{"id":"W2029677459","doi":"10.1007/s10844-013-0254-7","title":"Cost-sensitive three-way email spam filtering","year":2013,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Focus (optics); Set (abstract data type); Machine learning; Function (biology); Binary classification; Data mining; Binary number; Artificial intelligence; Support vector machine","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":[0.0006974103,0.0001139867,0.0002006339,0.0003181426,0.00009195897,0.0008254849,0.0004137496,0.00006839603,0.00002429356],"category_scores_gemma":[0.00009583835,0.0000888362,0.0001073725,0.0002530805,0.00001417548,0.005313002,0.00006495934,0.0002057898,0.0007617053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001396303,"about_ca_system_score_gemma":0.00004497979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001712504,"about_ca_topic_score_gemma":0.00000326657,"domain_scores_codex":[0.9983279,0.00005202774,0.0009073202,0.00006199627,0.000480966,0.0001697681],"domain_scores_gemma":[0.9978061,0.0000916745,0.0008752469,0.000212632,0.0008931353,0.0001211593],"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":[0.0001096611,0.0001514425,0.002389141,0.0004831726,0.000481357,0.00003390841,0.04137376,0.07295641,0.004571765,0.0341476,0.04754043,0.7957613],"study_design_scores_gemma":[0.0008754436,0.0008759424,0.006029048,0.0009784692,0.00002842664,0.002550117,0.005557073,0.7774924,0.0439749,0.00109639,0.1598213,0.0007205007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02710083,0.00007042575,0.9663028,0.0002210862,0.003428194,0.0002893156,0.000001222736,0.00004528021,0.002540801],"genre_scores_gemma":[0.9964986,0.00002995281,0.002911562,0.0001939897,0.0002808439,0.00001026435,0.000001402496,0.000004343116,0.0000689846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9693978,"threshold_uncertainty_score":0.9790435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03493937407291117,"score_gpt":0.2448378195062222,"score_spread":0.209898445433311,"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."}}