{"id":"https://openalex.org/W4308643029","doi":"https://doi.org/10.1145/3540250.3549171","title":"UTANGO: untangling commits with context-aware, graph-based, code change clustering learning model","display_name":"UTANGO: untangling commits with context-aware, graph-based, code change clustering learning model","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308643029","doi":"https://doi.org/10.1145/3540250.3549171"},"language":"en","primary_location":{"id":"doi:10.1145/3540250.3549171","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3540250.3549171","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3540250.3549171","source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3540250.3549171","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107249192","display_name":"Yi Li","orcid":"https://orcid.org/0009-0007-0143-0677"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Li","raw_affiliation_strings":["New Jersey Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070990953","display_name":"Shaohua Wang","orcid":"https://orcid.org/0000-0001-5777-7759"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaohua Wang","raw_affiliation_strings":["New Jersey Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089000736","display_name":"Tien N. Nguyen","orcid":"https://orcid.org/0009-0006-7962-6090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien N. Nguyen","raw_affiliation_strings":["University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"232"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9944999814033508,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9901000261306763,"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":0.8047769069671631},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7481896877288818},{"id":"https://openalex.org/keywords/program-comprehension","display_name":"Program comprehension","score":0.6585253477096558},{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.6237298846244812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5542369484901428},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5408918857574463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5362647771835327},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.481249064207077},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4533124268054962},{"id":"https://openalex.org/keywords/software-evolution","display_name":"Software evolution","score":0.4467136859893799},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44273698329925537},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.422702431678772},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41440510749816895},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3803151845932007},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27497512102127075},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.2543291449546814},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12258458137512207},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.1217045783996582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047769069671631},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7481896877288818},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.6585253477096558},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.6237298846244812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5542369484901428},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5408918857574463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5362647771835327},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.481249064207077},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4533124268054962},{"id":"https://openalex.org/C202105479","wikidata":"https://www.wikidata.org/wiki/Q265013","display_name":"Software evolution","level":5,"score":0.4467136859893799},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44273698329925537},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.422702431678772},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41440510749816895},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3803151845932007},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27497512102127075},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.2543291449546814},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12258458137512207},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.1217045783996582},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3540250.3549171","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3540250.3549171","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3540250.3549171","source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3540250.3549171","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3540250.3549171","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3540250.3549171","source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2127239100","display_name":null,"funder_award_id":"NCAE- C-002-2021","funder_id":"https://openalex.org/F4320311089","funder_display_name":"National Security Agency"},{"id":"https://openalex.org/G4403837408","display_name":null,"funder_award_id":"CNS-2120386, CCF-1723215, CCF-1723432, TWC-1723198","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4604030585","display_name":null,"funder_award_id":"NCAE-C-002-2021","funder_id":"https://openalex.org/F4320311089","funder_display_name":"National