{"id":"https://openalex.org/W3151553572","doi":"https://doi.org/10.1109/icse.2012.6227097","title":"On how often code is cloned across repositories","display_name":"On how often code is cloned across repositories","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W3151553572","doi":"https://doi.org/10.1109/icse.2012.6227097","mag":"3151553572"},"language":"en","primary_location":{"id":"doi:10.1109/icse.2012.6227097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icse.2012.6227097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 34th International Conference on Software Engineering (ICSE)","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/A5066018446","display_name":"Niko Schwarz","orcid":null},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Niko Schwarz","raw_affiliation_strings":["University of Bern, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017593978","display_name":"Mircea Lungu","orcid":"https://orcid.org/0000-0003-3944-5261"},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mircea Lungu","raw_affiliation_strings":["University of Bern, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031712876","display_name":"Romain Robbes","orcid":"https://orcid.org/0000-0003-4569-6868"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Romain Robbes","raw_affiliation_strings":["University of Chile, Chile"],"affiliations":[{"raw_affiliation_string":"University of Chile, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066018446"],"corresponding_institution_ids":["https://openalex.org/I118564535"],"apc_list":null,"apc_paid":null,"fwci":10.2448,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.97919552,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"1289","last_page":"1292"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9782999753952026,"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":0.6995711922645569},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.6383802890777588},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.62017422914505},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5597648024559021},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.511978268623352},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43873023986816406},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.43559131026268005},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42119839787483215},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4145217537879944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33999261260032654},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.16728615760803223},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13957619667053223},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.09113281965255737},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06789472699165344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995711922645569},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.6383802890777588},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.62017422914505},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5597648024559021},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.511978268623352},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43873023986816406},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.43559131026268005},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42119839787483215},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4145217537879944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33999261260032654},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.16728615760803223},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13957619667053223},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09113281965255737},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06789472699165344},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icse.2012.6227097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icse.2012.6227097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 34th International Conference on Software Engineering (ICSE)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.39UBZ_INST:11235424430001241","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/6227097/","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:unibz.it:11235424430001241","is_oa":false,"landing_page_url":"https://bia.unibz.it/esploro/outputs/conferenceProceeding/On-how-often-code-is-cloned/991005773297301241","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.6200000047683716,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G1441312571","display_name":null,"funder_award_id":"00020","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G3325298728","display_name":"Synchronizing Models and Code","funder_award_id":"131827","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G3880319504","display_name":null,"funder_award_id":"200020-131827","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G4836148144","display_name":"Immunologie des Typ-1 Diabetes.","funder_award_id":"20002","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5599649393","display_name":null,"funder_award_id":"200020","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G628552264","display_name":null,"funder_award_id":"200020","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1975770691","https://openalex.org/W1983316175","https://openalex.org/W2018986336","https://openalex.org/W2050703362","https://openalex.org/W2088211982","https://openalex.org/W2101832700","https://openalex.org/W2128888088","https://openalex.org/W2132069633","https://openalex.org/W2138756793","https://openalex.org/W2157532207","https://openalex.org/W2172244770","https://openalex.org/W3003280364"],"related_works":["https://openalex.org/W1973480752","https://openalex.org/W2805502594","https://openalex.org/W4253208712","https://openalex.org/W1603677234","https://openalex.org/W3132641048","https://openalex.org/W2217679042","https://openalex.org/W2525971763","https://openalex.org/W2984753899","https://openalex.org/W2783178962","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Detecting":[0],"code":[1,5,45,50,72],"duplication":[2],"in":[3,73,137],"large":[4,68],"bases,":[6],"or":[7],"even":[8],"across":[9,118],"project":[10],"boundaries,":[11],"is":[12,85],"problematic":[13],"due":[14],"to":[15,66,86,90],"the":[16,32,42,48,74,101,129],"massive":[17],"amount":[18],"of":[19,34,44,59,70,76,107,116,123,131],"data":[20],"involved.":[21],"Large-scale":[22],"clone":[23,37],"detection":[24],"also":[25],"opens":[26],"new":[27],"challenges":[28],"beyond":[29],"asking":[30],"for":[31,128],"provenance":[33],"a":[35,57,92,98],"single":[36],"fragment,":[38],"such":[39],"as":[40],"assessing":[41],"prevalence":[43,130],"clones":[46,136],"on":[47,97],"entire":[49],"base,":[51],"and":[52,134],"their":[53],"evolution.":[54,124],"We":[55,95,125],"propose":[56],"set":[58],"lightweight":[60],"techniques":[61,84],"that":[62],"may":[63],"scale":[64],"up":[65],"very":[67],"amounts":[69],"source":[71],"presence":[75],"multiple":[77],"versions.":[78],"The":[79],"common":[80],"idea":[81],"behind":[82],"these":[83],"use":[87],"bad":[88],"hashing":[89],"get":[91],"quick":[93],"answer.":[94],"report":[96],"case":[99],"study,":[100],"Squeaksource":[102],"ecosystem,":[103],"which":[104],"features":[105],"thousands":[106],"software":[108],"projects,":[109],"with":[110],"more":[111,119],"than":[112,120],"40":[113],"million":[114],"versions":[115],"methods,":[117],"seven":[121],"years":[122],"provide":[126],"estimates":[127],"type-1,":[132],"type-2,":[133],"type-3":[135],"Squeaksource.":[138]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
