{"id":"W1510882935","doi":"10.1007/978-3-540-24840-8_54","title":"Time-Sensitive Sampling for Spam Filtering","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Filter (signal processing); Set (abstract data type); Test set; Data mining; Training set; Data set; Artificial intelligence; Sampling (signal processing); Machine learning; Computer vision","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007079011,0.0004341124,0.0004220031,0.0006063331,0.0003497383,0.0005902698,0.001722482,0.0002927794,0.00001162545],"category_scores_gemma":[0.0001206603,0.0004323222,0.0001644475,0.0003749769,0.0003469857,0.0005708535,0.0006913096,0.0005307315,0.00006052369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004578343,"about_ca_system_score_gemma":0.000408286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002225167,"about_ca_topic_score_gemma":0.00002045416,"domain_scores_codex":[0.9970821,0.00001431589,0.0003665059,0.001373031,0.0005680314,0.0005959901],"domain_scores_gemma":[0.9979696,0.0005526128,0.0002200541,0.0008925843,0.0002327635,0.0001323786],"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":[0.00001890645,0.00002395666,0.000003778725,0.00008094611,0.00002267235,0.00004274125,0.001696642,0.2085263,0.00267669,0.021924,0.00002137766,0.764962],"study_design_scores_gemma":[0.000398692,0.0003155369,0.0000359392,0.0007471782,0.00001144405,0.00008090679,1.289504e-7,0.6764109,0.01278523,0.3065301,0.001807391,0.0008764849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009162947,0.00009239114,0.9949328,0.0004313725,0.002376192,0.0004571276,0.000008022054,0.0002468715,0.001363562],"genre_scores_gemma":[0.08110335,0.00001360292,0.9159778,0.001204069,0.001253251,0.00001564526,0.000009147552,0.00005400369,0.0003690765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7640855,"threshold_uncertainty_score":0.9998128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02578725749191961,"score_gpt":0.2512502793276299,"score_spread":0.2254630218357103,"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."}}