{"id":"https://openalex.org/W2787947717","doi":null,"title":"Large-Scale Clone Detection and Benchmarking","display_name":"Large-Scale Clone Detection and Benchmarking","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2787947717","mag":"2787947717"},"language":"en","primary_location":{"id":"pmh:oai:ecommons.usask.ca:10388/8432","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10388/8432","pdf_url":"https://harvest.usask.ca/bitstreams/632f34b3-ae56-4f82-8cde-203711f1d9f8/download","source":{"id":"https://openalex.org/S4377196608","display_name":"University Library - University of Saskatchewan (University of Saskatchewan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I32625721","host_organization_name":"University of Saskatchewan","host_organization_lineage":["https://openalex.org/I32625721"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://harvest.usask.ca/bitstreams/632f34b3-ae56-4f82-8cde-203711f1d9f8/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006573523","display_name":"Jeffrey Svajlenko","orcid":"https://orcid.org/0000-0001-9738-7421","observed_orcids":["https://orcid.org/0000-0001-9738-7421"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jeff Thomas Svajlenko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5006573523"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.0,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code-clones","display_name":"code clones","score":0.8999999761581421},{"id":"https://openalex.org/keywords/clone-detection","display_name":"clone detection","score":0.9129999876022339},{"id":"https://openalex.org/keywords/mutation-testing","display_name":"mutation testing","score":0.3840000033378601},{"id":"https://openalex.org/keywords/bigclonebench","display_name":"BigCloneBench","score":0.9629999995231628},{"id":"https://openalex.org/keywords/code-reuse","display_name":"code reuse","score":0.47200000286102295},{"id":"https://openalex.org/keywords/software-duplication","display_name":"software duplication","score":0.43799999356269836},{"id":"https://openalex.org/keywords/mutation-operator","display_name":"mutation operator","score":0.40799999237060547},{"id":"https://openalex.org/keywords/code-completion","display_name":"code completion","score":0.6510000228881836},{"id":"https://openalex.org/keywords/api-recommendation","display_name":"API recommendation","score":0.9070000052452087},{"id":"https://openalex.org/keywords/source-code-mining","display_name":"source code mining","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7945436239242554},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5481266975402832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34901514649391174},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34691566228866577},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2681196331977844},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.2117789089679718},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09262499213218689},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.07330918312072754}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:ecommons.usask.ca:10388/8432","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10388/8432","pdf_url":"https://harvest.usask.ca/bitstreams/632f34b3-ae56-4f82-8cde-203711f1d9f8/download","source":{"id":"https://openalex.org/S4377196608","display_name":"University Library - University of Saskatchewan (University of Saskatchewan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I32625721","host_organization_name":"University of Saskatchewan","host_organization_lineage":["https://openalex.org/I32625721"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"pmh:oai:harvest.usask.ca:10388/8432","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10388/8432","pdf_url":null,"source":{"id":"https://openalex.org/S7407063267","display_name":"HARVEST (University of