{"id":"W1964193191","doi":"10.1109/iscas.2012.6272177","title":"Content-based spam filtering using hybrid generative discriminative learning of both textual and visual features","year":2012,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminative model; Computer science; Artificial intelligence; Generative grammar; Probabilistic logic; Machine learning; Support vector machine; Generative model; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002077833,0.0001057659,0.0001297774,0.00008359009,0.0001436261,0.00008561808,0.0001036004,0.00002685721,0.00001048],"category_scores_gemma":[0.000059797,0.00008740749,0.00003329253,0.000099482,0.00005527889,0.000584921,0.000101561,0.0001200072,0.00000104726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002672942,"about_ca_system_score_gemma":0.00001880852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002941479,"about_ca_topic_score_gemma":0.000009258327,"domain_scores_codex":[0.9992723,0.00009291791,0.0001187271,0.0001740875,0.0001464723,0.0001955297],"domain_scores_gemma":[0.999615,0.00009875328,0.00008803555,0.0000802734,0.00004827154,0.00006970701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006920675,0.0002091509,0.02336165,0.00006787155,0.00008088097,0.000006664253,0.006619101,0.001416465,0.8773334,0.01742391,0.0002124535,0.07319924],"study_design_scores_gemma":[0.0003771001,0.0003191945,0.01801901,0.00004044204,0.00001456616,0.00002362159,0.0008576973,0.3094845,0.6705353,0.00003263274,0.00008718357,0.0002087431],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4688861,0.00009352672,0.5305163,0.00003016235,0.0001270304,0.00004530378,8.413124e-7,0.00003795997,0.0002628187],"genre_scores_gemma":[0.9646546,0.00000193823,0.03505157,0.00006515864,0.00009461816,0.000002234085,0.000001783269,0.000006247369,0.0001218114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4957685,"threshold_uncertainty_score":0.3564374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05041977615115414,"score_gpt":0.2834267517194009,"score_spread":0.2330069755682468,"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."}}