{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007192349,0.00004715111,0.00003749791,0.00004231485,0.0000562149,0.00007399293,0.000188096,0.00002683996,0.0001253672],"category_scores_gemma":[0.000006793306,0.00003625553,0.00002376518,0.000131274,0.000005459384,0.0001371629,0.00004703797,0.00004713478,0.0003709485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001090316,"about_ca_system_score_gemma":0.000005323523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001617824,"about_ca_topic_score_gemma":0.00003108599,"domain_scores_codex":[0.9995658,0.0000111921,0.0000655849,0.0001486044,0.0001170942,0.00009170124],"domain_scores_gemma":[0.9996899,0.00003283678,0.00001573479,0.0002254032,0.00001649065,0.00001960355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001875405,0.0002405202,0.0008589653,0.0000069184,0.000005271736,0.00002311537,0.0001140805,0.004526207,0.01081744,0.6863078,0.2043717,0.09270924],"study_design_scores_gemma":[0.0008542908,0.0006975195,0.01136958,0.00002728846,0.000004192667,0.00003262397,0.000004558861,0.5873541,0.1190814,0.1876808,0.09240245,0.000491154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06586196,0.0000106148,0.8609725,0.001385443,0.000694661,0.00004320087,2.633088e-7,0.0002805284,0.07075081],"genre_scores_gemma":[0.9846389,7.71304e-7,0.00873252,0.000596648,0.000179499,0.000001769385,0.000001230636,0.000002715948,0.005845909],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.918777,"threshold_uncertainty_score":0.4767916,"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."}}