_3_4_66_2","unstructured":"P. J. Linstrom W. G. Mallard NIST Chemistry Webbook NIST Standard Reference Database Number 69 (National Institute of Standards and Technology Gaithersburg MD 20899 2026). Retrieved 20 March 2026."},{"key":"e_1_3_4_67_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpclett.8b03679"},{"key":"e_1_3_4_68_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0283254"},{"key":"e_1_3_4_69_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.452363"},{"key":"e_1_3_4_70_2","volume-title":"Surface Forces, Chemistry and Materials Science","author":"Churaev N.","year":"2013","unstructured":"N. Churaev, B. Derjaguin, V. Muller, Surface Forces, Chemistry and Materials Science (Springer, US, 2013)."},{"key":"e_1_3_4_71_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature19363"},{"key":"e_1_3_4_72_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat4191"},{"key":"e_1_3_4_73_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09558-y"},{"key":"e_1_3_4_74_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2978-1"},{"key":"e_1_3_4_75_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.nanolett.1c02726"},{"key":"e_1_3_4_76_2","doi-asserted-by":"publisher","DOI":"10.1038\/nphys1708"},{"key":"e_1_3_4_77_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0707917105"},{"key":"e_1_3_4_78_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14295"},{"key":"e_1_3_4_79_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.nanolett.2c04187"},{"key":"e_1_3_4_80_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0238363"},{"key":"e_1_3_4_81_2","doi-asserted-by":"publisher","DOI":"10.1021\/acsnano.2c02784"},{"key":"e_1_3_4_82_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0131028"},{"key":"e_1_3_4_83_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2020.116447"},{"key":"e_1_3_4_84_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.energyfuels.5c00825"},{"key":"e_1_3_4_85_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1221581110"},{"key":"e_1_3_4_86_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.1601278"},{"key":"e_1_3_4_87_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.555991"},{"key":"e_1_3_4_88_2","doi-asserted-by":"publisher","DOI":"10.1201\/9780429491443"},{"key":"e_1_3_4_89_2","unstructured":"P. J. Linstrom W. G. Mallard NIST Chemistry WebBook NIST Standard Reference Database Number 69 (National Institute of Standards and Technology Gaithersburg MD 20899 2025). https:\/\/doi.org\/10.18434\/T4D303. Retrieved October 29 2025."},{"key":"e_1_3_4_90_2","doi-asserted-by":"publisher","DOI":"10.1080\/00268979300102621"},{"key":"e_1_3_4_91_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.1671624"},{"key":"e_1_3_4_92_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.3146"},{"key":"e_1_3_4_93_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.480598"},{"key":"e_1_3_4_94_2","doi-asserted-by":"publisher","DOI":"10.1038\/nphys1683"},{"key":"e_1_3_4_95_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0507870102"},{"key":"e_1_3_4_96_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms6806"},{"key":"e_1_3_4_97_2","doi-asserted-by":"publisher","DOI":"10.1038\/nphys1711"},{"key":"e_1_3_4_98_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.91.022111"},{"key":"e_1_3_4_99_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.97.245702"},{"key":"e_1_3_4_100_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.145701"},{"key":"e_1_3_4_101_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2400313121"},{"key":"e_1_3_4_102_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physrep.2021.10.002"},{"key":"e_1_3_4_103_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.479595"},{"key":"e_1_3_4_104_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0807623105"},{"key":"e_1_3_4_105_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2005847117"},{"key":"e_1_3_4_106_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29243-2"},{"key":"e_1_3_4_107_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-025-01577-7"},{"key":"e_1_3_4_108_2","unstructured":"I. J. Parker et al. False metallization in short-ranged machine learned interatomic potentials. arXiv [Preprint] (2026). http:\/\/arxiv.org\/abs\/2603.04228 (Accessed 7 July 2026)."},{"key":"e_1_3_4_109_2","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/6\/44\/008"},{"key":"e_1_3_4_110_2","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/21\/47\/474220"},{"key":"e_1_3_4_111_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0031215"},{"key":"e_1_3_4_112_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0067565"},{"key":"e_1_3_4_113_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0083669"},{"key":"e_1_3_4_114_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-20427-2"},{"key":"e_1_3_4_115_2","doi-asserted-by":"publisher","DOI":"10.1103\/ssp9-7s81"},{"key":"e_1_3_4_116_2","unstructured":"I. Batatia MACE-POLAR-1: A polarisable electrostatic foundation model for molecular chemistry. arXiv [Preprint] (2026). https:\/\/arxiv.org\/abs\/2602.19411 (Accessed 7 July 2026)."},{"key":"e_1_3_4_117_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.5c01400"},{"key":"e_1_3_4_118_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0251713"},{"key":"e_1_3_4_119_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-69715-3"},{"key":"e_1_3_4_120_2","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/20\/49\/494206"},{"key":"e_1_3_4_121_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1521570113"},{"key":"e_1_3_4_122_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.133.098201"},{"key":"e_1_3_4_123_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.116.025501"},{"key":"e_1_3_4_124_2","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad7191"},{"key":"e_1_3_4_125_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abj6511"},{"key":"e_1_3_4_126_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-022-00470-2"},{"key":"e_1_3_4_127_2","unstructured":"G. Luise Accurate and scalable exchange-correlation with deep learning. arXiv [Preprint] (2026). https:\/\/arxiv.org\/abs\/2506.14665 (Accessed 7 July 2026)."},{"key":"e_1_3_4_128_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2018.03.016"},{"key":"e_1_3_4_129_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.1473654"},{"key":"e_1_3_4_130_2","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(83)90014-1"},{"key":"e_1_3_4_131_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.69.134103"},{"key":"e_1_3_4_132_2","doi-asserted-by":"publisher","DOI":"10.1088\/0305-4470\/39\/19\/S18"},{"key":"e_1_3_4_133_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2021.108171"},{"key":"e_1_3_4_134_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.8b00770"},{"key":"e_1_3_4_135_2","volume-title":"Deep Learning with Python","author":"Chollet F.","year":"2017","unstructured":"F. Chollet, Deep Learning with Python (Manning Publications, 2017)."},{"key":"e_1_3_4_136_2","unstructured":"A. T. Bui GCMC with Gaussian truncated potentials\u2019. GitHub. https:\/\/github.com\/annatbui\/GCMC. Deposited 15 January 2026."},{"key":"e_1_3_4_137_2","unstructured":"A. T. Bui Neural density functional theory with MLIPs. GitHub. https:\/\/github.com\/annatbui\/mlipneuraldft. Deposited 23 June 2026."},{"key":"e_1_3_4_138_2","unstructured":"A. Bui S. Cox Research Data Supporting \u201cA Unified Machine-learning Framework for Ab Initio Multiscale Modeling of Liquids\u201d. Zenodo. https:\/\/zenodo.org\/records\/21245362. Deposited 7 July 2026."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.2610049123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T17:38:28Z","timestamp":1784914708000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/10.1073\/pnas.2610049123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,24]]},"references-count":138,"journal-issue":{"issue":"30","published-print":{"date-parts":[[2026,7,28]]}},"alternative-id":["10.1073\/pnas.2610049123"],"URL":"https:\/\/doi.org\/10.1073\/pnas.2610049123","relation":{},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,24]]},"assertion":[{"value":"2026-03-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2610049123"}}