{"id":"https://openalex.org/W4360770795","doi":"https://doi.org/10.1109/tse.2023.3235942","title":"DupHunter: Detecting Duplicate Pull Requests in Fork-Based Development","display_name":"DupHunter: Detecting Duplicate Pull Requests in Fork-Based Development","publication_year":2023,"publication_date":"2023-03-23","ids":{"openalex":"https://openalex.org/W4360770795","doi":"https://doi.org/10.1109/tse.2023.3235942"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2023.3235942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2023.3235942","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","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/A5002119636","display_name":"He Jiang","orcid":"https://orcid.org/0000-0001-8674-4948"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Jiang","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-8674-4948","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107953142","display_name":"Yulong Li","orcid":"https://orcid.org/0000-0003-0003-9653"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Li","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-0003-9653","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018071549","display_name":"Shikai Guo","orcid":"https://orcid.org/0000-0002-8554-6365"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikai Guo","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-8554-6365","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328758","display_name":"Xiaochen Li","orcid":"https://orcid.org/0000-0002-5068-1938"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochen Li","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375823","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-6272-4069"},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Macau University of Science and Technology, Taipa, Macao, China"],"raw_orcid":"https://orcid.org/0000-0002-6272-4069","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Macau University of Science and Technology, Taipa, Macao, China","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423958","display_name":"Hui Li","orcid":"https://orcid.org/0000-0003-1923-0669"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1923-0669","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418997","display_name":"Rong Chen","orcid":"https://orcid.org/0000-0001-5848-6398"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Chen","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-5848-6398","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1103,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94322491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"49","issue":"4","first_page":"2920","last_page":"2940"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7903748750686646},{"id":"https://openalex.org/keywords/fork","display_name":"Fork (system call)","score":0.6784863471984863},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4274742007255554},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4255187511444092},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.420976847410202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3698752522468567},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3345193862915039},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.24751996994018555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903748750686646},{"id":"https://openalex.org/C40523978","wikidata":"https://www.wikidata.org/wiki/Q14675","display_name":"Fork (system call)","level":2,"score":0.6784863471984863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4274742007255554},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4255187511444092},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.420976847410202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3698752522468567},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3345193862915039},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24751996994018555},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2023.3235942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2023.3235942","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5299999713897705,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3427093674","display_name":null,"funder_award_id":"62032004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6242089131","display_name":null,"funder_award_id":"61902050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7452592615","display_name":null,"funder_award_id":"DUT22RC(3)028","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G76141480","display_name":null,"funder_award_id":"2021-MS-136","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"},{"id":"https://openalex.org/G8200738200","display_name":null,"funder_award_id":"3132019355","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G874560949","display_name":null,"funder_award_id":"0014/2022/A","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"},{"id":"https://openalex.org/G913651422","display_name":null,"funder_award_id":"0047/2020/A1","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320323893","display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","ror":"https://ror.org/05vna4324"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1577851692","https://openalex.org/W1611198075","https://openalex.org/W1784051948","https://openalex.org/W1981109290","https://openalex.org/W1998900885","https://openalex.org/W2018582844","https://openalex.org/W2030793160","https://openalex.org/W2040915209","https://openalex.org/W2095