Security Agency"},{"id":"https://openalex.org/G4757794435","display_name":null,"funder_award_id":"CNS-2120386, CCF-1723215, CCF-1723432, TWC- 1723198","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5204842600","display_name":null,"funder_award_id":"CNS-2120386","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6913106001","display_name":"SHF: Large: Collaborative Research: Exploiting the Naturalness of Software","funder_award_id":"1723215","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7387244200","display_name":"SHF:Small: Build Code Maintenance and Detecting, Testing, Locating Configuration and Build Errors","funder_award_id":"1723432","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G758310216","display_name":"Collaborative Research: CCRI: ENS: Boa 2.0: Enhancing Infrastructure for Studying Software and its Evolution at a Large Scale","funder_award_id":"2120386","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8064159086","display_name":"TWC: Small: Detection and Prevention of Prior Known Software Security Vulnerabilities","funder_award_id":"1723198","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311089","display_name":"National Security Agency","ror":"https://ror.org/0047bvr32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308643029.pdf","grobid_xml":"https://content.openalex.org/works/W4308643029.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2049612634","https://openalex.org/W2075382909","https://openalex.org/W2088809147","https://openalex.org/W2093897789","https://openalex.org/W2097227214","https://openalex.org/W2113157806","https://openalex.org/W2137444776","https://openalex.org/W2144344516","https://openalex.org/W2149029960","https://openalex.org/W2222512263","https://openalex.org/W2602717139","https://openalex.org/W2620636222","https://openalex.org/W2785365618","https://openalex.org/W2901222374","https://openalex.org/W2913734115","https://openalex.org/W2963033680","https://openalex.org/W3102072454","https://openalex.org/W3195902719"],"related_works":["https://openalex.org/W2122804569","https://openalex.org/W2087378224","https://openalex.org/W2240979497","https://openalex.org/W2025599150","https://openalex.org/W3104152981","https://openalex.org/W2158202016","https://openalex.org/W2598318421","https://openalex.org/W3010807105","https://openalex.org/W4241100723","https://openalex.org/W2020166315"],"abstract_inverted_index":{"During":[0],"software":[1],"evolution,":[2],"developers":[3],"make":[4],"several":[5],"changes":[6,48,75],"and":[7,24,126,135,174,183,200,205,218,229],"commit":[8,51],"them":[9,16],"into":[10,99,111],"the":[11,47,74,92,97,107,118,132,136,164,175,179,193,213,223],"repositories.":[12],"Unfortunately,":[13],"many":[14],"of":[15,27,178,215],"tangle":[17],"different":[18,100,103],"purposes,":[19],"both":[20],"hampering":[21],"program":[22,172],"comprehension":[23],"reducing":[25],"separation":[26],"concerns.":[28,104,194],"Automated":[29],"approaches":[30,226],"with":[31,102,203],"deterministic":[32],"solutions":[33],"have":[34],"been":[35],"proposed":[36],"to":[37,72,90,162],"untangle":[38,73],"commits.":[39],"However,":[40],"specifying":[41],"an":[42],"effective":[43],"clustering":[44,85,109,114,144],"criteria":[45],"on":[46,117,198],"in":[49,76,130],"a":[50,65,77,81,112,127,149],"for":[52,56,167,227],"untangling":[53],"is":[54],"challenging":[55],"those":[57],"approaches.":[58],"In":[59],"this":[60],"work,":[61],"we":[62,147],"present":[63],"UTango,":[64],"machine":[66],"learning":[67,86,145,155],"(ML)-based":[68],"approach":[69],"that":[70,88,170,210],"learns":[71,89],"commit.":[78],"We":[79,105],"develop":[80,148],"novel":[82],"code":[83,93,120,152,168,185],"change":[84,121,153],"model":[87,115],"cluster":[91],"changes,":[94,169],"represented":[95],"by":[96],"embeddings,":[98],"groups":[101],"adapt":[106],"agglomerative":[108],"algorithm":[110],"supervised-learning":[113],"operating":[116],"learned":[119],"embeddings":[122,166],"via":[123],"trainable":[124],"parameters":[125],"loss":[128],"function":[129],"comparing":[131],"predicted":[133],"clusters":[134],"correct":[137],"ones":[138],"during":[139],"training.":[140],"To":[141],"facilitate":[142],"our":[143],"model,":[146,156],"context-aware,":[150],"graph-based,":[151],"representation":[154],"leveraging":[157],"Label,":[158],"Graph-based":[159],"Convolution":[160],"Network":[161],"produce":[163],"contextualized":[165],"integrates":[171],"dependencies":[173],"surrounding":[176],"contexts":[177,182],"changes.":[180],"The":[181],"cloned":[184],"are":[186],"also":[187],"explicitly":[188],"represented,":[189],"helping":[190],"UTango":[191],"distinguish":[192],"Our":[195],"empirical":[196],"evaluation":[197],"C#":[199,228],"Java":[201],"datasets":[202],"1,612":[204],"14k":[206],"tangled":[207],"commits":[208],"show":[209],"it":[211],"achieves":[212],"accuracy":[214],"28.6%\u2013":[216],"462.5%":[217],"13.3%\u2013100.0%":[219],"relatively":[220],"higher":[221],"than":[222],"state-of-the-art":[224],"commit-untangling":[225],"Java,":[230],"respectively.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}