{"id":"https://openalex.org/W2807817912","doi":"https://doi.org/10.14778/3213880.3213886","title":"Constraint-based explanation and repair of filter-based transformations","display_name":"Constraint-based explanation and repair of filter-based transformations","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2807817912","doi":"https://doi.org/10.14778/3213880.3213886","mag":"2807817912"},"language":"en","primary_location":{"id":"doi:10.14778/3213880.3213886","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3213880.3213886","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/A5020695376","display_name":"Dolan Antenucci","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dolan Antenucci","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020695376"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.9953,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86296166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"11","issue":"9","first_page":"947","last_page":"960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.992900013923645,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.7385861873626709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.645289957523346},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.617520272731781},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6169723272323608},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6130152940750122},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5698860883712769},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5688588619232178},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46789443492889404},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.415877103805542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37638694047927856},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3552151024341583},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3301265239715576},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.18640738725662231},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1710929572582245},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0960460901260376}],"concepts":[{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.7385861873626709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.645289957523346},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.617520272731781},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6169723272323608},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6130152940750122},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5698860883712769},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5688588619232178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46789443492889404},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.415877103805542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37638694047927856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3552151024341583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3301265239715576},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.18640738725662231},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1710929572582245},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0960460901260376},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3213880.3213886","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3213880.3213886","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":40,"referenced_works":["https://openalex.org/W1500075493","https://openalex.org/W1759598728","https://openalex.org/W1964151488","https://openalex.org/W1970101292","https://openalex.org/W1970672099","https://openalex.org/W1982597263","https://openalex.org/W1997008462","https://openalex.org/W2003251288","https://openalex.org/W2009591769","https://openalex.org/W2022171653","https://openalex.org/W2038670892","https://openalex.org/W2046010784","https://openalex.org/W2048864522","https://openalex.org/W2061560294","https://openalex.org/W2064766209","https://openalex.org/W2079592420","https://openalex.org/W2089737197","https://openalex.org/W2098516643","https://openalex.org/W2108223890","https://openalex.org/W2132525863","https://openalex.org/W2163925749","https://openalex.org/W2166709576","https://openalex.org/W2167428992","https://openalex.org/W2171972164","https://openalex.org/W2245236296","https://openalex.org/W2374855124","https://openalex.org/W2411583672","https://openalex.org/W2419228228","https://openalex.org/W2430871355","https://openalex.org/W2502366096","https://openalex.org/W2503361011","https://openalex.org/W2575233461","https://openalex.org/W2575776756","https://openalex.org/W2600954565","https://openalex.org/W2612824201","https://openalex.org/W2793382822","https://openalex.org/W2908930479","https://openalex.org/W3121785357","https://openalex.org/W4236206923","https://openalex.org/W4246215794"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W3046775127","https://openalex.org/W4205958290","https://openalex.org/W2078178908","https://openalex.org/W811092902"],"abstract_inverted_index":{"Data":[0],"analysts":[1],"often":[2,203],"need":[3,107],"to":[4,34,68,83,108,118],"transform":[5],"an":[6,161,169],"existing":[7],"dataset,":[8],"such":[9],"as":[10,64,155,157],"with":[11,58,85],"filtering,":[12],"into":[13],"a":[14,43,50,59,65,86,128,183],"new":[15,51],"dataset":[16,101],"for":[17,47,97,132,143,163],"downstream":[18],"analysis.":[19,93],"Even":[20],"the":[21,35,71,80,92,95,100,106,112,123,147,209],"most":[22],"trivial":[23],"of":[24,37,49,75,116,185],"mistakes":[25],"in":[26,99,111,137],"this":[27,186],"phase":[28],"can":[29,104],"introduce":[30],"bias":[31,79,98,120],"and":[32,146,159,181,194,204],"lead":[33],"formation":[36],"invalid":[38],"conclusions.":[39],"For":[40],"example,":[41],"consider":[42],"researcher":[44],"identifying":[45],"subjects":[46],"trials":[48],"statin":[52],"drug.":[53],"She":[54],"might":[55],"identify":[56],"patients":[57],"high":[60],"dietary":[61],"cholesterol":[62],"intake":[63],"population":[66,82],"likely":[67],"benefit":[69],"from":[70],"drug,":[72],"however,":[73],"selection":[74],"these":[76,153],"individuals":[77],"could":[78],"test":[81],"those":[84],"generally":[87],"unhealthy":[88],"lifestyle,":[89],"thereby":[90],"compromising":[91],"Reducing":[94],"potential":[96],"transformation":[102,135,144,174],"process":[103,115],"minimize":[105],"later":[109],"engage":[110],"tedious,":[113],"time-consuming":[114],"trying":[117],"eliminate":[119],"while":[121],"preserving":[122],"target":[124],"dataset.":[125],"We":[126,167,179],"propose":[127],"novel":[129],"interaction":[130],"model":[131],"explain-and-repair":[133],"data":[134],"systems,":[136],"which":[138],"users":[139],"inter-actively":[140],"define":[141],"constraints":[142,154],"code":[145,175],"resultant":[148],"data.":[149],"The":[150],"system":[151],"satisfies":[152],"far":[156],"possible,":[158],"provides":[160],"explanation":[162],"any":[164],"problems":[165],"encountered.":[166],"present":[168],"algorithm":[170],"that":[171],"yields":[172],"filter-based":[173],"satisfying":[176],"user":[177],"constraints.":[178],"implemented":[180],"evaluated":[182],"prototype":[184],"architecture,":[187],"E":[188],"meril":[189],",":[190],"using":[191],"both":[192],"synthetic":[193],"real-world":[195],"datasets.":[196],"Our":[197],"approach":[198],"finds":[199],"solutions":[200],"34%":[201],"more":[202,206],"77%":[205],"quickly":[207],"than":[208],"previous":[210],"state-of-the-art":[211],"solution.":[212]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}