Saskatchewan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"mag:2787947717","doi":null,"is_oa":false,"landing_page_url":"https://harvest.usask.ca/handle/10388/8432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:ecommons.usask.ca:10388/8432","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10388/8432","pdf_url":"https://harvest.usask.ca/bitstreams/632f34b3-ae56-4f82-8cde-203711f1d9f8/download","source":{"id":"https://openalex.org/S4377196608","display_name":"University Library - University of Saskatchewan (University of Saskatchewan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I32625721","host_organization_name":"University of Saskatchewan","host_organization_lineage":["https://openalex.org/I32625721"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310865","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2787947717.pdf","grobid_xml":"https://content.openalex.org/works/W2787947717.grobid-xml"},"referenced_works_count":92,"referenced_works":["https://openalex.org/W53074874","https://openalex.org/W184099340","https://openalex.org/W201176775","https://openalex.org/W1494137514","https://openalex.org/W1501652040","https://openalex.org/W1512615396","https://openalex.org/W1562646198","https://openalex.org/W1593203335","https://openalex.org/W1674221164","https://openalex.org/W1698439592","https://openalex.org/W1964795700","https://openalex.org/W1967388635","https://openalex.org/W1967408872","https://openalex.org/W1969031936","https://openalex.org/W1972466226","https://openalex.org/W1974446554","https://openalex.org/W1983316175","https://openalex.org/W1983944999","https://openalex.org/W1984348519","https://openalex.org/W1984610995","https://openalex.org/W1986601961","https://openalex.org/W1993673250","https://openalex.org/W1995301437","https://openalex.org/W1996676702","https://openalex.org/W1999515991","https://openalex.org/W2000473405","https://openalex.org/W2002559933","https://openalex.org/W2007818470","https://openalex.org/W2008085811","https://openalex.org/W2019374535","https://openalex.org/W2020161882","https://openalex.org/W2025962632","https://openalex.org/W2041190309","https://openalex.org/W2043140003","https://openalex.org/W2043169794","https://openalex.org/W2053112282","https://openalex.org/W2053264768","https://openalex.org/W2056830820","https://openalex.org/W2065053490","https://openalex.org/W2065622239","https://openalex.org/W2068743171","https://openalex.org/W2071867879","https://openalex.org/W2083140988","https://openalex.org/W2087343574","https://openalex.org/W2088211982","https://openalex.org/W2088479623","https://openalex.org/W2090222336","https://openalex.org/W2093861610","https://openalex.org/W2096491586","https://openalex.org/W2099658271","https://openalex.org/W2100060170","https://openalex.org/W2101832700","https://openalex.org/W2102543548","https://openalex.org/W2103640219","https://openalex.org/W2104301886","https://openalex.org/W2109223453","https://openalex.org/W2109943392","https://openalex.org/W2114303224","https://openalex.org/W2115534035","https://openalex.org/W2118024368","https://openalex.org/W2120319185","https://openalex.org/W2120326119","https://openalex.org/W2122334745","https://openalex.org/W2124173249","https://openalex.org/W2125260159","https://openalex.org/W2125513188","https://openalex.org/W2126208842","https://openalex.org/W2128698639","https://openalex.org/W2128888088","https://openalex.org/W2134329651","https://openalex.org/W2138756793","https://openalex.org/W2141973112","https://openalex.org/W2143151143","https://openalex.org/W2146483864","https://openalex.org/W2146659255","https://openalex.org/W2149864547","https://openalex.org/W2151573418","https://openalex.org/W2154151876","https://openalex.org/W2156062547","https://openalex.org/W2157532207","https://openalex.org/W2158439356","https://openalex.org/W2160841184","https://openalex.org/W2162261690","https://openalex.org/W2164030845","https://openalex.org/W2165739648","https://openalex.org/W2172244770","https://openalex.org/W2284972172","https://openalex.org/W2298313545","https://openalex.org/W2400579873","https://openalex.org/W2427333829","https://openalex.org/W2578208870","https://openalex.org/W4301168982"],"related_works":["https://openalex.org/W2984492265","https://openalex.org/W4241052220","https://openalex.org/W2296107677","https://openalex.org/W2286236884","https://openalex.org/W7100876203","https://openalex.org/W2621103691","https://openalex.org/W2620636222","https://openalex.org/W2467974757","https://openalex.org/W2099658271","https://openalex.org/W2795199270"],"abstract_inverted_index":{"Code":[0],"clones":[1,22,87,347,443,489],"are":[2,8,11,23,210,395,540],"pairs":[3],"of":[4,30,48,59,161,164,172,225,278,310,316,336,361,425,430,439,477,494,504,525,545,552,588,677,687,746],"code":[5,16,74,139],"fragments":[6],"that":[7,83,89,377,391,408],"similar.":[9],"They":[10],"created":[12],"when":[13,72],"developers":[14,84],"re-use":[15],"by":[17,42,103,242,458,766],"copy":[18],"and":[19,40,51,57,66,94,143,146,209,215,250,272,291,305,329,366,384,389,397,487,529,536,594,612,636,647,669,693,709,760,762,772,780],"paste,":[20],"although":[21],"known":[24],"to":[25,44,69,122,213,267,357,419,520,555,580,616,681,683,732,740],"occur":[26],"for":[27,130,184,205,233,257,288,399,422,461,474,479,484,488,508,571],"a":[28,34,63,255,284,321,341,349,436,445,569,589,596,719,767],"variety":[29],"reasons.":[31],"Clones":[32],"have":[33,123,181],"negative":[35],"impact":[36],"on":[37,651,689],"software":[38,49,64],"quality":[39],"development":[41],"leading":[43,68],"the":[45,55,104,110,162,165,170,185,192,217,226,259,276,279,308,311,313,327,334,354,359,362,371,378,392,409,427,491,500,509,523,526,542,550,566,573,586,657,661,678,695,706,724,729],"needless":[46],"duplication":[47,56],"maintenance":[50],"evolution":[52],"efforts,":[53],"causing":[54],"propagation":[58],"existing":[60,193,227,574],"bugs":[61,71],"throughout":[62],"system,":[65],"even":[67],"new":[70,131,244,285],"duplicate":[73],"is":[75,81,498,675,783],"not":[76,211],"evolved":[77],"in":[78,109,115,152,239,294,348,444,591,640,738],"parallel.":[79],"It":[80,497],"important":[82],"detect":[85],"their":[86,95,733],"so":[88,147],"they":[90],"can":[91,412,469,763],"be":[92,413,764],"managed":[93],"harm":[96],"mitigated.":[97],"This":[98,467],"need":[99],"has":[100,119,156,694,785],"been":[101,120,157,182],"recognized":[102],"many":[105,124],"clone":[106,113,153,166,173,179,195,207,231,245,252,286,323,337,364,373,386,402,471,506,513,553,577,610,628,638,649,667,715,736],"detectors":[107,180,196,507],"available":[108],"literature.":[111],"Additionally,":[112],"detection":[114,167,232,293,338,403,472,514,554,578,629,639,650,697,737],"large-scale":[116,186,194,219,260,511,581,627,641],"inter-project":[117,187,220,261,296,447,482,512,557,582,642,685],"repositories":[118],"shown":[121],"potential":[125],"applications":[126],"such":[127,751],"as":[128,712,752],"mining":[129,459],"APIs,":[132],"license":[133],"violation":[134],"detection,":[135,138,154],"similar":[136],"application":[137],"completion,":[140],"API":[141],"recommendation":[142],"usage":[144],"support,":[145],"on.\\n\\nDespite":[148],"this":[149,240,317,431,456,518,546,777],"great":[150],"interest":[151],"there":[155],"very":[158,177,342],"little":[159],"evaluation":[160,271],"performance":[163,593],"tools,":[168,528],"including":[169,254],"creation":[171],"benchmarks.":[174,374,716],"As":[175,222],"well,":[176,223],"few":[178],"proposed":[183],"use":[188,264,353,517],"cases.":[189],"In":[190,560,619],"particular,":[191],"require":[197],"extraordinary":[198],"hardware,":[199],"long":[200],"execution":[201],"times,":[202],"lack":[203],"support":[204],"common":[206],"types,":[208],"adaptable":[212,755,784],"target":[214,741],"explore":[216,549],"emerging":[218,510],"use-cases.":[221],"none":[224],"benchmarks":[228,246,266,304,394,539],"could":[229],"evaluate":[230,301,358,420,470,522,776],"these":[234,237,265],"scenarios.