{"id":"https://openalex.org/W3145055218","doi":"https://doi.org/10.1109/iwsc.2012.6227875","title":"Shuffling and randomization for scalable source code clone detection","display_name":"Shuffling and randomization for scalable source code clone detection","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W3145055218","doi":"https://doi.org/10.1109/iwsc.2012.6227875","mag":"3145055218"},"language":"en","primary_location":{"id":"doi:10.1109/iwsc.2012.6227875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwsc.2012.6227875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 6th International Workshop on Software Clones (IWSC)","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/A5086488087","display_name":"Iman Keivanloo","orcid":"https://orcid.org/0000-0001-9552-6950"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Iman Keivanloo","raw_affiliation_strings":["Department of Computer Science, Concordia University, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102756770","display_name":"Chanchal K. Roy","orcid":"https://orcid.org/0000-0003-0519-6164"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chanchal K. Roy","raw_affiliation_strings":["Department of Computer Science, University of Saskatchewan, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030827240","display_name":"Juergen Rilling","orcid":"https://orcid.org/0000-0002-5441-0385"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Juergen Rilling","raw_affiliation_strings":["Department of Computer Science, Concordia University, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052958340","display_name":"Philippe Charland","orcid":"https://orcid.org/0000-0003-4051-9942"},"institutions":[{"id":"https://openalex.org/I1297460800","display_name":"Defence Research and Development Canada","ror":"https://ror.org/00hgy8d33","country_code":"CA","type":"funder","lineage":["https://openalex.org/I1297460800","https://openalex.org/I1336338359","https://openalex.org/I2802286613"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Philippe Charland","raw_affiliation_strings":["System of Systems Section, Defence Research and Development Canada, Canada"],"affiliations":[{"raw_affiliation_string":"System of Systems Section, Defence Research and Development Canada, Canada","institution_ids":["https://openalex.org/I1297460800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086488087"],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":2.8422,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.92917079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"82","last_page":"83"},"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":0.9991999864578247,"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":0.9983999729156494,"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/shuffling","display_name":"Shuffling","score":0.9268913269042969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7759793400764465},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7374350428581238},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5385855436325073},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.511590301990509},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5074664950370789},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.425624817609787},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4157913625240326},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37441980838775635},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3299649953842163},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32459890842437744},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3242793083190918},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30258265137672424},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14401283860206604},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10601848363876343}],"concepts":[{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.9268913269042969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7759793400764465},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7374350428581238},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5385855436325073},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.511590301990509},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5074664950370789},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.425624817609787},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4157913625240326},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37441980838775635},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3299649953842163},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32459890842437744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3242793083190918},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30258265137672424},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14401283860206604},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10601848363876343},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","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":1,"locations":[{"id":"doi:10.1109/iwsc.2012.6227875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwsc.2012.6227875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 6th International Workshop on Software Clones (IWSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1983316175","https://openalex.org/W2088211982","https://openalex.org/W2165739648","https://openalex.org/W2172244770"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W2045745654","https://openalex.org/W2114337652","https://openalex.org/W4377131110","https://openalex.org/W4388857216","https://openalex.org/W4294559962","https://openalex.org/W2046590706","https://openalex.org/W4390419005","https://openalex.org/W2949444602","https://openalex.org/W1587991081"],"abstract_inverted_index":{"In":[0],"this":[1],"research,":[2],"we":[3,74],"present":[4],"a":[5,53,103],"novel":[6],"approach":[7,29,55,80],"that":[8,31,93],"allows":[9],"existing":[10],"state":[11,83],"of":[12,27,47,57,64,70,84,122],"the":[13,32,44,48,65,71,85,99,114,120,123,127],"art":[14,86],"clone":[15,87],"detection":[16,88],"tools":[17,34,101,125],"to":[18,20,97,102],"scale":[19,98],"very":[21,104],"large":[22,105],"datasets.":[23],"A":[24],"key":[25],"benefit":[26],"our":[28,76],"is":[30,36,95],"improved":[33],"scalability":[35],"achieved":[37],"using":[38,107],"standard":[39,108],"hardware":[40],"and":[41,60,78,110],"without":[42,111],"modifying":[43],"original":[45,124],"implementations":[46],"subject":[49,66],"tools.":[50,89],"We":[51],"use":[52],"hybrid":[54],"comprising":[56],"shuffling,":[58],"repetition,":[59],"random":[61],"subset":[62],"generation":[63],"dataset.":[67],"As":[68],"part":[69],"experimental":[72],"evaluation,":[73],"applied":[75],"shuffling":[77],"randomization":[79],"on":[81],"two":[82],"Our":[90],"experience":[91],"shows":[92],"it":[94],"possible":[96],"classical":[100],"dataset":[106],"hardware,":[109],"significantly":[112],"affecting":[113],"overall":[115],"recall":[116],"while":[117],"exploiting":[118],"all":[119],"strengths":[121],"including":[126],"precision.":[128]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
