{"id":"https://openalex.org/W7154982099","doi":"https://doi.org/10.48550/arxiv.2604.15380","title":"Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data","display_name":"Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data","publication_year":2026,"publication_date":"2026-04-15","ids":{"openalex":"https://openalex.org/W7154982099","doi":"https://doi.org/10.48550/arxiv.2604.15380"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15380","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.15380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019108731","display_name":"Massimiliano Lupo Pasini","orcid":"https://orcid.org/0000-0002-4980-6924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pasini, Massimiliano Lupo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054451484","display_name":"Jong Youl Choi","orcid":"https://orcid.org/0000-0002-6459-6152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Jong Youl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025779441","display_name":"Kshitij Mehta","orcid":"https://orcid.org/0000-0002-9714-9981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehta, Kshitij","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134058248","display_name":"Richard Messerly","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Messerly, Richard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113007674","display_name":"Rylie Weaver","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weaver, Rylie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134059317","display_name":"Linda Ungerboeck","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ungerboeck, Linda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004692421","display_name":"Isaac Lyngaas","orcid":"https://orcid.org/0000-0002-1682-4309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyngaas, Isaac","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134064028","display_name":"Benajmin Stump","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stump, Benajmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091417392","display_name":"Ashwin M. Aji","orcid":"https://orcid.org/0000-0002-5467-8357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aji, Ashwin M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107027979","display_name":"Karl W. Schulz","orcid":"https://orcid.org/0000-0003-3690-9614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schulz, Karl W.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060815572","display_name":"Jord\u00e0 Polo","orcid":"https://orcid.org/0000-0001-5422-7890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Polo, Jorda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9962000250816345,"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":0.9962000250816345,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7391999959945679},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6348999738693237},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5041999816894531},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.4259999990463257},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4163999855518341},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.4020000100135803},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4016999900341034},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.39959999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404000163078308},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7391999959945679},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6348999738693237},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.4259999990463257},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40470001101493835},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.4020000100135803},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15380","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.15380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15380","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,16,102],"present":[1],"an":[2],"exascale":[3],"workflow":[4],"for":[5],"materials":[6],"discovery":[7],"using":[8,30],"atomistic":[9,79],"graph":[10],"foundation":[11],"models":[12,60],"built":[13],"on":[14,19],"HydraGNN.":[15],"jointly":[17],"train":[18],"16":[20],"open":[21],"first-principles":[22,92,143],"datasets":[23],"(544+":[24],"million":[25],"structures":[26,80],"covering":[27],"85+":[28],"elements)":[29],"a":[31,38,66,85],"multi-task":[32],"architecture":[33],"with":[34],"per-dataset":[35],"heads":[36],"and":[37,55,94,115,119,124,130],"scalable":[39],"ADIOS2/DDStore":[40],"data":[41],"pipeline.":[42],"On":[43],"Frontier,":[44,122],"we":[45],"execute":[46],"six":[47],"large-scale":[48],"DeepHyper":[49],"hyperparameter":[50],"optimization":[51],"campaigns":[52],"in":[53,81],"FP64":[54],"promote":[56],"the":[57],"top-performing":[58],"message-passing":[59],"to":[61,142],"sustained":[62],"2,048-node":[63],"training,":[64],"yielding":[65],"PaiNN-based":[67],"lead":[68],"model.":[69],"The":[70],"resulting":[71],"model":[72],"enables":[73],"billion-scale":[74],"screening,":[75],"evaluating":[76],"1.1":[77],"billion":[78],"50":[82],"seconds,":[83],"compressing":[84],"workload":[86],"that":[87,138],"would":[88],"require":[89],"years":[90],"of":[91,133],"computation,":[93],"supports":[95],"data-scarce":[96],"fine-tuning":[97],"across":[98,109,121],"diverse":[99,112],"downstream":[100,113],"tasks.":[101],"quantify":[103],"precision-performance":[104],"tradeoffs":[105],"(BF16/FP32/FP64),":[106],"demonstrate":[107],"transfer":[108],"twelve":[110],"chemically":[111],"tasks,":[114],"establish":[116],"seamless":[117],"strong-":[118],"weak-scaling":[120],"Aurora,":[123],"Perlmutter.":[125],"This":[126],"work":[127],"allows":[128],"fast":[129],"reliable":[131],"exploration":[132],"vast":[134],"chemical":[135],"design":[136],"spaces":[137],"are":[139],"otherwise":[140],"inaccessible":[141],"methods.":[144]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-21T00:00:00"}