{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01324913,0.002026124,0.0008276181,0.001876737,0.0005737123,0.001791209,0.001334199,0.00192776,0.0004564173],"category_scores_gemma":[0.06672763,0.0005084647,0.0009259802,0.001371879,0.00103117,0.002949867,0.001379321,0.002407159,0.0002432753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009889441,"about_ca_system_score_gemma":0.0009017509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003619872,"about_ca_topic_score_gemma":0.00257676,"domain_scores_codex":[0.9899809,0.004839719,0.0009751713,0.002125164,0.001493588,0.0005854882],"domain_scores_gemma":[0.9223199,0.06114214,0.003734609,0.007933238,0.003996712,0.0008733476],"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":[0.002153448,0.001332764,0.07462434,0.0004514984,0.0007635978,0.0002615709,0.000290853,0.7597412,0.01345323,0.001795329,0.003990249,0.1411419],"study_design_scores_gemma":[0.0002486484,0.001850792,0.03589935,0.0001085335,0.000275013,0.0002459851,0.0003737556,0.9327003,0.02307327,0.003491584,0.001625434,0.0001072861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9494808,0.002195869,0.04234708,0.0007723498,0.0001587193,0.0002274271,0.0006589225,0.001787492,0.002371376],"genre_scores_gemma":[0.978438,0.0002957149,0.01938034,0.0001830628,0.00004300483,0.0001160037,0.001157713,0.0001133431,0.0002727956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01324913,"threshold_uncertainty_score":0.07006896,"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."}}