{"id":"https://openalex.org/W2922006620","doi":"https://doi.org/10.1109/saner.2019.8668039","title":"Learning-Based Recursive Aggregation of Abstract Syntax Trees for Code Clone Detection","display_name":"Learning-Based Recursive Aggregation of Abstract Syntax Trees for Code Clone Detection","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W2922006620","doi":"https://doi.org/10.1109/saner.2019.8668039","mag":"2922006620"},"language":"en","primary_location":{"id":"doi:10.1109/saner.2019.8668039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner.2019.8668039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088938582","display_name":"Lutz B\u00fcch","orcid":"https://orcid.org/0000-0003-1398-0565"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lutz Buch","raw_affiliation_strings":["Institute of Computer Science, Heidelberg University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054003032","display_name":"Artur Andrzejak","orcid":"https://orcid.org/0000-0003-0150-8220"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Artur Andrzejak","raw_affiliation_strings":["Institute of Computer Science, Heidelberg University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"104"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9746999740600586,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9739000201225281,"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/computer-science","display_name":"Computer science","score":0.7827625274658203},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6963377594947815},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6039498448371887},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.6019372940063477},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5789478421211243},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5766960978507996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5697544813156128},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5677425861358643},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5483959913253784},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48215433955192566},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.347331702709198},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15568310022354126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10171014070510864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827625274658203},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6963377594947815},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6039498448371887},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.6019372940063477},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5789478421211243},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5766960978507996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5697544813156128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5677425861358643},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5483959913253784},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48215433955192566},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.347331702709198},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15568310022354126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10171014070510864},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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:10.1109/saner.2019.8668039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner.2019.8668039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W183494281","https://openalex.org/W1614298861","https://openalex.org/W1857184435","https://openalex.org/W1899504021","https://openalex.org/W1990762361","https://openalex.org/W2064675550","https://openalex.org/W2104301886","https://openalex.org/W2104518905","https://openalex.org/W2109943392","https://openalex.org/W2127589108","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2143861926","https://openalex.org/W2152075773","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2158439356","https://openalex.org/W2163345210","https://openalex.org/W2164961799","https://openalex.org/W2171060037","https://openalex.org/W2187089797","https://openalex.org/W2286236884","https://openalex.org/W2298313545","https://openalex.org/W2387719207","https://openalex.org/W2402619042","https://openalex.org/W2511803001","https://openalex.org/W2598817001","https://openalex.org/W2618735982","https://openalex.org/W2619465136","https://openalex.org/W2740130862","https://openalex.org/W2741705590","https://openalex.org/W2762844179","https://openalex.org/W2767717989","https://openalex.org/W2796460440","https://openalex.org/W2807866521","https://openalex.org/W2883359218","https://openalex.org/W2899171197","https://openalex.org/W2950577311","https://openalex.org/W2963355447","https://openalex.org/W2964150020","https://openalex.org/W2964352358","https://openalex.org/W3005855585","https://openalex.org/W3098598077","https://openalex.org/W3105535951","https://openalex.org/W4294170691","https://openalex.org/W4301168982","https://openalex.org/W6607414916","https://openalex.org/W6631636882","https://openalex.org/W6636510571","https://openalex.org/W6638928880","https://openalex.org/W6675573446","https://openalex.org/W6682691769","https://openalex.org/W6697318023","https://openalex.org/W6750365960"],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2140186469","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W4318559728","https://openalex.org/W2775233965","https://openalex.org/W4360995913","https://openalex.org/W4312193868","https://openalex.org/W4308165509"],"abstract_inverted_index":{"Code":[0],"clone":[1,39,86,141],"detection":[2,40],"remains":[3],"a":[4,72,109],"crucial":[5],"challenge":[6],"in":[7,84,98],"maintaining":[8],"software":[9],"projects.":[10],"Many":[11],"classic":[12],"approaches":[13],"rely":[14],"on":[15,42],"handcrafted":[16],"aggregation":[17,35,115,120],"schemes,":[18],"while":[19],"recent":[20],"work":[21],"uses":[22],"supervised":[23,43],"or":[24],"unsupervised":[25],"learning.":[26,44],"In":[27],"this":[28,46],"work,":[29],"we":[30,48,89,129],"study":[31,58,90],"several":[32],"aspects":[33],"of":[34,62,93,108,133,147],"schemes":[36,121],"for":[37],"code":[38,85],"based":[41],"To":[45],"aim,":[47],"implement":[49],"an":[50],"AST-based":[51],"Recursive":[52],"Neural":[53],"Network.":[54],"Firstly,":[55],"our":[56],"ablation":[57],"shows":[59],"the":[60,79,91,131],"influence":[61,92],"model":[63],"choices":[64],"and":[65,76,137],"hyperparameters.":[66],"We":[67,100],"introduce":[68],"error":[69],"scaling":[70],"as":[71],"way":[73],"to":[74,143],"effectively":[75],"efficiently":[77],"address":[78],"class":[80],"imbalance":[81],"problem":[82],"arising":[83],"detection.":[87],"Secondly,":[88],"pretrained":[94,125],"embeddings":[95],"representing":[96],"nodes":[97],"ASTs.":[99],"show":[101,130],"that":[102],"simply":[103],"averaging":[104],"all":[105],"node":[106,126],"vectors":[107],"given":[110],"AST":[111,119],"yields":[112],"strong":[113],"baseline":[114],"scheme.":[116],"Further,":[117],"learned":[118,149],"greatly":[122],"benefit":[123],"from":[124],"embeddings.":[127],"Finally,":[128],"importance":[132],"carefully":[134],"separating":[135],"training":[136],"test":[138],"data":[139],"by":[140],"clusters,":[142],"reliably":[144],"measure":[145],"generalization":[146],"models":[148],"with":[150],"supervision.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}