{"id":"https://openalex.org/W7225756169","doi":"https://doi.org/10.5281/zenodo.24115801","title":"Ranking Commits by Size Beats Tabular Foundation Models Given Twenty Labels in Just-in-Time Defect Prediction","display_name":"Ranking Commits by Size Beats Tabular Foundation Models Given Twenty Labels in Just-in-Time Defect Prediction","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225756169","doi":"https://doi.org/10.5281/zenodo.24115801"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24115801","doi":"https://doi.org/10.5281/zenodo.24115801","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24115801","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24115801","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051159291","display_name":"Felipe Provezano Coutinho","orcid":"https://orcid.org/0000-0001-7206-5856","observed_orcids":["https://orcid.org/0000-0001-7206-5856"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Coutinho, Felipe Provezano","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0000-0001-7206-5856","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051159291"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6665999889373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5692999958992004},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45350000262260437},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3869999945163727},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3361999988555908},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26420000195503235},{"id":"https://openalex.org/C143095724","wikidata":"https://www.wikidata.org/wiki/Q515895","display_name":"Odds","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24115801","doi":"https://doi.org/10.5281/zenodo.24115801","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24115801","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24115802","doi":"https://doi.org/10.5281/zenodo.24115802","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24115802","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24115801","doi":"https://doi.org/10.5281/zenodo.24115801","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24115801","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Just-in-time":[0],"defect":[1],"prediction":[2],"ranks":[3],"new":[4,15,197],"commits":[5,20,43,183],"by":[6,44,61,74,129],"their":[7],"risk":[8],"of":[9,124,136,145,184,225],"introducing":[10],"a":[11,14,39,98,130,134],"defect,":[12],"but":[13,237],"project":[16],"has":[17],"few":[18,31,152],"labelled":[19],"to":[21,76,120,253,257],"learn":[22],"from.":[23],"Tabular":[24],"foundation":[25,108,232],"models":[26,109,233],"promise":[27],"good":[28],"predictions":[29],"from":[30,56,203],"labels,":[32,73],"so":[33],"we":[34,180,210],"asked":[35],"whether":[36],"they":[37,150],"beat":[38,63,94,230],"label-free":[40],"baseline:":[41],"ranking":[42,60,209],"size,":[45],"usually":[46],"lines":[47,176],"added.":[48],"They":[49],"do":[50],"not.":[51],"On":[52,90],"305":[53],"open-source":[54],"projects":[55,198],"seven":[57],"change-level":[58],"corpora,":[59],"size":[62,137,172,206,226],"TabPFN":[64,66],"v2,":[65],"v3.5":[67],"and":[68,97,114,148,169,229,245],"TabICL,":[69],"each":[70],"given":[71],"20":[72,105],"0.07":[75],"0.12":[77],"on":[78,102,220,227],"average":[79,221],"per":[80],"corpus":[81],"in":[82,174],"the":[83,86,103,125,139,143,146,182,190,193,208,231,254],"area":[84],"under":[85],"ROC":[87],"curve":[88],"(AUC).":[89],"JIT-Defects4J":[91,228],"it":[92],"also":[93],"JITLine,":[95],"DeepJIT":[96],"CodeBERT-based":[99],"model":[100,135],"trained":[101],"same":[104],"labels.":[106,247],"The":[107,158],"needed":[110],"at":[111,234,243],"least":[112],"100,":[113],"often":[115],"more":[116],"than":[117],"200,":[118],"labels":[119,140,202,213],"catch":[121],"up.":[122],"Part":[123],"gap":[126],"is":[127,155,207],"explained":[128],"short":[131],"proof:":[132],"for":[133],"alone,":[138],"only":[141,166],"set":[142],"direction":[144,154],"ranking,":[147],"when":[149],"are":[151],"that":[153,199],"sometimes":[156],"wrong.":[157],"label":[159],"generator":[160],"behind":[161],"several":[162],"public":[163],"benchmarks":[164],"blames":[165],"source-code":[167],"files,":[168],"this":[170],"makes":[171],"counted":[173],"code":[175],"look":[177],"stronger.":[178],"When":[179],"relabelled":[181],"28":[185],"newly":[186],"mined":[187],"repositories":[188],"without":[189],"file":[191],"filter,":[192],"gain":[194],"disappeared.":[195],"For":[196],"cannot":[200],"borrow":[201],"similar":[204],"ones,":[205],"recommend.":[211],"Once":[212],"arrive,":[214],"our":[215],"size-anchored":[216],"logistic":[217],"regression":[218],"stayed":[219],"within":[222],"0.013":[223],"AUC":[224],"every":[235],"budget,":[236],"missed":[238],"its":[239],"0.01":[240],"non-inferiority":[241],"margin":[242],"100":[244],"200":[246],"Preprint,":[248],"not":[249],"peer":[250],"reviewed.":[251],"Identical":[252],"version":[255],"submitted":[256],"Empirical":[258],"Software":[259],"Engineering.":[260]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}