{"id":"https://openalex.org/W3156041258","doi":"https://doi.org/10.1145/3460945.3464951","title":"Generating bug-fixes using pretrained transformers","display_name":"Generating bug-fixes using pretrained transformers","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3156041258","doi":"https://doi.org/10.1145/3460945.3464951","mag":"3156041258"},"language":"en","primary_location":{"id":"doi:10.1145/3460945.3464951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460945.3464951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM SIGPLAN International Symposium on Machine Programming","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.07896","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059021264","display_name":"Dawn Drain","orcid":"https://orcid.org/0000-0002-6606-4141"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Dawn Drain","raw_affiliation_strings":["Microsoft, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707380","display_name":"Chen Wu","orcid":"https://orcid.org/0000-0002-2492-0640"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Chen Wu","raw_affiliation_strings":["Microsoft, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105672745","display_name":"A. Svyatkovskiy","orcid":"https://orcid.org/0000-0001-7714-4481"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Alexey Svyatkovskiy","raw_affiliation_strings":["Microsoft, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085284883","display_name":"Neel Sundaresan","orcid":"https://orcid.org/0000-0002-0394-7588"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Neel Sundaresan","raw_affiliation_strings":["Microsoft, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059021264"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":1.7066,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87083824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9983999729156494,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9948999881744385,"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":0.8620287179946899},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.6320521831512451},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.567603349685669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5401292443275452},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5100350975990295},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4879969656467438},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4862891137599945},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4562389552593231},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4430859386920929},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4356827437877655},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4332001209259033},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.41736334562301636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3902824819087982},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38248535990715027},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.35247403383255005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8620287179946899},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.6320521831512451},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.567603349685669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401292443275452},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5100350975990295},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4879969656467438},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4862891137599945},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4562389552593231},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4430859386920929},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4356827437877655},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4332001209259033},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.41736334562301636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3902824819087982},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38248535990715027},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.35247403383255005},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3460945.3464951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460945.3464951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM SIGPLAN International Symposium on Machine Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.07896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07896","pdf_url":"https://arxiv.org/pdf/2104.07896","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3156041258","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.07896","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.07896","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.07896","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.07896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07896","pdf_url":"https://arxiv.org/pdf/2104.07896","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2098297786","https://openalex.org/W2145124323","https://openalex.org/W2153881107","https://openalex.org/W2766875678","https://openalex.org/W2907705732","https://openalex.org/W2923014074","https://openalex.org/W2951732578","https://openalex.org/W2952509486","https://openalex.org/W2952913664","https://openalex.org/W2962784628","https://openalex.org/W2963212250","https://openalex.org/W2963310665","https://openalex.org/W2963403868","https://openalex.org/W2963881719","https://openalex.org/W2970521905","https://openalex.org/W2972082064","https://openalex.org/W2977610714","https://openalex.org/W2981852735","https://openalex.org/W2982399380","https://openalex.org/W2995333547","https://openalex.org/W2995903212","https://openalex.org/W3001279689","https://openalex.org/W3021762813","https://openalex.org/W3034999214","https://openalex.org/W3098605233","https://openalex.org/W3108032709","https://openalex.org/W6739901393","https://openalex.org/W6771879896","https://openalex.org/W6772383348"],"related_works":["https://openalex.org/W3170962973","https://openalex.org/W2914161001","https://openalex.org/W2996248296","https://openalex.org/W2905288168","https://openalex.org/W2514538448","https://openalex.org/W2130858451","https://openalex.org/W3136840659","https://openalex.org/W3161282429","https://openalex.org/W2979566992","https://openalex.org/W2399578172","https://openalex.org/W2956515571","https://openalex.org/W2993007949","https://openalex.org/W3179601161","https://openalex.org/W2012604743","https://openalex.org/W2791610814","https://openalex.org/W2340053113","https://openalex.org/W1993833135","https://openalex.org/W2772007744","https://openalex.org/W2981196198","https://openalex.org/W2898498885"],"abstract_inverted_index":{"Detecting":[0],"and":[1,33,70,96,152,155],"fixing":[2],"bugs":[3,47,72],"are":[4,22],"two":[5,91],"of":[6,13,44,90,116,170],"the":[7,14,37,53,101,114,138,145,167,171,214],"most":[8],"important":[9],"yet":[10],"frustrating":[11],"parts":[12],"software":[15],"development":[16],"cycle.":[17],"Existing":[18],"bug":[19],"detection":[20],"tools":[21],"based":[23],"mainly":[24],"on":[25,30,100,109,234],"static":[26],"analyzers,":[27],"which":[28,66],"rely":[29],"mathematical":[31],"logic":[32],"symbolic":[34],"reasoning":[35],"about":[36],"program":[38,63],"execution":[39],"to":[40,52,68,123,134,175,189,196,226],"detect":[41,69],"common":[42],"types":[43],"bugs.":[45],"Fixing":[46],"is":[48,238],"typically":[49],"left":[50],"out":[51],"developer.":[54],"In":[55,173],"this":[56],"work":[57],"we":[58,178,203],"introduce":[59],"DeepDebug:":[60],"a":[61,85,205,243],"data-driven":[62],"repair":[64],"approach":[65,237],"learns":[67],"fix":[71],"in":[73],"Java":[74],"methods":[75],"mined":[76],"from":[77,126,131,208],"real-world":[78],"GitHub":[79],"repositories.":[80],"We":[81,105,143],"frame":[82],"bug-patching":[83],"as":[84,121,187,218,220,247],"sequence-to-sequence":[86],"learning":[87],"task":[88,225],"consisting":[89],"steps:":[92],"(i)":[93],"denoising":[94],"pretraining,":[95],"(ii)":[97],"supervised":[98,124],"finetuning":[99],"target":[102],"translation":[103],"task.":[104],"show":[106,156],"that":[107,157,194],"pretraining":[108,130],"source":[110],"code":[111,135,193],"programs":[112],"improves":[113,137],"number":[115],"patches":[117],"found":[118],"by":[119,140],"33%":[120],"compared":[122],"training":[125],"scratch,":[127],"while":[128],"domain-adaptive":[129],"natural":[132],"language":[133,239],"further":[136],"accuracy":[139,147],"another":[141],"32%.":[142],"refine":[144],"standard":[146,215],"evaluation":[148],"metric":[149],"into":[150],"non-deletion":[151,164],"deletion-only":[153],"fixes,":[154],"our":[158,180,236],"best":[159,181],"model":[160],"generates":[161],"75%":[162],"more":[163],"fixes":[165],"than":[166],"previous":[168],"state":[169],"art.":[172],"contrast":[174],"prior":[176],"work,":[177],"attain":[179],"results":[182],"when":[183],"generating":[184],"raw":[185],"code,":[186],"opposed":[188],"working":[190],"with":[191,213,221],"abstracted":[192],"tends":[195],"only":[197,242],"benefit":[198],"smaller":[199],"capacity":[200],"models.":[201],"Finally,":[202],"observe":[204],"subtle":[206],"improvement":[207],"adding":[209,222],"syntax":[210],"embeddings":[211],"along":[212],"positional":[216],"embeddings,":[217],"well":[219],"an":[223],"auxiliary":[224],"predict":[227],"each":[228],"token's":[229],"syntactic":[230],"class.":[231],"Despite":[232],"focusing":[233],"Java,":[235],"agnostic,":[240],"requiring":[241],"general-purpose":[244],"parser":[245],"such":[246],"tree-sitter.":[248]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}