{"id":"W2138625739","doi":"10.1109/dnsr.2004.1344731","title":"Adaptive filtering of spam","year":2004,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Filter (signal processing); Set (abstract data type); Vocabulary; Process (computing); Artificial intelligence; Layer (electronics); Natural language processing; Speech recognition; Programming language; Computer vision; Linguistics","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":[0.00004560225,0.00002586161,0.00003482,0.00002671073,0.00001753513,0.00001446026,0.0001596234,0.00001305112,0.00001023809],"category_scores_gemma":[0.000005735665,0.00002243699,0.00001730392,0.0001095452,0.000007469779,0.0001732916,0.00004589603,0.00002424121,0.00001975862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001145569,"about_ca_system_score_gemma":0.00001184311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000159347,"about_ca_topic_score_gemma":0.00001157829,"domain_scores_codex":[0.9997533,0.00000403832,0.00005004437,0.00007650738,0.00006386463,0.00005225658],"domain_scores_gemma":[0.9998118,0.000008851593,0.00001780817,0.0001289221,0.00001656277,0.0000160828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001397107,0.00009604222,0.0003512328,0.0000148981,0.00002447202,0.00001193948,0.002955398,0.008988686,0.06040516,0.8394862,0.0003692368,0.0872827],"study_design_scores_gemma":[0.0006257032,0.00048851,0.008422634,0.00004631835,0.00000339187,0.00002869301,0.00006435315,0.02783255,0.8796983,0.08110533,0.001461101,0.0002230828],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03314402,0.000009793624,0.9539216,0.0001440327,0.0001767809,0.0000198679,1.086677e-7,0.00006967578,0.01251416],"genre_scores_gemma":[0.922979,8.682564e-7,0.07686627,0.00003973514,0.00001808677,7.498734e-7,3.969346e-8,0.000001109518,0.00009413991],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.889835,"threshold_uncertainty_score":0.09149537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01786434222543604,"score_gpt":0.2101225512118674,"score_spread":0.1922582089864314,"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."}}