{"id":"https://openalex.org/W2138756793","doi":"https://doi.org/10.1109/tse.2002.1019480","title":"CCFinder: a multilinguistic token-based code clone detection system for large scale source code","display_name":"CCFinder: a multilinguistic token-based code clone detection system for large scale source code","publication_year":2002,"publication_date":"2002-07-01","ids":{"openalex":"https://openalex.org/W2138756793","doi":"https://doi.org/10.1109/tse.2002.1019480","mag":"2138756793"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2002.1019480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2002.1019480","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ir.library.osaka-u.ac.jp/repo/ouka/all/51063/arou_3_22.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112522132","display_name":"T. Kamiya","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kamiya","raw_affiliation_strings":["Graduate Sch. of Eng. Sci., Osaka Univ., Japan","Graduate School of Engineering Science, Osaka University , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Sch. of Eng. Sci., Osaka Univ., Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University , Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077367961","display_name":"S. Kusumoto","orcid":"https://orcid.org/0000-0002-4551-6719"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Kusumoto","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Toyonaka, Osaka, Japan","Graduate School of Engineering Science, Osaka University, 1-3, Machikaneyama-cho, Toyonaka, Osaka, 560-8531, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Toyonaka, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, 1-3, Machikaneyama-cho, Toyonaka, Osaka, 560-8531, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087002387","display_name":"Koji Inoue","orcid":"https://orcid.org/0000-0003-3926-0646"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Inoue","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Toyonaka, Osaka, Japan","Graduate School of Engineering Science, Osaka University, 1-3, Machikaneyama-cho, Toyonaka, Osaka, 560-8531, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Toyonaka, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, 1-3, Machikaneyama-cho, Toyonaka, Osaka, 560-8531, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":100.7476,"has_fulltext":true,"cited_by_count":1733,"citation_normalized_percentile":{"value":0.99908993,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"28","issue":"7","first_page":"654","last_page":"670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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":0.9984999895095825,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8406221866607666},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.7532436847686768},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7079141139984131},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.6898478269577026},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.610880434513092},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.6061736345291138},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5762637257575989},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5170653462409973},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5137027502059937},{"id":"https://openalex.org/keywords/maintainability","display_name":"Maintainability","score":0.5008993148803711},{"id":"https://openalex.org/keywords/software-maintenance","display_name":"Software maintenance","score":0.48968270421028137},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.43322306871414185},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.40217792987823486},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.39246031641960144},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2605050206184387},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.0904163122177124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406221866607666},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7532436847686768},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7079141139984131},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.6898478269577026},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.610880434513092},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.6061736345291138},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5762637257575989},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5170653462409973},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5137027502059937},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.5008993148803711},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.48968270421028137},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.43322306871414185},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.40217792987823486},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.39246031641960144},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2605050206184387},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0904163122177124},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tse.2002.1019480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2002.1019480","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:ir.library.osaka-u.ac.jp:11094/51063","is_oa":true,"landing_page_url":null,"pdf_url":"https://ir.library.osaka-u.ac.jp/repo/ouka/all/51063/arou_3_22.pdf","source":{"id":"https://openalex.org/S4306402540","display_name":"OUKA (Osaka University Knowledge Archive) (Osaka University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98285908","host_organization_name":"The University of Osaka","host_organization_lineage":["https://openalex.org/I98285908"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:ir.library.osaka-u.ac.jp:11094/51063","is_oa":true,"landing_page_url":null,"pdf_url":"https://ir.library.osaka-u.ac.jp/repo/ouka/all/51063/arou_3_22.pdf","source":{"id":"https://openalex.org/S4306402540","display_name":"OUKA (Osaka University Knowledge Archive) (Osaka University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98285908","host_organization_name":"The University of Osaka","host_organization_lineage":["https://openalex.org/I98285908"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2138756793.pdf","grobid_xml":"https://content.openalex.org/works/W2138756793.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W110351611","https://openalex.org/W938539187","https://openalex.org/W1512285202","https://openalex.org/W1547965516","https://openalex.org/W1698439592","https://openalex.org/W1885561873","https://openalex.org/W1990061958","https://openalex.org/W2109943392","https://openalex.org/W2114261632","https://openalex.org/W2115534035","https://openalex.org/W2118024368","https://openalex.org/W2128698639","https://openalex.org/W2157532207","https://openalex.org/W2157663777","https://openalex.org/W2164030845","https://openalex.org/W2610179052","https://openalex.org/W4239812996","https://openalex.org/W6604492289","https://openalex.org/W6630818679"],"related_works":["https://openalex.org/W2146134503","https://openalex.org/W4367397452","https://openalex.org/W2026866620","https://openalex.org/W2512989791","https://openalex.org/W1979226027","https://openalex.org/W4312691020","https://openalex.org/W2186150085","https://openalex.org/W2993450831","https://openalex.org/W2069073539","https://openalex.org/W3128560401"],"abstract_inverted_index":{"A":[0],"code":[1,5,18,29,79,95,124],"clone":[2,30,43,166],"is":[3,11],"a":[4,41,56,70,135],"portion":[6],"in":[7,81],"source":[8,53,88,123],"files":[9],"that":[10],"identical":[12],"or":[13],"similar":[14],"to":[15,22,102,121,148],"another.":[16],"Since":[17],"clones":[19,80,96,141],"are":[20],"believed":[21],"reduce":[23],"the":[24,49,94,104,118,122,143,151,154,161],"maintainability":[25],"of":[26,48,51,106,125,153],"software,":[27],"several":[28,63,112],"detection":[31,44,167],"techniques":[32],"and":[33,55,86,108,130,142],"tools":[34],"have":[35,68,97,145,159],"been":[36,98,146],"proposed.":[37],"This":[38],"paper":[39],"proposes":[40],"new":[42,119],"technique,":[45],"which":[46,77],"consists":[47],"transformation":[50],"input":[52],"text":[54],"token-by-token":[57],"comparison.":[58],"For":[59],"its":[60],"implementation":[61],"with":[62,164],"useful":[64],"optimization":[65],"techniques,":[66],"we":[67,110,116,158],"developed":[69],"tool,":[71],"named":[72],"CCFinder":[73,107,137],"(Code":[74],"Clone":[75],"Finder),":[76],"extracts":[78],"C,":[82],"C++,":[83],"Java,":[84],"COBOL":[85],"other":[87,132,165],"files.":[89],"In":[90,100,156],"addition,":[91,157],"metrics":[92,144],"for":[93],"developed.":[99],"order":[101],"evaluate":[103],"usefulness":[105],"metrics,":[109],"conducted":[111],"case":[113],"studies":[114],"where":[115],"applied":[117],"tool":[120],"JDK,":[126],"FreeBSD,":[127],"NetBSD,":[128],"Linux,":[129],"many":[131],"systems.":[133,155],"As":[134],"result,":[136],"has":[138],"effectively":[139,149],"found":[140],"able":[147],"identify":[150],"characteristics":[152],"compared":[160],"proposed":[162],"technique":[163],"techniques.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":53},{"year":2024,"cited_by_count":54},{"year":2023,"cited_by_count":71},{"year":2022,"cited_by_count":81},{"year":2021,"cited_by_count":110},{"year":2020,"cited_by_count":99},{"year":2019,"cited_by_count":99},{"year":2018,"cited_by_count":87},{"year":2017,"cited_by_count":92},{"year":2016,"cited_by_count":85},{"year":2015,"cited_by_count":97},{"year":2014,"cited_by_count":91},{"year":2013,"cited_by_count":114},{"year":2012,"cited_by_count":107}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}
