{"id":"https://openalex.org/W4313563766","doi":"https://doi.org/10.1145/3551349.3560426","title":"Detecting Semantic Code Clones by Building AST-based Markov Chains Model","display_name":"Detecting Semantic Code Clones by Building AST-based Markov Chains Model","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4313563766","doi":"https://doi.org/10.1145/3551349.3560426"},"language":"en","primary_location":{"id":"doi:10.1145/3551349.3560426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551349.3560426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","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/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":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, 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":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, 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":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, 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":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056381213"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":6.0648,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96557975,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"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":0.9973999857902527,"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":0.9937000274658203,"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":0.7852003574371338},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6257472038269043},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.5943114757537842},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5773892402648926},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5328688621520996},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5212767124176025},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5145878195762634},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.45729103684425354},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3744676113128662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36667299270629883},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3445388674736023},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33859506249427795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2527156472206116},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15931907296180725},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.15780821442604065},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10641881823539734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852003574371338},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6257472038269043},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.5943114757537842},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5773892402648926},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5328688621520996},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5212767124176025},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5145878195762634},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.45729103684425354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3744676113128662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36667299270629883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3445388674736023},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33859506249427795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2527156472206116},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15931907296180725},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.15780821442604065},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10641881823539734},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551349.3560426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551349.3560426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","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/W154143472","https://openalex.org/W1593203335","https://openalex.org/W1596612291","https://openalex.org/W1698439592","https://openalex.org/W2065053490","https://openalex.org/W2096491586","https://openalex.org/W2118024368","https://openalex.org/W2120326119","https://openalex.org/W2128698639","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2138756793","https://openalex.org/W2148099973","https://openalex.org/W2165739648","https://openalex.org/W2282866165","https://openalex.org/W2402290068","https://openalex.org/W2511803001","https://openalex.org/W2564651042","https://openalex.org/W2572741336","https://openalex.org/W2602016889","https://openalex.org/W2611246357","https://openalex.org/W2620636222","https://openalex.org/W2624164341","https://openalex.org/W2741705590","https://openalex.org/W2756212243","https://openalex.org/W2767717989","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/W3013476178","https://openalex.org/W3045279034","https://openalex.org/W3105535951","https://openalex.org/W3125205154","https://openalex.org/W3125675786","https://openalex.org/W3160804878","https://openalex.org/W3198988786","https://openalex.org/W3211224881","https://openalex.org/W4301168982"],"related_works":["https://openalex.org/W4389751695","https://openalex.org/W4310447811","https://openalex.org/W2165004968","https://openalex.org/W2320787857","https://openalex.org/W3086207785","https://openalex.org/W2969229669","https://openalex.org/W3012064729","https://openalex.org/W2955426500","https://openalex.org/W2388254906","https://openalex.org/W3049398420"],"abstract_inverted_index":{"Code":[0,138],"clone":[1,25,70,120,153],"detection":[2,26,154],"aims":[3],"to":[4,37,47,49,53,83,116,149],"find":[5],"functionally":[6],"similar":[7],"code":[8,24,40,51,69,119,152],"fragments,":[9],"which":[10,32],"is":[11,147],"becoming":[12],"more":[13,15],"and":[14,93,140,165],"important":[16],"in":[17,100],"the":[18,54,85,95,124],"field":[19],"of":[20,56,97,126],"software":[21],"engineering.":[22],"Many":[23],"methods":[27,34,44],"have":[28],"been":[29],"proposed,":[30],"among":[31],"tree-based":[33,67],"are":[35,45],"able":[36],"handle":[38],"semantic":[39,68],"clones.":[41],"However,":[42],"these":[43,101],"difficult":[46],"scale":[48],"big":[50],"due":[52],"complexity":[55],"tree":[57,88],"structures.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,78,108,128],"design":[63],"Amain,":[64,127],"a":[65,80,112,118],"scalable":[66],"detector":[71],"by":[72],"building":[73],"Markov":[74,91],"chains":[75,92],"models.":[76],"Specifically,":[77],"propose":[79],"novel":[81],"method":[82],"transform":[84],"original":[86],"complex":[87],"into":[89,111],"simple":[90],"measure":[94],"distance":[96,106],"all":[98,105],"states":[99],"chains.":[102],"After":[103],"obtaining":[104],"values,":[107],"feed":[109],"them":[110],"machine":[113],"learning":[114],"classifier":[115],"train":[117],"detector.":[121],"To":[122],"examine":[123],"effectiveness":[125],"evaluate":[129],"it":[130],"on":[131],"two":[132],"widely":[133],"used":[134],"datasets":[135],"namely":[136],"Google":[137],"Jam":[139],"BigCloneBench.":[141],"Experimental":[142],"results":[143],"show":[144],"that":[145],"Amain":[146],"superior":[148],"nine":[150],"state-of-the-art":[151],"tools":[155],"(i.e.,":[156],"SourcererCC,":[157],"RtvNN,":[158],"Deckard,":[159],"ASTNN,":[160],"TBCNN,":[161],"CDLH,":[162],"FCCA,":[163],"DeepSim,":[164],"SCDetector).":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}