{"id":"W1818536891","doi":"","title":"Evaluating security products with clinical trials","year":2009,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Carleton University","funders":"","keywords":"Computer science; Software deployment; Overhead (engineering); Computer security; Quality (philosophy); Field (mathematics); Security testing; Risk analysis (engineering); Security information and event management; Cloud computing security; Software engineering; Business","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":[0.01148155,0.0004736512,0.0009427399,0.0004514778,0.0003316831,0.0003763351,0.001507337,0.0003488544,0.00001106873],"category_scores_gemma":[0.005094715,0.0004016685,0.0002624546,0.001422548,0.0001151739,0.001276235,0.0002868517,0.0009297594,0.00001724745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003347877,"about_ca_system_score_gemma":0.0005056059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002976368,"about_ca_topic_score_gemma":0.0001373524,"domain_scores_codex":[0.9941658,0.001475017,0.001486374,0.001202737,0.0007975632,0.000872465],"domain_scores_gemma":[0.9952722,0.0006958432,0.0009212151,0.00219418,0.0005192496,0.0003972851],"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":[0.0003517659,0.0007400767,0.00259348,0.00003600193,0.00007759481,0.0001511981,0.0003619655,0.001080381,0.01581138,0.09218183,0.003838776,0.8827755],"study_design_scores_gemma":[0.00329605,0.007577197,0.03278743,0.000314364,0.0001421697,0.001054076,0.00007661399,0.4191592,0.3345212,0.1881334,0.01045247,0.002485857],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02637035,0.000474344,0.958044,0.008326079,0.0001962138,0.00169446,0.000007139185,0.004404303,0.0004831362],"genre_scores_gemma":[0.4489491,0.00008295783,0.5476661,0.00261443,0.0002367219,0.0002557389,0.000003973497,0.00002924981,0.0001617072],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8802897,"threshold_uncertainty_score":0.9998435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06640636235969086,"score_gpt":0.3791811216732849,"score_spread":0.3127747593135941,"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."}}