{"id":"W2952361316","doi":"10.48550/arxiv.math/0510449","title":"Improving Classification When a Class Hierarchy is Available Using a Hierarchy-Based Prior","year":2005,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hierarchy; Multinomial logistic regression; Class hierarchy; Computer science; Class (philosophy); Softmax function; Artificial intelligence; Multinomial distribution; Bayesian probability; Machine learning; Tree (set theory); Prior probability; Data mining; Mathematics; Statistics; Artificial neural network","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001112141,0.0007707566,0.000720711,0.0007987443,0.0004652127,0.0007647228,0.004316129,0.0007960946,0.0002500147],"category_scores_gemma":[0.0002754606,0.0008384601,0.000308397,0.0006839221,0.0002614916,0.001291725,0.002416699,0.001658848,0.0008753015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001615175,"about_ca_system_score_gemma":0.001927377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003898983,"about_ca_topic_score_gemma":0.00001734172,"domain_scores_codex":[0.9941103,0.0003382113,0.001203026,0.002469629,0.000905471,0.0009733124],"domain_scores_gemma":[0.9925693,0.000192913,0.001311485,0.005061317,0.0005633219,0.0003016666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002085616,0.001977568,0.1433173,0.002495541,0.0004846514,0.0001137458,0.004630609,0.0004814146,0.43875,0.02135756,0.1123671,0.2738159],"study_design_scores_gemma":[0.0008350409,0.00009939542,0.01244807,0.0005363332,0.00008787578,0.0000170417,0.00002813877,0.8119448,0.07983035,0.001976971,0.09044023,0.00175573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06568819,0.0004022904,0.9212497,0.005742865,0.000751664,0.001618001,0.0001466913,0.002164154,0.002236398],"genre_scores_gemma":[0.3425061,0.0001006303,0.6494892,0.003490094,0.0005901597,0.0005324328,0.0003065307,0.0001438012,0.00284096],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8114634,"threshold_uncertainty_score":0.9999026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1040938347933459,"score_gpt":0.303829299863808,"score_spread":0.1997354650704621,"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."}}