{"id":"https://openalex.org/W4386767024","doi":"https://doi.org/10.1109/tr.2023.3312294","title":"Goner: Building Tree-Based N-Gram-Like Model for Semantic Code Clone Detection","display_name":"Goner: Building Tree-Based N-Gram-Like Model for Semantic Code Clone Detection","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386767024","doi":"https://doi.org/10.1109/tr.2023.3312294"},"language":"en","primary_location":{"id":"doi:10.1109/tr.2023.3312294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2023.3312294","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Reliability","raw_type":"journal-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/A5056381213","display_name":"Yueming Wu","orcid":"https://orcid.org/0000-0002-1515-3558"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yueming Wu","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028101591","display_name":"Siyue Feng","orcid":"https://orcid.org/0000-0002-6694-9126"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyue Feng","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092877303","display_name":"Wenqi Suo","orcid":"https://orcid.org/0000-0002-9984-8348"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqi Suo","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074676946","display_name":"Deqing Zou","orcid":"https://orcid.org/0000-0001-8534-5048"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqing Zou","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Hubei Engineering Research Center on Big Data Security, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056381213"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":3.2162,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93070178,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"73","issue":"2","first_page":"1310","last_page":"1324"},"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":0.9940999746322632,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9925000071525574,"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/computer-science","display_name":"Computer science","score":0.7203995585441589},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6188170909881592},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5982214212417603},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5383623242378235},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44843170046806335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4442687928676605},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4325195550918579},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35337743163108826},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3033565878868103},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1883562207221985},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15425997972488403},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10923781991004944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203995585441589},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6188170909881592},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5982214212417603},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5383623242378235},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44843170046806335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442687928676605},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4325195550918579},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35337743163108826},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3033565878868103},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1883562207221985},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15425997972488403},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10923781991004944},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/tr.2023.3312294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2023.3312294","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Reliability","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7170798094","display_name":null,"funder_award_id":"U1936211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1490878083","https://openalex.org/W1593203335","https://openalex.org/W1596612291","https://openalex.org/W1678356000","https://openalex.org/W1698439592","https://openalex.org/W1885561873","https://openalex.org/W1988790447","https://openalex.org/W2065053490","https://openalex.org/W2096491586","https://openalex.org/W2118024368","https://openalex.org/W2120326119","https://openalex.org/W2122111042","https://openalex.org/W2128698639","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2138756793","https://openalex.org/W2165739648","https://openalex.org/W2282866165","https://openalex.org/W2295598076","https://openalex.org/W2298313545","https://openalex.org/W2402290068","https://openalex.org/W2564651042","https://openalex.org/W2572741336","https://openalex.org/W2584966780","https://openalex.org/W2602016889","https://openalex.org/W2611246357","https://openalex.org/W2620636222","https://openalex.org/W