{"id":"W2077512673","doi":"10.1214/07-ba209","title":"Improving classification when a class hierarchy is available using a hierarchy-based prior","year":2007,"lang":"en","type":"article","venue":"Bayesian Analysis","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hierarchy; Multinomial logistic regression; Class hierarchy; Computer science; Class (philosophy); Machine learning; Artificial intelligence; Multinomial distribution; Bayesian probability; Tree (set theory); Data mining; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001020241,0.0002750694,0.0003880284,0.001881816,0.0003955406,0.0005062144,0.00138614,0.0002082427,0.0003978417],"category_scores_gemma":[0.000108897,0.0002687766,0.0003562243,0.004043818,0.0001507999,0.0007715565,0.0002030478,0.0002551402,0.0001862748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004566361,"about_ca_system_score_gemma":0.0002404266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002604588,"about_ca_topic_score_gemma":0.00007222577,"domain_scores_codex":[0.997104,0.00008442237,0.000655738,0.0009307492,0.0006031868,0.0006218944],"domain_scores_gemma":[0.9973353,0.0001476378,0.0004509182,0.001688691,0.0001953619,0.0001821662],"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":[0.0001142314,0.0008372234,0.06725814,0.0001566827,0.001720859,0.0001053697,0.002341725,0.0002581308,0.09966429,0.2137783,0.01151895,0.602246],"study_design_scores_gemma":[0.0004261737,0.00004897438,0.003992012,0.00001304357,0.0003362149,0.000003115822,0.0002111167,0.9663775,0.01684521,0.002210925,0.00907199,0.0004637044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005505625,0.0001401087,0.9868657,0.002653972,0.00007227575,0.0002356449,0.000005182279,0.0007410078,0.003780468],"genre_scores_gemma":[0.696539,0.000006364703,0.3011951,0.0005787318,0.00003598466,0.00001730749,0.00001422289,0.00001642582,0.001596859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9661194,"threshold_uncertainty_score":0.9999765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03222386111863169,"score_gpt":0.2757000272695841,"score_spread":0.2434761661509524,"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."}}