{"id":"https://openalex.org/W4210550462","doi":"https://doi.org/10.1109/ase51524.2021.9678907","title":"Can Neural Clone Detection Generalize to Unseen Functionalities\u0192","display_name":"Can Neural Clone Detection Generalize to Unseen Functionalities\u0192","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4210550462","doi":"https://doi.org/10.1109/ase51524.2021.9678907"},"language":"en","primary_location":{"id":"doi:10.1109/ase51524.2021.9678907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase51524.2021.9678907","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","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/A5021607964","display_name":"Chenyao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenyao Liu","raw_affiliation_strings":["School of Software, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of Software, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061546771","display_name":"Zeqi Lin","orcid":"https://orcid.org/0009-0001-2563-7601"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeqi Lin","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025118710","display_name":"Jian\u2013Guang Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian-Guang Lou","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030845033","display_name":"Lijie Wen","orcid":"https://orcid.org/0000-0003-0358-3160"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijie Wen","raw_affiliation_strings":["School of Software, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of Software, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331488","display_name":"Dongmei Zhang","orcid":"https://orcid.org/0000-0002-9230-2799"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Zhang","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021607964"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.269,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89967943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"629"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9745000004768372,"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":0.9580000042915344,"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/generalizability-theory","display_name":"Generalizability theory","score":0.7951170206069946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7614049315452576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6681790351867676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5966048240661621},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5309801697731018},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.517006516456604},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.46954354643821716},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46554622054100037},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.453605979681015},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.43784087896347046},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43149739503860474},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41822347044944763},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35196053981781006},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14103755354881287}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7951170206069946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7614049315452576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6681790351867676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5966048240661621},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5309801697731018},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.517006516456604},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.46954354643821716},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46554622054100037},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.453605979681015},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43784087896347046},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43149739503860474},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41822347044944763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35196053981781006},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14103755354881287},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ase51524.2021.9678907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase51524.2021.9678907","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W5897337","https://openalex.org/W1983316175","https://openalex.org/W2042932437","https://openalex.org/W2065053490","https://openalex.org/W2101832700","https://openalex.org/W2104982710","https://openalex.org/W2117763124","https://openalex.org/W2119887272","https://openalex.org/W2125513188","https://openalex.org/W2127811329","https://openalex.org/W2128888088","https://openalex.org/W2143861926","https://openalex.org/W2155863608","https://openalex.org/W2158439356","https://openalex.org/W2161276236","https://openalex.org/W2171293873","https://openalex.org/W2282866165","https://openalex.org/W2298313545","https://openalex.org/W2360967250","