{"id":"https://openalex.org/W4399872350","doi":"https://doi.org/10.1145/3656409","title":"GenSQL: A Probabilistic Programming System for Querying Generative Models of Database Tables","display_name":"GenSQL: A Probabilistic Programming System for Querying Generative Models of Database Tables","publication_year":2024,"publication_date":"2024-06-20","ids":{"openalex":"https://openalex.org/W4399872350","doi":"https://doi.org/10.1145/3656409"},"language":"en","primary_location":{"id":"doi:10.1145/3656409","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656409","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656409","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3656409","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066894896","display_name":"Mathieu Huot","orcid":"https://orcid.org/0000-0002-5294-9088"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mathieu Huot","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014964882","display_name":"Matin Ghavami","orcid":"https://orcid.org/0000-0003-3052-7412"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matin Ghavami","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056016273","display_name":"Alexander K. Lew","orcid":"https://orcid.org/0000-0002-9262-4392"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander K. Lew","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005463369","display_name":"Ulrich Schaechtle","orcid":"https://orcid.org/0009-0005-8897-6394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ulrich Schaechtle","raw_affiliation_strings":["Digital Garage, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Garage, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037836079","display_name":"Cameron E. Freer","orcid":"https://orcid.org/0000-0003-1791-6843"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cameron E. Freer","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078307684","display_name":"Z. Shelby","orcid":"https://orcid.org/0009-0003-2976-4581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zane Shelby","raw_affiliation_strings":["Digital Garage, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Garage, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045127387","display_name":"Martin Rinard","orcid":"https://orcid.org/0000-0001-8095-8523"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin C. Rinard","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009835778","display_name":"Feras A. Saad","orcid":"https://orcid.org/0000-0002-0505-795X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feras A. Saad","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068340465","display_name":"Vikash K. Mansinghka","orcid":"https://orcid.org/0000-0003-2507-0833"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikash K. Mansinghka","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5066894896"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.3719,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81625616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"8","issue":"PLDI","first_page":"790","last_page":"815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9973999857902527,"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/T11106","display_name":"Data Management and Algorithms","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7744578123092651},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.591367244720459},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5710400342941284},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.45505625009536743},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.42594635486602783},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36604052782058716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23242345452308655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744578123092651},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.591367244720459},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5710400342941284},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.45505625009536743},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42594635486602783},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36604052782058716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23242345452308655}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3656409","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656409","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656409","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2406.15652","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.15652","pdf_url":"https://arxiv.org/pdf/2406.15652","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/155514","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/155514","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/155514/1/3656409.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computing Machinery","raw_type":"http://purl.org/eprint/type/JournalArticle"}],"best_oa_location":{"id":"doi:10.1145/3656409","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656409","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656409","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5853564017","display_name":null,"funder_award_id":"FA8750-17-C-0239","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7928622218","display_name":null,"funder_award_id":"140D0422C0045","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8393553921","display_name":null,"funder_award_id":"FA8750-17-C-02","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8704047134","display_name":null,"funder_award_id":"2311983","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"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399872350.