{"id":"https://openalex.org/W2796141603","doi":"https://doi.org/10.1109/saner.2018.8330194","title":"Benchmarks for software clone detection: A ten-year retrospective","display_name":"Benchmarks for software clone detection: A ten-year retrospective","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2796141603","doi":"https://doi.org/10.1109/saner.2018.8330194","mag":"2796141603"},"language":"en","primary_location":{"id":"doi:10.1109/saner.2018.8330194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner.2018.8330194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER)","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/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":true,"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":"last","author":{"id":"https://openalex.org/A5111905373","display_name":"James R. Cordy","orcid":null},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James R. Cordy","raw_affiliation_strings":["School of Computing, Queen's University, Canada"],"affiliations":[{"raw_affiliation_string":"School of Computing, Queen's University, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102756770"],"corresponding_institution_ids":["https://openalex.org/I32625721"],"apc_list":null,"apc_paid":null,"fwci":8.2151,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.97599555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"37"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.995199978351593,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9947999715805054,"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/clone","display_name":"clone (Java method)","score":0.8374228477478027},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7817760705947876},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.7611380219459534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6824386119842529},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.614019513130188},{"id":"https://openalex.org/keywords/software-maintenance","display_name":"Software maintenance","score":0.5408976078033447},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.5386751294136047},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5136627554893494},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5001029968261719},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4552038013935089},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.4515664577484131},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4422789216041565},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4199938476085663},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.41642138361930847},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4150037169456482},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.41348108649253845},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32497555017471313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2551424205303192},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07047247886657715},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06931054592132568}],"concepts":[{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.8374228477478027},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7817760705947876},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.7611380219459534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6824386119842529},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.614019513130188},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.5408976078033447},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5386751294136047},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5136627554893494},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5001029968261719},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4552038013935089},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.4515664577484131},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4422789216041565},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4199938476085663},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.41642138361930847},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4150037169456482},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.41348108649253845},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32497555017471313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2551424205303192},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07047247886657715},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06931054592132568},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/saner.2018.8330194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner.2018.8330194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":117,"referenced_works":["https://openalex.org/W127146430","https://openalex.org/W1544303214","https://openalex.org/W1674221164","https://openalex.org/W1698439592","https://openalex.org/W1851694071","https://openalex.org/W1964788505","https://openalex.org/W1967028047","https://openalex.org/W1967388635","https://openalex.org/W1967408872","https://openalex.org/W1975394407","https://openalex.org/W1979296382","https://openalex.org/W1980482639","https://openalex.org/W1986601961","https://openalex.org/W1994815767","https://openalex.org/W1995810748","https://openalex.org/W1998569777","https://openalex.org/W1999457095","https://openalex.org/W2007818470","https://openalex.org/W2010362022","https://openalex.org/W2019374535","https://openalex.org/W2020161882","https://openalex.org/W2025962632","https://openalex.org/W2042711539","https://openalex.org/W2043169794","https://openalex.org/W2049386694","https://openalex.org/W2053264768","https://openalex.org/W2065053490","https://openalex.org/W2068743171","https://openalex.org/W2074529754","https://openalex.org/W2087343574","https://openalex.org/W2088479623","https://openalex.org/W2090222336","https://openalex.org/W2090432523","https://openalex.org/W2096491586","https://openalex.org/W