{"id":"https://openalex.org/W4385653229","doi":"https://doi.org/10.14778/3603581.3603602","title":"Causal Data Integration","display_name":"Causal Data Integration","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4385653229","doi":"https://doi.org/10.14778/3603581.3603602"},"language":"en","primary_location":{"id":"doi:10.14778/3603581.3603602","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3603581.3603602","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/A5026215174","display_name":"Brit Youngmann","orcid":"https://orcid.org/0000-0002-0031-5550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brit Youngmann","raw_affiliation_strings":["CSAIL MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL MIT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["CSAIL, MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103209063","display_name":"Babak Salimi","orcid":"https://orcid.org/0000-0003-2485-9533"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Babak Salimi","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091602664","display_name":"Anna Zeng","orcid":"https://orcid.org/0009-0001-7224-363X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna Zeng","raw_affiliation_strings":["CSAIL, MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1211,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89785916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"16","issue":"10","first_page":"2659","last_page":"2665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9957000017166138,"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":0.9957000017166138,"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/T11719","display_name":"Data Quality and Management","score":0.9907000064849854,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.9861999750137329,"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":0.8600219488143921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6883245706558228},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.647674560546875},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.644783616065979},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6291237473487854},{"id":"https://openalex.org/keywords/causal-analysis","display_name":"Causal analysis","score":0.5946365594863892},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5658643841743469},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5483515858650208},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5000724792480469},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.4793882369995117},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.4139050841331482},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.38368165493011475},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3492142856121063},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3303355574607849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2892166078090668},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.17583692073822021},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10326966643333435},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10212534666061401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09574276208877563},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09228560328483582}],"concepts":[{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.8600219488143921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883245706558228},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.647674560546875},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.644783616065979},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6291237473487854},{"id":"https://openalex.org/C2987525970","wikidata":"https://www.wikidata.org/wiki/Q96374569","display_name":"Causal analysis","level":2,"score":0.5946365594863892},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5658643841743469},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5483515858650208},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5000724792480469},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.4793882369995117},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.4139050841331482},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.38368165493011475},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3492142856121063},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3303355574607849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2892166078090668},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.17583692073822021},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10326966643333435},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10212534666061401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09574276208877563},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09228560328483582},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3603581.3603602","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3603581.3603602","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2036705516","https://openalex.org/W2039610696","https://openalex.org/W2125580539","https://openalex.org/W2133919533","https://openalex.org/W2151226328","https://openalex.org/W2171450492","https://openalex.org/W2437617937","https://openalex.org/W2798664493","https://openalex.org/W2798682670","https://openalex.org/W2916603171","https://openalex.org/W2948163032","https://openalex.org/W2952095478","https://openalex.org/W2965536863","https://openalex.org/W2966787092","https://openalex.org/W3013778764","https://openalex.org/W3031898476","https://openalex.org/W3036364901","https://openalex.org/W3036644138","https://openalex.org/W3093972645","https://openalex.org/W3099747923","https://openalex.org/W3139909695","https://openalex.org/W3196904276","https://openalex.org/W4220941910","https://openalex.org/W4240301789","https://openalex.org/W4242428206","https://openalex.org/W4300011764","https://openalex.org/W4302423442"],"related_works":["https://openalex.org/W4313422683","https://openalex.org/W4320159092","https://openalex.org/W2574301230","https://openalex.org/W344802256","https://openalex.org/W4361865420","https://openalex.org/W4385893294","https://openalex.org/W2018580387","https://openalex.org/W4210420802","https://openalex.org/W2161504683","https://openalex.org/W2011959240"],"abstract_inverted_index":{"Causal":[0,108],"inference":[1],"is":[2,80,127,160],"fundamental":[3],"to":[4,26,47,58,72,75],"empirical":[5],"scientific":[6],"discoveries":[7],"in":[8,14,50,83,113,137],"natural":[9],"and":[10,41,61,122,134,142,162],"social":[11],"sciences;":[12],"however,":[13],"the":[15,51,84,107,149,164],"process":[16],"of":[17,86,99],"conducting":[18],"causal":[19,88,125],"inference,":[20],"data":[21,93],"management":[22,94],"problems":[23,31],"can":[24,96],"lead":[25],"false":[27],"discoveries.":[28],"Two":[29],"such":[30],"are":[32,46,117],"(i)":[33],"not":[34],"having":[35],"all":[36],"attributes":[37,45,74,116],"required":[38],"for":[39,77,147,166],"analysis,":[40,78],"(ii)":[42],"misidentifying":[43],"which":[44,79,114],"be":[48],"included":[49],"analysis.":[52],"Analysts":[53],"often":[54,81],"only":[55],"have":[56],"access":[57],"partial":[59],"data,":[60],"they":[62],"critically":[63],"rely":[64],"on":[65],"(often":[66],"unavailable":[67],"or":[68],"incomplete)":[69],"domain":[70],"knowledge":[71],"identify":[73,131],"include":[76],"given":[82],"form":[85],"a":[87,123,139,144],"DAG.":[89],"We":[90,130],"argue":[91],"that":[92,157],"techniques":[95],"surmount":[97],"both":[98],"these":[100],"challenges.":[101],"In":[102],"this":[103],"work,":[104],"we":[105],"introduce":[106],"Data":[109],"Integration":[110],"(CDI)":[111],"problem,":[112],"unobserved":[115],"mined":[118],"from":[119],"external":[120],"sources":[121],"corresponding":[124],"DAG":[126],"automatically":[128],"built.":[129],"key":[132],"challenges":[133],"research":[135],"opportunities":[136],"designing":[138],"CDI":[140,150,159],"system,":[141],"present":[143],"system":[145],"architecture":[146],"solving":[148,158],"problem.":[151],"Our":[152],"preliminary":[153],"experimental":[154],"results":[155],"demonstrate":[156],"achievable":[161],"pave":[163],"way":[165],"future":[167],"research.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}