{"id":"W3093369224","doi":"10.22215/etd/2017-11856","title":"Statistical Evaluation of Malware Classification Algorithms","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Malware; Univariate; Computer science; Data mining; Data set; Variance (accounting); Malware analysis; Set (abstract data type); Multivariate analysis of variance; Machine learning; Algorithm; Artificial intelligence; Statistical classification; Feature (linguistics); Multivariate statistics; Operating system","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":[0.0007953912,0.0002109197,0.0002831074,0.0002413167,0.0001394156,0.0001061817,0.0009995811,0.0002851665,0.0002023838],"category_scores_gemma":[0.0005188124,0.0002101147,0.00007122047,0.0001259027,0.00003948407,0.0005360615,0.00004118594,0.0002249111,0.00003287368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001502408,"about_ca_system_score_gemma":0.0003760991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004615312,"about_ca_topic_score_gemma":0.00008722367,"domain_scores_codex":[0.9976277,0.0001184686,0.0004374027,0.0005443617,0.001105242,0.0001668231],"domain_scores_gemma":[0.9964805,0.00008010148,0.0007434905,0.001218266,0.001419042,0.00005864436],"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":[0.000008403669,0.00003726792,0.00000974489,0.00006339285,0.00001714914,0.000001078457,0.0001114077,0.000007342665,0.001302376,0.04332077,0.0009828658,0.9541382],"study_design_scores_gemma":[0.001068731,0.000467698,0.05812845,0.0004325864,0.000321969,0.0000188265,0.0005039044,0.3559738,0.3265479,0.2471134,0.007961406,0.001461282],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003553554,0.00009323838,0.9430406,0.0000365651,0.0008312805,0.0005793555,0.00002398711,0.0003636243,0.05467598],"genre_scores_gemma":[0.4418906,0.00008263297,0.5422109,0.00002292937,0.0001326813,0.0005176591,0.001507625,0.00005489004,0.01358006],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9526769,"threshold_uncertainty_score":0.8568227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07140947260885143,"score_gpt":0.4024733857216201,"score_spread":0.3310639131127687,"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."}}