{"id":"https://openalex.org/W3155853464","doi":"https://doi.org/10.1145/3404835.3463246","title":"CopyCat: Near-Duplicates Within and Between the ClueWeb and the Common Crawl","display_name":"CopyCat: Near-Duplicates Within and Between the ClueWeb and the Common Crawl","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3155853464","doi":"https://doi.org/10.1145/3404835.3463246","mag":"3155853464"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463246","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5068616222","display_name":"Maik Fr\u00f6be","orcid":"https://orcid.org/0000-0002-1003-981X"},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Maik Fr\u00f6be","raw_affiliation_strings":["Martin-Luther-Universit\u00e4t Halle-Wittenberg, Halle, Germany"],"affiliations":[{"raw_affiliation_string":"Martin-Luther-Universit\u00e4t Halle-Wittenberg, Halle, Germany","institution_ids":["https://openalex.org/I68956291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079524270","display_name":"Janek Bevendorff","orcid":"https://orcid.org/0000-0002-3797-0559"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Janek Bevendorff","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008775203","display_name":"Lukas Gienapp","orcid":"https://orcid.org/0000-0001-5707-3751"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Gienapp","raw_affiliation_strings":["Leipzig University, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Leipzig University, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037682495","display_name":"Michael V\u00f6lske","orcid":"https://orcid.org/0000-0002-9283-6846"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael V\u00f6lske","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benno Stein","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Potthast","raw_affiliation_strings":["Leipzig University, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Leipzig University, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014322854","display_name":"Matthias Hagen","orcid":"https://orcid.org/0000-0002-9733-2890"},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Hagen","raw_affiliation_strings":["Martin-Luther-Universit\u00e4t Halle-Wittenberg, Halle, Germany"],"affiliations":[{"raw_affiliation_string":"Martin-Luther-Universit\u00e4t Halle-Wittenberg, Halle, Germany","institution_ids":["https://openalex.org/I68956291"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5068616222"],"corresponding_institution_ids":["https://openalex.org/I68956291"],"apc_list":null,"apc_paid":null,"fwci":4.682,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95014273,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2398","last_page":"2404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9940999746322632,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9782999753952026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8251653909683228},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.7959414124488831},{"id":"https://openalex.org/keywords/copycat","display_name":"Copycat","score":0.739058792591095},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6024499535560608},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.49926185607910156},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4947509169578552},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.48728787899017334},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.47816258668899536},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.44334080815315247},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42876285314559937},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4245625138282776},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4159243702888489},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37092697620391846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18698650598526},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09639453887939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251653909683228},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.7959414124488831},{"id":"https://openalex.org/C130191384","wikidata":"https://www.wikidata.org/wiki/Q2996887","display_name":"Copycat","level":2,"score":0.739058792591095},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6024499535560608},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.49926185607910156},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4947509169578552},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.48728787899017334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47816258668899536},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.44334080815315247},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42876285314559937},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4245625138282776},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4159243702888489},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37092697620391846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18698650598526},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09639453887939453},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3463246","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2012833704","https://openalex.org/W2016746605","https://openalex.org/W2037022968","https://openalex.org/W2068098598","https://openalex.org/W2085922539","https://openalex.org/W2120101509","https://openalex.org/W2127536142","https://openalex.org/W2132069633","https://openalex.org/W2134491992","https://openalex.org/W2139532006","https://openalex.org/W2145349611","https://openalex.org/W2148931201","https://openalex.org/W2157748587","https://openalex.org/W2169557227","https://openalex.org/W2740321901","https://openalex.org/W2882999209","https://openalex.org/W2954264361","https://openalex.org/W3035303465","https://openalex.org/W3103686454","https://openalex.org/W3104239639","https://openalex.org/W3106983564"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2089702591","https://openalex.org/W4255854114"],"abstract_inverted_index":{"The":[0],"amount":[1],"of":[2,46,63,81,93,102,122],"near-duplicates":[3,40],"in":[4,31,57],"web":[5],"crawls":[6,112],"like":[7],"the":[8,36,67,69,91,103,111,118],"ClueWeb":[9],"or":[10,34],"Common":[11,73],"Crawl":[12,74],"demands":[13],"from":[14],"their":[15],"users":[16],"either":[17],"to":[18],"develop":[19],"a":[20,86,106],"preprocessing":[21],"pipeline":[22],"for":[23],"deduplication,":[24],"which":[25,51],"is":[26],"costly":[27],"both":[28],"computationally":[29],"and":[30,44,71,84,108,120],"person":[32],"hours,":[33],"accepting":[35],"undesired":[37],"effects":[38],"that":[39,89,100],"have":[41],"on":[42],"reliability":[43],"validity":[45],"experiments.":[47],"We":[48],"introduce":[49],"ChatNoir-CopyCat-21,":[50],"simplifies":[52],"deduplication":[53,92],"significantly.":[54],"It":[55],"comes":[56],"two":[58,72],"parts:":[59],"(1)":[60],"A":[61],"compilation":[62],"near-duplicate":[64],"documents":[65,104],"within":[66,105],"ClueWeb09,":[68],"ClueWeb12,":[70],"snapshots,":[75],"as":[76,78],"well":[77],"between":[79,110],"selections":[80],"these":[82],"crawls,":[83],"(2)":[85],"software":[87],"library":[88],"implements":[90],"arbitrary":[94],"document":[95],"sets.":[96],"Our":[97],"analysis":[98],"shows":[99],"14--52,":[101],"crawl":[107],"around~0.7--2.5,":[109],"are":[113],"near-duplicates.":[114],"Two":[115],"showcases":[116],"demonstrate":[117],"application":[119],"usefulness":[121],"our":[123],"resource.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
