{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.310369,0.003648149,0.005264025,0.00429808,0.0009884519,0.00484492,0.002799866,0.00452807,0.006974726],"category_scores_gemma":[0.4720911,0.0009246177,0.004459681,0.004968818,0.003439872,0.003976024,0.003188673,0.002428541,0.001333837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003035358,"about_ca_system_score_gemma":0.004557362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004586293,"about_ca_topic_score_gemma":0.000514831,"domain_scores_codex":[0.5529659,0.3981407,0.02328388,0.00717527,0.01693604,0.0014982],"domain_scores_gemma":[0.3577669,0.5048234,0.07327172,0.03025967,0.02896682,0.004911463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.2413366,0.01265389,0.09343753,0.02105523,0.02985867,0.001002244,0.001329278,0.04249435,0.003703471,0.01525573,0.01847988,0.5193931],"study_design_scores_gemma":[0.1009516,0.5333842,0.08182196,0.005910903,0.03762829,0.002128775,0.001384842,0.09975086,0.01184562,0.04619052,0.07833378,0.0006686487],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4532133,0.07714886,0.263118,0.01276124,0.005669641,0.135684,0.01156455,0.001025586,0.03981476],"genre_scores_gemma":[0.7895911,0.007723756,0.1202596,0.002602408,0.001852725,0.07192626,0.003779951,0.0001458081,0.002118433],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.310369,"threshold_uncertainty_score":0.8504378,"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."}}