{"id":"W1952205872","doi":"","title":"Estimating the Credibility of Examples in Automatic Document Classification","year":2010,"lang":"en","type":"article","venue":"Cadernos de Linguística e Teoria da Literatura (Universidade Federal de Minas Gerais)","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Credibility; Naive Bayes classifier; Computer science; Classifier (UML); Macro; Information retrieval; Set (abstract data type); Function (biology); Document classification; Artificial intelligence; Class (philosophy); Data mining; Machine learning","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001145683,0.0002401332,0.0002715719,0.0002328787,0.0003651374,0.001169728,0.001056466,0.0002460764,0.00004490513],"category_scores_gemma":[0.0009794704,0.0002125275,0.0001142893,0.0006903881,0.0001727696,0.0007957708,0.0001856486,0.0008909676,0.00001061069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002101188,"about_ca_system_score_gemma":0.0002223456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002489495,"about_ca_topic_score_gemma":0.00003908432,"domain_scores_codex":[0.9979396,0.0002691208,0.0004435258,0.0005216818,0.0003417376,0.0004843497],"domain_scores_gemma":[0.9978293,0.0007913592,0.0002746691,0.0007867543,0.000165418,0.0001524618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001188994,0.000338711,0.01335104,0.0004855011,0.0001018035,0.0001389653,0.06564061,0.001371331,0.3933449,0.452287,0.0008950188,0.07192626],"study_design_scores_gemma":[0.0007982815,0.0001547331,0.107758,0.0002083862,0.00003405824,0.0001249595,0.0006650271,0.8515128,0.00347131,0.03340092,0.001451112,0.0004203218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.907141,0.00007828015,0.08849486,0.001921441,0.001168084,0.000321819,0.000005743957,0.0001766462,0.0006920907],"genre_scores_gemma":[0.9019738,0.000001594157,0.0974603,0.0001424278,0.0002946794,0.00001570026,0.000009448279,0.00001388549,0.00008819706],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8501415,"threshold_uncertainty_score":0.9998671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0167937233486682,"score_gpt":0.2599941863775126,"score_spread":0.2432004630288445,"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."}}