{"id":"https://openalex.org/W4400190916","doi":"https://doi.org/10.1145/3674731","title":"Automated Commit Intelligence by Pre-training","display_name":"Automated Commit Intelligence by Pre-training","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4400190916","doi":"https://doi.org/10.1145/3674731"},"language":"en","primary_location":{"id":"doi:10.1145/3674731","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674731","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","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/A5045943684","display_name":"Shangqing Liu","orcid":"https://orcid.org/0000-0002-5598-4006"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Shangqing Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102015751","display_name":"Yanzhou Li","orcid":"https://orcid.org/0009-0008-2263-7383"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yanzhou Li","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084396416","display_name":"Xiaofei Xie","orcid":"https://orcid.org/0000-0002-1288-6502"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaofei Xie","raw_affiliation_strings":["Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057849611","display_name":"Wei Ma","orcid":"https://orcid.org/0000-0002-0044-466X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Ma","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017417068","display_name":"Guozhu Meng","orcid":"https://orcid.org/0000-0001-6388-2571"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guozhu Meng","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045943684"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":4.6765,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95030988,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9975000023841858,"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":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8880231976509094},{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.8345887660980225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4887087345123291},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4814433455467224},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.475670725107193},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.47250306606292725},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4705653190612793},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4527552127838135},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4518057107925415},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43621155619621277},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25963568687438965},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14023810625076294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8880231976509094},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.8345887660980225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887087345123291},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4814433455467224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.475670725107193},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.47250306606292725},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4705653190612793},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4527552127838135},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4518057107925415},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43621155619621277},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25963568687438965},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14023810625076294},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674731","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674731","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2604348044","https://openalex.org/W2741609678","https://openalex.org/W2747329762","https://openalex.org/W2894732341","https://openalex.org/W2911282308","https://openalex.org/W2963341956","https://openalex.org/W2981852735","https://openalex.org/W3034999214","https://openalex.org/W3081159607","https://openalex.org/W3098605233","https://openalex.org/W3108032709","https://openalex.org/W3156636935","https://openalex.org/W3167276542","https://openalex.org/W3170092793","https://openalex.org/W3198685994","https://openalex.org/W3202579690","https://openalex.org/W4205371973","https://openalex.org/W4221166942","https://openalex.org/W4234552385","https://openalex.org/W4284709233","https://openalex.org/W4287889995","https://openalex.org/W4288089799","https://openalex.org/W4289365316","https://openalex.org/W4307932749","https://openalex.org/W4308643994","https://openalex.org/W4377238789","https://openalex.org/W4384155563","https://openalex.org/W4384302803","https://openalex.org/W4385571453","https://openalex.org/W4385572856","https://openalex.org/W4385572925","https://openalex.org/W4385573867"],"related_works":["https://openalex.org/W2476117260","https://openalex.org/W2770531922","https://openalex.org/W1845068655","https://openalex.org/W4321354308","https://openalex.org/W3092441607","https://openalex.org/W2290299503","https://openalex.org/W3029851195","https://openalex.org/W2183585111","https://openalex.org/W2211158793","https://openalex.org/W2046884474"],"abstract_inverted_index":{"GitHub":[0,37,115],"commits,":[1,38],"which":[2,69],"record":[3],"the":[4,63,80,180],"code":[5,66],"changes":[6],"with":[7],"natural":[8],"language":[9],"messages":[10],"for":[11,36,58,114,132,153,169],"description,":[12],"play":[13],"a":[14,89,109],"critical":[15],"role":[16],"in":[17,28],"software":[18,22,29,84],"developers\u2019":[19],"comprehension":[20],"of":[21,65,82],"evolution.":[23],"Due":[24],"to":[25,78,136],"their":[26,72],"importance":[27],"development,":[30],"several":[31],"learning-based":[32],"works":[33,51,168],"are":[34],"conducted":[35],"such":[39],"as":[40],"commit":[41,91,138],"message":[42],"generation":[43,151],"and":[44,129,149],"security":[45],"patch":[46],"identification.":[47],"However,":[48],"most":[49],"existing":[50],"focus":[52],"on":[53,103,145,158],"customizing":[54],"specialized":[55],"neural":[56],"networks":[57],"different":[59,75],"tasks.":[60],"Inspired":[61],"by":[62,121],"superiority":[64],"pre-trained":[67,110,120,167],"models,":[68],"has":[70],"confirmed":[71],"effectiveness":[73],"across":[74,98],"downstream":[76],"tasks,":[77],"promote":[79],"development":[81],"open-source":[83],"community,":[85],"we":[86,106],"first":[87],"collect":[88],"large-scale":[90],"benchmark":[92],"including":[93],"over":[94],"7.99":[95],"million":[96],"commits":[97],"7":[99],"programming":[100],"languages.":[101],"Based":[102],"this":[104],"benchmark,":[105],"present":[107],"CommitBART,":[108],"encoder-decoder":[111],"Transformer":[112],"model":[113,118,142,181],"commits.":[116,154],"The":[117,155],"is":[119,143],"three":[122,150],"categories":[123],"(i.e.,":[124],"denoising":[125],"objectives,":[126],"cross-modal":[127],"generation,":[128],"contrastive":[130],"learning)":[131],"six":[133],"pre-training":[134,177],"tasks":[135,152,160],"learn":[137],"fragment":[139],"representations.":[140],"Our":[141],"evaluated":[144],"one":[146],"understanding":[147],"task":[148,178],"comprehensive":[156],"experiments":[157],"these":[159],"demonstrate":[161],"that":[162,175],"CommitBART":[163],"significantly":[164],"outperforms":[165],"previous":[166],"code.":[170],"Further":[171],"analysis":[172],"also":[173],"reveals":[174],"each":[176],"enhances":[179],"performance.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}