{"id":"W2962696883","doi":"10.48550/arxiv.1511.03225","title":"Label Efficient Learning by Exploiting Multi-class Output Codes","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Intuition; Class (philosophy); Artificial intelligence; Theoretical computer science; Supervised learning; Semi-supervised learning; Machine learning; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004451642,0.0001763264,0.0001748642,0.0001183162,0.0002617202,0.0001174587,0.0007715932,0.00006901789,0.000006732832],"category_scores_gemma":[0.0001500283,0.0001889704,0.00005970475,0.0005656143,0.00006330527,0.0002691395,0.000388253,0.0003670999,0.000214646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009959583,"about_ca_system_score_gemma":0.00006083334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001252205,"about_ca_topic_score_gemma":0.000003337951,"domain_scores_codex":[0.9985743,0.00020051,0.000126482,0.0005884763,0.0001231355,0.0003870995],"domain_scores_gemma":[0.9990248,0.0001029299,0.0001209882,0.0003596832,0.0001231933,0.0002684209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001590197,0.0003062171,0.01128983,0.00001499598,0.00003969235,0.0002407793,0.001506774,0.9362213,0.0002747268,0.03977853,0.001848922,0.008462355],"study_design_scores_gemma":[0.001061289,0.00008720709,0.0001317984,0.00001727829,0.000008625996,0.000005776863,0.0004349209,0.9914744,0.000168145,0.0001584853,0.006208107,0.00024399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3016274,0.00004994063,0.6953577,0.0001152541,0.0001897035,0.0000570087,0.000001406543,0.0003792347,0.002222357],"genre_scores_gemma":[0.984735,0.000007441234,0.00492517,0.00008942981,0.00004334806,3.444199e-7,0.000004077682,0.00001358204,0.01018164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6904325,"threshold_uncertainty_score":0.7705988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09271439463421345,"score_gpt":0.2039915599581275,"score_spread":0.1112771653239141,"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."}}