{"id":"W1965231990","doi":"10.1145/2030376.2030391","title":"Clustering for semi-supervised spam filtering","year":2011,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Medoid; Filter (signal processing); Data mining; Artificial intelligence; Set (abstract data type); Training set; Bag-of-words model; Partition (number theory); Pattern recognition (psychology); Machine learning; Mathematics","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":[0.0001283783,0.00006456632,0.00006181647,0.00004400339,0.000080556,0.00007237287,0.0003513296,0.00003246632,0.00006066629],"category_scores_gemma":[0.00001405463,0.00005887652,0.00004298361,0.00009334194,0.000006090708,0.0003685585,0.0001180071,0.00003656424,0.00002938811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000128529,"about_ca_system_score_gemma":0.00000791183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007616227,"about_ca_topic_score_gemma":0.00002240947,"domain_scores_codex":[0.999489,0.000008435908,0.00009234489,0.0001898681,0.00006298121,0.0001573656],"domain_scores_gemma":[0.9996249,0.00002614429,0.00001987011,0.0002585781,0.00002546718,0.00004503514],"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":[0.0001593674,0.0002648125,0.003934517,0.0003240306,0.0001227129,0.00002264046,0.02596734,0.0006232022,0.1510361,0.06270406,0.009528092,0.7453132],"study_design_scores_gemma":[0.0004120337,0.0001798768,0.001841118,0.0000203691,0.00000433667,0.00001549512,0.0000403344,0.9008123,0.08759427,0.003683383,0.005149017,0.0002474892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01134958,0.00000952656,0.9739107,0.00006982606,0.000664415,0.0001015992,3.734871e-7,0.000283913,0.01361003],"genre_scores_gemma":[0.7286971,0.000001601219,0.2704208,0.0002227968,0.00008476091,0.00002018197,4.084326e-7,0.000006346029,0.000546031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9001891,"threshold_uncertainty_score":0.2400915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06678280629149759,"score_gpt":0.2353020050680726,"score_spread":0.168519198776575,"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."}}