{"id":"W2162836425","doi":"10.1109/issre.1991.145373","title":"Metrics evaluation of software reliability growth models","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Metric (unit); Reliability (semiconductor); Computer science; Software quality; Software metric; Field (mathematics); Software; Reliability engineering; Predictive validity; Term (time); Data mining; Machine learning; Software development; Statistics; Mathematics; Engineering; 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":[0.003442721,0.00009380715,0.000197953,0.0002785241,0.00007141442,0.00005826822,0.0008386239,0.00007331157,0.0003641761],"category_scores_gemma":[0.003670801,0.00007682149,0.0001438373,0.002175182,0.00006956923,0.0007228843,0.0002349755,0.0001223915,0.00005569115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001114019,"about_ca_system_score_gemma":0.00006530095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001321717,"about_ca_topic_score_gemma":0.000004582318,"domain_scores_codex":[0.996909,0.0003328728,0.0003378431,0.0004165424,0.001781082,0.000222702],"domain_scores_gemma":[0.9965789,0.0005867646,0.000073186,0.0008958266,0.001770827,0.00009449478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007281654,0.001616351,0.03310097,0.0002175984,0.000122724,0.000002581656,0.001332919,0.07156928,0.0001050662,0.09107009,0.006622455,0.7942327],"study_design_scores_gemma":[0.0001772545,0.00003465119,0.0008174705,0.000004272718,0.00001667024,7.249469e-7,0.000008105781,0.9027031,0.000856288,0.09525431,0.0000466633,0.00008049263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02657022,0.0003721917,0.967516,0.0006630801,0.00005054812,0.0001957019,0.000001646024,0.0001551863,0.004475419],"genre_scores_gemma":[0.9143364,0.00008036878,0.08533861,0.00004464103,0.00001149896,0.00001550767,0.000001133327,0.00000383422,0.0001680272],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8877662,"threshold_uncertainty_score":0.4394557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1057111148427386,"score_gpt":0.3088034808344209,"score_spread":0.2030923659916823,"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."}}