{"id":"https://openalex.org/W2247123384","doi":"https://doi.org/10.14778/2824032.2824122","title":"Wisteria","display_name":"Wisteria","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2247123384","doi":"https://doi.org/10.14778/2824032.2824122","mag":"2247123384"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824122","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824122","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/A5037061685","display_name":"Daniel Haas","orcid":"https://orcid.org/0000-0002-0033-0128"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Haas","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018480426","display_name":"Sanjay Krishnan","orcid":"https://orcid.org/0000-0001-6968-4090"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Krishnan","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019638","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0003-3332-8574"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.0193,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.98231112,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":"12","first_page":"2004","last_page":"2007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9958000183105469,"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":0.9958000183105469,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9905999898910522,"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/workflow","display_name":"Workflow","score":0.7639738321304321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7123834490776062},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.6645528078079224},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6215615272521973},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5843183994293213},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.5814611315727234},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4913467466831207},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.45400500297546387},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.41597023606300354},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4122942090034485},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2178019881248474},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20361164212226868},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.15457165241241455},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1485157012939453}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7639738321304321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123834490776062},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6645528078079224},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6215615272521973},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5843183994293213},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.5814611315727234},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4913467466831207},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.45400500297546387},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.41597023606300354},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4122942090034485},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2178019881248474},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20361164212226868},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.15457165241241455},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1485157012939453},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2824032.2824122","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824122","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1876812886","https://openalex.org/W1975184797","https://openalex.org/W2013666871","https://openalex.org/W2032655922","https://openalex.org/W2044102377","https://openalex.org/W2046298800","https://openalex.org/W2064766209","https://openalex.org/W2107966677","https://openalex.org/W2164187405","https://openalex.org/W2288244345","https://openalex.org/W2296195275","https://openalex.org/W2616338822","https://openalex.org/W2912506132","https://openalex.org/W4291720518","https://openalex.org/W6696516842","https://openalex.org/W6737834103"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W4384486036","https://openalex.org/W135177976","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114","https://openalex.org/W4286908577"],"abstract_inverted_index":{"Analysts":[0],"report":[1],"spending":[2],"upwards":[3],"of":[4,6,35,81,99,129],"80%":[5],"their":[7],"time":[8],"on":[9,32],"problems":[10],"in":[11,136],"data":[12,15,30,100,163],"cleaning.":[13,166],"The":[14,167],"cleaning":[16,23,44,101],"process":[17],"is":[18,169],"inherently":[19],"iterative,":[20],"with":[21,27,41],"evolving":[22],"workflows":[24],"that":[25,105],"start":[26],"basic":[28],"exploratory":[29],"analysis":[31,40,164],"small":[33],"samples":[34],"dirty":[36],"data,":[37],"then":[38,151],"refine":[39],"more":[42],"sophisticated/expensive":[43],"operators":[45,83],"(e.g.,":[46],"crowdsourcing),":[47],"and":[48,84,97,116,141,148,165],"finally":[49],"apply":[50],"the":[51,94,107,126,145],"insights":[52],"to":[53,69,75,92,125,156],"a":[54,63,77,89,153],"full":[55],"dataset.":[56],"While":[57],"an":[58],"analyst":[59,119],"often":[60,73],"knows":[61],"at":[62],"logical":[64,111],"level":[65],"what":[66],"operations":[67,112],"need":[68],"be":[70],"done,":[71],"they":[72],"have":[74],"manage":[76],"large":[78],"search":[79],"space":[80],"physical":[82,114,130],"parameters.":[85],"We":[86,132,143],"present":[87],"Wisteria,":[88],"system":[90,146],"designed":[91,155],"support":[93],"iterative":[95,162],"development":[96],"optimization":[98],"workflows,":[102],"especially":[103],"ones":[104],"utilize":[106],"crowd.":[108],"Wisteria":[109,159],"separates":[110],"from":[113],"implementations,":[115],"driven":[117],"by":[118],"feedback,":[120],"suggests":[121],"optimizations":[122],"and/or":[123],"replacements":[124],"analyst's":[127],"choice":[128],"implementation.":[131],"highlight":[133],"research":[134],"challenges":[135],"sampling,":[137],"in-flight":[138],"operator":[139],"replacement,":[140],"crowdsourcing.":[142],"overview":[144],"architecture":[147],"these":[149],"techniques,":[150],"provide":[152],"demonstration":[154],"showcase":[157],"how":[158],"can":[160],"improve":[161],"code":[168],"available":[170],"at:":[171],"http://www.sampleclean.org.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}