{"id":"https://openalex.org/W2921323488","doi":"https://doi.org/10.1109/saner.2019.8668015","title":"On Precision of Code Clone Detection Tools","display_name":"On Precision of Code Clone Detection Tools","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W2921323488","doi":"https://doi.org/10.1109/saner.2019.8668015","mag":"2921323488"},"language":"en","primary_location":{"id":"doi:10.1109/saner.2019.8668015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner.2019.8668015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 26th 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/A5028074588","display_name":"Farima Farmahinifarahani","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farima Farmahinifarahani","raw_affiliation_strings":["University of California, Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846745","display_name":"Vaibhav Saini","orcid":"https://orcid.org/0000-0002-6107-9504"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav Saini","raw_affiliation_strings":["University of California, Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031154480","display_name":"Di Yang","orcid":"https://orcid.org/0000-0002-4702-6393"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Yang","raw_affiliation_strings":["University of California, Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015641612","display_name":"Hitesh Sajnani","orcid":"https://orcid.org/0009-0004-9973-6241"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hitesh Sajnani","raw_affiliation_strings":["Microsoft, Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Inc, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103284742","display_name":"Cristina Videira Lopes","orcid":"https://orcid.org/0000-0003-0551-3908"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristina V Lopes","raw_affiliation_strings":["University of California, Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5267,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93554223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"94"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9944000244140625,"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":0.9918000102043152,"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":0.8791375756263733},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.8483017683029175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7449088096618652},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.699711263179779},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5935793519020081},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5327603220939636},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5163558721542358},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4476699233055115},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4317507743835449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28618288040161133},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25473105907440186},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13144278526306152},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.11476388573646545},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08355244994163513},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08163902163505554}],"concepts":[{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.8791375756263733},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8483017683029175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449088096618652},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.699711263179779},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5935793519020081},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5327603220939636},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5163558721542358},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4476699233055115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4317507743835449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28618288040161133},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25473105907440186},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13144278526306152},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.11476388573646545},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08355244994163513},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08163902163505554},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/saner.2019.8668015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner.2019.8668015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER)","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":41,"referenced_works":["https://openalex.org/W1500382227","https://openalex.org/W1967408872","https://openalex.org/W1971959540","https://openalex.org/W1973650376","https://openalex.org/W2003285370","https://openalex.org/W2037537863","https://openalex.org/W2041190309","https://openalex.org/W2049461910","https://openalex.org/W2065053490","https://openalex.org/W2065622239","https://openalex.org/W2088479623","https://openalex.org/W2101832700","https://openalex.org/W2118024368","https://openalex.org/W2120326119","https://openalex.org/W2127811329","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2134329651","https://openalex.org/W2136099030","https://openalex.org/W2138756793","https://openalex.org/W2141403362","https://openalex.org/W2141535436","https://openalex.org/W2151573418","https://openalex.org/W2158439356","https://openalex.org/W2165739648","https://openalex.org/W2279076754","https://openalex.org/W2286236884","https://openalex.org/W2298313545","https://openalex.org/W2467974757","https://openalex.org/W2578208870","https://openalex.org/W2598817001","https://openalex.org/W2620636222","https://openalex.org/W2766078762","https://openalex.org/W2794744252","https://openalex.org/W2807866521","https://openalex.org/W3105535951","https://openalex.org/W4301168982","https://openalex.org/W6629824143","https://openalex.org/W6681393918","https://openalex.org/W6694879404","https://openalex.org/W6697318023"],"related_works":["https://openalex.org/W3008339103","https://openalex.org/W2404647514","https://openalex.org/W1667647204","https://openalex.org/W3119814709","https://openalex.org/W2018477250","https://openalex.org/W35919320","https://openalex.org/W3081644756","https://openalex.org/W2921323488","https://openalex.org/W2100060170","https://openalex.org/W2158439356"],"abstract_inverted_index":{"Precision":[0],"and":[1,31,71,101,133,169,189],"recall":[2],"are":[3,42,199],"the":[4,10,18,24,69,78,99,104,131,171,178,192,208],"main":[5],"metrics":[6,16],"used":[7],"to":[8,56,76,97,113,129,157,161,185],"measure":[9],"correctness":[11],"of":[12,20,29,59,68,92,103,116,136,153,181,197,210],"clone":[13,30,37,106,119,127,149],"detectors.":[14,107],"These":[15],"require":[17],"existence":[19],"labeled":[21],"datasets":[22],"containing":[23],"ground":[25],"truth":[26],"-":[27],"samples":[28],"non-clone":[32],"pairs.":[33],"For":[34],"source":[35],"code":[36,118,148],"detectors,":[38],"in":[39,147],"particular,":[40],"there":[41],"some":[43],"techniques,":[44],"as":[45,47],"well":[46],"a":[48,141],"concrete":[49],"framework,":[50],"for":[51,144],"automatically":[52],"evaluating":[53,62],"recall,":[54],"down":[55],"different":[57,187,195],"types":[58,91,196],"clones.":[60],"However,":[61],"precision":[63,82,115,135,167,180],"is":[64,83,86,156],"still":[65],"challenging,":[66],"because":[67],"intensive":[70],"specialized":[72],"manual":[73],"effort":[74],"required":[75],"accomplish":[77],"task.":[79],"Moreover,":[80],"when":[81,165,194],"reported,":[84],"it":[85,95],"typically":[87],"done":[88],"over":[89],"all":[90],"clones,":[93],"making":[94],"hard":[96],"assess":[98],"strengths":[100],"weaknesses":[102],"corresponding":[105],"This":[108],"paper":[109],"presents":[110],"systematic":[111],"experiments":[112],"evaluate":[114],"eight":[117],"detection":[120],"tools.":[121,138],"Three":[122],"judges":[123],"independently":[124],"reviewed":[125],"12,800":[126],"pairs":[128],"compute":[130],"undifferentiated":[132],"type-based":[134],"these":[137,182],"Besides":[139],"providing":[140],"useful":[142],"baseline":[143],"future":[145],"research":[146],"detection,":[150],"another":[151],"contribution":[152],"our":[154,174],"work":[155,175],"unveil":[158],"important":[159],"considerations":[160],"take":[162],"into":[163,201],"account":[164],"doing":[166],"measurements":[168],"reporting":[170,211],"results.":[172],"Specifically,":[173],"shows":[176],"that":[177],"reported":[179],"tools":[183,193],"leads":[184],"significantly":[186],"conclusions":[188],"insights":[190],"about":[191],"clones":[198],"taken":[200],"account.":[202],"It":[203],"also":[204],"stresses,":[205],"once":[206],"again,":[207],"importance":[209],"inter-rater":[212],"agreement.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}