{"id":"https://openalex.org/W7118020002","doi":"https://doi.org/10.48550/arxiv.2512.23939","title":"Training Dataset Matters for Machine Learning Interatomic Potentials: Water Simulation as an Example","display_name":"Training Dataset Matters for Machine Learning Interatomic Potentials: Water Simulation as an Example","publication_year":2025,"publication_date":"2025-12-30","ids":{"openalex":"https://openalex.org/W7118020002","doi":"https://doi.org/10.48550/arxiv.2512.23939"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2512.23939","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.23939","pdf_url":"https://arxiv.org/pdf/2512.23939","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.23939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100427058","display_name":"Yifan Li","orcid":"https://orcid.org/0000-0003-2543-9741","observed_orcids":["https://orcid.org/0000-0003-2543-9741","https://orcid.org/0000-0002-3437-1198","https://orcid.org/0009-0003-0241-0118"]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yifan","raw_affiliation_strings":["\u2021Eastern Institute of Technology , Ningbo , Zhejiang 315200 , China \u00b6Program in Applied and Computational Mathematics ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Eastern Institute of Technology , Ningbo , Zhejiang 315200 , China \u00b6Program in Applied and Computational Mathematics ,","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058381838","display_name":"Bingjia Yang","orcid":"https://orcid.org/0000-0003-4074-9553","observed_orcids":["https://orcid.org/0000-0003-4074-9553"]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Bingjia","raw_affiliation_strings":["\u2021Eastern Institute of Technology , Ningbo , Zhejiang 315200 , China \u00b6Program in Applied and Computational Mathematics ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Eastern Institute of Technology , Ningbo , Zhejiang 315200 , China \u00b6Program in Applied and Computational Mathematics ,","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121782366","display_name":"Chunyi Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Chunyi","raw_affiliation_strings":["\u2020Department of Chemistry , Princeton University , Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020Department of Chemistry , Princeton University , Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029658762","display_name":"Axel Gomez","orcid":"https://orcid.org/0000-0002-0378-4352","observed_orcids":["https://orcid.org/0000-0002-0378-4352"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gomez, Axel","raw_affiliation_strings":["\u2020Department of Chemistry , Princeton University , Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020Department of Chemistry , Princeton University , Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085187008","display_name":"Pinchen Xie","orcid":"https://orcid.org/0000-0002-9330-4032","observed_orcids":["https://orcid.org/0000-0002-9330-4032"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xie, Pinchen","raw_affiliation_strings":["\u2020Department of Chemistry , Princeton University , Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020Department of Chemistry , Princeton University , Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084103157","display_name":"Yuli Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yixiao","raw_affiliation_strings":["\u2021Eastern Institute of Technology , Ningbo , Zhejiang 315200 , China \u00b6Program in Applied and Computational Mathematics ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Eastern Institute of Technology , Ningbo , Zhejiang 315200 , China \u00b6Program in Applied and Computational Mathematics ,","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073103976","display_name":"Pablo M. Piaggi","orcid":"https://orcid.org/0000-0003-0225-0081","observed_orcids":["https://orcid.org/0000-0003-0225-0081"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piaggi, Pablo M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007841515","display_name":"Roberto Car","orcid":"https://orcid.org/0000-0001-5243-2647","observed_orcids":["https://orcid.org/0000-0001-5243-2647"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Car, Roberto","raw_affiliation_strings":["\u2020Department of Chemistry , Princeton University , Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020Department of Chemistry , Princeton University , Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-learning-interatomic-potentials","display_name":"machine learning interatomic potentials","score":0.996999979019165},{"id":"https://openalex.org/keywords/water","display_name":"water","score":0.6729999780654907},{"id":"https://openalex.org/keywords/melting-point","display_name":"melting point","score":0.949999988079071},{"id":"https://openalex.org/keywords/nuclear-quantum-effects","display_name":"nuclear quantum