{"id":"W4406012448","doi":"10.1109/access.2024.3525069","title":"Leveraging an Enhanced CodeBERT-Based Model for Multiclass Software Defect Prediction via Defect Classification","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Software Engineering Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Università degli Studi di Firenze","keywords":"Computer science; Machine learning; Software bug; Artificial intelligence; Software reliability testing; Software development; Software; Software quality; Software construction; Software development process; Context (archaeology); Software engineering; Data mining; Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005080989,0.0002005832,0.0001898719,0.0003505244,0.0002416074,0.0004265223,0.001460468,0.0001284054,0.000001249747],"category_scores_gemma":[0.0006572546,0.000210295,0.0001501446,0.0007106798,0.00003350082,0.001186703,0.0001104285,0.0002048059,0.000005207096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002665387,"about_ca_system_score_gemma":0.0002658705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004019411,"about_ca_topic_score_gemma":0.00003790304,"domain_scores_codex":[0.9981453,0.00007661853,0.0002759475,0.0007178885,0.0003464214,0.0004378002],"domain_scores_gemma":[0.9974675,0.001128371,0.0000728188,0.0008986425,0.0003212713,0.0001113603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006499195,0.000170637,0.01092514,0.0002485198,0.00006487542,0.000001744668,0.0003074016,0.8955445,0.02490821,0.0002563701,0.0008979153,0.0666097],"study_design_scores_gemma":[0.0007046035,0.00004196114,0.01206789,0.00005859517,0.00001768524,6.476977e-7,0.000002667716,0.9415464,0.04443442,0.0009031477,0.00004415004,0.0001777958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1200416,0.00003681297,0.8775566,0.0001286029,0.0006547438,0.0006170902,0.0000104874,0.0009341694,0.0000199148],"genre_scores_gemma":[0.9478683,0.000002142473,0.05120058,0.0002172719,0.00005525145,0.0005062374,0.00002478718,0.00002574552,0.00009967132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8278267,"threshold_uncertainty_score":0.857558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05998664035314283,"score_gpt":0.345326418826465,"score_spread":0.2853397784733222,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}