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W342302233","https://openalex.org/W1437335841","https://openalex.org/W1545129310","https://openalex.org/W1609127433","https://openalex.org/W1891298814","https://openalex.org/W1973944070","https://openalex.org/W2046536636","https://openalex.org/W2048027175","https://openalex.org/W2071989194","https://openalex.org/W2086128349","https://openalex.org/W2099655235","https://openalex.org/W2102539288","https://openalex.org/W2128984831","https://openalex.org/W2132940078","https://openalex.org/W2134153749","https://openalex.org/W2183668859","https://openalex.org/W2185907055","https://openalex.org/W2188564768","https://openalex.org/W2217402295","https://openalex.org/W2234140215","https://openalex.org/W2330245166","https://openalex.org/W2338065342","https://openalex.org/W2494200839","https://openalex.org/W2551925796","https://openalex.org/W2565964471","https://openalex.org/W2577537660","https://openalex.org/W2591700809","https://openalex.org/W2736213971","https://openalex.org/W2750756391","https://openalex.org/W2753599755","https://openalex.org/W2762833920","https://openalex.org/W2765370125","https://openalex.org/W2808311877","https://openalex.org/W2862455684","https://openalex.org/W2900091806","https://openalex.org/W2902895875","https://openalex.org/W2950748699","https://openalex.org/W2964024268","https://openalex.org/W2997591727","https://openalex.org/W2998758053","https://openalex.org/W3013555795","https://openalex.org/W3090482648","https://openalex.org/W3104822289","https://openalex.org/W3123228431","https://openalex.org/W3159836140","https://openalex.org/W3173567886","https://openalex.org/W3185730212","https://openalex.org/W3202178925","https://openalex.org/W4200377602","https://openalex.org/W4205412526","https://openalex.org/W4205814206","https://openalex.org/W4214948091","https://openalex.org/W4247690662","https://openalex.org/W4292080426","https://openalex.org/W4292691288","https://openalex.org/W4300564796","https://openalex.org/W4301005547","https://openalex.org/W4378718473","https://openalex.org/W4379536898","https://openalex.org/W6911341818","https://openalex.org/W6965408117"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W2494523064","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W2943623134","https://openalex.org/W2588219639","https://openalex.org/W4237784285","https://openalex.org/W2215759665"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"GenSQL,":[3],"a":[4,21,44,65,89,97,137,180,189],"probabilistic":[5,10,27,51,68,84],"programming":[6,69],"system":[7,100,120],"for":[8,25,48,136],"querying":[9,26],"generative":[11],"models":[12,52,62,78],"of":[13,53,67,91,149],"database":[14],"tables.":[15],"By":[16],"augmenting":[17],"SQL":[18],"with":[19,50],"only":[20],"few":[22],"key":[23],"primitives":[24],"models,":[28],"GenSQL":[29,93,143,165,178],"enables":[30],"complex":[31],"Bayesian":[32],"inference":[33],"workflows":[34],"to":[35,60,74,108,154,174,184,198,204],"be":[36,80],"concisely":[37],"implemented.":[38],"GenSQL\u2019s":[39],"query":[40],"planner":[41],"rests":[42],"on":[43,121,188],"unified":[45],"programmatic":[46],"interface":[47],"interacting":[49],"tabular":[54],"data,":[55],"which":[56,104],"makes":[57],"it":[58],"possible":[59],"use":[61],"written":[63],"in":[64,128,164,195,201],"variety":[66],"languages":[70],"that":[71,111,142,160],"are":[72],"tailored":[73],"specific":[75],"workflows.":[76],"Probabilistic":[77],"may":[79],"automatically":[81],"learned":[82],"via":[83],"program":[85],"synthesis,":[86],"hand-designed,":[87],"or":[88],"combination":[90],"both.":[92],"is":[94,166],"formalized":[95],"using":[96],"novel":[98],"type":[99],"and":[101,131,169,193,208],"denotational":[102],"semantics,":[103],"together":[105],"enable":[106],"us":[107],"establish":[109],"proofs":[110],"precisely":[112],"characterize":[113],"its":[114,185,205],"soundness":[115],"guarantees.":[116],"We":[117,157],"evaluate":[118],"our":[119],"two":[122],"case":[123],"real-world":[124],"studies\u2014an":[125],"anomaly":[126],"detection":[127],"clinical":[129],"trials":[130],"conditional":[132],"synthetic":[133],"data":[134,151],"generation":[135],"virtual":[138],"wet":[139],"lab\u2014and":[140],"show":[141,159],"more":[144,167],"accurately":[145],"captures":[146],"the":[147,150,161],"complexity":[148],"as":[152,172],"compared":[153,173,183],"common":[155],"baselines.":[156],"also":[158],"declarative":[162],"syntax":[163],"concise":[168],"less":[170],"error-prone":[171],"several":[175],"alternatives.":[176],"Finally,":[177],"delivers":[179],"1.7-6.8x":[181],"speedup":[182],"closest":[186],"competitor":[187],"representative":[190],"benchmark":[191],"set":[192],"runs":[194],"comparable":[196],"time":[197],"hand-written":[199],"code,":[200],"part":[202],"due":[203],"reusable":[206],"optimizations":[207],"code":[209],"specialization.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}