{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009063582,0.0007733842,0.001363848,0.004973458,0.0008833602,0.00226927,0.001369026,0.002164985,0.0009898051],"category_scores_gemma":[0.05540156,0.0003798375,0.0007344612,0.00267117,0.001278783,0.002919208,0.001344822,0.001694786,0.0006315121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001555912,"about_ca_system_score_gemma":0.001011878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003655787,"about_ca_topic_score_gemma":0.001881554,"domain_scores_codex":[0.9928445,0.003348893,0.0004790715,0.0009248363,0.002147256,0.0002553842],"domain_scores_gemma":[0.9390058,0.05060555,0.002924136,0.002098658,0.004751538,0.0006143376],"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":[0.001475201,0.0002838803,0.02329052,0.0005767408,0.0003002986,0.0002905954,0.0006584747,0.2559042,0.007650728,0.007322479,0.003757403,0.6984894],"study_design_scores_gemma":[0.00002320365,0.00007433372,0.003054267,0.00008418858,0.00004913731,0.0001281207,0.0001113156,0.9828781,0.005897861,0.006716262,0.0009592845,0.00002398535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3378717,0.003421076,0.650777,0.0009367358,0.0001929894,0.0002074692,0.0003525969,0.001831152,0.004409237],"genre_scores_gemma":[0.8257639,0.0003847418,0.1721347,0.00008872062,0.0001298366,0.00006565204,0.0004726104,0.00009248521,0.000867378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009063582,"threshold_uncertainty_score":0.0479334,"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."}}