{"id":"W7126460059","doi":"10.21428/594757db.0c81653b","title":"To Label or to Pseudo Label? Active Learning vsSemi-Supervised Learning for Windows Malware Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Malware; Active learning (machine learning); Software deployment; Focus (optics); Task (project management); Random forest; Deep learning","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":[0.0003579014,0.0002737905,0.0002468879,0.0004589603,0.0003552637,0.000368354,0.0005744832,0.0001353971,0.00009536318],"category_scores_gemma":[0.0005925823,0.0002396327,0.00007456498,0.001394528,0.00001583212,0.001095377,0.0004101488,0.0004743323,0.0001879513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002608065,"about_ca_system_score_gemma":0.0001053318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002375201,"about_ca_topic_score_gemma":0.00002565041,"domain_scores_codex":[0.9978281,0.00008269273,0.000319423,0.000929762,0.0003344167,0.0005055895],"domain_scores_gemma":[0.9986953,0.0003769722,0.00004930238,0.0003731957,0.000260772,0.0002444786],"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":[0.0002594389,0.00006917042,0.000107431,0.0001453247,0.00006449097,0.00003308363,0.00327936,0.008857054,0.06722932,0.004386362,0.007345984,0.908223],"study_design_scores_gemma":[0.0008062286,0.003925565,0.0002217434,0.0003847154,0.00002700598,0.00007490301,0.0007239564,0.555084,0.2087443,0.00151979,0.2277017,0.0007860865],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008668429,0.00002881309,0.9810991,0.001622498,0.000552191,0.001226787,0.00001095819,0.005703718,0.001087499],"genre_scores_gemma":[0.2704703,0.00002264182,0.7011234,0.001107917,0.000321344,0.001250477,0.00001424885,0.00009614942,0.02559359],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9074369,"threshold_uncertainty_score":0.977194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0269062141814643,"score_gpt":0.306924887772049,"score_spread":0.2800186735905847,"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."}}