{"id":"https://openalex.org/W2762844179","doi":"https://doi.org/10.1145/3133908","title":"D\u00e9j\u00e0Vu: a map of code duplicates on GitHub","display_name":"D\u00e9j\u00e0Vu: a map of code duplicates on GitHub","publication_year":2017,"publication_date":"2017-10-12","ids":{"openalex":"https://openalex.org/W2762844179","doi":"https://doi.org/10.1145/3133908","mag":"2762844179"},"language":"en","primary_location":{"id":"doi:10.1145/3133908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3133908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3133908","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3133908","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103284742","display_name":"Cristina Videira Lopes","orcid":"https://orcid.org/0000-0003-0551-3908"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cristina V. Lopes","raw_affiliation_strings":["University of California at Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004904234","display_name":"Petr Maj","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Maj","raw_affiliation_strings":["Czech Technical University, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University, Czechia","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059466587","display_name":"Pedro Martins","orcid":"https://orcid.org/0000-0002-4024-7599"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Martins","raw_affiliation_strings":["University of California at Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846745","display_name":"Vaibhav Saini","orcid":"https://orcid.org/0000-0002-6107-9504"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav Saini","raw_affiliation_strings":["University of California at Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031154480","display_name":"Di Yang","orcid":"https://orcid.org/0000-0002-4702-6393"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Yang","raw_affiliation_strings":["University of California at Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080675173","display_name":"\u017ditn\u00fd Jakub","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jakub Zitny","raw_affiliation_strings":["Czech Technical University, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University, Czechia","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015641612","display_name":"Hitesh Sajnani","orcid":"https://orcid.org/0009-0004-9973-6241"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hitesh Sajnani","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084307280","display_name":"Jan V\u00edtek","orcid":"https://orcid.org/0000-0003-4052-3458"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Vitek","raw_affiliation_strings":["Northeastern University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103284742"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":31.8923,"has_fulltext":true,"cited_by_count":178,"citation_normalized_percentile":{"value":0.99656393,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"1","issue":"OOPSLA","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/javascript","display_name":"JavaScript","score":0.7896279096603394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7857730388641357},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7362560033798218},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.7003751397132874},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6050130128860474},{"id":"https://openalex.org/keywords/fork","display_name":"Fork (system call)","score":0.5721392631530762},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48028823733329773},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.4543575048446655},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4539811313152313},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43496960401535034},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36758726835250854},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36574622988700867},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25479352474212646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1116604208946228}],"concepts":[{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.7896279096603394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857730388641357},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7362560033798218},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.7003751397132874},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6050130128860474},{"id":"https://openalex.org/C40523978","wikidata":"https://www.wikidata.org/wiki/Q14675","display_name":"Fork (system call)","level":2,"score":0.5721392631530762},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48028823733329773},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.4543575048446655},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4539811313152313},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43496960401535034},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36758726835250854},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36574622988700867},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25479352474212646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1116604208946228},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3133908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3133908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3133908","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3133908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3133908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3133908","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1300113294","display_name":null,"funder_award_id":"1544542","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2760615557","display_name":null,"funder_award_id":"503353","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6492659061","display_name":"Evolving Language Ecosystems","funder_award_id":"695412","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2762844179.pdf","grobid_xml":"https://content.openalex.org/works/W2762844179.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W19752705","https://openalex.org/W1482624438","https://openalex.org/W1948496691","https://openalex.org/W1972386298","https://openalex.org/W2015018654","https://openalex.org/W2056830820","https://openalex.org/W2086303410","https://openalex.org/W2097908858","https://openalex.org/W2099677903","https://openalex.org/W2100060170","https://openalex.org/W2115052242","https://openalex.org/W2132944054","https://openalex.org/W2135261046","https://openalex.org/W2138756793","https://openalex.org/W2140952846","https://openalex.org/W2142958724","https://openalex.org/W2150650310","https://openalex.org/W2158439356","https://openalex.org/W2166091242","https://openalex.org/W2169090130","https://openalex.org/W2286236884","https://openalex.org/W2404313524","https://openalex.org/W2417033663","https://openalex.org/W2440056063","https://openalex.org/W2467974757","https://openalex.org/W3102273185","https://openalex.org/W4301168982","https://openalex.org/W4386707048"],"related_works":["https://openalex.org/W2937118960","https://openalex.org/W2808525305","https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W3208656504","https://openalex.org/W2461078469","https://openalex.org/W4287027380","https://openalex.org/W1699080303","https://openalex.org/W2789551765"],"abstract_inverted_index":{"Previous":[0],"studies":[1],"have":[2,132,160],"shown":[3],"that":[4,42,109,123],"there":[5],"is":[6,69],"a":[7,18,46,105,153,163],"non-trivial":[8],"amount":[9],"of":[10,20,56,62,64,80,85,100,114,121,130,156,167],"duplication":[11,131],"in":[12,34,147,170],"source":[13,139],"code.":[14],"This":[15],"paper":[16],"analyzes":[17],"corpus":[19,44],"4.5":[21],"million":[22,31,49],"non-fork":[23],"projects":[24,116],"hosted":[25],"on":[26,59,91,137],"GitHub":[27,60,171],"representing":[28],"over":[29],"428":[30],"files":[32,87,101,122],"written":[33],"Java,":[35,90],"C++,":[36],"Python,":[37],"and":[38,112],"JavaScript.":[39],"We":[40],"found":[41,126],"this":[43,157],"has":[45,76,95],"mere":[47],"85":[48],"unique":[50],"files.":[51,67],"In":[52],"other":[53,93],"words,":[54],"70%":[55],"the":[57,77,86,92,96,115],"code":[58,150,168],"consists":[61],"clones":[63],"previously":[65],"created":[66,161],"There":[68],"considerable":[70],"variation":[71],"between":[72,110],"language":[73],"ecosystems.":[74],"JavaScript":[75],"highest":[78],"rate":[79],"file":[81],"duplication,":[82,98],"only":[83],"6%":[84],"are":[88,102],"distinct.":[89,103],"hand,":[94],"least":[97,119],"60%":[99],"Lastly,":[104],"project-level":[106],"analysis":[107],"shows":[108],"9%":[111],"31%":[113],"contain":[117],"at":[118],"80%":[120],"can":[124],"be":[125],"elsewhere.":[127],"These":[128],"rates":[129],"implications":[133],"for":[134,144],"systems":[135],"built":[136],"open":[138],"software":[140],"as":[141,143],"well":[142],"researchers":[145],"interested":[146],"analyzing":[148],"large":[149],"bases.":[151],"As":[152],"concrete":[154],"artifact":[155],"study,":[158],"we":[159],"D\u00e9j\u00e0Vu,":[162],"publicly":[164],"available":[165],"map":[166],"duplicates":[169],"repositories.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":17}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
