{"id":"https://openalex.org/W1044605864","doi":"https://doi.org/10.1145/2882903.2882909","title":"Estimating the Impact of Unknown Unknowns on Aggregate Query Results","display_name":"Estimating the Impact of Unknown Unknowns on Aggregate Query Results","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W1044605864","doi":"https://doi.org/10.1145/2882903.2882909","mag":"1044605864"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2882909","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2882903.2882909","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2882903.2882909","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 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/10.1145/2882903.2882909","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087758743","display_name":"Yeounoh Chung","orcid":"https://orcid.org/0000-0002-6535-9001"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yeounoh Chung","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014453263","display_name":"Michael Lind Mortensen","orcid":null},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Michael Lind Mortensen","raw_affiliation_strings":["Aarhus University, Aarhus, Denmark","Aarhus University, Aarhus C, Denmark"],"affiliations":[{"raw_affiliation_string":"Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]},{"raw_affiliation_string":"Aarhus University, Aarhus C, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073504200","display_name":"Carsten Binnig","orcid":"https://orcid.org/0000-0002-2744-7836"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carsten Binnig","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087758743"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":5.41816238,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96701738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"861","last_page":"876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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":0.9994000196456909,"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/T11106","display_name":"Data Management and Algorithms","score":0.9919999837875366,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9891999959945679,"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/aggregate","display_name":"Aggregate (composite)","score":0.8205630779266357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7286182045936584},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6682877540588379},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5583707094192505},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5130883455276489},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48290443420410156},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.48176929354667664},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4539756774902344},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3214390277862549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15065032243728638},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.09246361255645752},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06342056393623352}],"concepts":[{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.8205630779266357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286182045936584},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6682877540588379},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5583707094192505},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5130883455276489},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48290443420410156},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.48176929354667664},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4539756774902344},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3214390277862549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15065032243728638},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.09246361255645752},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06342056393623352},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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":1,"locations":[{"id":"doi:10.1145/2882903.2882909","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2882903.2882909","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2882903.2882909","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2882903.2882909","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2882903.2882909","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2882903.2882909","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"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/W1044605864.pdf","grobid_xml":"https://content.openalex.org/works/W1044605864.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W40202779","https://openalex.org/W141764152","https://openalex.org/W189284728","https://openalex.org/W191253868","https://openalex.org/W327170683","https://openalex.org/W600148761","https://openalex.org/W1521736627","https://openalex.org/W1524520778","https://openalex.org/W1532364676","https://openalex.org/W1539550814","https://openalex.org/W1551839888","https://openalex.org/W1553554986","https://openalex.org/W1558982506","https://openalex.org/W1583345983","https://openalex.org/W1585701772","https://openalex.org/W1592068762","https://openalex.org/W1592355944","https://openalex.org/W1601435884","https://openalex.org/W1605921839","https://openalex.org/W1610496399","https://openalex.org/W1971405816","https://openalex.org/W1987094625","https://openalex.org/W2001947543","https://openalex.org/W2002287579","https://openalex.org/W2006346002","https://openalex.org/W2010436309","https://openalex.org/W2012315687","https://openalex.org/W2018592576","https://openalex.org/W2020740057","https://openalex.org/W2022257958","https://openalex.org/W2026289298","https://openalex.org/W2026462408","https://openalex.org/W2032421424","https://openalex.org/W2041457600","https://openalex.org/W2049633694","https://openalex.org/W2056210580","https://openalex.org/W2058991275","https://openalex.org/W2068645020","https://openalex.org/W2082092506","https://openalex.org/W2083293881","https://openalex.org/W2093189534","https://openalex.org/W2100358124","https://openalex.org/W2114413252","https://openalex.org/W2127090196","https://openalex.org/W2129728332","https://openalex.org/W2137479650","https://openalex.org/W2138309709","https://openalex.org/W2138965424","https://openalex.org/W2152057064","https://openalex.org/W2168144930","https://openalex.org/W2312391515","https://openalex.org/W2398093188","https://openalex.org/W2510474575","https://openalex.org/W2523117481","https://openalex.org/W2571791871","https://openalex.org/W6633139782","https://openalex.org/W6635170618","https://openalex.org/W6635371082","https://openalex.org/W6681987778","https://openalex.org/W6698873770","https://openalex.org/W6711965808","https://openalex.org/W6832264174","https://openalex.org/W7002050966","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2027108423","https://openalex.org/W2135768893","https://openalex.org/W1855666948","https://openalex.org/W2758561209","https://openalex.org/W176219849","https://openalex.org/W3021414116","https://openalex.org/W1548095260","https://openalex.org/W2094985717","https://openalex.org/W2594414941","https://openalex.org/W2781711915"],"abstract_inverted_index":{"It":[0],"is":[1,34,43],"common":[2],"practice":[3],"for":[4],"data":[5,12,27,37,51],"scientists":[6],"to":[7,14],"acquire":[8],"and":[9,25,40],"integrate":[10],"disparate":[11],"sources":[13],"achieve":[15],"higher":[16],"quality":[17],"results.":[18],"But":[19],"even":[20],"with":[21],"a":[22],"perfectly":[23],"cleaned":[24],"merged":[26],"set,":[28],"two":[29],"fundamental":[30],"questions":[31],"remain:":[32],"(1)":[33],"the":[35,44],"integrated":[36],"set":[38],"complete":[39],"(2)":[41],"what":[42],"impact":[45],"of":[46],"any":[47],"unknown":[48],"(i.e.,":[49],"unobserved)":[50],"on":[52],"query":[53],"results?":[54]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}