{"id":"https://openalex.org/W4313547604","doi":"https://doi.org/10.1145/3551349.3556955","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","display_name":"CoditT5: Pretraining for Source Code and Natural Language Editing","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4313547604","doi":"https://doi.org/10.1145/3551349.3556955"},"language":"en","primary_location":{"id":"doi:10.1145/3551349.3556955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3556955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3556955","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3556955","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107247510","display_name":"Jiyang Zhang","orcid":"https://orcid.org/0000-0001-8211-3321"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiyang Zhang","raw_affiliation_strings":["The University of Texas at Austin, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8211-3321","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, United States of America","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054581139","display_name":"Sheena Panthaplackel","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheena Panthaplackel","raw_affiliation_strings":["The University of Texas at Austin, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, United States of America","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043609524","display_name":"Pengyu Nie","orcid":"https://orcid.org/0000-0003-1529-3216"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengyu Nie","raw_affiliation_strings":["The University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021057186","display_name":"Junyi Jessy Li","orcid":"https://orcid.org/0000-0002-2550-5262"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyi Jessy Li","raw_affiliation_strings":["The University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063052820","display_name":"Milos Gligoric","orcid":"https://orcid.org/0000-0002-5894-7649"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milos Gligoric","raw_affiliation_strings":["The University of Texas at Austin, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, United States of America","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":18.5919,"has_fulltext":true,"cited_by_count":82,"citation_normalized_percentile":{"value":0.99579933,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9958000183105469,"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":0.9958000183105469,"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/T13629","display_name":"Text Readability and Simplification","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9056699872016907},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5777352452278137},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5513395071029663},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.550297737121582},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5486562252044678},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5475021004676819},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5172355771064758},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5162258148193359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5020017623901367},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.48854073882102966},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.46536755561828613},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4292256236076355},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.11799073219299316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9056699872016907},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5777352452278137},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5513395071029663},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.550297737121582},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5486562252044678},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5475021004676819},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5172355771064758},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5162258148193359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5020017623901367},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48854073882102966},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.46536755561828613},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4292256236076355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.11799073219299316},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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:10.1145/3551349.3556955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3556955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3556955","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3551349.3556955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3556955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3556955","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1221862560","display_name":"Collaborative Research: SHF: Medium: Efficient and Trustworthy Proof Engineering","funder_award_id":"2107291","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2044781645","display_name":null,"funder_award_id":"CCF-2107291","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2190198004","display_name":"CAREER:  Discourse Processing and Content Generation for Document Simplification","funder_award_id":"2145479","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2943845835","display_name":null,"funder_award_id":"CCF-1652517, CCF-2107291","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3492201139","display_name":null,"funder_award_id":"CCF-1652517","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4326398606","display_name":"CAREER: Advancing Regression Testing: Theory and Practice","funder_award_id":"1652517","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7678768243","display_name":null,"funder_award_id":"CCF-1652517, CCF-2107291, IIS-2107524, IIS-2145479","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8811855750","display_name":null,"funder_award_id":"IIS-2107524","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/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313547604.pdf","grobid_xml":"https://content.openalex.org/works/W4313547604.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1985610876","https://openalex.org/W2048679005","https://openalex.org/W2133556223","https://openalex.org/W2257051837","https://openalex.org/W2534253848","https://openalex.org/W2621430944","https://openalex.org/W2789204155","https://openalex.org/W2905463374","https://openalex.org/W2927213876","https://openalex.org/W2954823997","https://openalex.org/W2963018920","https://openalex.org/W2963617989","https://openalex.org/W2981852735","https://openalex.org/W2995903212","https://openalex.org/W3034999214","https://openalex.org/W3035657086","https://openalex.org/W3086007799","https://openalex.org/W3089183726","https://openalex.org/W3098605233","https://openalex.org/W3105247453","https://openalex.org/W3161997752","https://openalex.org/W3170962973","https://openalex.org/W3174589346","https://openalex.org/W3176914858","https://openalex.org/W3191096151","https://openalex.org/W3193393431","https://openalex.org/W3198685994","https://openalex.org/W4206738852","https://openalex.org/W4206756860","https://openalex.org/W4284697810","https://openalex.org/W4284709233","https://openalex.org/W4288077069","https://openalex.org/W4288089799","https://openalex.org/W4289105807"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W3034878914","https://openalex.org/W3122369893","https://openalex.org/W2407476586","https://openalex.org/W4388483263","https://openalex.org/W3019688513","https://openalex.org/W2750654225"],"abstract_inverted_index":{"Pretrained":[0],"language":[1,52,69],"models":[2,42],"have":[3],"been":[4],"shown":[5],"to":[6,27,47],"be":[7],"effective":[8],"in":[9],"many":[10],"software-related":[11,55],"generation":[12,112],"tasks;":[13],"however,":[14],"they":[15,23],"are":[16,24],"not":[17,25],"well-suited":[18],"for":[19,54,103,132],"editing":[20,56,77,104,136],"tasks":[21,57],"as":[22],"designed":[26],"reason":[28],"about":[29],"edits.":[30],"To":[31],"address":[32],"this,":[33],"we":[34,93,128],"propose":[35],"a":[36,50,110],"novel":[37],"pretraining":[38],"objective":[39],"which":[40,127],"explicitly":[41],"edits":[43],"and":[44,67,84,100,114],"use":[45],"it":[46,73],"build":[48],"CoditT5,":[49],"large":[51,62],"model":[53,113,117],"that":[58],"is":[59],"pretrained":[60],"on":[61,74],"amounts":[63],"of":[64,97],"source":[65],"code":[66,86],"natural":[68],"comments.":[70],"We":[71,106],"fine-tune":[72],"various":[75],"downstream":[76,135],"tasks,":[78],"including":[79],"comment":[80],"updating,":[81],"bug":[82],"fixing,":[83],"automated":[85],"review.":[87],"By":[88],"outperforming":[89],"standard":[90,111],"generation-based":[91],"models,":[92],"demonstrate":[94],"the":[95,133],"generalizability":[96],"our":[98,115],"approach":[99],"its":[101],"suitability":[102],"tasks.":[105,137],"also":[107],"show":[108],"how":[109],"edit-based":[116],"can":[118],"complement":[119],"one":[120],"another":[121],"through":[122],"simple":[123],"reranking":[124],"strategies,":[125],"with":[126],"achieve":[129],"state-of-the-art":[130],"performance":[131],"three":[134]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":21}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}