{"id":"W2062614982","doi":"10.1145/1321440.1321486","title":"Spam filtering for short messages","year":2007,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Computer security","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":[0.000337747,0.00004088923,0.00004070808,0.00004048653,0.00006263883,0.00007345979,0.0002172169,0.00002469428,0.00001073199],"category_scores_gemma":[0.00001650063,0.00003575004,0.00002879429,0.00009319591,0.000005074277,0.0002138713,0.00004467769,0.00002829486,0.000009432559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001148214,"about_ca_system_score_gemma":0.000004854706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001422007,"about_ca_topic_score_gemma":0.00002407291,"domain_scores_codex":[0.9995854,0.000003036596,0.00007100149,0.0001326598,0.00007158897,0.0001362761],"domain_scores_gemma":[0.9997066,0.00006544415,0.000008758357,0.0001640778,0.00002103079,0.0000340335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002143393,0.00004795129,0.002874447,0.00002871354,0.00002355315,0.000008957534,0.0006879129,0.00009588107,0.05389038,0.1141902,0.01132061,0.81681],"study_design_scores_gemma":[0.0003455913,0.0002733839,0.02572983,0.00001948694,0.000007088966,0.00002974518,0.000054705,0.07170282,0.7339962,0.01126313,0.1561412,0.0004368738],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01528987,0.00001496927,0.9704311,0.0001887326,0.0005120425,0.00006518346,1.636373e-7,0.0001922802,0.0133056],"genre_scores_gemma":[0.8958147,0.000001239425,0.1029483,0.0001839866,0.000119887,0.000004025753,3.528405e-7,0.000003137114,0.0009243704],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8805248,"threshold_uncertainty_score":0.1457844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02603713313869163,"score_gpt":0.2815240983558139,"score_spread":0.2554869652171222,"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."}}