{"id":"https://openalex.org/W3102072454","doi":"https://doi.org/10.1145/3368089.3409693","title":"Flexeme: untangling commits using lexical flows","display_name":"Flexeme: untangling commits using lexical flows","publication_year":2020,"publication_date":"2020-11-08","ids":{"openalex":"https://openalex.org/W3102072454","doi":"https://doi.org/10.1145/3368089.3409693","mag":"3102072454"},"language":"en","primary_location":{"id":"doi:10.1145/3368089.3409693","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368089.3409693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/10107163/2/Barr_Flexeme-%20Untangling%20Commits%20Using%20Lexical%20Flows_AAM.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051026501","display_name":"Profir-Petru P\u00e2r\u0163achi","orcid":"https://orcid.org/0000-0003-4940-6864"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Profir-Petru P\u00e2r\u021bachi","raw_affiliation_strings":["University College London, UK"],"raw_orcid":"https://orcid.org/0000-0003-4940-6864","affiliations":[{"raw_affiliation_string":"University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004997665","display_name":"Santanu Kumar Dash","orcid":"https://orcid.org/0000-0002-5674-8531"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Santanu Kumar Dash","raw_affiliation_strings":["University of Surrey, UK"],"raw_orcid":"https://orcid.org/0000-0002-5674-8531","affiliations":[{"raw_affiliation_string":"University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080221214","display_name":"Miltiadis Allamanis","orcid":"https://orcid.org/0000-0002-5819-9900"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Miltiadis Allamanis","raw_affiliation_strings":["Microsoft Research, UK"],"raw_orcid":"https://orcid.org/0000-0002-5819-9900","affiliations":[{"raw_affiliation_string":"Microsoft Research, UK","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076587279","display_name":"Earl T. Barr","orcid":"https://orcid.org/0000-0003-0771-7891"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Earl T. Barr","raw_affiliation_strings":["University College London, UK"],"raw_orcid":"https://orcid.org/0000-0003-0771-7891","affiliations":[{"raw_affiliation_string":"University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051026501"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":1.9485,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89971205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"74"},"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":0.995199978351593,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9907000064849854,"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":0.7945740222930908},{"id":"https://openalex.org/keywords/program-comprehension","display_name":"Program comprehension","score":0.7857087850570679},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5971596837043762},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5765784978866577},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5022361278533936},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4957762658596039},{"id":"https://openalex.org/keywords/control-flow-graph","display_name":"Control flow graph","score":0.45523929595947266},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4342394173145294},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3495338261127472},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32726359367370605},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30026987195014954},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2385444939136505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2324478030204773},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.15000048279762268},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.13074839115142822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945740222930908},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.7857087850570679},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5971596837043762},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5765784978866577},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5022361278533936},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4957762658596039},{"id":"https://openalex.org/C27458966","wikidata":"https://www.wikidata.org/wiki/Q1187693","display_name":"Control flow graph","level":2,"score":0.45523929595947266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4342394173145294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3495338261127472},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32726359367370605},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30026987195014954},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2385444939136505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2324478030204773},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.15000048279762268},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.13074839115142822}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3368089.3409693","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368089.3409693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10107163","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10107163/","pdf_url":"https://discovery.ucl.ac.uk/10107163/2/Barr_Flexeme-%20Untangling%20Commits%20Using%20Lexical%20Flows_AAM.