{"id":"https://openalex.org/W4388328821","doi":"https://doi.org/10.48550/arxiv.2311.00862","title":"Role of Structural and Conformational Diversity for Machine Learning Potentials","display_name":"Role of Structural and Conformational Diversity for Machine Learning Potentials","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W4388328821","doi":"https://doi.org/10.48550/arxiv.2311.00862"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.00862","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00862","pdf_url":"https://arxiv.org/pdf/2311.00862","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2311.00862","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045851340","display_name":"Nikhil Shenoy","orcid":"https://orcid.org/0009-0003-3083-1454","observed_orcids":["https://orcid.org/0009-0003-3083-1454"]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shenoy, Nikhil","raw_affiliation_strings":["University of British Columbia","Valence Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Valence Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037753193","display_name":"Prudencio Tossou","orcid":"https://orcid.org/0000-0002-9841-9867","observed_orcids":["https://orcid.org/0000-0002-9841-9867"]},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tossou, Prudencio","raw_affiliation_strings":["Laval University","Valence Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laval University","institution_ids":["https://openalex.org/I43406934"]},{"raw_affiliation_string":"Valence Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012750505","display_name":"Emmanuel Noutahi","orcid":"https://orcid.org/0000-0001-5216-9703","observed_orcids":["https://orcid.org/0000-0001-5216-9703"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noutahi, Emmanuel","raw_affiliation_strings":["Valence Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Valence Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086305312","display_name":"Hadrien Mary","orcid":"https://orcid.org/0000-0001-8199-5932","observed_orcids":["https://orcid.org/0000-0001-8199-5932"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mary, Hadrien","raw_affiliation_strings":["Valence Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Valence Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064214996","display_name":"Dominique Beaini","orcid":"https://orcid.org/0000-0002-4613-9388","observed_orcids":["https://orcid.org/0000-0002-4613-9388"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beaini, Dominique","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050542674","display_name":"Jiarui Ding","orcid":"https://orcid.org/0000-0003-3670-7764","observed_orcids":["https://orcid.org/0000-0003-3670-7764"]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ding, Jiarui","raw_affiliation_strings":["University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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":0.9984999895095825,"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":0.9984999895095825,"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":0.0010999999940395355,"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/T10211","display_name":"Computational Drug Discovery Methods","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-learning-interatomic-potentials","display_name":"machine learning interatomic potentials","score":0.9980000257492065},{"id":"https://openalex.org/keywords/conformational-heterogeneity","display_name":"conformational heterogeneity","score":0.9129999876022339},{"id":"https://openalex.org/keywords/structural-diversity","display_name":"structural diversity","score":1.0},{"id":"https://openalex.org/keywords/model-generalization","display_name":"model generalization","score":0.7710000276565552},{"id":"https://openalex.org/keywords/dataset-bias","display_name":"data bias","score":0.7009999752044678},{"id":"https://openalex.org/keywords/applicability-domain","display_name":"applicability domain","score":0.8659999966621399}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7962461709976196},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.7064827680587769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.577663779258728},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5394708514213562},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47354811429977417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3926820158958435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3314220905303955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2203889787197113},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16639012098312378},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0830335021018982},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.00862","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00862","pdf_url":"https://arxiv.org/pdf/2311.00862","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.00862","doi":"https://doi.org/10.48550/arxiv.2311.00862","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.00862","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.00862","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00862","pdf_url":"https://arxiv.org/pdf/2311.00862","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388328821.pdf","grobid_xml":"https://content.openalex.org/works/W4388328821.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2788775653","https://openalex.org/W3196587573","https://openalex.org/W4283641078","https://openalex.org/W4287163433","https://openalex.org/W4287828570","https://openalex.org/W4386516947","https://openalex.org/W4406405186","https://openalex.org/W6893847888"],"related_works":["https://openalex.org/W6923582220","https://openalex.org/W4409665612","https://openalex.org/W4404580258","https://openalex.org/W4388444408","https://openalex.org/W4391831269","https://openalex.org/W4385738720","https://openalex.org/W4297811813","https://openalex.org/W7118020002","https://openalex.org/W7223348796","https://openalex.org/W6948247245"],"abstract_inverted_index":{"In":[0],"the":[1,10,28,50,109,112,122],"field":[2],"of":[3,30,111,124],"Machine":[4],"Learning":[5],"Interatomic":[6],"Potentials":[7],"(MLIPs),":[8],"understanding":[9],"intricate":[11],"relationship":[12],"between":[13,89],"data":[14,34,140],"biases,":[15],"specifically":[16],"conformational":[17,69,84,92],"and":[18,21,55,83,91,136],"structural":[19,65,82,90],"diversity,":[20],"model":[22,129],"generalization":[23,77],"is":[24,94],"critical":[25],"in":[26,76],"improving":[27],"quality":[29],"Quantum":[31],"Mechanics":[32],"(QM)":[33],"generation":[35,141],"efforts.":[36,142],"We":[37],"investigate":[38],"these":[39],"dynamics":[40],"through":[41],"two":[42],"distinct":[43],"experiments:":[44],"a":[45,56,86],"fixed":[46,57,64],"budget":[47],"one,":[48,60],"where":[49],"dataset":[51],"size":[52],"remains":[53],"constant,":[54],"molecular":[58],"set":[59],"which":[61],"focuses":[62],"on":[63],"diversity":[66,93],"while":[67],"varying":[68],"diversity.":[70],"Our":[71],"results":[72,107],"reveal":[73],"nuanced":[74],"patterns":[75],"metrics.":[78],"Notably,":[79],"for":[80,138],"optimal":[81],"generalization,":[85],"careful":[87],"balance":[88],"required,":[95],"but":[96],"existing":[97],"QM":[98,139],"datasets":[99],"do":[100],"not":[101],"meet":[102],"that":[103],"trade-off.":[104],"Additionally,":[105],"our":[106],"highlight":[108],"limitation":[110],"MLIP":[113],"models":[114],"at":[115],"generalizing":[116],"beyond":[117],"their":[118],"training":[119],"distribution,":[120],"emphasizing":[121],"importance":[123],"defining":[125],"applicability":[126],"domain":[127],"during":[128],"deployment.":[130],"These":[131],"findings":[132],"provide":[133],"valuable":[134],"insights":[135],"guidelines":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-11-04T00:00:00"}