\\n\\nWe":[235],"address":[236],"problems":[238],"thesis":[241],"introducing":[243],"using":[247,302,345,656],"both":[248,532],"synthetic":[249,322,533],"real":[251,442],"data,":[253],"benchmark":[256,324,438,457,468,502,519],"evaluating":[258,400,505],"use-case.":[262,515],"We":[263,282,352,375,405,454,516],"conduct":[268],"comprehensive":[269],"tool":[270],"comparison":[273],"studies":[274,774],"considering":[275],"state":[277,309,360,524],"art":[280,363,527],"tools.":[281,404],"introduce":[283,320,434,565,624],"detector":[287],"fast,":[289,634],"scalable":[290,635,648],"user-guided":[292,637,720,778],"large":[295,437,446,556],"datasets,":[297,583],"which":[298,332,632,722],"we":[299,319,325,433,548,564,623,775],"extensively":[300],"our":[303,561,620,625,714],"compare":[306,367],"against":[307,370],"art.\\n\\nIn":[312],"first":[314,562],"part":[315,429,544],"thesis,":[318,432,547],"call":[326],"Mutation":[328,355,379,410],"Injection":[330],"Framework":[331,356,380,411,602],"measures":[333],"recall":[335,592,708],"tools":[339,421,473,579,680],"at":[340,585,699],"fine":[343],"granularity":[344],"artificial":[346],"mutation-analysis":[350],"procedure.":[351],"detectors,":[365],"its":[368],"results":[369],"previous":[372,393],"demonstrate":[376,530],"enables":[381,633],"accurate,":[382],"precise":[383],"bias-free":[385],"benchmarking":[387],"experiments,":[388],"show":[390,407],"outdated":[396],"inappropriate":[398],"modern":[401],"also":[406,499,704],"adapted":[414],"with":[415],"custom":[416],"mutation":[417],"operators":[418],"any":[423,742],"kind":[424,745],"clone.\\n\\nIn":[426],"second":[428,621],"BigCloneBench,":[435],"8":[440],"million":[441],"source":[448,558],"datasets":[449],"(IJaDataset:":[450],"25K":[451],"projects,":[452],"250MLOC).":[453],"built":[455],"IJaDataset":[460],"functions":[462],"implementing":[463],"commonly":[464],"needed":[465],"functionalities.":[466],"all":[475],"types":[476],"clones,":[478,483,486],"intra-project":[480],"vs":[481],"semantic":[485],"across":[490],"entire":[492],"spectrum":[493],"syntactical":[495],"similarity.":[496],"only":[501,679],"capable":[503],"thoroughly":[521],"why":[531],"(Mutation":[534],"Framework)":[535],"real-world":[537],"(BigCloneBench)":[538],"needed.\\n\\nIn":[541],"third":[543],"scaling":[551,572],"datasets.":[559,643],"study":[563],"Shuffling":[567,601],"Framework,":[568],"strategy":[570],"natively":[575],"non-scalable":[576],"but":[584],"cost":[587],"reduction":[590],"requiring":[595],"small":[597],"compute":[598],"cluster.":[599],"The":[600],"exploits":[603],"non-deterministic":[604],"input":[605,671],"partitioning,":[606],"partition":[607],"shuffling,":[608],"inverted":[609,666],"indexing":[611],"coarse-grained":[613],"similarity":[614,659],"metrics":[615],"achieve":[617],"scalability.":[618],"study,":[622],"premier":[626],"tool,":[630],"CloneWorks,":[631],"CloneWorks":[644,674,717,748],"achieves":[645],"fast":[646],"an":[652,665,684,690],"average":[653,691],"personal":[654],"workstation":[655],"Jaccard":[658],"coefficient,":[660],"sub-block":[662],"filtering":[663],"heuristic,":[664],"index,":[668],"index-based":[670],"partitioning":[672],"heuristic.":[673],"one":[676],"scale":[682],"dataset":[686],"250MLOC":[688],"workstation,":[692],"fastest":[696],"time":[698],"just":[700],"2-10":[701],"hours,":[702],"while":[703],"achieving":[705],"best":[707],"precision":[710],"performances":[711],"per":[713],"uses":[718],"approach,":[721],"gives":[723],"user":[725],"full":[726],"control":[727],"over":[728],"transformations":[730,750],"applied":[731],"source-code":[734],"before":[735],"order":[739],"type":[743],"or":[744],"clones.":[747],"includes":[749],"tunable":[753],"pretty-printing,":[754],"identifier":[756],"renaming,":[757],"syntax":[758],"abstraction":[759],"filtering,":[761],"extended":[765],"plug-in":[768],"architecture.":[769],"Through":[770],"scenarios":[771],"case":[773],"aspect,":[779],"find":[781],"it":[782],"high":[786],"precision.":[787]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-03-06T00:00:00"}