{"id":"W2004511978","doi":"10.1007/s11416-009-0122-8","title":"Unknown malcode detection and the imbalance problem","year":2009,"lang":"en","type":"article","venue":"Journal in Computer Virology","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Code (set theory); Set (abstract data type); Malware; Binary classification; Feature selection; Categorization; Class (philosophy); Signature (topology); Selection (genetic algorithm); Data mining; Artificial intelligence; Information retrieval; Computer security; Support vector machine; 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":[0.0006805856,0.0001247787,0.0002076503,0.0001816252,0.0001614058,0.0001371448,0.0005242242,0.00009006191,0.000001695284],"category_scores_gemma":[0.00001737286,0.00008660412,0.00004943683,0.000266215,0.00009719209,0.0004433874,0.0001456466,0.0005770389,0.00000379252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005477361,"about_ca_system_score_gemma":0.00001677596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004148088,"about_ca_topic_score_gemma":0.00001606674,"domain_scores_codex":[0.9987928,0.000246584,0.0003219731,0.0002529143,0.0001224985,0.0002632213],"domain_scores_gemma":[0.9993088,0.0001444575,0.0001806255,0.0002532569,0.00005670841,0.00005612729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001294637,0.00005691648,0.0001381915,0.00000393186,0.00001113801,0.000135257,0.0003909849,0.002488574,0.002246275,0.02843552,0.0001914058,0.9657723],"study_design_scores_gemma":[0.002742362,0.001167654,0.02511329,0.00003088222,0.000006284889,0.009451324,0.000003397327,0.39751,0.003120231,0.5501866,0.01037634,0.000291613],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01867794,0.0002212194,0.974288,0.006000339,0.0003579766,0.0001538628,7.768521e-8,0.000144109,0.0001564023],"genre_scores_gemma":[0.7981148,0.0001632514,0.1986246,0.002833073,0.000227109,0.000009055686,4.744786e-8,0.000004799628,0.00002329299],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9654807,"threshold_uncertainty_score":0.3531613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005380248098878364,"score_gpt":0.2360256257957565,"score_spread":0.2306453776968782,"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."}}