{"id":"https://openalex.org/W2000809552","doi":"https://doi.org/10.1145/2723372.2750549","title":"Data X-Ray","display_name":"Data X-Ray","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W2000809552","doi":"https://doi.org/10.1145/2723372.2750549","mag":"2000809552"},"language":"en","primary_location":{"id":"doi:10.1145/2723372.2750549","doi":"https://doi.org/10.1145/2723372.2750549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2723372.2750549","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2750549&type=pdf","source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2750549&type=pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100767225","display_name":"Xiaolan Wang","orcid":"https://orcid.org/0000-0002-2293-5160","observed_orcids":["https://orcid.org/0000-0002-2293-5160"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolan Wang","raw_affiliation_strings":["University of Massachusetts, Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001402526","display_name":"Xin Luna Dong","orcid":"https://orcid.org/0009-0000-8667-322X","observed_orcids":["https://orcid.org/0009-0000-8667-322X"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Luna Dong","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048013","display_name":"Alexandra Meliou","orcid":"https://orcid.org/0000-0001-7346-6002","observed_orcids":["https://orcid.org/0000-0001-7346-6002"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandra Meliou","raw_affiliation_strings":["University of Massachusetts, Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.5114,"has_fulltext":true,"cited_by_count":78,"citation_normalized_percentile":{"value":0.99534884,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1231","last_page":"1245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8970000147819519,"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":0.8970000147819519,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.022199999541044235,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.010400000028312206,"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/data-cleaning","display_name":"data cleaning","score":0.796999990940094},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.6899999976158142},{"id":"https://openalex.org/keywords/data-provenance","display_name":"data provenance","score":0.48899999260902405}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.9268965125083923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041099905967712},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6456742882728577},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6229211091995239},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5252087712287903},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44509774446487427},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4283270537853241},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2356995940208435},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.23484420776367188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22959864139556885},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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:10.1145/2723372.2750549","doi":"https://doi.org/10.1145/2723372.2750549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2723372.2750549","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2750549&type=pdf","source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2723372.2750549","doi":"https://doi.org/10.1145/2723372.2750549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2723372.2750549","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2750549&type=pdf","source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1061934380","display_name":"EAGER: Data Debugging","funder_award_id":"1349784","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8231386676","display_name":"III: Small: Collaborative Research: The Package Query Paradigm","funder_award_id":"1421322","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/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2000809552.pdf","grobid_xml":"https://content.openalex.org/works/W2000809552.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W3219084","https://openalex.org/W333550619","https://openalex.org/W1503398984","https://openalex.org/W1551438051","https://openalex.org/W1552694902","https://openalex.org/W1562570268","https://openalex.org/W1565102206","https://openalex.org/W1610496399","https://openalex.org/W1981873012","https://openalex.org/W1983178058","https://openalex.org/W1985694287","https://openalex.org/W1988545508","https://openalex.org/W1996430422","https://openalex.org/W2004915807","https://openalex.org/W2007682403","https://openalex.org/W2008896880","https://openalex.org/W2011039300","https://openalex.org/W2016753842","https://openalex.org/W2022953760","https://openalex.org/W2023052779","https://openalex.org/W2024505010","https://openalex.org/W2024834471","https://openalex.org/W2028438572","https://openalex.org/W2044469685","https://openalex.org/W2047182010","https://openalex.org/W2054967933","https://openalex.org/W2063103859","https://openalex.org/W2074663022","https://openalex.org/W2087183379","https://openalex.org/W2088958550","https://openalex.org/W2089634871","https://openalex.org/W2096544401","https://openalex.org/W2106895292","https://openalex.org/W2107080109","https://openalex.org/W2110411158","https://openalex.org/W2112840274","https://openalex.org/W2114643899","https://openalex.org/W2115010808","https://openalex.org/W2118388899","https://openalex.org/W2122865749","https://openalex.org/W2124026371","https://openalex.org/W2127767383","https://openalex.org/W2133409729","https://openalex.org/W2133986470","https://openalex.org/W2133990480","https://openalex.org/W2135046866","https://openalex.org/W2137775416","https://openalex.org/W2144767994","https://openalex.org/W2149706766","https://openalex.org/W2151763080","https://openalex.org/W2155160033","https://openalex.org/W2157054705","https://openalex.org/W2164334663","https://openalex.org/W2167187514","https://openalex.org/W2167541073","https://openalex.org/W2169585110","https://openalex.org/W2171332293","https://openalex.org/W2261544779","https://openalex.org/W2293299776","https://openalex.org/W2402668406","https://openalex.org/W2596356468","https://openalex.org/W2625773614","https://openalex.org/W2745560456","https://openalex.org/W2962727278","https://openalex.org/W3123128004","https://openalex.org/W4250102289","https://openalex.org/W4285719527","https://openalex.org/W6600944653"],"related_works":["https://openalex.org/W7100827437","https://openalex.org/W1014725521","https://openalex.org/W2394811972","https://openalex.org/W2952551828","https://openalex.org/W4403577492","https://openalex.org/W2039548475","https://openalex.org/W2389991500","https://openalex.org/W2948434003","https://openalex.org/W4400909558","https://openalex.org/W6926644034"],"abstract_inverted_index":{"A":[0],"lot":[1,42],"of":[2,11,19,34,43],"systems":[3],"and":[4,8,55,84],"applications":[5],"are":[6,45],"data-driven,":[7],"the":[9,17,38,49,53,61,86],"correctness":[10,18],"their":[12,20],"operation":[13],"relies":[14],"heavily":[15],"on":[16,79],"data.":[21],"While":[22],"existing":[23],"data":[24,72,80,91],"cleaning":[25],"techniques":[26],"can":[27],"be":[28],"quite":[29],"effective":[30],"at":[31,65],"purging":[32],"datasets":[33],"errors,":[35],"they":[36],"disregard":[37],"fact":[39],"that":[40,51],"a":[41,90],"errors":[44,87],"systematic,":[46],"inherent":[47],"to":[48,70],"process":[50],"produces":[52],"data,":[54],"thus":[56],"will":[57],"keep":[58],"occurring":[59],"unless":[60],"problem":[62],"is":[63],"corrected":[64],"its":[66],"source.":[67],"In":[68],"contrast":[69],"traditional":[71],"cleaning,":[73],"in":[74,89],"this":[75],"paper":[76],"we":[77],"focus":[78],"diagnosis:":[81],"explaining":[82],"where":[83],"how":[85],"happen":[88],"generative":[92],"process.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}