{"id":"https://openalex.org/W4417516793","doi":"https://doi.org/10.1016/j.eswa.2026.132154","title":"Self-bootstrapping automated program repair: using LLMs to generate and evaluate synthetic training data for bug repair","display_name":"Self-bootstrapping automated program repair: using LLMs to generate and evaluate synthetic training data for bug repair","publication_year":2026,"publication_date":"2026-03-22","ids":{"openalex":"https://openalex.org/W4417516793","doi":"https://doi.org/10.1016/j.eswa.2026.132154"},"language":"en","primary_location":{"id":"doi:10.1016/j.eswa.2026.132154","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132154","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.eswa.2026.132154","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093701215","display_name":"David de-Fitero-Dominguez","orcid":null},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David de-Fitero-Dominguez","raw_affiliation_strings":["Departamento de Ciencias de la Computaci\u00f3n, Universidad de Alcal\u00e1, Alcal\u00e1 de Henares, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ciencias de la Computaci\u00f3n, Universidad de Alcal\u00e1, Alcal\u00e1 de Henares, Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019212220","display_name":"Antonio Garc\u00eda\u2010Cabot","orcid":"https://orcid.org/0000-0002-0298-3237"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Antonio Garcia-Cabot","raw_affiliation_strings":["Departamento de Ciencias de la Computaci\u00f3n, Universidad de Alcal\u00e1, Alcal\u00e1 de Henares, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ciencias de la Computaci\u00f3n, Universidad de Alcal\u00e1, Alcal\u00e1 de Henares, Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002675398","display_name":"Eva Garc\u00eda\u2010L\u00f3pez","orcid":"https://orcid.org/0000-0002-7598-3289"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eva Garcia-Lopez","raw_affiliation_strings":["Departamento de Ciencias de la Computaci\u00f3n, Universidad de Alcal\u00e1, Alcal\u00e1 de Henares, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ciencias de la Computaci\u00f3n, Universidad de Alcal\u00e1, Alcal\u00e1 de Henares, Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5019212220"],"corresponding_institution_ids":["https://openalex.org/I189268942"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":{"value":3220,"currency":"USD","value_usd":3220},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01441441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"319","issue":null,"first_page":"132154","last_page":"132154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.4887999892234802,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.4887999892234802,"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/T10260","display_name":"Software Engineering Research","score":0.28540000319480896,"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/T11424","display_name":"Security and Verification in Computing","score":0.06520000100135803,"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/commit","display_name":"Commit","score":0.779699981212616},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5597000122070312},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.44760000705718994},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44589999318122864},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4163999855518341},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4041999876499176},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.396699994802475},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.779699981212616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670799970626831},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5597000122070312},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3125},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.26190000772476196}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.eswa.2026.132154","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132154","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2505.07372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07372","pdf_url":"https://arxiv.org/pdf/2505.07372","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ebuah.uah.es:10017/69047","is_oa":true,"landing_page_url":"http://hdl.handle.net/10017/69047","pdf_url":null,"source":{"id":"https://openalex.org/S7407055200","display_name":"e_Buah","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"doi:10.48550/arxiv.2505.07372","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.07372","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.eswa.2026.132154","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132154","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1156303603","display_name":null,"funder_award_id":"SBPLY/23/180225/000063","funder_id":"https://openalex.org/F4320327216","funder_display_name":"Junta