https://openalex.org/W2413794162","https://openalex.org/W2516621648","https://openalex.org/W2557805692","https://openalex.org/W2608787653","https://openalex.org/W2740130862","https://openalex.org/W2741705590","https://openalex.org/W2768572539","https://openalex.org/W2786865417","https://openalex.org/W2794601162","https://openalex.org/W2806718802","https://openalex.org/W2808509424","https://openalex.org/W2887364112","https://openalex.org/W2888557792","https://openalex.org/W2888651608","https://openalex.org/W2899171197","https://openalex.org/W2904067867","https://openalex.org/W2942259124","https://openalex.org/W2949297108","https://openalex.org/W2951061410","https://openalex.org/W2954552517","https://openalex.org/W2955426500","https://openalex.org/W2962995178","https://openalex.org/W2963499994","https://openalex.org/W2963935794","https://openalex.org/W2964150020","https://openalex.org/W2964194820","https://openalex.org/W2968179027","https://openalex.org/W2997170297","https://openalex.org/W3003572584","https://openalex.org/W3005951744","https://openalex.org/W3011564318","https://openalex.org/W3014339000","https://openalex.org/W3036257804","https://openalex.org/W3098044990","https://openalex.org/W3098605233","https://openalex.org/W3099023595","https://openalex.org/W3099302725","https://openalex.org/W4245415816","https://openalex.org/W4289106754","https://openalex.org/W4301168982","https://openalex.org/W6600222735","https://openalex.org/W6692071231","https://openalex.org/W6695202613","https://openalex.org/W6697318023","https://openalex.org/W6730121546","https://openalex.org/W6745034332","https://openalex.org/W6748774801","https://openalex.org/W6752455799","https://openalex.org/W6754601402","https://openalex.org/W6762003241","https://openalex.org/W6764588566","https://openalex.org/W6772449105","https://openalex.org/W6779498098","https://openalex.org/W6779729747"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W4384158943"],"abstract_inverted_index":{"Many":[0],"recently":[1],"proposed":[2],"code":[3,219,253],"clone":[4,26,51,75,133,152,215],"detectors":[5,27,76,153,216],"exploit":[6],"neural":[7,25,50,74,132,151,214],"networks":[8],"to":[9,81,90,100,164,217],"capture":[10],"latent":[11],"semantics":[12],"of":[13,32,35,59,131,223,233,247],"source":[14],"code,":[15],"thus":[16],"achieving":[17],"impressive":[18],"results":[19,147,240],"for":[20,49],"detecting":[21,56],"semantic":[22,57,83],"clones.":[23],"These":[24],"rely":[28],"on":[29,70,136,189],"the":[30,45,61,79,108,128,146,171,186,197,231,245],"availability":[31],"large":[33],"amounts":[34],"labeled":[36],"training":[37,95,177,202],"data.":[38],"We":[39,119,160,173,206],"identify":[40],"a":[41,208],"key":[42,166],"oversight":[43],"in":[44,65,94],"current":[46,150],"evaluation":[47,122,138],"methodology":[48,123],"detection:":[52],"cross-functionality":[53,129],"generalization":[54],"(i.e.,":[55],"clones":[58],"which":[60],"functionalities":[62,93,191],"are":[63,116,256],"unseen":[64,102,190,224],"training).":[66],"Specifically,":[67],"we":[68],"focus":[69],"this":[71,137],"question:":[72],"do":[73],"truly":[77],"learn":[78,88],"ability":[80],"detect":[82],"clones,":[84],"or":[85],"they":[86],"just":[87],"how":[89,107],"model":[91],"specific":[92],"data":[96,178,203,255],"while":[97],"cannot":[98,154],"generalize":[99,155],"realistic":[101],"functionalities\u0192":[103],"This":[104],"paper":[105],"investigates":[106],"generalizability":[109,130],"can":[110,125,169,192],"be":[111,193],"evaluated":[112],"and":[113,145,181,200,236,254],"improved.Our":[114],"contributions":[115],"3-folds:":[117],"(1)":[118],"propose":[120,207],"an":[121,140],"that":[124,149,168,185,211,242],"systematically":[126],"measure":[127],"detection.":[134],"Based":[135],"methodology,":[139],"empirical":[141,162],"study":[142],"is":[143],"conducted":[144],"indicate":[148],"well":[156],"as":[157],"expected.":[158],"(2)":[159],"conduct":[161],"analysis":[163],"understand":[165],"factors":[167],"impact":[170],"generalizability.":[172],"investigate":[174],"3":[175],"factors:":[176],"diversity,":[179],"vocabulary,":[180],"locality.":[182],"Results":[183],"show":[184,241],"performance":[187],"loss":[188],"reduced":[194],"through":[195],"addressing":[196],"out-of-vocabulary":[198],"problem":[199],"increasing":[201],"diversity.":[204],"(3)":[205],"human-in-the-loop":[209],"mechanism":[210],"help":[212],"adapt":[213],"new":[218],"repositories":[220],"containing":[221],"lots":[222],"functionalities.":[225],"It":[226],"improves":[227],"annotation":[228],"efficiency":[229],"with":[230],"combination":[232],"transfer":[234],"learning":[235],"active":[237],"learning.":[238],"Experimental":[239],"it":[243],"reduces":[244],"amount":[246],"annotations":[248],"by":[249],"about":[250],"88%.":[251],"Our":[252],"publicly":[257],"available":[258],"<sup":[259],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[260],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[261],".":[262]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}