effects","score":0.9919999837875366},{"id":"https://openalex.org/keywords/thermodynamic-conditions","display_name":"thermodynamic conditions","score":0.5320000052452087},{"id":"https://openalex.org/keywords/phase-coverage","display_name":"phase coverage","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C152365726","wikidata":"https://www.wikidata.org/wiki/Q1048589","display_name":"Density functional theory","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C2781442258","wikidata":"https://www.wikidata.org/wiki/Q46310","display_name":"Ab initio","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.477400004863739},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.44940000772476196},{"id":"https://openalex.org/C2989277613","wikidata":"https://www.wikidata.org/wiki/Q283","display_name":"Liquid water","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C2780973484","wikidata":"https://www.wikidata.org/wiki/Q282699","display_name":"Warm dense matter","level":3,"score":0.40230000019073486},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.3817000091075897},{"id":"https://openalex.org/C2777042112","wikidata":"https://www.wikidata.org/wiki/Q5281658","display_name":"Discontinuity (linguistics)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.34850001335144043},{"id":"https://openalex.org/C62792017","wikidata":"https://www.wikidata.org/wiki/Q6795889","display_name":"Maximum density","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C41999313","wikidata":"https://www.wikidata.org/wiki/Q489328","display_name":"Molecular physics","level":1,"score":0.3425000011920929},{"id":"https://openalex.org/C2985276288","wikidata":"https://www.wikidata.org/wiki/Q16873139","display_name":"Melting temperature","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C183971685","wikidata":"https://www.wikidata.org/wiki/Q547605","display_name":"Ab initio quantum chemistry methods","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C112887158","wikidata":"https://www.wikidata.org/wiki/Q169324","display_name":"Hydrogen bond","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C30475298","wikidata":"https://www.wikidata.org/wiki/Q909554","display_name":"Computational physics","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.28220000863075256},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C512968161","wikidata":"https://www.wikidata.org/wiki/Q556","display_name":"Hydrogen","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C119049451","wikidata":"https://www.wikidata.org/wiki/Q3318070","display_name":"Water model","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C154018700","wikidata":"https://www.wikidata.org/wiki/Q898323","display_name":"Path integral formulation","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C9249130","wikidata":"https://www.wikidata.org/wiki/Q898241","display_name":"Local-density approximation","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.23939","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.23939","pdf_url":"https://arxiv.org/pdf/2512.23939","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.23939","doi":"https://doi.org/10.48550/arxiv.2512.23939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.23939","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.23939","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.23939","pdf_url":"https://arxiv.org/pdf/2512.23939","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7118020002.pdf","grobid_xml":"https://content.openalex.org/works/W7118020002.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7167601820"],"related_works":["https://openalex.org/W7163640865","https://openalex.org/W4389680298","https://openalex.org/W4413037896","https://openalex.org/W3211809011","https://openalex.org/W4416048304","https://openalex.org/W4400856948","https://openalex.org/W4407925765","https://openalex.org/W4412069616","https://openalex.org/W4412789389","https://openalex.org/W4393002362"],"abstract_inverted_index":{"Accurate":[0],"predictions":[1,34,59],"of":[2,29,35,61],"machine":[3],"learning":[4],"interatomic":[5],"potentials":[6],"(MLIPs)":[7],"rely":[8],"on":[9,47],"training":[10],"datasets":[11,28,49],"covering":[12],"relevant":[13],"thermodynamic":[14],"conditions":[15],"and":[16,39],"phases.":[17],"Using":[18],"water":[19],"as":[20],"an":[21],"example,":[22],"we":[23],"show":[24],"that":[25],"insufficiently":[26],"sampled":[27],"MLIPs":[30,45],"lead":[31],"to":[32],"wrong":[33],"densities,":[36],"melting":[37],"temperatures,":[38],"nuclear":[40],"quantum":[41],"effects.":[42],"In":[43],"contrast,":[44],"trained":[46],"comprehensive":[48],"with":[50,64,69],"the":[51],"same":[52],"electronic":[53],"structure":[54],"method":[55],"yield":[56],"consistent":[57],"property":[58],"agnostic":[60],"MLIP":[62],"architecture,":[63],"densities":[65],"in":[66],"quantitative":[67],"agreement":[68],"reference":[70],"calculations.":[71]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-01-02T00:00:00"}