{"id":"https://openalex.org/W7160857301","doi":"https://doi.org/10.48550/arxiv.2605.07204","title":"Arrow: A Foundation Model for Causal Discovery","display_name":"Arrow: A Foundation Model for Causal Discovery","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160857301","doi":"https://doi.org/10.48550/arxiv.2605.07204"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07204","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.2605.07204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135868583","display_name":"Ryan Thompson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thompson, Ryan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135851221","display_name":"He Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135853641","display_name":"Daniel M. Steinberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steinberg, Daniel M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023657363","display_name":"Edwin V. Bonilla","orcid":"https://orcid.org/0000-0002-9904-2408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bonilla, Edwin V.","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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9707000255584717,"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"}},"topics":[{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9707000255584717,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.006099999882280827,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.005799999926239252,"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/causal-inference","display_name":"Causal inference","score":0.6812000274658203},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.6776999831199646},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.546999990940094},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.5418999791145325},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.46889999508857727},{"id":"https://openalex.org/keywords/arrow","display_name":"Arrow","score":0.4643999934196472},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4221999943256378},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4068000018596649},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.40639999508857727}],"concepts":[{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.6812000274658203},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.6776999831199646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6028000116348267},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4683000147342682},{"id":"https://openalex.org/C2780339515","wikidata":"https://www.wikidata.org/wiki/Q3074698","display_name":"Arrow","level":2,"score":0.4643999934196472},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36739999055862427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C137002209","wikidata":"https://www.wikidata.org/wiki/Q898521","display_name":"Hidden variable theory","level":3,"score":0.3580999970436096},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07204","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.2605.07204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07204","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"Arrow,":[2],"a":[3,16,25,33,38,60,66],"foundation":[4],"model":[5],"for":[6],"zero-shot":[7,139],"causal":[8,116,140],"discovery":[9,117,141],"on":[10,69,133,149],"observational":[11],"tabular":[12],"data.":[13],"Arrow":[14,62,111],"factorizes":[15],"directed":[17,79],"acyclic":[18],"graph":[19,93],"into":[20],"an":[21,76],"undirected":[22],"skeleton":[23,50],"and":[24,45,53,99,104,108,147],"topological":[26],"order,":[27],"guaranteeing":[28],"acyclicity":[29],"by":[30,84],"construction.":[31],"Given":[32],"new":[34,150],"dataset,":[35],"it":[36],"uses":[37],"transformer-based":[39],"architecture":[40],"to":[41],"contextualize":[42],"variables":[43],"within":[44],"across":[46],"observations,":[47],"then":[48],"predicts":[49],"edge":[51,80],"probabilities":[52],"node":[54],"order":[55],"scores":[56],"that":[57,130,143],"together":[58],"define":[59],"graph.":[61],"is":[63],"trained":[64],"in":[65],"supervised":[67],"fashion":[68],"synthetic":[70,135],"datasets":[71],"with":[72],"ground-truth":[73],"graphs,":[74],"using":[75],"end-to-end":[77],"differentiable":[78],"composite":[81],"likelihood":[82],"induced":[83],"the":[85],"skeleton-order":[86],"factorization.":[87],"The":[88],"training":[89],"distribution":[90],"spans":[91],"diverse":[92,134],"families,":[94],"functional":[95],"forms,":[96],"noise":[97],"models,":[98],"dataset":[100],"shapes.":[101],"Across":[102],"in-":[103],"out-of-distribution":[105],"synthetic,":[106],"semi-synthetic,":[107],"real":[109],"datasets,":[110],"matches":[112],"or":[113],"outperforms":[114],"existing":[115],"methods":[118],"at":[119],"substantially":[120],"lower":[121],"inference":[122],"cost":[123],"than":[124],"competitive":[125],"alternatives.":[126],"Our":[127],"results":[128],"demonstrate":[129],"large-scale":[131],"pretraining":[132],"data":[136],"can":[137],"yield":[138],"models":[142],"are":[144],"fast,":[145],"accurate,":[146],"reusable":[148],"datasets.":[151]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}