{"id":"W2108672713","doi":"10.1145/1631272.1631393","title":"Improving automatic music tag annotation using stacked generalization of probabilistic SVM outputs","year":2009,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Annotation; Computer science; Probabilistic logic; Generalization; Support vector machine; Music information retrieval; Information retrieval; Recommender system; Artificial intelligence; Scheme (mathematics); Natural language processing; Machine learning; Speech recognition; Musical","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":[],"consensus_categories":[],"category_scores_codex":[0.0002197454,0.0001130711,0.0001554747,0.0001162047,0.0001080229,0.0001311943,0.0002658467,0.00004324051,0.00001933074],"category_scores_gemma":[0.00008067609,0.0001000196,0.00003507282,0.0004901774,0.00002457235,0.0007328013,0.00004824345,0.00004458245,0.000003214985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005143388,"about_ca_system_score_gemma":0.0001275143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002961086,"about_ca_topic_score_gemma":0.000003802785,"domain_scores_codex":[0.9989077,0.00004245137,0.0003440857,0.0002649986,0.0002495114,0.0001912312],"domain_scores_gemma":[0.9992416,0.00002307985,0.000258061,0.0002676331,0.0001644905,0.00004514793],"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":[0.000003046012,0.0001414469,0.0001852468,0.000301218,0.000009732374,0.000004549299,0.002837556,0.01057295,0.1928505,0.05953065,0.0003091025,0.733254],"study_design_scores_gemma":[0.0001853158,0.00004947075,0.001209152,0.00005567606,0.000009153592,0.000004779901,0.00001863516,0.982686,0.010245,0.005391363,0.00001531368,0.000130143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2610667,0.00003416226,0.7380179,0.0001545,0.0001030782,0.000132031,3.104227e-7,0.0001354476,0.0003559043],"genre_scores_gemma":[0.7435014,4.829798e-7,0.2558993,0.0004915954,0.00003887502,0.000001479006,0.000002724437,0.000004400266,0.00005969236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.972113,"threshold_uncertainty_score":0.407868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02967875432838947,"score_gpt":0.2574788825945556,"score_spread":0.2278001282661661,"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."}}