{"id":"W7056365920","doi":"","title":"Evaluating Predictions of Faulty Software Using Thresholds","year":2000,"lang":"en","type":"other","venue":"NPARC","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Software; Measure (data warehouse); Reliability (semiconductor); Work (physics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003966667,0.0008498969,0.0004541677,0.001824264,0.0003193193,0.001090052,0.001102369,0.0008642479,0.003279823],"category_scores_gemma":[0.0350845,0.0003024323,0.000555866,0.001118771,0.0004237561,0.001619491,0.0004929798,0.0006694742,0.001025074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009370204,"about_ca_system_score_gemma":0.001516364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01288479,"about_ca_topic_score_gemma":0.01262406,"domain_scores_codex":[0.9948941,0.0008402147,0.0003360961,0.000821613,0.002857107,0.0002508911],"domain_scores_gemma":[0.9640614,0.02538151,0.001557574,0.003636669,0.004729389,0.0006333956],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002754918,0.0009917553,0.1325011,0.0004227717,0.0004576654,0.0004809065,0.0002156628,0.400536,0.01216912,0.003877874,0.05477246,0.3908198],"study_design_scores_gemma":[0.00006661243,0.0002874682,0.009586412,0.00002737455,0.00008124289,0.00007899001,0.00005869715,0.9722149,0.01206876,0.003723525,0.001788927,0.00001704656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8621863,0.000845256,0.08994763,0.001250431,0.0006057904,0.0001741529,0.007837039,0.01989725,0.01725611],"genre_scores_gemma":[0.951466,0.0001367141,0.03642187,0.0001556138,0.00006802427,0.00005091639,0.007674558,0.0006050236,0.003421271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9960333,"threshold_uncertainty_score":0.02561957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04834272682828186,"score_gpt":0.3523579272567875,"score_spread":0.3040152004285057,"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."}}