{"id":"https://openalex.org/W4412390717","doi":"https://doi.org/10.3390/software4030017","title":"Investigating Reproducibility Challenges in LLM Bugfixing on the HumanEvalFix Benchmark","display_name":"Investigating Reproducibility Challenges in LLM Bugfixing on the HumanEvalFix Benchmark","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412390717","doi":"https://doi.org/10.3390/software4030017"},"language":"en","primary_location":{"id":"doi:10.3390/software4030017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/software4030017","pdf_url":"https://www.mdpi.com/2674-113X/4/3/17/pdf?version=1752485643","source":{"id":"https://openalex.org/S4210183365","display_name":"Software","issn_l":"2674-113X","issn":["2674-113X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mdpi.com/2674-113X/4/3/17/pdf?version=1752485643","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065193980","display_name":"Bal\u00e1zs Szalontai","orcid":"https://orcid.org/0000-0002-0458-2576"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Bal\u00e1zs Szalontai","raw_affiliation_strings":["Department of Software Technology, Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Software Technology, Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117754445","display_name":"Bal\u00e1zs M\u00e1rton","orcid":null},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Bal\u00e1zs M\u00e1rton","raw_affiliation_strings":["Department of Software Technology, Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Software Technology, Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028728217","display_name":"Bal\u00e1zs Pint\u00e9r","orcid":"https://orcid.org/0000-0003-3431-0667"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Bal\u00e1zs Pint\u00e9r","raw_affiliation_strings":["Department of Software Technology, Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Software Technology, Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066115803","display_name":"Tibor Gregorics","orcid":"https://orcid.org/0000-0002-9503-9623"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tibor Gregorics","raw_affiliation_strings":["Department of Software Technology, Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Software Technology, Faculty of Informatics, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028728217"],"corresponding_institution_ids":["https://openalex.org/I106118109"],"apc_list":null,"apc_paid":null,"fwci":5.2114,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94821803,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"4","issue":"3","first_page":"17","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9922999739646912,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9887999892234802,"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/reproducibility","display_name":"Reproducibility","score":0.8453859090805054},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6483989357948303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3889754116535187},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1793726682662964},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17182296514511108},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15030300617218018},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.14605405926704407}],"concepts":[{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.8453859090805054},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6483989357948303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3889754116535187},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1793726682662964},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17182296514511108},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15030300617218018},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.14605405926704407}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/software4030017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/software4030017","pdf_url":"https://www.mdpi.com/2674-113X/4/3/17/pdf?version=1752485643","source":{"id":"https://openalex.org/S4210183365","display_name":"Software","issn_l":"2674-113X","issn":["2674-113X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:09c4adbc79154d78b902af56cd458be1","is_oa":true,"landing_page_url":"https://doaj.org/article/09c4adbc79154d78b902af56cd458be1","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Software, Vol 4, Iss 3, p 17 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/software4030017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/software4030017","pdf_url":"https://www.mdpi.com/2674-113X/4/3/17/pdf?version=1752485643","source":{"id":"https://openalex.org/S4210183365","display_name":"Software","issn_l":"2674-113X","issn":["2674-113X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412390717.pdf","grobid_xml":"https://content.openalex.org/works/W4412390717.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1502957213","https://openalex.org/W2762550985","https://openalex.org/W3105943882","https://openalex.org/W4385562549","https://openalex.org/W4385849242","https://openalex.org/W4390136244","https://openalex.org/W4399114781","https://openalex.org/W4402672073","https://openalex.org/W4404782882","https://openalex.org/W6888016194"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2413717610","https://openalex.org/W1973270181","https://openalex.org/W2417696084","https://openalex.org/W2368782778","https://openalex.org/W2087830269","https://openalex.org/W3106281778","https://openalex.org/W4324138256"],"abstract_inverted_index":{"Benchmark":[0],"results":[1,20,37,72,107],"for":[2,75],"large":[3],"language":[4],"models":[5,52,77,97],"often":[6],"show":[7],"inconsistencies":[8],"across":[9,78],"different":[10,63],"studies.":[11],"This":[12],"paper":[13],"investigates":[14],"the":[15,27,32,35,39,54,93,135],"challenges":[16],"of":[17,34,47,69,80,130],"reproducing":[18],"these":[19,76],"in":[21,38,53,62],"automatic":[22],"bugfixing":[23],"using":[24,124],"LLMs,":[25],"on":[26,152],"HumanEvalFix":[28],"benchmark.":[29],"To":[30],"determine":[31],"cause":[33],"differing":[36],"literature,":[40],"we":[41,82],"attempted":[42],"to":[43],"reproduce":[44],"a":[45],"subset":[46],"them":[48],"by":[49],"evaluating":[50],"12":[51],"DeepSeekCoder,":[55],"CodeGemma,":[56],"CodeLlama,":[57],"and":[58,65,146],"WizardCoder":[59],"model":[60],"families,":[61],"sizes":[64],"tunings.":[66],"A":[67],"total":[68],"35":[70],"unique":[71],"were":[73],"reported":[74],"studies,":[79],"which":[81],"successfully":[83],"reproduced":[84],"12.":[85],"We":[86,142],"identified":[87],"several":[88],"relevant":[89],"factors":[90],"that":[91,144],"influenced":[92],"results.":[94,154],"The":[95],"base":[96],"can":[98,117,133],"be":[99],"confused":[100],"with":[101,138],"their":[102,106],"instruction-tuned":[103],"variants,":[104],"making":[105],"better":[108],"than":[109],"expected.":[110],"Incorrect":[111],"prompt":[112],"templates":[113],"or":[114],"generation":[115],"length":[116],"decrease":[118],"benchmark":[119,153],"performance,":[120],"as":[121,123],"well":[122],"4-bit":[125],"quantization.":[126],"Using":[127],"sampling":[128],"instead":[129],"greedy":[131],"decoding":[132],"increase":[134],"variance,":[136],"especially":[137],"higher":[139],"temperature":[140],"values.":[141],"found":[143],"precision":[145],"8-bit":[147],"quantization":[148],"have":[149],"less":[150],"influence":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}
