{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007038782,0.001027978,0.001135453,0.001184121,0.0007282565,0.0015757,0.00216368,0.002101748,0.001239086],"category_scores_gemma":[0.0139686,0.0002731971,0.0006577411,0.0006630992,0.001360794,0.00313126,0.001261673,0.002631018,0.0007227637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000658384,"about_ca_system_score_gemma":0.0009179863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001813961,"about_ca_topic_score_gemma":0.002991079,"domain_scores_codex":[0.9967808,0.001775324,0.0001391372,0.0005401541,0.000536724,0.0002278242],"domain_scores_gemma":[0.9841814,0.01104214,0.0009096235,0.001927752,0.001531534,0.0004076107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002139321,0.001948812,0.01778712,0.0004455256,0.0003006934,0.0001824086,0.0005485782,0.2549486,0.007498757,0.01072403,0.01428374,0.6891923],"study_design_scores_gemma":[0.0000340916,0.0001484643,0.001029425,0.00002636554,0.00002099908,0.00005922608,0.00007128438,0.9852803,0.004484927,0.007978627,0.0008510134,0.00001521826],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2806915,0.002710904,0.7037361,0.002700585,0.0003559767,0.0002879229,0.000656983,0.003825349,0.005034718],"genre_scores_gemma":[0.8834383,0.0002952062,0.1117646,0.0005525431,0.0002666953,0.0001514126,0.0009277752,0.0001212347,0.002482292],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007038782,"threshold_uncertainty_score":0.03722513,"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."}}