{"id":"https://openalex.org/W4379390291","doi":"https://doi.org/10.1145/3555041.3589728","title":"NEXUS: On Explaining Confounding Bias","display_name":"NEXUS: On Explaining Confounding Bias","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4379390291","doi":"https://doi.org/10.1145/3555041.3589728"},"language":"en","primary_location":{"id":"doi:10.1145/3555041.3589728","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3555041.3589728","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3555041.3589728","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3555041.3589728","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026215174","display_name":"Brit Youngmann","orcid":"https://orcid.org/0000-0002-0031-5550"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brit Youngmann","raw_affiliation_strings":["CSAIL MIT, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0031-5550","affiliations":[{"raw_affiliation_string":"CSAIL MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I126820664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["CSAIL MIT, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6122-0590","affiliations":[{"raw_affiliation_string":"CSAIL MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I126820664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005553562","display_name":"Yuval Moskovitch","orcid":"https://orcid.org/0000-0002-0325-7392"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yuval Moskovitch","raw_affiliation_strings":["Ben Gurion University of the Negev, Beer Sheva, Israel"],"raw_orcid":"https://orcid.org/0000-0002-0325-7392","affiliations":[{"raw_affiliation_string":"Ben Gurion University of the Negev, Beer Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"last","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, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2485-9533","affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.236,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55478158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9876000285148621,"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":0.9876000285148621,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9781000018119812,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nexus","display_name":"Nexus (standard)","score":0.8538668155670166},{"id":"https://openalex.org/keywords/confounding","display_name":"Confounding","score":0.7243086099624634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6548054814338684},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.546829104423523},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4864904284477234},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.368634968996048},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32635802030563354},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2308470904827118},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17892968654632568},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11198928952217102}],"concepts":[{"id":"https://openalex.org/C148609458","wikidata":"https://www.wikidata.org/wiki/Q7021281","display_name":"Nexus (standard)","level":2,"score":0.8538668155670166},{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.7243086099624634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6548054814338684},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.546829104423523},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4864904284477234},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.368634968996048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32635802030563354},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2308470904827118},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17892968654632568},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11198928952217102},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3555041.3589728","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3555041.3589728","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3555041.3589728","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/150997","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/150997","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/150997/1/3555041.3589728.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/ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3555041.3589728","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3555041.3589728","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3555041.3589728","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1573942047","display_name":null,"funder_award_id":"2132318","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379390291.pdf","grobid_xml":"https://content.openalex.org/works/W4379390291.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2798682670","https://openalex.org/W3139909695","https://openalex.org/W3173871096"],"related_works":["https://openalex.org/W3126909309","https://openalex.org/W4256360871","https://openalex.org/W2747100754","https://openalex.org/W3117832639","https://openalex.org/W2885513359","https://openalex.org/W2802787844","https://openalex.org/W1578170453","https://openalex.org/W2965101536","https://openalex.org/W2891178753","https://openalex.org/W3121214617"],"abstract_inverted_index":{"When":[0],"analyzing":[1],"large":[2],"datasets,":[3],"analysts":[4],"are":[5,125],"often":[6],"interested":[7],"in":[8,30,66,92,107,119,129],"the":[9,31,38,61,75,78,103,123,130,142,147,163,175],"explanations":[10,91,124],"for":[11,167],"unexpected":[12,51,104,169],"results":[13,171],"produced":[14],"by":[15,172],"their":[16],"queries.":[17],"In":[18,81],"this":[19,82],"work,":[20,83],"we":[21,84],"focus":[22],"on":[23],"aggregate":[24],"SQL":[25,58],"queries":[26,42],"that":[27,36,89,101],"expose":[28,70],"correlations":[29],"data.":[32,132],"A":[33],"major":[34],"challenge":[35],"hinders":[37],"interpretation":[39],"of":[40,94,97,165],"such":[41,151],"is":[43],"confounding":[44,99,113],"bias,":[45],"which":[46],"can":[47],"lead":[48],"to":[49],"an":[50],"association":[52,143],"between":[53,74,144],"variables.":[54],"For":[55,133],"example,":[56],"a":[57,71,87,95,108],"query":[59,170],"computes":[60],"average":[62],"Covid-19":[63,148],"death":[64,79,149],"rate":[65],"each":[67],"country,":[68],"may":[69],"puzzling":[72],"correlation":[73,105],"country":[76],"and":[77,146,157],"rate.":[80],"demonstrate":[85,162],"NEXUS,":[86],"system":[88],"generates":[90],"terms":[93],"set":[96],"potential":[98],"variables":[100,114],"explain":[102],"observed":[106],"query.":[109],"NEXUS":[110,135,166],"mines":[111],"candidate":[112],"from":[115],"external":[116],"sources":[117],"since,":[118],"many":[120],"real-life":[121],"scenarios,":[122],"not":[126],"solely":[127],"contained":[128],"input":[131],"instance,":[134],"might":[136],"extract":[137],"data":[138,182],"about":[139,154],"factors":[140],"explaining":[141],"countries":[145],"rate,":[150],"as":[152,181],"information":[153],"countries'":[155],"economies":[156],"health":[158],"outcomes.":[159],"We":[160],"will":[161,179],"utility":[164],"investigating":[168],"interacting":[173],"with":[174],"SIGMOD'23":[176],"participants,":[177],"who":[178],"act":[180],"analysts.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}