2624164341","https://openalex.org/W2634106992","https://openalex.org/W2741705590","https://openalex.org/W2756212243","https://openalex.org/W2767717989","https://openalex.org/W2789627069","https://openalex.org/W2794304550","https://openalex.org/W2794744252","https://openalex.org/W2795237776","https://openalex.org/W2807866521","https://openalex.org/W2899171197","https://openalex.org/W2955426500","https://openalex.org/W2963355447","https://openalex.org/W3013476178","https://openalex.org/W3045279034","https://openalex.org/W3105535951","https://openalex.org/W3160804878","https://openalex.org/W3198988786","https://openalex.org/W3211224881","https://openalex.org/W4212883601","https://openalex.org/W4236137412","https://openalex.org/W4301168982","https://openalex.org/W4313563607","https://openalex.org/W4313563766","https://openalex.org/W6697318023","https://openalex.org/W6725533135"],"related_works":["https://openalex.org/W2377327490","https://openalex.org/W2560253012","https://openalex.org/W1524590520","https://openalex.org/W2412288087","https://openalex.org/W2371792548","https://openalex.org/W1697705604","https://openalex.org/W2419862115","https://openalex.org/W2017092658","https://openalex.org/W2100349471","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Code":[0,193],"clone":[1,22,31,42,86,174],"detection":[2,6,23,32,43,87],"refers":[3],"to":[4,25,63,71,108,128,279],"the":[5,18,52,65,91,110,129,132,138,141,251],"of":[7,20,29,55,61,105,131,140,152,158,253],"code":[8,21,30,41,48,73,85,173,282],"fragments":[9],"that":[10,199],"are":[11,155],"functionally":[12],"similar.":[13],"As":[14],"software":[15],"engineering":[16],"progresses,":[17],"significance":[19],"continues":[24],"grow.":[26],"A":[27],"number":[28],"techniques":[33],"have":[34],"been":[35],"designed.":[36],"Among":[37],"these":[38],"methods,":[39],"tree-based":[40,82,269],"approaches":[44],"can":[45],"discover":[46],"semantic":[47,84,172,281],"clones.":[49,283],"However,":[50],"given":[51],"intricate":[53],"nature":[54],"tree":[56,66,93,113],"structures,":[57],"they":[58],"consume":[59],"plenty":[60],"time":[62],"complete":[64],"analysis,":[67],"thus":[68],"cannot":[69],"scale":[70],"large-scale":[72],"scanning.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,101,121,165],"propose":[79],"a":[80,103,159,167],"novel":[81],"scalable":[83],"method":[88],"by":[89,148],"transforming":[90],"heavy-weight":[92],"processing":[94],"into":[95,114,124],"efficient":[96],"N-gram-like":[97],"subtrees":[98],"analysis.":[99],"Specifically,":[100],"build":[102],"variant":[104],"N-gram":[106],"model":[107,170],"partition":[109],"original":[111],"complex":[112],"small":[115],"subtrees.":[116],"After":[117],"collecting":[118],"all":[119,153],"subtrees,":[120],"divide":[122],"them":[123],"different":[125],"groups":[126,154],"according":[127],"positions":[130],"subtree":[133],"nodes,":[134],"and":[135,181,191,244],"then":[136],"calculate":[137],"similarity":[139],"same":[142],"group":[143],"between":[144],"two":[145,185],"functions":[146],"one":[147],"one.":[149],"Similarity":[150],"scores":[151],"made":[156],"up":[157],"feature":[160,163],"vector.":[161],"Given":[162],"vectors,":[164],"train":[166],"machine":[168],"learning":[169],"for":[171],"detection.":[175],"We":[176],"implement":[177],"<italic":[178,200,208,212,216,220,224,228,232,236,240,245,255,272],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[179,201,209,213,217,221,225,229,233,237,241,246,256,273],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Goner</i>":[180,202,257],"conduct":[182],"evaluations":[183],"on":[184],"extensively":[186],"utilized":[187],"datasets,":[188],"namely":[189,271],"BigCloneBench":[190],"Google":[192],"Jam.":[194],"The":[195],"experimental":[196],"results":[197],"indicate":[198],"outperforms":[203],"our":[204],"comparative":[205],"systems":[206],"(i.e.":[207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SourcererCC</i>":[210],",":[211,215,219,223,227,231,235,239,243,275],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">RtvNN</i>":[214],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Deckard</i>":[218],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ASTNN</i>":[222,274],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">TBCNN</i>":[226],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CDLH</i>":[230],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Amain</i>":[234],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">FCCA</i>":[238],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DeepSim</i>":[242],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SCDetector</i>":[247],").":[248],"Additionally,":[249],"in":[250],"context":[252],"scalability,":[254],"demonstrates":[258],"remarkable":[259],"speed,":[260],"being":[261],"approximately":[262],"56":[263],"times":[264],"faster":[265],"than":[266],"another":[267],"advanced":[268],"tool,":[270],"when":[276],"it":[277],"comes":[278],"identifying":[280]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}