{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001684984,0.001098853,0.001000055,0.002276528,0.000513208,0.001246134,0.002258607,0.001586446,0.001161028],"category_scores_gemma":[0.004966124,0.0004566394,0.0010037,0.001148142,0.0005816962,0.001330982,0.0009214069,0.001748216,0.000804576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001246756,"about_ca_system_score_gemma":0.001370789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01727,"about_ca_topic_score_gemma":0.01742265,"domain_scores_codex":[0.9992944,0.0001477239,0.00004314099,0.0002580725,0.0001791695,0.00007751002],"domain_scores_gemma":[0.996806,0.001746264,0.0003514196,0.0002690947,0.0007213205,0.0001059953],"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":[0.0002442049,0.0003704351,0.01751444,0.00006410945,0.0001181522,0.0001664808,0.0001176778,0.7837945,0.003404623,0.002413951,0.002998864,0.1887926],"study_design_scores_gemma":[0.000002297801,0.00001342386,0.0003739884,0.000003417648,0.000005270579,0.00001327947,0.000002619642,0.9984578,0.0003545487,0.0006497193,0.0001201578,0.00000342988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1343741,0.0004651514,0.856349,0.0006681312,0.00007613372,0.0001654564,0.0005549111,0.005552502,0.001794653],"genre_scores_gemma":[0.8252781,0.0002167494,0.1672742,0.0003422255,0.00008469592,0.0002804345,0.001611114,0.0002404103,0.004672055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01727,"threshold_uncertainty_score":0.03433895,"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."}}