{"id":"W2058737869","doi":"10.1145/1247715.1247717","title":"Online supervised spam filter evaluation","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Filter (signal processing); Set (abstract data type); Software; Receiver operating characteristic; Confidence interval; Information retrieval; Data mining; Machine learning; Artificial intelligence; Statistics; Mathematics; Operating system","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":[0.001423345,0.0001340457,0.0001201748,0.0004395843,0.000252541,0.0003242281,0.0005265882,0.0001168729,0.00005034481],"category_scores_gemma":[0.00006093248,0.0001271665,0.00007486576,0.0006147232,0.00001423222,0.003187826,0.000007364036,0.0001852314,0.000430677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001704604,"about_ca_system_score_gemma":0.00005869551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001238842,"about_ca_topic_score_gemma":0.00003121264,"domain_scores_codex":[0.9983114,0.00007381439,0.0005317117,0.0001540612,0.0007096652,0.0002193273],"domain_scores_gemma":[0.9985028,0.0001449955,0.0001468947,0.0007632796,0.0003499627,0.00009205045],"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":[0.00007374081,0.0002600287,0.0001587091,0.00009997499,0.00007899866,0.000001634502,0.006762241,0.05287727,0.0004258721,0.003438558,0.001183537,0.9346395],"study_design_scores_gemma":[0.002432073,0.0004169035,0.007154703,0.0001448591,0.00005299967,0.0001120734,0.002008959,0.8989283,0.006475163,0.0006632661,0.08093654,0.0006741566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01745955,0.00002102756,0.9763684,0.0003436571,0.00262818,0.0004538041,0.00001595286,0.000324894,0.0023846],"genre_scores_gemma":[0.9929525,0.00000677236,0.006419579,0.0003193716,0.0001075736,0.00004527009,0.00004488679,0.000006098046,0.00009795129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.975493,"threshold_uncertainty_score":0.5535626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03922481280749248,"score_gpt":0.2785531126448064,"score_spread":0.2393282998373139,"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."}}