{"id":"https://openalex.org/W4387635006","doi":"https://doi.org/10.1145/3624062.3626081","title":"Towards Foundation Models for Materials Science: The Open MatSci ML Toolkit","display_name":"Towards Foundation Models for Materials Science: The Open MatSci ML Toolkit","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4387635006","doi":"https://doi.org/10.1145/3624062.3626081"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3626081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3626081","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3624062.3626081","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004865099","display_name":"Kin Long Kelvin Lee","orcid":"https://orcid.org/0000-0002-1903-9242"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kin Long Kelvin Lee","raw_affiliation_strings":["Intel Corporation, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-1903-9242","affiliations":[{"raw_affiliation_string":"Intel Corporation, United States of America","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028502615","display_name":"Carmelo Gonzales","orcid":"https://orcid.org/0000-0002-5048-1901"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carmelo Gonzales","raw_affiliation_strings":["Intel Labs, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5048-1901","affiliations":[{"raw_affiliation_string":"Intel Labs, United States of America","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063817417","display_name":"Matthew Spellings","orcid":"https://orcid.org/0000-0002-4061-4299"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthew Spellings","raw_affiliation_strings":["Vector Institute, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4061-4299","affiliations":[{"raw_affiliation_string":"Vector Institute, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102805449","display_name":"Mikhail Galkin","orcid":"https://orcid.org/0000-0003-3526-0155"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mikhail Galkin","raw_affiliation_strings":["Intel Labs, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3526-0155","affiliations":[{"raw_affiliation_string":"Intel Labs, United States of America","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013678286","display_name":"Santiago Miret","orcid":"https://orcid.org/0000-0002-5121-3853"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santiago Miret","raw_affiliation_strings":["Intel Labs, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5121-3853","affiliations":[{"raw_affiliation_string":"Intel Labs, United States of America","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005128859","display_name":"Nalini Kumar","orcid":"https://orcid.org/0000-0002-6173-9963"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nalini Kumar","raw_affiliation_strings":["Intel Corporation, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-6173-9963","affiliations":[{"raw_affiliation_string":"Intel Corporation, United States of America","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5004865099"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":0.9336,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.70746743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":1.0,"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":1.0,"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/T13552","display_name":"Advanced Materials Characterization Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12613","display_name":"X-ray Diffraction in Crystallography","score":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6951777935028076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5668078064918518},{"id":"https://openalex.org/keywords/open-science","display_name":"Open science","score":0.45058366656303406},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3435223698616028},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33334553241729736},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.09914889931678772},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07459133863449097},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.074494868516922}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6951777935028076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5668078064918518},{"id":"https://openalex.org/C2778149293","wikidata":"https://www.wikidata.org/wiki/Q309823","display_name":"Open science","level":2,"score":0.45058366656303406},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3435223698616028},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33334553241729736},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.09914889931678772},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07459133863449097},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.074494868516922},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3624062.3626081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3626081","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.07864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.07864","pdf_url":"https://arxiv.org/pdf/2310.07864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.1145/3624062.3626081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3626081","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1009610150","https://openalex.org/W1678356000","https://openalex.org/W1980780902","https://openalex.org/W1992156271","https://openalex.org/W1992985800","https://openalex.org/W2080635178","https://openalex.org/W2101234009","https://openalex.org/W2230728100","https://openalex.org/W2467249088","https://openalex.org/W2473930607","https://openalex.org/W2622263826","https://openalex.org/W2889326414","https://openalex.org/W2908510526","https://openalex.org/W2940974134","https://openalex.org/W2949095042","https://openalex.org/W2963211188","https://openalex.org/W2963454111","https://openalex.org/W2979402468","https://openalex.org/W2981040094","https://openalex.org/W2983301919","https://openalex.org/W2997591727","https://openalex.org/W3005610174","https://openalex.org/W3023937119","https://openalex.org/W3033607892","https://openalex.org/W3080555959","https://openalex.org/W3093999435","https://openalex.org/W3099406979","https://openalex.org/W3100220443","https://openalex.org/W3101694814","https://openalex.org/W3125167458","https://openalex.org/W3192953411","https://openalex.org/W3195577433","https://openalex.org/W4224308101","https://openalex.org/W4244254628","https://openalex.org/W4281691175","https://openalex.org/W4286910206","https://openalex.org/W4287126984","https://openalex.org/W4287325738","https://openalex.org/W4300537282","https://openalex.org/W4307936700","https://openalex.org/W4309870673","https://openalex.org/W4321085451","https://openalex.org/W4353007232","https://openalex.org/W4366731970","https://openalex.org/W4378942352","https://openalex.org/W6601487527","https://openalex.org/W6912515347","https://openalex.org/W6964039048"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"and":[2,19,25,60,71,79,93,121,126,166],"machine":[3],"learning":[4],"have":[5],"shown":[6],"great":[7],"promise":[8],"in":[9],"their":[10],"ability":[11],"to":[12,23,35,113,138,161],"accelerate":[13],"novel":[14],"materials":[15,41,192],"discovery.":[16],"As":[17],"researchers":[18],"domain":[20],"scientists":[21],"seek":[22],"unify":[24],"consolidate":[26],"chemical":[27],"knowledge,":[28],"the":[29,65,102,171],"case":[30],"for":[31,67,123,133,150,191],"models":[32,145,190],"with":[33,45,53,73],"potential":[34],"generalize":[36],"across":[37,163],"different":[38],"tasks":[39],"within":[40],"science\u2014so-called":[42],"\u201cfoundation":[43],"models\u201d\u2014grows":[44],"ambitions.":[46],"This":[47,180],"manuscript":[48],"reviews":[49],"our":[50,74],"recent":[51],"progress":[52],"development":[54,72],"of":[55,109,119,168],"Open":[56],"MatSci":[57],"ML":[58],"Toolkit,":[59],"details":[61],"experiments":[62],"that":[63,85,132],"lay":[64],"groundwork":[66],"foundation":[68,114,189],"model":[69,115,158],"research":[70],"framework.":[75],"First,":[76],"we":[77,105],"describe":[78],"characterize":[80],"a":[81,107,157],"new":[82],"pretraining":[83,136,175],"task":[84],"uses":[86],"synthetic":[87],"data":[88],"generated":[89],"from":[90,146,174],"symmetry":[91],"operations,":[92],"reveal":[94],"complex":[95,152],"training":[96,144],"dynamics":[97],"at":[98],"large":[99],"scales.":[100],"Using":[101],"pretrained":[103],"model,":[104],"discuss":[106],"number":[108],"use":[110],"cases":[111],"relevant":[112],"development:":[116],"semantic":[117],"architecture":[118],"datasets,":[120],"fine-tuning":[122],"property":[124],"prediction":[125],"classification.":[127],"Our":[128],"key":[129],"results":[130],"show":[131],"simple":[134],"applications,":[135],"appears":[137],"provide":[139],"worse":[140],"modeling":[141],"performance":[142],"than":[143],"random":[147],"initialization.":[148],"However,":[149],"more":[151],"instances,":[153],"such":[154],"as":[155],"when":[156],"is":[159],"required":[160],"learn":[162],"multiple":[164],"datasets":[165],"types":[167],"targets":[169],"simultaneously,":[170],"inductive":[172],"bias":[173],"provides":[176],"significantly":[177],"better":[178],"performance.":[179],"insight":[181],"will":[182],"hopefully":[183],"inform":[184],"subsequent":[185],"efforts":[186],"into":[187],"creating":[188],"science":[193],"applications.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-10-14T00:00:00"}