{"id":"W2066546027","doi":"10.1145/1148170.1148195","title":"On-line spam filter fusion","year":2006,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Filter (signal processing); Computer science; Stacking; Line (geometry); Margin (machine learning); Set (abstract data type); Logistic regression; Artificial intelligence; Data mining; Pattern recognition (psychology); Machine learning; Mathematics; Computer vision","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":[0.005775201,0.00180844,0.002444376,0.003043487,0.001382674,0.002252371,0.001435777,0.002415158,0.004125394],"category_scores_gemma":[0.009021524,0.000686897,0.00177547,0.00181041,0.0006184449,0.002786244,0.002498494,0.001236017,0.004116758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001065943,"about_ca_system_score_gemma":0.001111408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002907419,"about_ca_topic_score_gemma":0.003523604,"domain_scores_codex":[0.9938334,0.00152922,0.0003079699,0.0009179353,0.002622446,0.0007891242],"domain_scores_gemma":[0.9921018,0.001893246,0.0004701146,0.002481418,0.002866701,0.0001866339],"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":[0.001318793,0.001245046,0.01551003,0.0002260615,0.000717523,0.000325235,0.0005344881,0.07456353,0.07889787,0.002291073,0.01068124,0.813689],"study_design_scores_gemma":[0.0000831963,0.0009248618,0.01818032,0.00003347608,0.0004739828,0.0007911306,0.0002895921,0.720498,0.2367288,0.006080135,0.01577329,0.0001432414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2766146,0.0006458315,0.6977656,0.000312397,0.0002009305,0.0004019267,0.0006201112,0.01189535,0.01154322],"genre_scores_gemma":[0.6563756,0.0002303208,0.3280129,0.0003761116,0.0002012407,0.0002262163,0.002671553,0.0007507809,0.01115522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005775201,"threshold_uncertainty_score":0.03054255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01702298616228354,"score_gpt":0.2285401948556886,"score_spread":0.211517208693405,"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."}}