{"id":"https://openalex.org/W4399208169","doi":"https://doi.org/10.14778/3659437.3659461","title":"Chorus: Foundation Models for Unified Data Discovery and Exploration","display_name":"Chorus: Foundation Models for Unified Data Discovery and Exploration","publication_year":2024,"publication_date":"2024-04-01","ids":{"openalex":"https://openalex.org/W4399208169","doi":"https://doi.org/10.14778/3659437.3659461"},"language":"en","primary_location":{"id":"doi:10.14778/3659437.3659461","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3659437.3659461","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042488652","display_name":"Moe Kayali","orcid":"https://orcid.org/0000-0002-0643-6468"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Moe Kayali","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001897228","display_name":"Anton Lykov","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anton Lykov","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028997771","display_name":"Ilias Fountalis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilias Fountalis","raw_affiliation_strings":["RelationalAI"],"affiliations":[{"raw_affiliation_string":"RelationalAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034623242","display_name":"Nikolaos Vasiloglou","orcid":"https://orcid.org/0000-0001-8499-7781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Vasiloglou","raw_affiliation_strings":["RelationalAI"],"affiliations":[{"raw_affiliation_string":"RelationalAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035180920","display_name":"Dan Olteanu","orcid":"https://orcid.org/0000-0002-4682-7068"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dan Olteanu","raw_affiliation_strings":["University of Zurich"],"affiliations":[{"raw_affiliation_string":"University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048204602","display_name":"Dan Suciu","orcid":"https://orcid.org/0000-0002-4144-0868"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Suciu","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042488652"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":9.1981,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.982595,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"17","issue":"8","first_page":"2104","last_page":"2114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7681655883789062},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6737916469573975},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5384976267814636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.516943633556366},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5114111304283142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49348247051239014},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3608802556991577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681655883789062},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6737916469573975},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5384976267814636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.516943633556366},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5114111304283142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49348247051239014},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3608802556991577},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3659437.3659461","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3659437.3659461","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4127838089","display_name":null,"funder_award_id":"NSF-BSF","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1656014545","https://openalex.org/W1984566373","https://openalex.org/W2001306005","https://openalex.org/W2064766209","https://openalex.org/W2087275828","https://openalex.org/W2108223890","https://openalex.org/W2251958415","https://openalex.org/W2293299776","https://openalex.org/W2394595640","https://openalex.org/W2440094130","https://openalex.org/W2524643686","https://openalex.org/W2604190938","https://openalex.org/W2747329762","https://openalex.org/W2948163032","https://openalex.org/W2951621897","https://openalex.org/W2952642069","https://openalex.org/W2969723769","https://openalex.org/W2970992672","https://openalex.org/W3021274480","https://openalex.org/W3035231859","https://openalex.org/W3082424964","https://openalex.org/W3100355250","https://openalex.org/W3145728363","https://openalex.org/W3166853427","https://openalex.org/W3172943453","https://openalex.org/W3195577433","https://openalex.org/W3196904276","https://openalex.org/W3201174429","https://openalex.org/W3207690803","https://openalex.org/W3213241618","https://openalex.org/W4210558765","https://openalex.org/W4214671568","https://openalex.org/W4226278401","https://openalex.org/W4289533971","https://openalex.org/W4311725589","https://openalex.org/W4313197536","https://openalex.org/W4319049323","https://openalex.org/W4320005767","https://openalex.org/W4321448364","https://openalex.org/W4322718191","https://openalex.org/W4366731740","https://openalex.org/W4378464611","https://openalex.org/W4379390735","https://openalex.org/W4380353763","https://openalex.org/W4380433117","https://openalex.org/W4381247912","https://openalex.org/W4384918448","https://openalex.org/W4385567134","https://openalex.org/W6633154970","https://openalex.org/W6761551260","https://openalex.org/W6788175385","https://openalex.org/W6803440504","https://openalex.org/W6838461927","https://openalex.org/W6850936240","https://openalex.org/W6852505888"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W2084164722"],"abstract_inverted_index":{"We":[0,31,94],"apply":[1],"foundation":[2,106,134],"models":[3,11,15,35,78,107],"to":[4,28,39,104],"data":[5,41,44,127],"discovery":[6,42],"and":[7,43,62,79,108],"exploration":[8,45],"tasks.":[9],"Foundation":[10],"are":[12,36],"large":[13],"language":[14],"(LLMS)":[16],"that":[17,33,71],"show":[18,32,70],"promising":[19],"performance":[20],"on":[21,54,113],"a":[22,72,121],"range":[23],"of":[24,83,99,111],"diverse":[25],"tasks":[26,129],"unrelated":[27],"their":[29],"training.":[30],"these":[34],"highly":[37],"applicable":[38],"the":[40,76,81,84,96,109,114],"domain.":[46],"When":[47],"carefully":[48],"used,":[49],"they":[50],"have":[51],"superior":[52],"capability":[53],"three":[55,67],"representative":[56],"tasks:":[57],"table-class":[58],"detection,":[59],"column-type":[60],"annotation":[61],"join-column":[63],"prediction.":[64],"On":[65],"all":[66],"tasks,":[68],"we":[69],"foundation-model-based":[73],"approach":[74,88,101],"outperforms":[75],"task-specific":[77],"so":[80],"state":[82],"art.":[85],"Further,":[86],"our":[87],"often":[89],"surpasses":[90],"human-expert":[91],"task":[92],"performance.":[93],"investigate":[95],"fundamental":[97],"characteristics":[98],"this":[100,119],"including":[102],"generalizability":[103],"several":[105],"impact":[110],"non-determinism":[112],"outputs.":[115],"All":[116],"in":[117,124],"all,":[118],"suggests":[120],"future":[122],"direction":[123],"which":[125],"disparate":[126],"management":[128],"can":[130],"be":[131],"unified":[132],"under":[133],"models.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}