{"id":"W4226366790","doi":"10.1109/tdsc.2022.3170011","title":"Classifier Calibration: With Application to Threat Scores in Cybersecurity","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Classifier (UML); Computer science; Logistic regression; Artificial intelligence; Calibration; Machine learning; Binary number; Binary classification; Pattern recognition (psychology); Data mining; Statistics; Support vector machine; Mathematics","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":[0.0001961255,0.0001463912,0.0001504264,0.0002702795,0.0005581087,0.00008395009,0.0002865726,0.00004066504,0.00001465838],"category_scores_gemma":[0.000001793824,0.0001477136,0.00002856397,0.0008454495,0.00002232124,0.0003556841,0.00001776039,0.0003909527,0.000002434641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001176115,"about_ca_system_score_gemma":0.00004612896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001308009,"about_ca_topic_score_gemma":0.000356924,"domain_scores_codex":[0.9987327,0.00007866164,0.0002031748,0.0004989975,0.0002599327,0.0002265149],"domain_scores_gemma":[0.9994089,0.00008416916,0.00006341021,0.0003224307,0.00003828021,0.00008283119],"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":[0.00015744,0.0003222873,0.0004064925,0.00003805637,0.0000262293,0.00006694839,0.003530436,0.723887,0.002286702,0.008826098,0.0001419529,0.2603104],"study_design_scores_gemma":[0.0008629349,0.0008795671,0.0004135315,0.00005554523,0.00001174058,0.0002731201,0.000479187,0.9391294,0.05065914,0.00367668,0.002946269,0.0006129516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03713285,0.00002701562,0.96138,0.0004196771,0.000134296,0.0004032276,0.000006197854,0.0003522796,0.0001444314],"genre_scores_gemma":[0.9628428,0.000004603717,0.03657876,0.0003663862,0.00001763376,0.0001311769,0.000001442863,0.00001348637,0.00004371691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.92571,"threshold_uncertainty_score":0.6023585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008903308616086904,"score_gpt":0.2356450145513168,"score_spread":0.2267417059352299,"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."}}