{"id":"W1505796919","doi":"","title":"Email classification with co-training","year":2011,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":191,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Co-training; Naive Bayes classifier; Computer science; Labeled data; Support vector machine; Artificial intelligence; Training set; Machine learning; Classifier (UML); Training (meteorology); Statistical classification; Pattern recognition (psychology); Semi-supervised learning","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":[0.0001114477,0.00003902742,0.0000347998,0.00003441191,0.00005859707,0.00004661622,0.0001982253,0.00002101053,0.00006549246],"category_scores_gemma":[0.000005056509,0.00002870985,0.000009699996,0.0001329808,0.00001455407,0.0003169423,0.00001175062,0.00004241147,0.0001001814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008599032,"about_ca_system_score_gemma":0.00001944931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005478574,"about_ca_topic_score_gemma":0.00002448803,"domain_scores_codex":[0.9996259,0.00001312317,0.00005246524,0.0001371645,0.0000876557,0.00008369153],"domain_scores_gemma":[0.9996958,0.00001153606,0.00002670481,0.0002099282,0.00002407267,0.00003193158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002685258,0.00007812074,0.01713317,0.000008474512,0.00002610453,0.0000112604,0.02474273,0.000005674648,0.005572554,0.6806764,0.002709889,0.2690088],"study_design_scores_gemma":[0.001269237,0.001302876,0.7517868,0.00005666256,0.00002061255,0.0002193006,0.00208002,0.1086413,0.08077843,0.02667429,0.02613837,0.001032092],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03112452,0.00000319092,0.7893667,0.0001093099,0.0001085108,0.00003417773,6.621563e-8,0.0002363337,0.1790172],"genre_scores_gemma":[0.9431367,7.233902e-7,0.05626161,0.000140872,0.00002463132,0.000004531983,3.828188e-7,0.000002617371,0.0004279164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9120122,"threshold_uncertainty_score":0.1287663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1506716980756978,"score_gpt":0.2509912884462742,"score_spread":0.1003195903705764,"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."}}