{"id":"https://openalex.org/W2116079723","doi":"https://doi.org/10.1145/2629687","title":"Reach for gold","display_name":"Reach for gold","publication_year":2014,"publication_date":"2014-09-04","ids":{"openalex":"https://openalex.org/W2116079723","doi":"https://doi.org/10.1145/2629687","mag":"2116079723"},"language":"en","primary_location":{"id":"doi:10.1145/2629687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2629687","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","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/A5103253344","display_name":"Tobias Vogel","orcid":"https://orcid.org/0000-0003-2608-8859"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Vogel","raw_affiliation_strings":["Hasso Plattner Institute"],"raw_orcid":"https://orcid.org/0000-0003-2608-8859","affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015327612","display_name":"Arvid Heise","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arvid Heise","raw_affiliation_strings":["Hasso Plattner Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076248342","display_name":"Uwe Draisbach","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Uwe Draisbach","raw_affiliation_strings":["Hasso Plattner Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070190076","display_name":"Dustin Lange","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dustin Lange","raw_affiliation_strings":["Hasso Plattner Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso Plattner Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1008,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88404234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"5","issue":"1-2","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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":0.9933000206947327,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8091096878051758},{"id":"https://openalex.org/keywords/gold-standard","display_name":"Gold standard (test)","score":0.6613192558288574},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46721187233924866},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4373125731945038},{"id":"https://openalex.org/keywords/annealing","display_name":"Annealing (glass)","score":0.41338372230529785},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0929180383682251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08028468489646912},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.062472909688949585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091096878051758},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.6613192558288574},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46721187233924866},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4373125731945038},{"id":"https://openalex.org/C2777855556","wikidata":"https://www.wikidata.org/wiki/Q4339544","display_name":"Annealing (glass)","level":2,"score":0.41338372230529785},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0929180383682251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08028468489646912},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.062472909688949585},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2629687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2629687","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.6600000262260437,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W45942636","https://openalex.org/W1487130678","https://openalex.org/W1490467549","https://openalex.org/W1518784700","https://openalex.org/W1528361845","https://openalex.org/W1553682320","https://openalex.org/W1564124598","https://openalex.org/W1585742040","https://openalex.org/W1597164057","https://openalex.org/W1600487529","https://openalex.org/W1689241477","https://openalex.org/W1970381522","https://openalex.org/W1982499516","https://openalex.org/W1995099886","https://openalex.org/W2000672666","https://openalex.org/W2042913039","https://openalex.org/W2046020929","https://openalex.org/W2056616115","https://openalex.org/W2067566391","https://openalex.org/W2080021732","https://openalex.org/W2095644746","https://openalex.org/W2103753221","https://openalex.org/W2104511295","https://openalex.org/W2106568252","https://openalex.org/W2108991785","https://openalex.org/W2112076978","https://openalex.org/W2117974736","https://openalex.org/W2125943921","https://openalex.org/W2129113459","https://openalex.org/W2133990480","https://openalex.org/W2148524305","https://openalex.org/W2149273804","https://openalex.org/W2158486893","https://openalex.org/W2164456230","https://openalex.org/W2171574281","https://openalex.org/W2179182988","https://openalex.org/W2230830246","https://openalex.org/W2318063279","https://openalex.org/W2752496176","https://openalex.org/W2912373720","https://openalex.org/W2912934387","https://openalex.org/W2930957955","https://openalex.org/W3122078363"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W832193342","https://openalex.org/W2382290278","https://openalex.org/W2135768893","https://openalex.org/W176219849","https://openalex.org/W3021414116"],"abstract_inverted_index":{"Duplicates":[0],"in":[1,52,91],"a":[2,104,172],"database":[3],"are":[4,15,60,114,121,132,142],"one":[5],"of":[6,10,47,54,107,112,119],"the":[7,17,21,135,157,185],"prime":[8],"causes":[9],"poor":[11],"data":[12,24],"quality":[13,25],"and":[14,31,37,40,78,80,94,117,129,139,144,148,156,160],"at":[16],"same":[18],"time":[19],"among":[20],"most":[22],"difficult":[23],"problems":[26],"to":[27,63,171,184],"alleviate.":[28],"To":[29],"detect":[30],"remove":[32],"such":[33,48],"duplicates,":[34],"many":[35,92,125],"commercial":[36],"academic":[38],"products":[39],"methods":[41],"have":[42],"been":[43,89],"developed.":[44],"The":[45,99],"evaluation":[46],"systems":[49],"is":[50,69,103],"usually":[51],"need":[53],"pre-classified":[55],"results.":[56],"Such":[57],"gold":[58,173],"standards":[59],"often":[61],"expensive":[62],"come":[64],"by":[65,124],"(much":[66],"manual":[67],"classification":[68],"necessary),":[70],"not":[71],"representative":[72],"(too":[73],"small":[74],"or":[75],"too":[76],"synthetic),":[77],"proprietary":[79],"thus":[81],"preclude":[82],"repetition":[83],"(company-internal":[84],"data).":[85],"This":[86],"lament":[87],"has":[88],"uttered":[90],"papers":[93],"even":[95],"more":[96,128,130,138,140,147,149],"paper":[97],"reviews.":[98],"proposed":[100],"annealing":[101,136,158,168,179],"standard":[102,159,169,180],"structured":[105],"set":[106],"duplicate":[108,186],"detection":[109,187],"results,":[110],"some":[111,118],"which":[113,120],"manually":[115],"verified":[116,143],"merely":[122],"validated":[123],"classifiers.":[126],"As":[127],"classifiers":[131],"evaluated":[133],"against":[134],"standard,":[137],"results":[141],"validation":[145],"becomes":[146],"confident.":[150],"We":[151],"formally":[152],"define":[153],"gold,":[154],"silver,":[155],"their":[161],"maintenance.":[162],"Experiments":[163],"show":[164],"how":[165],"quickly":[166],"an":[167,178],"converges":[170],"standard.":[174],"Finally,":[175],"we":[176],"provide":[177],"for":[181],"750,000":[182],"CDs":[183],"community.":[188]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
