{"id":"W2159112514","doi":"10.1109/tasl.2007.906178","title":"Approximate Test Risk Bound Minimization Through Soft Margin Estimation","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University","keywords":"Discriminative model; Margin (machine learning); Computer science; Hidden Markov model; Artificial intelligence; Machine learning; Pattern recognition (psychology); Statistical learning theory; Support vector machine; Speech recognition","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":[],"consensus_categories":[],"category_scores_codex":[0.0004586195,0.0002064298,0.000179314,0.0002079846,0.0005319597,0.0003773117,0.0002000154,0.0001146983,0.00008261747],"category_scores_gemma":[0.000073365,0.0001944663,0.00006222538,0.0005433591,0.00007020373,0.0009152896,0.000003009031,0.000235513,0.00004377898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005547924,"about_ca_system_score_gemma":0.0000527848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004876945,"about_ca_topic_score_gemma":0.00008254035,"domain_scores_codex":[0.9985912,0.00004996969,0.0003026994,0.0004266467,0.0002959915,0.0003335227],"domain_scores_gemma":[0.9991077,0.000284538,0.0001669297,0.0002444252,0.00008487423,0.0001114895],"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":[0.00001703808,0.0001349381,0.00002461641,0.00005256645,0.00001077094,0.00002769483,0.0019282,0.000167199,0.001531402,0.00001742244,0.000037458,0.9960507],"study_design_scores_gemma":[0.00106886,0.0001461417,0.0004723617,0.0002438761,0.00008739936,0.0002957533,0.001281549,0.563399,0.4304436,0.001435102,0.0004645496,0.0006617974],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01608057,0.0003201899,0.9808987,0.0002722071,0.0001682045,0.0001966599,0.00001378104,0.000383417,0.001666309],"genre_scores_gemma":[0.644143,0.00006913816,0.3549851,0.0003683206,0.00004503526,0.00001342199,0.000004290307,0.0000191285,0.0003524872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9953889,"threshold_uncertainty_score":0.7930106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01297854365011363,"score_gpt":0.2585397057577212,"score_spread":0.2455611621076075,"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."}}