{"id":"W3127051039","doi":"10.24433/co.4889911.v1","title":"Classifier Calibration: with implications to threat scores in cybersecurity","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"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; Mathematics; Support vector machine; Arithmetic","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009981731,0.0002520766,0.000265021,0.0003680906,0.0001131977,0.0001593748,0.001121683,0.000211328,0.00001867945],"category_scores_gemma":[0.00002742741,0.0002840403,0.00008387196,0.001369484,0.00007211509,0.0007023802,0.001427809,0.0005032439,0.000008925891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003413467,"about_ca_system_score_gemma":0.0002831955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003225478,"about_ca_topic_score_gemma":0.002164751,"domain_scores_codex":[0.9981903,0.00009367871,0.0001799332,0.001186784,0.00008279992,0.0002665242],"domain_scores_gemma":[0.9979602,0.00006343659,0.0001368801,0.001473997,0.0002065262,0.00015894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009062423,0.0003640658,0.04536113,0.0001211502,0.00009916838,0.000942954,0.001612318,0.3735611,0.0004521516,0.5724136,0.0005917354,0.00438994],"study_design_scores_gemma":[0.002044568,0.0006531884,0.1600838,0.001256072,0.0001408737,0.0001281236,0.0009587143,0.3718342,0.02327195,0.4329482,0.00237228,0.004308088],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1270734,0.0000218476,0.8703262,0.0004626751,0.0001174672,0.0004133387,0.000008961879,0.0004755851,0.001100468],"genre_scores_gemma":[0.9675264,0.00004970798,0.03182191,0.0002289739,0.00002794646,0.00001406457,0.00001399528,0.00001611221,0.0003008246],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.840453,"threshold_uncertainty_score":0.9999612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06451919731018332,"score_gpt":0.2073099659456039,"score_spread":0.1427907686354206,"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."}}