{"id":"W4415481257","doi":"10.1109/tse.2025.3624631","title":"Contrasting the Hyperparameter Tuning Impact Across Software Defect Prediction Scenarios","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperparameter; Software; Hyperparameter optimization; Software quality assurance; Software bug; Scope (computer science); Quality (philosophy)","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.001835655,0.001290381,0.0009526308,0.0009614452,0.001882053,0.001558907,0.00227921,0.0006678204,0.00009158876],"category_scores_gemma":[0.002861162,0.001156919,0.001290188,0.00382156,0.0002507062,0.001281074,0.00006535887,0.003664474,0.0001280315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00150753,"about_ca_system_score_gemma":0.0006595899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000161091,"about_ca_topic_score_gemma":0.00001379636,"domain_scores_codex":[0.9929148,0.0002573983,0.001251284,0.001719391,0.001344892,0.002512223],"domain_scores_gemma":[0.9873373,0.009110777,0.0001919223,0.002331874,0.0005174103,0.0005107491],"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":[0.00007795027,0.0001888709,0.004432985,0.0003358506,0.0009681905,0.00005157444,0.001485277,0.8988761,0.0007461262,0.0000132636,0.0002000397,0.09262373],"study_design_scores_gemma":[0.001995175,0.0005580035,0.02422887,0.002508797,0.0003355517,0.0002114985,0.0001217263,0.9607837,0.00699668,0.00001877913,0.0008640563,0.001377179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1291116,0.001283123,0.8580884,0.0001175483,0.007100849,0.001175608,0.0002980935,0.002818411,0.000006337525],"genre_scores_gemma":[0.9683149,0.000121904,0.02994527,0.0001566349,0.0002763046,0.0003876676,0.000007320635,0.0001971857,0.0005927699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8392033,"threshold_uncertainty_score":0.9999848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01596740700747058,"score_gpt":0.2777652525143255,"score_spread":0.2617978455068549,"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."}}