{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01247881,0.002204717,0.003294304,0.003903004,0.00172675,0.002605957,0.003416336,0.004929604,0.002747437],"category_scores_gemma":[0.03370918,0.00100083,0.001521743,0.003772663,0.001579596,0.007605765,0.004128665,0.004414296,0.003357119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053853,"about_ca_system_score_gemma":0.001123654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002152,"about_ca_topic_score_gemma":0.003209313,"domain_scores_codex":[0.9865276,0.007393479,0.0007094234,0.002655132,0.001908637,0.0008058735],"domain_scores_gemma":[0.956349,0.02390946,0.001858896,0.009781363,0.007337625,0.0007637995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001573097,0.001582337,0.01884098,0.0003736735,0.0003990559,0.0003426916,0.0004606642,0.1113433,0.006969549,0.003672208,0.01113405,0.8433084],"study_design_scores_gemma":[0.00005064964,0.0002200609,0.001551519,0.00003477993,0.00007276407,0.0002942915,0.00008600252,0.9784721,0.008823982,0.007953127,0.002409074,0.00003175106],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1424187,0.002228569,0.8370087,0.001548222,0.0004171625,0.0004893455,0.0004410167,0.008181345,0.007267092],"genre_scores_gemma":[0.6500786,0.0002549798,0.3418736,0.0005449341,0.0003602772,0.0004159258,0.001345972,0.0002514649,0.004874312],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01247881,"threshold_uncertainty_score":0.06599504,"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."}}