{"id":"https://openalex.org/W1975184797","doi":"https://doi.org/10.1145/2588555.2610505","title":"A sample-and-clean framework for fast and accurate query processing on dirty data","display_name":"A sample-and-clean framework for fast and accurate query processing on dirty data","publication_year":2014,"publication_date":"2014-06-18","ids":{"openalex":"https://openalex.org/W1975184797","doi":"https://doi.org/10.1145/2588555.2610505","mag":"1975184797"},"language":"en","primary_location":{"id":"doi:10.1145/2588555.2610505","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-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/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"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"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","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, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","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, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010019244","display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0001-6747-9499"},"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":"Ken Goldberg","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110095410","display_name":"Tova Milo","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tova Milo","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel","Tel Aviv University, Tel Aviv, Israel,"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel,","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101850961"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":18.9184,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.99434257,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"469","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9922000169754028,"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/T11106","display_name":"Data Management and Algorithms","score":0.9872999787330627,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7747857570648193},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6328806281089783},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6208317279815674},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6133557558059692},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5782737731933594},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5102007389068604},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.48651689291000366},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.48429861664772034},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4812855124473572},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4495741128921509},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3473937511444092},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.15533217787742615},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08007344603538513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7747857570648193},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6328806281089783},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6208317279815674},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6133557558059692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5782737731933594},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5102007389068604},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.48651689291000366},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.48429861664772034},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4812855124473572},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4495741128921509},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3473937511444092},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.15533217787742615},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08007344603538513},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2588555.2610505","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.472.1968","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.472.1968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://goldberg.berkeley.edu/pubs/sampleclean-sigmod14.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.9670","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.9670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.math.tau.ac.il/~milo/projects/modas/papers/sigmod14b.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.550000011920929,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3399181978","display_name":null,"funder_award_id":"291071","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G7103680314","display_name":null,"funder_award_id":"FA8750-12-2-0331","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8056273921","display_name":null,"funder_award_id":"CCF-1139158","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W643487436","https://openalex.org/W646670893","https://openalex.org/W1493148361","https://openalex.org/W1551385575","https://openalex.org/W1579798859","https://openalex.org/W1582775886","https://openalex.org/W1586825695","https://openalex.org/W1600034692","https://openalex.org/W1601435884","https://openalex.org/W1603054560","https://openalex.org/W1785933978","https://openalex.org/W1976597724","https://openalex.org/W1981590391","https://openalex.org/W1992363839","https://openalex.org/W2013666871","https://openalex.org/W2022805598","https://openalex.org/W2022858489","https://openalex.org/W2029685080","https://openalex.org/W2031250218","https://openalex.org/W2033057584","https://openalex.org/W2035415465","https://openalex.org/W2037701287","https://openalex.org/W2046298800","https://openalex.org/W2056748234","https://openalex.org/W2056760934","https://openalex.org/W2058991275","https://openalex.org/W2062163196","https://openalex.org/W2063103859","https://openalex.org/W2069897123","https://openalex.org/W2071989194","https://openalex.org/W2081877251","https://openalex.org/W2083293881","https://openalex.org/W2099637074","https://openalex.org/W2100836068","https://openalex.org/W2101654853","https://openalex.org/W2103212156","https://openalex.org/W2108991785","https://openalex.org/W2113878109","https://openalex.org/W2119072946","https://openalex.org/W2119803607","https://openalex.org/W2120793724","https://openalex.org/W2123838014","https://openalex.org/W2139276812","https://openalex.org/W2152029707","https://openalex.org/W2161163216","https://openalex.org/W2163051926","https://openalex.org/W2164456230","https://openalex.org/W2164507334","https://openalex.org/W2199389590","https://openalex.org/W2284530523","https://openalex.org/W2296677182","https://openalex.org/W2334520752","https://openalex.org/W2471080787","https://openalex.org/W2798167046","https://openalex.org/W2989661724","https://openalex.org/W4242587584","https://openalex.org/W4249682906","https://openalex.org/W4250212406","https://openalex.org/W4253248423","https://openalex.org/W4376620677","https://openalex.org/W6770207831"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370","https://openalex.org/W4386427058"],"abstract_inverted_index":{"In":[0,46,70],"emerging":[1],"Big":[2],"Data":[3],"scenarios,":[4],"obtaining":[5],"timely,":[6],"high-quality":[7],"answers":[8],"to":[9,15,86,100,116,196,205],"aggregate":[10,124],"queries":[11],"is":[12],"difficult":[13],"due":[14],"the":[16,28,82,93,106,110,113,118,147,155,164,179,186],"challenges":[17],"of":[18,30,38,84,105,112,120,134,163],"processing":[19,44,198],"and":[20,59,108,137,169,183,202],"cleaning":[21,56,99,114,201,207],"large,":[22],"dirty":[23,121],"data":[24,55,98,107,122,151,172,200,206],"sets.":[25],"To":[26],"increase":[27],"speed":[29,203],"query":[31,43,125,197],"processing,":[32],"there":[33],"has":[34],"been":[35],"a":[36,101,132,161,170],"resurgence":[37],"interest":[39],"in":[40,60,193],"sampling-based":[41],"approximate":[42],"(SAQP).":[45],"its":[47],"usual":[48],"formulation,":[49],"however,":[50],"SAQP":[51],"does":[52],"not":[53],"address":[54],"at":[57],"all,":[58],"fact,":[61],"exacerbates":[62],"answer":[63,89],"quality":[64],"problems":[65],"by":[66],"introducing":[67],"sampling":[68,85],"error.":[69],"this":[71],"paper,":[72],"we":[73,80],"explore":[74,81],"an":[75],"intriguing":[76],"opportunity.":[77],"That":[78],"is,":[79],"use":[83],"actually":[87],"improve":[88],"quality.":[90],"We":[91,127,145],"introduce":[92],"Sample-and-Clean":[94,148,187],"framework,":[95],"which":[96],"applies":[97],"relatively":[102],"small":[103],"subset":[104,162],"uses":[109],"results":[111,175],"process":[115],"lessen":[117],"impact":[119],"on":[123],"answers.":[126],"derive":[128],"confidence":[129,181],"intervals":[130,182],"as":[131],"function":[133],"sample":[135],"size":[136],"show":[138],"how":[139],"our":[140],"approach":[141],"addresses":[142],"error":[143],"bias.":[144],"evaluate":[146],"framework":[149,188],"using":[150],"from":[152],"three":[153],"sources:":[154],"TPC-H":[156],"benchmark":[157],"with":[158,178],"synthetic":[159],"noise,":[160],"Microsoft":[165],"academic":[166],"citation":[167],"index":[168],"sensor":[171],"set.":[173],"Our":[174],"are":[176],"consistent":[177],"theoretical":[180],"suggest":[184],"that":[185],"can":[189],"produce":[190],"significant":[191],"improvements":[192],"accuracy":[194],"compared":[195,204],"without":[199,208],"sampling.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}