{"id":"https://openalex.org/W4415746274","doi":"https://doi.org/10.1109/icsme64153.2025.00033","title":"AST-Enhanced or AST-Overloaded? The Surprising Impact of Hybrid Graph Representations on Code Clone Detection","display_name":"AST-Enhanced or AST-Overloaded? The Surprising Impact of Hybrid Graph Representations on Code Clone Detection","publication_year":2025,"publication_date":"2025-09-07","ids":{"openalex":"https://openalex.org/W4415746274","doi":"https://doi.org/10.1109/icsme64153.2025.00033"},"language":null,"primary_location":{"id":"doi:10.1109/icsme64153.2025.00033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsme64153.2025.00033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Maintenance and Evolution (ICSME)","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/A5100317171","display_name":"Zixian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Zixian Zhang","raw_affiliation_strings":["University of Galway,Ireland"],"affiliations":[{"raw_affiliation_string":"University of Galway,Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089955586","display_name":"Takfarinas Saber","orcid":"https://orcid.org/0000-0003-2958-7979"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Takfarinas Saber","raw_affiliation_strings":["University of Galway,Ireland"],"affiliations":[{"raw_affiliation_string":"University of Galway,Ireland","institution_ids":["https://openalex.org/I188760350"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100317171"],"corresponding_institution_ids":["https://openalex.org/I188760350"],"apc_list":null,"apc_paid":null,"fwci":7.2527,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97236395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9851999878883362,"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":0.9851999878883362,"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":0.0013000000035390258,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/source-code","display_name":"Source code","score":0.47369998693466187},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.435699999332428},{"id":"https://openalex.org/keywords/control-flow-graph","display_name":"Control flow graph","score":0.41370001435279846},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3952000141143799},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3912000060081482},{"id":"https://openalex.org/keywords/graph-kernel","display_name":"Graph kernel","score":0.38370001316070557},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.37049999833106995},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620999813079834},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48350000381469727},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.421999990940094},{"id":"https://openalex.org/C27458966","wikidata":"https://www.wikidata.org/wiki/Q1187693","display_name":"Control flow graph","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3952000141143799},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C100595998","wikidata":"https://www.wikidata.org/wiki/Q11731931","display_name":"Graph kernel","level":5,"score":0.38370001316070557},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.26910001039505005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsme64153.2025.00033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsme64153.2025.00033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Maintenance and Evolution (ICSME)","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":27,"referenced_works":["https://openalex.org/W2065053490","https://openalex.org/W2158439356","https://openalex.org/W2578208870","https://openalex.org/W2741705590","https://openalex.org/W2806530724","https://openalex.org/W2922006620","https://openalex.org/W3014339000","https://openalex.org/W3014596957","https://openalex.org/W3043078865","https://openalex.org/W3198988786","https://openalex.org/W3207955138","https://openalex.org/W3214115326","https://openalex.org/W4206299714","https://openalex.org/W4213130063","https://openalex.org/W4225723247","https://openalex.org/W4231449374","https://openalex.org/W4285238952","https://openalex.org/W4285263385","https://openalex.org/W4285280217","https://openalex.org/W4309023067","https://openalex.org/W4312084729","https://openalex.org/W4313466484","https://openalex.org/W4384158943","https://openalex.org/W4384302844","https://openalex.org/W4384345648","https://openalex.org/W4386472818","https://openalex.org/W4391148896"],"related_works":[],"abstract_inverted_index":{"As":[0],"one":[1],"of":[2,76,106,124],"the":[3,74,104,122,204],"most":[4],"detrimental":[5],"code":[6,8,35,107,134],"smells,":[7],"clones":[9],"significantly":[10],"increase":[11],"software":[12,26],"maintenance":[13],"costs":[14],"and":[15,68,81,168,202],"heighten":[16],"vulnerability":[17],"risks,":[18],"making":[19],"their":[20,40,82,99],"detection":[21,37,201],"a":[22,115],"critical":[23],"challenge":[24],"in":[25,102,129],"engineering.":[27],"Abstract":[28],"Syntax":[29],"Trees":[30],"(ASTs)":[31],"dominate":[32],"deep":[33],"learning-based":[34],"clone":[36,108,135],"due":[38],"to":[39,97,119],"precise":[41],"syntactic":[42],"structure":[43],"representation,":[44],"but":[45],"they":[46],"inherently":[47],"lack":[48],"semantic":[49,60],"depth.":[50],"Recent":[51],"studies":[52],"address":[53],"this":[54,111],"by":[55],"enriching":[56],"AST-based":[57,79,125],"representations":[58,80,128,142,157],"with":[59,84,192],"graphs,":[61],"such":[62],"as":[63],"Control":[64],"Flow":[65,70],"Graphs":[66,71],"(CFGs)":[67],"Data":[69],"(DFGs).":[72],"However,":[73],"effectiveness":[75,123],"various":[77,140],"enriched":[78,207],"compatibility":[83],"different":[85],"graph-based":[86],"machine":[87],"learning":[88],"techniques":[89],"remains":[90],"an":[91],"open":[92],"question,":[93],"warranting":[94],"further":[95],"investigation":[96],"unlock":[98],"full":[100],"potential":[101],"addressing":[103],"complexities":[105],"detection.":[109,136],"In":[110],"paper,":[112],"we":[113],"present":[114],"comprehensive":[116],"empirical":[117],"study":[118],"rigorously":[120],"evaluate":[121],"hybrid":[126,141,156],"graph":[127],"Graph":[130,175],"Neural":[131],"Network":[132],"(GNN)-based":[133],"We":[137],"systematically":[138],"compare":[139],"((CFG,":[143],"DFG,":[144],"Flow-Augmented":[145],"ASTs":[146],"(FA-AST))":[147],"across":[148],"multiple":[149],"GNN":[150],"architectures.":[151],"Our":[152],"experiments":[153],"reveal":[154],"that":[155,184],"impact":[158],"GNNs":[159],"differently:":[160],"while":[161],"AST+CFG+DFG":[162],"consistently":[163],"enhances":[164],"accuracy":[165],"for":[166,206],"convolution-":[167],"attention-based":[169],"models":[170],"(Graph":[171],"Convolutional":[172],"Networks":[173,177],"(GCN),":[174],"Attention":[176],"(GAT)),":[178],"FA-AST":[179],"frequently":[180],"introduces":[181],"structural":[182],"complexity":[183],"harms":[185],"performance.":[186],"Notably,":[187],"GMN":[188],"outperforms":[189],"others":[190],"even":[191],"standard":[193],"AST":[194],"representations,":[195],"highlighting":[196],"its":[197],"superior":[198],"cross-code":[199],"similarity":[200],"reducing":[203],"need":[205],"structures.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-31T00:00:00"}