{"id":"W2283429330","doi":"","title":"Towards improving e-mail content classification for spam control: architecture, abstraction, and strategies","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Server; Naive Bayes classifier; Computer network; Machine learning; Artificial intelligence; Data mining; Support vector machine","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":[0.001251446,0.0009150439,0.0007539903,0.001464038,0.0008112148,0.002656616,0.001859123,0.001016158,0.00245825],"category_scores_gemma":[0.002589479,0.0006856981,0.0006283545,0.001353748,0.001004062,0.00388728,0.001014511,0.001362596,0.002044668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001672443,"about_ca_system_score_gemma":0.001467078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003164858,"about_ca_topic_score_gemma":0.003111704,"domain_scores_codex":[0.9991485,0.0002019812,0.00005921282,0.0001372734,0.0002943858,0.0001586149],"domain_scores_gemma":[0.9980629,0.0003972108,0.0001585222,0.0005546649,0.0007439727,0.00008274404],"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":[0.0008813394,0.0005256573,0.009144326,0.0006383692,0.0001384173,0.0001934027,0.000796948,0.03293949,0.1514951,0.05617549,0.008391378,0.7386801],"study_design_scores_gemma":[0.0001552795,0.0004586002,0.004200668,0.0001365297,0.0003221558,0.0004421205,0.0002943977,0.686792,0.2319787,0.04377457,0.03134433,0.0001006756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06253038,0.001863701,0.9224098,0.0009314413,0.00008061367,0.0002368069,0.0000506826,0.005368454,0.006528154],"genre_scores_gemma":[0.4726014,0.001493615,0.5169741,0.0004658169,0.0001364802,0.0001703947,0.0002093888,0.0002290905,0.007719716],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003164858,"threshold_uncertainty_score":0.01213449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0380434695267245,"score_gpt":0.2982931228488558,"score_spread":0.2602496533221313,"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."}}