{"id":"https://openalex.org/W2158439356","doi":"https://doi.org/10.1109/icsm.2015.7332459","title":"Evaluating clone detection tools with BigCloneBench","display_name":"Evaluating clone detection tools with BigCloneBench","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2158439356","doi":"https://doi.org/10.1109/icsm.2015.7332459","mag":"2158439356"},"language":"en","primary_location":{"id":"doi:10.1109/icsm.2015.7332459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsm.2015.7332459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Software Maintenance and Evolution (ICSME)","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/A5006573523","display_name":"Jeffrey Svajlenko","orcid":"https://orcid.org/0000-0001-9738-7421"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jeffrey Svajlenko","raw_affiliation_strings":["Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]}]},{"author_position":"last","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":["University of Saskatchewan, Canada"],"affiliations":[{"raw_affiliation_string":"University of Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006573523"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":29.9195,"has_fulltext":false,"cited_by_count":164,"citation_normalized_percentile":{"value":0.99544985,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"140"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9939000010490417,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9904999732971191,"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/clone","display_name":"clone (Java method)","score":0.883378267288208},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.8404232859611511},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7921460866928101},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.7289469242095947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6678307056427002},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6315578818321228},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5055174827575684},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45590656995773315},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4555964469909668},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39366430044174194},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3330599069595337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3201475739479065},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3057110905647278},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17908287048339844},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09246501326560974},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08701461553573608}],"concepts":[{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.883378267288208},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.8404232859611511},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7921460866928101},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.7289469242095947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6678307056427002},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6315578818321228},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5055174827575684},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45590656995773315},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4555964469909668},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39366430044174194},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3330599069595337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3201475739479065},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3057110905647278},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17908287048339844},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09246501326560974},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08701461553573608},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsm.2015.7332459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsm.2015.7332459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Software Maintenance and Evolution (ICSME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1964788505","https://openalex.org/W1967028047","https://openalex.org/W1967408872","https://openalex.org/W1993673250","https://openalex.org/W1996676702","https://openalex.org/W2007818470","https://openalex.org/W2025962632","https://openalex.org/W2041190309","https://openalex.org/W2053264768","https://openalex.org/W2065053490","https://openalex.org/W2100060170","https://openalex.org/W2101832700","https://openalex.org/W2102543548","https://openalex.org/W2120319185","https://openalex.org/W2120326119","https://openalex.org/W2125513188","https://openalex.org/W2128698639","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2131477050","https://openalex.org/W2135841285","https://openalex.org/W2136128399","https://openalex.org/W2138756793","https://openalex.org/W2151573418","https://openalex.org/W2165739648","https://openalex.org/W2298313545","https://openalex.org/W3147701173","https://openalex.org/W4242739280","https://openalex.org/W6678850886","https://openalex.org/W6679170867","https://openalex.org/W6697318023"],"related_works":["https://openalex.org/W4313549863","https://openalex.org/W2072205733","https://openalex.org/W116591315","https://openalex.org/W1564657277","https://openalex.org/W2799887323","https://openalex.org/W194942058","https://openalex.org/W2088986462","https://openalex.org/W2921323488","https://openalex.org/W2100060170","https://openalex.org/W2158439356"],"abstract_inverted_index":{"Many":[0],"clone":[1,33,42,77,91,99,135],"detection":[2,43,111,185],"tools":[3,89,105,163,182],"have":[4,164,183],"been":[5],"proposed":[6],"in":[7,16],"the":[8,38,74,85,88,95,104,119,122,126,157,162],"literature.":[9],"However,":[10],"our":[11,30,144],"knowledge":[12],"of":[13,40,49,73,87,98,121,125,156,186],"their":[14,23],"performance":[15],"real":[17],"software":[18,59],"systems":[19],"is":[20,46],"limited,":[21],"particularly":[22],"recall.":[24],"In":[25],"this":[26,81],"paper,":[27],"we":[28,117],"use":[29,80],"big":[31,57],"data":[32,58],"benchmark,":[34,151],"BigCloneBench,":[35],"to":[36,83,131,152],"evaluate":[37,84,103,118],"recall":[39,86,166],"ten":[41],"tools.":[44,158],"BigCloneBench":[45,66],"a":[47,56,149],"collection":[48],"eight":[50],"million":[51],"validated":[52],"clones":[53,72,128,176,187],"within":[54],"IJaDataset-2.0,":[55],"repository":[60],"containing":[61],"25,000":[62],"open-source":[63],"Java":[64],"systems.":[65],"contains":[67],"both":[68,107],"intra-project":[69],"and":[70,93,109,133,146,169],"inter-project":[71],"four":[75],"primary":[76],"types.":[78],"We":[79,102,138,159],"benchmark":[82,127],"per":[90],"type":[92],"across":[94],"entire":[96],"range":[97],"syntactical":[100,179,190],"similarity.":[101,180,191],"for":[106,167],"single-system":[108],"cross-project":[110],"scenarios.":[112],"Using":[113],"multiple":[114],"clone-matching":[115],"metrics,":[116],"quality":[120],"tools'":[123],"reporting":[124],"with":[129,177,188],"respect":[130],"refactoring":[132],"automatic":[134],"analysis":[136],"use-cases.":[137],"compare":[139],"these":[140],"real-world":[141],"results":[142],"against":[143],"Mutation":[145],"Injection":[147],"Framework,":[148],"synthetic":[150],"reveal":[153],"deeper":[154],"understanding":[155],"found":[160],"that":[161],"strong":[165],"Type-1":[168],"Type-2":[170],"clones,":[171],"as":[172,174],"well":[173],"Type-3":[175],"high":[178],"The":[181],"weaker":[184],"lower":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}
