{"id":"W2018558592","doi":"10.1016/j.comnet.2008.11.012","title":"Targeting spam control on middleboxes: Spam detection based on layer-3 e-mail content classification","year":2008,"lang":"en","type":"article","venue":"Computer Networks","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Byte; Network packet; Naive Bayes classifier; Server; Computer network; Artificial intelligence; Machine learning; Data mining; Support vector machine; Operating system","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":[0.0005563474,0.0003744594,0.0003606301,0.0002444097,0.0007527301,0.0002028632,0.0007167491,0.0002804391,0.00002428982],"category_scores_gemma":[0.00003568655,0.0003557341,0.0002030856,0.0005980522,0.00008872015,0.0003803519,0.0001059677,0.0006879736,0.0001560946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001891049,"about_ca_system_score_gemma":0.00004487247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002062852,"about_ca_topic_score_gemma":0.000007441804,"domain_scores_codex":[0.9970523,0.0003719605,0.0005522738,0.0008837178,0.0005514979,0.0005882196],"domain_scores_gemma":[0.9979846,0.0004413429,0.0003190349,0.0008344601,0.0002133036,0.0002072832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002902941,0.0003849133,0.0006260992,0.0000140281,0.00003987273,0.00005282028,0.0001713468,0.8241355,0.0006112473,0.002669761,0.008515627,0.1624885],"study_design_scores_gemma":[0.001323827,0.000893743,0.003298052,0.0001022322,0.000008879103,0.00002439341,0.000004461783,0.9826778,0.0004337607,0.0001149602,0.01074174,0.0003761275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01552956,0.0001190756,0.9780026,0.0006051486,0.003980704,0.0005198169,0.000001735044,0.0006164623,0.0006249023],"genre_scores_gemma":[0.9872006,0.00006794557,0.006261003,0.004182453,0.002119181,0.00006099583,0.00001523706,0.00003024083,0.00006232926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9717416,"threshold_uncertainty_score":0.9998895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04526274844761223,"score_gpt":0.2193355770046894,"score_spread":0.1740728285570771,"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."}}