{"id":"W4404838900","doi":"10.1142/s0218539324500578","title":"Machine Learning-Based Reliability Evaluation for Software Defect Prediction and Model Validation Assessment","year":2024,"lang":"en","type":"article","venue":"International Journal of Reliability Quality and Safety Engineering","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reliability engineering; Reliability (semiconductor); Computer science; Software quality; Verification and validation; Model validation; Software; Machine learning; Predictive modelling; Artificial intelligence; Engineering; Software development; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.01226764,0.0001680994,0.0002905924,0.0002966376,0.0001160553,0.0003489233,0.0003671598,0.0001252965,0.000007904345],"category_scores_gemma":[0.005769119,0.0001495851,0.0002732782,0.0002278463,0.00005947911,0.0008940563,0.0001185811,0.0005232318,4.648113e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004850027,"about_ca_system_score_gemma":0.0003938328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000275261,"about_ca_topic_score_gemma":0.000002631266,"domain_scores_codex":[0.9969824,0.0002968403,0.0008909535,0.0004453154,0.001205064,0.0001794058],"domain_scores_gemma":[0.9953344,0.002656559,0.0001795796,0.0002476063,0.001451364,0.0001304283],"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":[0.00008724141,0.00008206582,0.00833646,0.0003809732,0.0001211299,0.000001674358,0.0001921467,0.9513726,0.0002081945,0.00376585,0.0000114223,0.0354402],"study_design_scores_gemma":[0.0006015178,0.0001439049,0.01027786,0.0001637631,0.00005706766,0.00001457466,0.00001106079,0.974974,0.0001818834,0.01255048,0.0008945289,0.0001293564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08103604,0.0007065003,0.914269,0.003093771,0.0004494777,0.0002753955,0.0000495524,0.0001110274,0.000009196136],"genre_scores_gemma":[0.9115717,0.0003427696,0.08785224,0.00003361882,0.0001073843,0.00002515471,0.00004302743,0.00001112089,0.00001299019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8305357,"threshold_uncertainty_score":0.690659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03188100837465722,"score_gpt":0.3559982628762541,"score_spread":0.3241172545015968,"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."}}