{"id":"W2003798735","doi":"10.1145/2184489.2184491","title":"SMSAssassin","year":2011,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Computer science; Short Message Service; Support vector machine; Machine learning; Artificial intelligence; Naive Bayes classifier; Filter (signal processing); Bag-of-words model; Communication source; Blacklist; Blacklisting; Forum spam; Spamming; World Wide Web; The Internet; Spambot; Computer security; Computer network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006110691,0.00002158515,0.00001882881,0.00002109709,0.00002691073,0.00002671537,0.0002144658,0.00001412935,0.0001694116],"category_scores_gemma":[0.000004942687,0.00001767866,0.00001222519,0.0000903941,0.000004977393,0.0002126146,0.00003563998,0.00002277682,0.0002467766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003749627,"about_ca_system_score_gemma":0.000005767211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009241748,"about_ca_topic_score_gemma":0.000009262669,"domain_scores_codex":[0.9997805,0.000007673759,0.00003187357,0.00007758236,0.00004530255,0.00005709028],"domain_scores_gemma":[0.9997911,0.000005382372,0.000008193329,0.000162879,0.000009787522,0.0000226549],"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":[0.000003150318,0.00005968674,0.003524218,0.000002252532,0.000007446549,0.00001052688,0.002352921,7.103829e-7,0.002001098,0.7096899,0.01654657,0.2658015],"study_design_scores_gemma":[0.0005634505,0.0004035654,0.2294575,0.00001134622,0.000006286259,0.00008397148,0.00006745658,0.02431673,0.3889694,0.2644358,0.09103126,0.0006532844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004518081,0.000005917129,0.6984869,0.00009604006,0.0003093675,0.00001113549,1.677376e-8,0.0001900384,0.2963825],"genre_scores_gemma":[0.9299197,5.302966e-7,0.06869514,0.0002235687,0.0000198184,0.000001167407,3.108893e-8,0.000001130013,0.001138878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9254016,"threshold_uncertainty_score":0.3171896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05160695508429729,"score_gpt":0.1959812090071653,"score_spread":0.144374253922868,"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."}}