de Comunidades de Castilla-La Mancha"},{"id":"https://openalex.org/G4261093408","display_name":null,"funder_award_id":"PLEC2023-010251","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320327216","display_name":"Junta de Comunidades de Castilla-La Mancha","ror":"https://ror.org/02jv91m18"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W3156480510","https://openalex.org/W4402393484","https://openalex.org/W7133233472","https://openalex.org/W2285839903","https://openalex.org/W3091588759","https://openalex.org/W3098605233","https://openalex.org/W7084760361","https://openalex.org/W2923436575","https://openalex.org/W7126448819","https://openalex.org/W4415589175","https://openalex.org/W3143822685","https://openalex.org/W4412945568","https://openalex.org/W4408124887","https://openalex.org/W2895570420","https://openalex.org/W4387321091","https://openalex.org/W2145373440","https://openalex.org/W3089621332","https://openalex.org/W4256377773","https://openalex.org/W2373227884","https://openalex.org/W4412444947","https://openalex.org/W1498436455","https://openalex.org/W2168745915","https://openalex.org/W4404134046","https://openalex.org/W2972082064","https://openalex.org/W2318802957","https://openalex.org/W3198685994","https://openalex.org/W2139410856","https://openalex.org/W2344973853","https://openalex.org/W4313563660","https://openalex.org/W2963909831","https://openalex.org/W4388422146"],"related_works":[],"abstract_inverted_index":{"This":[0,180],"paper":[1],"presents":[2],"a":[3,49,52,58,138,174,183],"novel":[4],"methodology":[5,149],"for":[6,199,216],"enhancing":[7],"Automated":[8],"Program":[9],"Repair":[10],"(APR)":[11],"through":[12,48,152],"synthetic":[13,53,121],"data":[14,33,201],"generation":[15,55],"utilizing":[16],"Large":[17],"Language":[18],"Models":[19],"(LLMs).":[20],"Current":[21],"APR":[22],"systems":[23,171],"are":[24],"constrained":[25],"by":[26,57],"the":[27,105,119,131,166,210],"limited":[28],"availability":[29],"of":[30,73,212],"high-quality":[31],"training":[32,194],"encompassing":[34],"diverse":[35],"bug":[36,84],"types":[37],"across":[38,78],"multiple":[39],"programming":[40,80],"languages.":[41],"The":[42,148],"proposed":[43],"approach":[44],"addresses":[45],"this":[46],"limitation":[47],"two-phase":[50],"process:":[51],"sample":[54],"followed":[56],"rigorous":[59,153],"quality":[60],"assessment.":[61],"Multiple":[62],"state-of-the-art":[63],"LLMs":[64,188],"were":[65],"employed":[66],"to":[67,130],"generate":[68,189],"approximately":[69],"30,000":[70],"paired":[71],"examples":[72],"buggy":[74],"and":[75,82,100,126,134,144,158,190,208],"fixed":[76],"code":[77,96,218],"12":[79],"languages":[81],"13":[83],"categories.":[85],"Subsequently,":[86],"these":[87],"samples":[88],"underwent":[89],"cross-model":[90],"evaluation":[91,103],"against":[92],"five":[93],"criteria:":[94],"correctness,":[95],"quality,":[97],"security,":[98],"performance,":[99],"completeness.":[101],"Experimental":[102],"on":[104],"VulRepair":[106],"test":[107],"set":[108],"dataset":[109,122],"showed":[110],"statistically":[111],"significant":[112],"improvements":[113],"in":[114,142,146,186,203],"Perfect":[115],"Prediction":[116],"rates,":[117],"with":[118],"quality-filtered":[120],"achieving":[123],"17.18%":[124],"(Top@1)":[125],"23.00%":[127],"(Top@5)":[128],"compared":[129],"baseline\u2019s":[132],"11.68%":[133],"18.88%":[135],"respectively,":[136],"representing":[137],"47%":[139],"relative":[140],"improvement":[141],"Top@1":[143],"22%":[145],"Top@5.":[147],"was":[150],"validated":[151],"statistical":[154],"testing,":[155],"including":[156],"ANOVA":[157],"post-hoc":[159],"Tukey\u2019s":[160],"Honest":[161],"Significant":[162],"Difference":[163],"analysis.":[164],"Furthermore,":[165],"best-performing":[167],"configurations":[168],"surpassed":[169],"existing":[170],"despite":[172],"using":[173],"less":[175],"computationally":[176],"intensive":[177],"decoding":[178],"strategy.":[179],"research":[181],"establishes":[182],"self-bootstrapping":[184],"paradigm":[185],"which":[187],"evaluate":[191],"their":[192],"own":[193],"data,":[195],"suggesting":[196],"promising":[197],"directions":[198],"addressing":[200],"scarcity":[202],"similar":[204],"software":[205],"engineering":[206],"tasks":[207],"advancing":[209],"development":[211],"robust,":[213],"adaptable":[214],"tools":[215],"automated":[217],"maintenance":[219]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}