{"id":"W2936568671","doi":"10.48550/arxiv.1904.09024","title":"When is a Prediction Knowledge?","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Variety (cybernetics); Computer science; Reinforcement learning; Value (mathematics); Artificial intelligence; Predictive value; Body of knowledge; Work (physics); Knowledge management; Data science; Epistemology; Machine learning; Engineering","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":[0.0002202522,0.0003090132,0.000292907,0.0002974714,0.0001193,0.000189227,0.002277746,0.0003692662,0.0001048547],"category_scores_gemma":[0.00002750573,0.0003716812,0.0002149338,0.0003573435,0.0000659933,0.0004633403,0.003135888,0.0007439039,0.001417339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003166965,"about_ca_system_score_gemma":0.0002914165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004038916,"about_ca_topic_score_gemma":0.000003030762,"domain_scores_codex":[0.9981047,0.0001121301,0.0002175131,0.001083974,0.000122737,0.0003589422],"domain_scores_gemma":[0.9974902,0.00008284473,0.0002731713,0.001823778,0.0001948704,0.000135168],"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":[0.000006397679,0.00003063336,0.003406824,0.00009342525,0.00008224099,0.0000270531,0.0009470109,0.9566151,0.000005189029,0.03311725,0.005419091,0.0002497482],"study_design_scores_gemma":[0.0003391374,0.00006678515,0.0006776692,0.0001103214,0.00005083171,0.000002438562,0.00002576253,0.9758659,0.00004420189,0.01006074,0.01242325,0.0003329431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009176275,0.00004888804,0.9555806,0.0001142538,0.001547053,0.0003695124,0.000008103856,0.0004335137,0.03272179],"genre_scores_gemma":[0.9630311,0.00009927189,0.002459701,0.0001305672,0.00009589589,8.020002e-7,0.00001833277,0.00002181678,0.03414248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9538549,"threshold_uncertainty_score":0.9998735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07118221310828741,"score_gpt":0.1907548266309062,"score_spread":0.1195726135226188,"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."}}