709152","https://openalex.org/W2099162911","https://openalex.org/W2109962300","https://openalex.org/W2124100711","https://openalex.org/W2139092060","https://openalex.org/W2139270835","https://openalex.org/W2144160189","https://openalex.org/W2154151876","https://openalex.org/W2156833313","https://openalex.org/W2160160234","https://openalex.org/W2165022036","https://openalex.org/W2167630669","https://openalex.org/W2239327973","https://openalex.org/W2285056549","https://openalex.org/W2288177242","https://openalex.org/W2288898007","https://openalex.org/W2343875716","https://openalex.org/W2368671040","https://openalex.org/W2401290433","https://openalex.org/W2499134242","https://openalex.org/W2593833795","https://openalex.org/W2598872606","https://openalex.org/W2603119212","https://openalex.org/W2604420197","https://openalex.org/W2735681515","https://openalex.org/W2758152813","https://openalex.org/W2794957215","https://openalex.org/W2794967409","https://openalex.org/W2798869704","https://openalex.org/W2892202790","https://openalex.org/W2920924032","https://openalex.org/W2936503027","https://openalex.org/W2962946486","https://openalex.org/W2967932715","https://openalex.org/W2970641574","https://openalex.org/W2981381779","https://openalex.org/W2998277008","https://openalex.org/W3034328552","https://openalex.org/W3035568641","https://openalex.org/W3044950360","https://openalex.org/W3080820911","https://openalex.org/W3085258507","https://openalex.org/W3093815602","https://openalex.org/W3152377126","https://openalex.org/W3163060204","https://openalex.org/W4225143092","https://openalex.org/W4237158495","https://openalex.org/W6636283824","https://openalex.org/W6638052707","https://openalex.org/W6690815549","https://openalex.org/W6695817786","https://openalex.org/W6753221617","https://openalex.org/W6762003241"],"related_works":["https://openalex.org/W2937118960","https://openalex.org/W2808525305","https://openalex.org/W3208656504","https://openalex.org/W3127613622","https://openalex.org/W2808177972","https://openalex.org/W4379380002","https://openalex.org/W2808535951","https://openalex.org/W3085385306","https://openalex.org/W3201151259","https://openalex.org/W2483304392"],"abstract_inverted_index":{"The":[0,157,204],"emergence":[1],"of":[2,10,36,74,100,113,176,190,229,253,277,286],"numerous":[3,39],"fork-based":[4],"development":[5,9],"platforms":[6],"facilitates":[7],"the":[8,17,30,34,59,72,96,107,154,171,180,183,188,194,199,210,221,257],"Open-Source":[11],"Software":[12],"(OSS)":[13],"projects.":[14,31,60],"Developers":[15],"across":[16,226],"world":[18],"can":[19,265],"fork":[20],"software":[21],"projects":[22,242],"and":[23,54,105,146,174,182,224,279],"submit":[24],"their":[25],"Pull":[26],"Requests":[27],"(PRs)":[28],"to":[29,89,152,165,197,262],"However,":[32,79],"as":[33,185,187],"number":[35],"forks":[37],"increases,":[38],"duplicate":[40,46,63,123,148,205,268],"PRs":[41,47,104,124,135,149,206],"might":[42],"be":[43],"submitted.":[44],"These":[45],"may":[48],"cause":[49],"extra":[50],"code":[51],"review":[52],"workload":[53],"frustrate":[55],"developers":[56],"working":[57],"on":[58,239],"To":[61],"detect":[62,267],"PRs,":[64,269],"many":[65],"approaches":[66,81,259],"have":[67],"been":[68],"proposed,":[69],"which":[70,140,219],"analyze":[71],"similarity":[73],"different":[75,111,227],"elements":[76,102,112,178,192,228],"in":[77,103],"PRs.":[78,115],"previous":[80],"still":[82],"suffer":[83],"from":[84],"unsatisfied":[85],"detection":[86,150,207],"accuracy":[87],"due":[88],"two":[90,114,230],"challenges.":[91,156],"That":[92],"is,":[93],"they":[94],"ignore":[95],"syntactic":[97,172,200],"structural":[98,201],"information":[99,202,222],"text":[101,177],"lack":[106],"joint":[108,211],"reasoning":[109,212],"between":[110],"In":[116],"this":[117],"study,":[118],"we":[119],"propose":[120],"an":[121,234,247,271,280],"automated":[122],"detector":[125],"named":[126],"<italic":[127,136,249,273,282],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[128,132,137,250,274,283],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DupHunter</i>":[129],"(":[130],"<bold":[131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Dup</b>":[133],"licate":[134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Hunter</i>":[138],"),":[139],"includes":[141],"a":[142,147,162,167,215],"graph":[143,158,164,216],"embedding":[144,159],"component":[145,151,160,208],"address":[153,198],"above":[155],"uses":[161],"feature":[163,231],"represent":[166],"PR.":[168],"It":[169],"encodes":[170],"structure":[173],"semantics":[175],"(e.g.,":[179,193],"title":[181],"description),":[184],"well":[186],"knowledge":[189],"non-text":[191],"submission":[195],"time),":[196],"challenge.":[203],"tackles":[209],"challenge":[213],"using":[214],"matching":[217,225],"network,":[218],"enables":[220],"exchange":[223],"graphs":[232],"with":[233,270],"attention":[235],"coefficient":[236],"mechanism.":[237],"Experiments":[238],"26":[240],"open-source":[241],"show":[243],"that":[244],"DupHunter":[245,264],"achieves":[246],"average":[248,272,281],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">F1-score@1</i>":[251],"value":[252,276,285],"0.650,":[254],"significantly":[255],"outperforming":[256],"state-of-the-art":[258],"by":[260],"3.2%":[261],"48.1%.":[263],"accurately":[266],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Precision@1</i>":[275],"0.922":[278],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Recall@1</i>":[284],"0.502.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}