{"id":"https://openalex.org/W4412719020","doi":"https://doi.org/10.1109/tse.2025.3592841","title":"Directional Diffusion-Style Code Editing Pre-Training","display_name":"Directional Diffusion-Style Code Editing Pre-Training","publication_year":2025,"publication_date":"2025-07-25","ids":{"openalex":"https://openalex.org/W4412719020","doi":"https://doi.org/10.1109/tse.2025.3592841"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2025.3592841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2025.3592841","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","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/A5034794084","display_name":"Qingyuan Liang","orcid":"https://orcid.org/0000-0002-1697-3451"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyuan Liang","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1697-3451","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047965752","display_name":"Zeyu Sun","orcid":"https://orcid.org/0000-0002-9990-9120"},"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/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Sun","raw_affiliation_strings":["National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9990-9120","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047271595","display_name":"Qihao Zhu","orcid":"https://orcid.org/0000-0001-8036-2623"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihao Zhu","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8036-2623","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junhao Hu","orcid":"https://orcid.org/0009-0007-7087-4642"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Hu","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-7087-4642","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yifan Zhao","orcid":"https://orcid.org/0000-0002-2035-0791"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zhao","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2035-0791","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009476223","display_name":"Yizhou Chen","orcid":"https://orcid.org/0000-0003-1821-3170"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Chen","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1821-3170","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101528906","display_name":"Mingxuan Zhu","orcid":"https://orcid.org/0000-0001-8676-4017"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxuan Zhu","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8676-4017","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guoqing Wang","orcid":"https://orcid.org/0009-0000-5208-4750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Wang","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5208-4750","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0001-8304-7055"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8304-7055","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7117,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85102569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"51","issue":"9","first_page":"2583","last_page":"2600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9782999753952026,"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"}},"topics":[{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9782999753952026,"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":0.8463255167007446},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5894816517829895},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5804653763771057},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5528303980827332},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49286723136901855},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4499184489250183},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.36396628618240356},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33515894412994385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8463255167007446},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5894816517829895},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5804653763771057},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5528303980827332},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49286723136901855},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4499184489250183},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36396628618240356},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33515894412994385},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2025.3592841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2025.3592841","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6223597658","display_name":null,"funder_award_id":"62232003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8355433955","display_name":null,"funder_award_id":"62402482","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2074562477","https://openalex.org/W2097227214","https://openalex.org/W2101105183","https://openalex.org/W2103107119","https://openalex.org/W2156723666","https://openalex.org/W2534253848","https://openalex.org/W2954823997","https://openalex.org/W2972082064","https://openalex.org/W3034999214","https://openalex.org/W3035657086","https://openalex.org/W3098605233","https://openalex.org/W3129831491","https://openalex.org/W3161903544","https://openalex.org/W3161997752","https://openalex.org/W3170092793","https://openalex.org/W3193682477","https://openalex.org/W3198685994","https://openalex.org/W4206756860","https://openalex.org/W4285605736","https://openalex.org/W4308643152","https://openalex.org/W4313547604","https://openalex.org/W4377238789","https://openalex.org/W4384159044","https://openalex.org/W4385245566","https://openalex.org/W4389162095","https://openalex.org/W4391558404","https://openalex.org/W4394769313","https://openalex.org/W4394769500","https://openalex.org/W4402237118","https://openalex.org/W4403579163","https://openalex.org/W4409920472","https://openalex.org/W4412888189"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W2356229341","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611"],"abstract_inverted_index":{"Code":[0],"pre-trained":[1,28,62,203,265,278,286],"models":[2,29,232,241,250,279],"have":[3],"shown":[4],"promising":[5],"effectiveness":[6,212],"in":[7,229,242,251,260],"various":[8,145],"software":[9,20],"engineering":[10],"tasks.":[11,80,195],"Among":[12],"these":[13],"tasks,":[14],"many":[15],"tasks":[16,88,133,228],"are":[17],"related":[18],"to":[19,48,105,117,135,163,231],"evolution":[21,172],"and/or":[22],"code":[23,27,34,52,95,107,125],"editing.":[24],"However,":[25],"existing":[26],"often":[30],"overlook":[31],"the":[32,38,42,50,69,106,114,119,124,137,160,165,169,202,234],"real-world":[33],"editing":[35,43,53],"data":[36,70],"and":[37,86,111,154,157,188,209,244,276],"evolutionary":[39,138],"nature":[40],"of":[41,55,78,151,186,233,268,289],"process.":[44],"In":[45,72],"this":[46],"paper,":[47],"simulate":[49],"step-by-step":[51],"process":[54,104,116,162],"human":[56],"developers,":[57],"we":[58,74,99,142,200],"propose":[59],"DivoT5,":[60,73],"a":[61,91,102,184],"model":[63],"based":[64],"on":[65,205,226,266,287],"directional":[66],"diffusion":[67,92],"at":[68],"level.":[71],"adopt":[75],"two":[76,180],"categories":[77],"pre-training":[79,115,161],"The":[81,129],"first":[82,100,143],"category":[83,131],"is":[84,132],"mask":[85],"denoising":[87],"augmented":[89],"with":[90,121,280],"direction":[93],"representing":[94],"evolution.":[96,128],"That":[97,140],"is,":[98,141],"apply":[101],"noising":[103],"snippets":[108,120,126,152],"before":[109,153],"evolution,":[110,156],"then":[112,158],"ask":[113,159],"restore":[118],"noise":[122],"into":[123,168],"after":[127,155,171],"second":[130],"aiming":[134],"reinforce":[136],"direction.":[139],"generate":[144],"intermediate":[146,166],"versions":[147,167],"for":[148,173,179,284],"each":[149,174,197],"pair":[150],"transform":[164],"snippet":[170],"pair.":[175],"We":[176],"evaluate":[177,210],"DivoT5":[178,204,264,285],"code-editing":[181,256],"scenarios":[182,215],"(including":[183],"number":[185],"tasks)":[187],"one":[189,255],"non-editing":[190],"scenario":[191],"using":[192],"four":[193],"downstream":[194,198],"For":[196,254],"task,":[199],"fine-tune":[201],"multiple":[206],"corresponding":[207],"datasets":[208],"its":[211],"across":[213],"diverse":[214],"Our":[216],"experimental":[217],"results":[218],"show":[219],"that":[220],"ivoT5":[221],"achieves":[222],"state-of-the-art":[223],"(SOTA)":[224],"performance":[225],"most":[227],"comparison":[230],"same":[235],"scale":[236],"(220M),":[237],"large-scale":[238],"(770M,":[239],"6.7B)":[240],"fine-tuning,":[243],"billion-scale":[245],"(6.7B,":[246],"8B,":[247],"ChatGPT)":[248],"instruct":[249],"few-shot":[252],"settings.":[253],"task":[257],"(i.e.,":[258],"CodeReview":[259],"NL-based":[261],"CodeRefinement":[262],"task),":[263],"top":[267,288],"CodeT5-small":[269],"(60M)":[270],"can":[271],"even":[272],"outperform":[273],"CodeT5-base":[274,290],"(220M)":[275],"other":[277],"220M":[281],"parameters":[282],"except":[283],"(220M).":[291]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}