{"id":"https://openalex.org/W4283525684","doi":"https://doi.org/10.1145/3502852","title":"Assessing and Improving an Evaluation Dataset for Detecting Semantic Code Clones via Deep Learning","display_name":"Assessing and Improving an Evaluation Dataset for Detecting Semantic Code Clones via Deep Learning","publication_year":2022,"publication_date":"2022-06-25","ids":{"openalex":"https://openalex.org/W4283525684","doi":"https://doi.org/10.1145/3502852"},"language":"en","primary_location":{"id":"doi:10.1145/3502852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502852","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","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/A5027133048","display_name":"Hao Yu","orcid":"https://orcid.org/0000-0002-3828-7612"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Yu","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047688641","display_name":"Xing Hu","orcid":"https://orcid.org/0000-0003-0093-3292"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Hu","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447682","display_name":"Ge Li","orcid":"https://orcid.org/0000-0002-5828-0186"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414277","display_name":"Ying Li","orcid":"https://orcid.org/0000-0002-6278-2357"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["National Research Center of Software Engineering, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Software Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012567911","display_name":"Qianxiang Wang","orcid":"https://orcid.org/0000-0002-6598-0041"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxiang Wang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048118068","display_name":"Tao Xie","orcid":"https://orcid.org/0000-0002-6731-216X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xie","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027133048"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.2261,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90094353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":"4","first_page":"1","last_page":"25"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9646000266075134,"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":0.9409000277519226,"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/computer-science","display_name":"Computer science","score":0.869694173336029},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8027771711349487},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7494349479675293},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7037091255187988},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6224416494369507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.589016318321228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5157306790351868},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.48487386107444763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4184279143810272},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.380641371011734},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12420958280563354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869694173336029},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8027771711349487},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7494349479675293},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7037091255187988},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6224416494369507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.589016318321228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5157306790351868},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.48487386107444763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4184279143810272},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.380641371011734},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12420958280563354},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3502852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502852","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8821883043","display_name":null,"funder_award_id":"62161146003","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":46,"referenced_works":["https://openalex.org/W1593203335","https://openalex.org/W1964357740","https://openalex.org/W1965206591","https://openalex.org/W2030841479","https://openalex.org/W2049386694","https://openalex.org/W2065053490","https://openalex.org/W2096491586","https://openalex.org/W2100060170","https://openalex.org/W2106259924","https://openalex.org/W2107697055","https://openalex.org/W2125260159","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2138756793","https://openalex.org/W2158439356","https://openalex.org/W2165739648","https://openalex.org/W2166278331","https://openalex.org/W2282866165","https://openalex.org/W2298313545","https://openalex.org/W2511803001","https://openalex.org/W2572741336","https://openalex.org/W2634106992","https://openalex.org/W2741705590","https://openalex.org/W2767717989","https://openalex.org/W2781491433","https://openalex.org/W2794744252","https://openalex.org/W2796141603","https://openalex.org/W2806718802","https://openalex.org/W2807964941","https://openalex.org/W2808509424","https://openalex.org/W2884276923","https://openalex.org/W2888312537","https://openalex.org/W2899171197","https://openalex.org/W2949297108","https://openalex.org/W2954552517","https://openalex.org/W2955426500","https://openalex.org/W2964194820","https://openalex.org/W2979792666","https://openalex.org/W2980153788","https://openalex.org/W2993743533","https://openalex.org/W3006181408","https://openalex.org/W3014339000","https://openalex.org/W3101228802","https://openalex.org/W4214583996","https://openalex.org/W4233104424","https://openalex.org/W4301168982"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W2378211422","https://openalex.org/W1979633005","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W2352307597","https://openalex.org/W2087343574"],"abstract_inverted_index":{"In":[0,75],"recent":[1],"years,":[2],"applying":[3],"deep":[4,42,140,182],"learning":[5,43,141,183],"to":[6,37,54,67,83,138,169,176],"detect":[7],"semantic":[8,47,72,89,130,147,190],"code":[9,73,120],"clones":[10,131],"has":[11],"received":[12],"substantial":[13],"attention":[14],"from":[15],"the":[16,25,94,158,179,186],"research":[17],"community.":[18],"Accordingly,":[19],"various":[20],"evaluation":[21,58],"benchmark":[22,59],"datasets,":[23],"with":[24],"most":[26],"popular":[27],"one":[28],"as":[29,35,62],"BigCloneBench,":[30,135],"are":[31,100],"constructed":[32],"and":[33,39,164,173],"selected":[34],"benchmarks":[36],"assess":[38,178],"compare":[40],"different":[41],"models":[44,69,142,184],"for":[45,70,128,145],"detecting":[46,71,129,146,189],"clones.":[48,74,148,191],"However,":[49],"there":[50],"is":[51,64],"no":[52],"study":[53,82],"investigate":[55],"whether":[56],"an":[57,80,109],"dataset":[60],"such":[61],"BigCloneBench":[63,86,168],"properly":[65],"used":[66,102],"evaluate":[68],"this":[76,122],"article,":[77],"we":[78,107,153],"present":[79],"experimental":[81],"show":[84],"that":[85,92,112],"typically":[87],"includes":[88],"clone":[90],"pairs":[91],"use":[93,174],"same":[95],"identifier":[96,159],"names,":[97],"which":[98,115],"however":[99],"not":[101],"in":[103,118,167,171],"non-semantic-clone":[104],"pairs.":[105],"Subsequently,":[106],"propose":[108],"undesirable-by-design":[110],"Linear-Model":[111],"considers":[113],"only":[114],"identifiers":[116],"appear":[117],"a":[119,155],"fragment;":[121],"model":[123],"can":[124],"achieve":[125],"high":[126],"effectiveness":[127,180],"when":[132],"evaluated":[133],"on":[134,185],"even":[136],"comparable":[137],"state-of-the-art":[139],"recently":[143],"proposed":[144],"To":[149],"alleviate":[150],"these":[151],"issues,":[152],"abstract":[154],"subset":[156],"of":[157,181,188],"names":[160],"(including":[161],"type,":[162],"variable,":[163],"method":[165],"names)":[166],"result":[170],"AbsBigCloneBench":[172,175],"better":[177],"task":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}