2097631008","https://openalex.org/W2098347799","https://openalex.org/W2100060170","https://openalex.org/W2100860272","https://openalex.org/W2101832700","https://openalex.org/W2102543548","https://openalex.org/W2103928642","https://openalex.org/W2108516706","https://openalex.org/W2109580177","https://openalex.org/W2109943392","https://openalex.org/W2117867487","https://openalex.org/W2118869973","https://openalex.org/W2119887272","https://openalex.org/W2120293505","https://openalex.org/W2120319185","https://openalex.org/W2121051182","https://openalex.org/W2121866903","https://openalex.org/W2122334745","https://openalex.org/W2125260159","https://openalex.org/W2126036011","https://openalex.org/W2128466029","https://openalex.org/W2128698639","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2131477050","https://openalex.org/W2131491818","https://openalex.org/W2134329651","https://openalex.org/W2138756793","https://openalex.org/W2143151143","https://openalex.org/W2144854572","https://openalex.org/W2146483864","https://openalex.org/W2147363209","https://openalex.org/W2151573418","https://openalex.org/W2153887189","https://openalex.org/W2157532207","https://openalex.org/W2158439356","https://openalex.org/W2162261690","https://openalex.org/W2165739648","https://openalex.org/W2166278331","https://openalex.org/W2170284712","https://openalex.org/W2271818296","https://openalex.org/W2282845548","https://openalex.org/W2284972172","https://openalex.org/W2286236884","https://openalex.org/W2298313545","https://openalex.org/W2400997415","https://openalex.org/W2407458134","https://openalex.org/W2470393560","https://openalex.org/W2516395483","https://openalex.org/W2578208870","https://openalex.org/W2588556346","https://openalex.org/W2619704817","https://openalex.org/W2620636222","https://openalex.org/W2765706740","https://openalex.org/W2768306496","https://openalex.org/W2787379525","https://openalex.org/W2794744252","https://openalex.org/W3003280364","https://openalex.org/W3007450248","https://openalex.org/W3104103145","https://openalex.org/W3175483041","https://openalex.org/W4232048224","https://openalex.org/W4240754846","https://openalex.org/W4241674441","https://openalex.org/W4242739280","https://openalex.org/W4247488451","https://openalex.org/W4248487140","https://openalex.org/W4249744258","https://openalex.org/W4255420728","https://openalex.org/W4255660245","https://openalex.org/W4301168982","https://openalex.org/W6647178968","https://openalex.org/W6667782601","https://openalex.org/W6669100502","https://openalex.org/W6672215119","https://openalex.org/W6672629006","https://openalex.org/W6674626504","https://openalex.org/W6678850886","https://openalex.org/W6681044279","https://openalex.org/W6697318023","https://openalex.org/W6712677135","https://openalex.org/W6731825365","https://openalex.org/W6980476409"],"related_works":["https://openalex.org/W2186150085","https://openalex.org/W2010680342","https://openalex.org/W2069073539","https://openalex.org/W1985559452","https://openalex.org/W2027488246","https://openalex.org/W2116610783","https://openalex.org/W1966036917","https://openalex.org/W3098265572","https://openalex.org/W1938356314","https://openalex.org/W2406602165"],"abstract_inverted_index":{"There":[0],"have":[1,44,92,131],"been":[2,18,33,46,93],"a":[3,55,114,153,163,176,188,209,233],"great":[4],"many":[5],"methods":[6],"and":[7,22,42,65,133,144,159,198,211,218,224,239,249],"tools":[8,61],"proposed":[9],"for":[10,99,235],"software":[11,214],"clone":[12,57,102,122,185,215,236],"detection.":[13],"While":[14],"some":[15],"work":[16,136,172],"has":[17,32,173],"done":[19],"on":[20],"assessing":[21],"comparing":[23],"performance":[24],"of":[25,76,156,165,193,202,213,222,256],"these":[26],"tools,":[27],"very":[28],"little":[29],"empirical":[30,117],"evaluation":[31],"done.":[34],"In":[35,79,204],"particular,":[36],"accuracy":[37],"measures":[38],"such":[39,149],"as":[40,150],"precision":[41],"recall":[43],"only":[45],"roughly":[47],"estimated,":[48],"due":[49],"both":[50,245],"to":[51,66,71,81,137,175,226,228,241,244,250,252],"problems":[52],"in":[53,147,169,187],"creating":[54],"validated":[56,184],"benchmark":[58,177],"against":[59],"which":[60],"can":[62],"be":[63],"compared,":[64],"the":[67,87,120,126,220,254,257],"manual":[68],"effort":[69],"required":[70],"hand":[72],"check":[73],"large":[74,116,189],"numbers":[75],"candidate":[77],"clones.":[78],"order":[80],"cope":[82],"with":[83,106,119,180],"this":[84,205,229],"issue,":[85],"over":[86,125],"last":[88],"10":[89],"years":[90,129],"we":[91,112,130,207],"working":[94],"towards":[95],"building":[96,253],"cloning":[97],"benchmarks":[98,238,248,255],"objectively":[100],"evaluating":[101],"detection":[103,123,216,237],"tools.":[104],"Beginning":[105],"our":[107,135,171],"WCRE":[108],"2008":[109],"paper,":[110,206],"where":[111],"conducted":[113],"modestly":[115],"study":[118],"NiCad":[121],"tool,":[124],"past":[127],"ten":[128],"extended":[132],"grown":[134],"include":[138],"several":[139],"languages,":[140],"much":[141],"larger":[142],"datasets,":[143],"model":[145],"clones":[146],"languages":[148],"Simulink.":[151],"From":[152],"modest":[154],"set":[155],"15":[157],"C":[158],"Java":[160],"systems":[161],"comprising":[162],"total":[164],"7":[166],"million":[167,182,200],"lines":[168,201],"2008,":[170],"progressed":[174],"called":[178],"BigCloneBench":[179],"eight":[181],"manually":[183],"pairs":[186],"inter-project":[190],"source":[191],"dataset":[192],"more":[194],"than":[195],"25,000":[196],"projects":[197],"365":[199],"code.":[203],"present":[208],"history":[210],"overview":[212],"benchmarks,":[217],"review":[219],"steps":[221],"ourselves":[223],"others":[225],"come":[227],"stage.":[230],"We":[231],"outline":[232],"future":[234],"hope":[240],"encourage":[242],"researchers":[243],"use":[246],"existing":[247],"contribute":[251],"future.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}