{"id":"https://openalex.org/W4321448364","doi":"https://doi.org/10.14778/3574245.3574258","title":"Can Foundation Models Wrangle Your Data?","display_name":"Can Foundation Models Wrangle Your Data?","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4321448364","doi":"https://doi.org/10.14778/3574245.3574258"},"language":"en","primary_location":{"id":"doi:10.14778/3574245.3574258","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574258","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/A5039749428","display_name":"Avanika Narayan","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Avanika Narayan","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055452554","display_name":"Ines Chami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ines Chami","raw_affiliation_strings":["Numbers Station"],"affiliations":[{"raw_affiliation_string":"Numbers Station","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054285881","display_name":"Laurel Orr","orcid":"https://orcid.org/0000-0002-2183-3541"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laurel Orr","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109519525","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R\u00e9","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039749428"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":19.8315,"has_fulltext":false,"cited_by_count":128,"citation_normalized_percentile":{"value":0.99716805,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"16","issue":"4","first_page":"738","last_page":"746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9926000237464905,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.7950524091720581},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7029057741165161},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5617936253547668},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5004308223724365},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4768851101398468},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4597248435020447},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4452369511127472},{"id":"https://openalex.org/keywords/proof-of-concept","display_name":"Proof of concept","score":0.43090397119522095},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3602529466152191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3388928771018982},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.214048832654953},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12571337819099426},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.10012203454971313},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09042295813560486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950524091720581},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7029057741165161},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5617936253547668},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5004308223724365},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4768851101398468},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4597248435020447},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4452369511127472},{"id":"https://openalex.org/C124978682","wikidata":"https://www.wikidata.org/wiki/Q1201019","display_name":"Proof of concept","level":2,"score":0.43090397119522095},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3602529466152191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3388928771018982},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.214048832654953},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12571337819099426},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10012203454971313},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09042295813560486},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3574245.3574258","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574258","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":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2021651899","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2056748234","https://openalex.org/W2064766209","https://openalex.org/W2107966677","https://openalex.org/W2139077857","https://openalex.org/W2164187405","https://openalex.org/W2340222647","https://openalex.org/W2544486974","https://openalex.org/W2546672044","https://openalex.org/W2591700809","https://openalex.org/W2593831809","https://openalex.org/W2741609678","https://openalex.org/W2744999500","https://openalex.org/W2798649495","https://openalex.org/W2929941791","https://openalex.org/W2963341956","https://openalex.org/W2964303773","https://openalex.org/W2970476646","https://openalex.org/W2981852735","https://openalex.org/W2994017552","https://openalex.org/W2997200074","https://openalex.org/W2997919412","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3081168214","https://openalex.org/W3105977086","https://openalex.org/W3123375411","https://openalex.org/W3126220825","https://openalex.org/W3160638507","https://openalex.org/W3168771811","https://openalex.org/W3170344956","https://openalex.org/W3172642864","https://openalex.org/W3174770825","https://openalex.org/W3203321135","https://openalex.org/W3205068155","https://openalex.org/W3212496002","https://openalex.org/W4205991051","https://openalex.org/W4281826654","https://openalex.org/W4288089799","https://openalex.org/W4385696152","https://openalex.org/W6772013027"],"related_works":["https://openalex.org/W2332779545","https://openalex.org/W2381393187","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2220552745","https://openalex.org/W2777605427","https://openalex.org/W2501983714"],"abstract_inverted_index":{"Foundation":[0],"Models":[1],"(FMs)":[2],"are":[3,109],"models":[4,27,42,125],"trained":[5,111],"on":[6,45,87,100],"large":[7,14,93],"corpora":[8],"of":[9,39,58,85],"data":[10,61,73,101,114,139],"that,":[11],"at":[12],"very":[13],"scale,":[15],"can":[16,43],"generalize":[17,95],"to":[18,29,35,53,137,144],"new":[19],"tasks":[20,62,77,80],"without":[21],"any":[22],"task-specific":[23],"finetuning.":[24],"As":[25,67],"these":[26,41,88,113,124],"continue":[28,34],"grow":[30],"in":[31],"size,":[32],"innovations":[33],"push":[36],"the":[37,83],"boundaries":[38],"what":[40],"do":[44],"language":[46],"and":[47,65,75,81,96,103,121,131,135,150],"image":[48],"tasks.":[49,89,115],"This":[50],"paper":[51],"aims":[52],"understand":[54],"an":[55],"underexplored":[56],"area":[57],"FMs:":[59],"classical":[60],"like":[63],"cleaning":[64,74,102],"integration.":[66],"a":[68],"proof-of-concept,":[69],"we":[70],"cast":[71],"five":[72],"integration":[76,104],"as":[78],"prompting":[79],"evaluate":[82],"performance":[84,99],"FMs":[86,94],"We":[90,116,146],"find":[91],"that":[92,123],"achieve":[97],"SoTA":[98],"tasks,":[105],"even":[106],"though":[107],"they":[108],"not":[110],"for":[112],"identify":[117],"specific":[118,133],"research":[119],"challenges":[120,128],"opportunities":[122,136],"present,":[126],"including":[127],"with":[129],"private":[130],"domain":[132],"data,":[134],"make":[138,147],"management":[140],"systems":[141],"more":[142],"accessible":[143],"non-experts.":[145],"our":[148],"code":[149],"experiments":[151],"publicly":[152],"available":[153],"at:":[154],"https://github.com/HazyResearch/fm_data_tasks.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":58},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":17}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}