{"id":"https://openalex.org/W7162764273","doi":"https://doi.org/10.48550/arxiv.2605.29283","title":"Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts","display_name":"Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162764273","doi":"https://doi.org/10.48550/arxiv.2605.29283"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29283","pdf_url":null,"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":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.2605.29283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137328150","display_name":"Mengdi Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Mengdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137377734","display_name":"Yang; Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137323105","display_name":"Ayan Biswas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biswas, Ayan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137316304","display_name":"Han-Wei Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Han-Wei","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.4016000032424927,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.4016000032424927,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.11289999634027481,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.10779999941587448,"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/generality","display_name":"Generality","score":0.8468999862670898},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7027999758720398},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6633999943733215},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6565999984741211},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5691999793052673},{"id":"https://openalex.org/keywords/physical-system","display_name":"Physical system","score":0.4311000108718872},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.38429999351501465}],"concepts":[{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.8468999862670898},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7027999758720398},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6633999943733215},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6565999984741211},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5144000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4180999994277954},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C50773583","wikidata":"https://www.wikidata.org/wiki/Q1294199","display_name":"Physics education","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29283","pdf_url":null,"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":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.2605.29283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29283","pdf_url":null,"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":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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"physics":[1,77,101,153],"foundation":[2,78,102,154],"models":[3,103,155,160],"claim":[4],"general":[5],"spatiotemporal":[6],"forecasting":[7],"ability,":[8],"yet":[9],"their":[10,111,146],"evaluations":[11],"often":[12],"collapse":[13],"performance":[14],"into":[15],"a":[16,21,32,48],"single":[17],"average":[18],"score":[19],"under":[20,43],"fixed":[22],"training":[23,129],"distribution.":[24],"This":[25],"makes":[26],"it":[27],"difficult":[28],"to":[29,143],"determine":[30],"whether":[31],"model":[33,79,83,123],"has":[34],"learned":[35],"generalizable":[36],"physical":[37,52,116,171],"dynamics":[38],"or":[39,161],"only":[40,132],"performs":[41],"well":[42],"particular":[44],"settings.":[45,73],"We":[46,74,149],"construct":[47],"benchmark":[49],"with":[50],"8":[51],"dynamics,":[53],"3":[54],"training-data":[55],"mixtures,":[56],"and":[57,64,71,81,88,125,138,177],"25":[58],"test":[59],"regimes":[60],"induced":[61],"by":[62],"dynamic-scale":[63],"initial-condition":[65,120],"complexity":[66],"shifts,":[67],"covering":[68],"in-distribution,":[69],"distribution-shift,":[70],"out-of-distribution":[72],"evaluate":[75],"five":[76],"architectures":[80],"four":[82],"variants":[84],"per":[85],"architecture":[86],"(scratch":[87],"three":[89],"pretrained":[90],"sizes),":[91],"resulting":[92],"in":[93],"60,000":[94],"measurements.":[95],"Our":[96],"results":[97],"show":[98],"that":[99,151,167],"current":[100],"behave":[104],"as":[105],"conditional":[106],"rather":[107],"than":[108],"universal":[109],"generalists:":[110],"generality":[112],"depends":[113],"on":[114],"the":[115,128],"regime,":[117],"temporal":[118,175],"scale,":[119],"setting,":[121],"pretraining,":[122],"size,":[124],"architecture.":[126],"Improving":[127],"data":[130],"distribution":[131,178],"partially":[133],"mitigates":[134],"this":[135],"limitation.":[136],"Pretraining":[137],"scaling":[139,159],"are":[140],"also":[141],"unable":[142],"reliably":[144],"remove":[145],"ability":[147],"biases.":[148],"argue":[150],"improving":[152],"requires":[156],"moving":[157],"beyond":[158],"expanding":[162],"data,":[163],"toward":[164],"learning":[165],"mechanisms":[166],"better":[168],"capture":[169],"transferable":[170],"knowledge":[172],"across":[173],"regimes,":[174],"scales,":[176],"shifts.":[179]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}