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE '20).    Association for Computing Machinery (ACM): New York, NY, USA. (2020)    (In press).  ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10107163","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10107163/","pdf_url":"https://discovery.ucl.ac.uk/10107163/2/Barr_Flexeme-%20Untangling%20Commits%20Using%20Lexical%20Flows_AAM.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE '20).    Association for Computing Machinery (ACM): New York, NY, USA. (2020)    (In press).  ","raw_type":"Proceedings paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2818692517","display_name":null,"funder_award_id":"EP/P005659/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3816790016","display_name":null,"funder_award_id":"EP/P005314/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6794522244","display_name":null,"funder_award_id":"EP/J017515/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8385396385","display_name":"DAASE: Dynamic Adaptive Automated Software Engineering","funder_award_id":"EP/J017515/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3102072454.pdf","grobid_xml":"https://content.openalex.org/works/W3102072454.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1516632679","https://openalex.org/W1575308494","https://openalex.org/W1999739253","https://openalex.org/W2000473405","https://openalex.org/W2020400699","https://openalex.org/W2040385668","https://openalex.org/W2075382909","https://openalex.org/W2093897789","https://openalex.org/W2097227214","https://openalex.org/W2113157806","https://openalex.org/W2137444776","https://openalex.org/W2139885493","https://openalex.org/W2141558501","https://openalex.org/W2142498761","https://openalex.org/W2149672479","https://openalex.org/W2222512263","https://openalex.org/W2241447802","https://openalex.org/W2482390396","https://openalex.org/W2587571325","https://openalex.org/W2602717139","https://openalex.org/W2787299871","https://openalex.org/W2842584488","https://openalex.org/W3021091026","https://openalex.org/W4231404931","https://openalex.org/W4254623384","https://openalex.org/W6681029592","https://openalex.org/W6758327135"],"related_works":["https://openalex.org/W4389670110","https://openalex.org/W2187546663","https://openalex.org/W2429057255","https://openalex.org/W148745890","https://openalex.org/W2611942503","https://openalex.org/W4315621326","https://openalex.org/W2899790217","https://openalex.org/W1576092969","https://openalex.org/W2122222797","https://openalex.org/W2788734033"],"abstract_inverted_index":{"Today,":[0],"most":[1],"developers":[2],"bundle":[3],"changes":[4],"into":[5],"commits":[6,16],"that":[7,101,121],"they":[8,38],"submit":[9],"to":[10,60,120,123],"a":[11,22,26,66,72,109,132,148],"shared":[12],"code":[13],"repository.":[14],"Tangled":[15],"intermix":[17],"distinct":[18],"concerns,":[19],"such":[20,44],"as":[21,45],"bug":[23],"fix":[24],"and":[25,35,53,84,93],"new":[27],"feature.":[28],"They":[29],"cause":[30],"issues":[31],"for":[32],"developers,":[33],"reviewers,":[34],"researchers":[36,55],"alike:":[37],"restrict":[39],"the":[40,70,99,128,139,151,159],"usability":[41],"of":[42,150],"tools":[43],"git":[46],"bisect,":[47],"make":[48],"patch":[49],"comprehension":[50],"more":[51],"difficult,":[52],"force":[54],"who":[56],"mine":[57],"software":[58],"repositories":[59],"contend":[61],"with":[62,78,98],"noise.":[63],"We":[64],"present":[65],"novel":[67],"data":[68,95],"structure,":[69],"\ud835\udeff-NFG,":[71],"multiversion":[73],"Program":[74],"Dependency":[75],"Graph":[76,118],"augmented":[77],"name":[79],"flows.":[80],"A":[81],"\ud835\udeff-NFG":[82,110,122],"directly":[83],"simultaneously":[85],"encodes":[86],"different":[87],"program":[88],"versions,":[89],"thereby":[90],"capturing":[91],"commits,":[92,112],"annotates":[94],"flow":[96,102],"edges":[97],"names/lexemes":[100],"across":[103],"them.":[104],"Our":[105],"technique,":[106],"Flexeme,":[107],"builds":[108],"from":[111],"then":[113],"applies":[114],"Agglomerative":[115],"Clustering":[116],"using":[117],"Similarity":[119],"untangle":[124],"its":[125],"commits.":[126],"At":[127],"untangling":[129],"task":[130],"on":[131,141],"C#":[133],"corpus,":[134],"our":[135],"implementation,":[136],"Heddle,":[137],"improves":[138],"state-of-the-art":[140],"accuracy":[142],"by":[143],"0.14,":[144],"achieving":[145],"0.81,":[146],"in":[147],"fraction":[149],"time:":[152],"Heddle":[153],"is":[154],"32":[155],"times":[156],"faster":[157],"than":[158],"previous":[160],"state-of-the-art.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}