{"id":"https://openalex.org/W4225247778","doi":"https://doi.org/10.1587/transinf.2021edp7222","title":"NCDSearch: Sliding Window-Based Code Clone Search Using Lempel-Ziv Jaccard Distance","display_name":"NCDSearch: Sliding Window-Based Code Clone Search Using Lempel-Ziv Jaccard Distance","publication_year":2022,"publication_date":"2022-04-30","ids":{"openalex":"https://openalex.org/W4225247778","doi":"https://doi.org/10.1587/transinf.2021edp7222"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2021edp7222","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7222","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/5/E105.D_2021EDP7222/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/5/E105.D_2021EDP7222/_pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031518343","display_name":"Takashi Ishio","orcid":"https://orcid.org/0000-0003-4106-699X"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi ISHIO","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104327386","display_name":"Naoto Maeda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoto MAEDA","raw_affiliation_strings":["NEC Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084957063","display_name":"Kensuke Shibuya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kensuke SHIBUYA","raw_affiliation_strings":["NEC Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013181767","display_name":"Kenho IWAMOTO","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenho IWAMOTO","raw_affiliation_strings":["NEC Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102258593","display_name":"Katsuro Inoue","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":"Katsuro INOUE","raw_affiliation_strings":["Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3187,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59107312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"E105.D","issue":"5","first_page":"973","last_page":"981"},"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":0.9994000196456909,"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":0.9987999796867371,"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":0.7961072325706482},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.6882877945899963},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6408309936523438},{"id":"https://openalex.org/keywords/redundant-code","display_name":"Redundant code","score":0.5666628479957581},{"id":"https://openalex.org/keywords/constant-weight-code","display_name":"Constant-weight code","score":0.5376046895980835},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5277755260467529},{"id":"https://openalex.org/keywords/mistake","display_name":"Mistake","score":0.4993157386779785},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4783339500427246},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.46839475631713867},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.42549264430999756},{"id":"https://openalex.org/keywords/dead-code","display_name":"Dead code","score":0.4204785227775574},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.38106638193130493},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.286403089761734},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.26092153787612915},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23843711614608765},{"id":"https://openalex.org/keywords/linear-code","display_name":"Linear code","score":0.15286880731582642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10300353169441223},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.07648143172264099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961072325706482},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.6882877945899963},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6408309936523438},{"id":"https://openalex.org/C151578736","wikidata":"https://www.wikidata.org/wiki/Q1251793","display_name":"Redundant code","level":4,"score":0.5666628479957581},{"id":"https://openalex.org/C197242373","wikidata":"https://www.wikidata.org/wiki/Q5163613","display_name":"Constant-weight code","level":5,"score":0.5376046895980835},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5277755260467529},{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.4993157386779785},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4783339500427246},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.46839475631713867},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.42549264430999756},{"id":"https://openalex.org/C47434764","wikidata":"https://www.wikidata.org/wiki/Q1770035","display_name":"Dead code","level":5,"score":0.4204785227775574},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.38106638193130493},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.286403089761734},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.26092153787612915},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23843711614608765},{"id":"https://openalex.org/C2400350","wikidata":"https://www.wikidata.org/wiki/Q1752667","display_name":"Linear code","level":4,"score":0.15286880731582642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10300353169441223},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.07648143172264099},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1587/transinf.2021edp7222","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7222","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/5/E105.D_2021EDP7222/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782881","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4430","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal article"},{"id":"pmh:oai:library.naist.jp:10061/14791","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/14791","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2021edp7222","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7222","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/5/E105.D_2021EDP7222/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225247778.pdf","grobid_xml":"https://content.openalex.org/works/W4225247778.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1943075983","https://openalex.org/W1990762361","https://openalex.org/W2092483417","https://openalex.org/W2101832700","https://openalex.org/W2107745473","https://openalex.org/W2118805943","https://openalex.org/W2122962290","https://openalex.org/W2136128399","https://openalex.org/W2138110817","https://openalex.org/W2138756793","https://openalex.org/W2144221002","https://openalex.org/W2166901988","https://openalex.org/W2539312235","https://openalex.org/W2565892306","https://openalex.org/W2634106992","https://openalex.org/W2726916722","https://openalex.org/W2742475488","https://openalex.org/W2747969544","https://openalex.org/W2767905745","https://openalex.org/W2901247971","https://openalex.org/W2919074952","https://openalex.org/W2921323488","https://openalex.org/W2999200532","https://openalex.org/W3098166657","https://openalex.org/W3147107715","https://openalex.org/W3164944236","https://openalex.org/W4229558641","https://openalex.org/W4233760227","https://openalex.org/W4298377646"],"related_works":["https://openalex.org/W2025383691","https://openalex.org/W1539844444","https://openalex.org/W2042804080","https://openalex.org/W1818370264","https://openalex.org/W2391342321","https://openalex.org/W4293664087","https://openalex.org/W2093178562","https://openalex.org/W2063916720","https://openalex.org/W4206106662","https://openalex.org/W2380710632"],"abstract_inverted_index":{"Software":[0],"developers":[1,24,84],"may":[2,69],"write":[3],"a":[4,31,65,77,91,97,103,127,131],"number":[5],"of":[6,48,80,89,113],"similar":[7],"source":[8],"code":[9,22,26,38,50,61,67,74,87,94,142],"fragments":[10,143],"including":[11],"the":[12,60,145],"same":[13],"mistake":[14],"in":[15,33,96,130],"software":[16,99,150],"products.":[17],"To":[18,82],"remove":[19],"such":[20,90],"faulty":[21,66,93,141],"fragments,":[23],"inspect":[25],"clones":[27,47,88],"if":[28],"they":[29],"found":[30],"bug":[32],"their":[34],"code.":[35,81],"While":[36],"various":[37],"clone":[39],"detection":[40],"methods":[41],"have":[42],"been":[43],"proposed":[44],"to":[45,85],"identify":[46],"either":[49],"blocks":[51],"or":[52],"functions,":[53],"those":[54],"tools":[55],"do":[56],"not":[57],"always":[58],"fit":[59],"inspection":[62],"task":[63],"because":[64],"fragment":[68,95],"be":[70],"much":[71],"smaller":[72],"than":[73],"blocks,":[75],"e.g.":[76],"single":[78],"line":[79],"enable":[83],"search":[86],"small":[92],"large-scale":[98],"product,":[100],"we":[101],"propose":[102],"method":[104,137],"using":[105,121],"Lempel-Ziv":[106],"Jaccard":[107],"Distance,":[108],"which":[109],"is":[110,147],"an":[111,119,122],"approximation":[112],"Normalized":[114],"Compression":[115],"Distance.":[116],"We":[117],"conducted":[118],"experiment":[120],"existing":[123],"research":[124],"dataset":[125],"and":[126,144],"user":[128],"survey":[129],"company.":[132],"The":[133],"result":[134],"shows":[135],"our":[136],"efficiently":[138],"reports":[139],"cloned":[140],"performance":[146],"acceptable":[148],"for":[149],"developers.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
