{"id":"W4382197597","doi":"10.21203/rs.3.rs-3080402/v1","title":"Long short-term prediction guides human metacognitive reinforcement learning","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Samsung; Ministry of Science and ICT, South Korea; University of Oxford; Korea Advanced Institute of Science and Technology; National Research Foundation; National Research Foundation of Korea; Somerville College, University of Oxford","keywords":"Term (time); Reinforcement learning; Metacognition; Reinforcement; Cognitive psychology; Psychology; Computer science; Artificial intelligence; Machine learning; Social psychology; Cognition; Neuroscience","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009715817,0.0003390132,0.0002676698,0.0001733259,0.0002080935,0.001647342,0.0006206193,0.0008303801,0.00569427],"category_scores_gemma":[0.01284754,0.000373285,0.0002156992,0.0001562563,0.0004514563,0.001468146,0.0005646421,0.001207721,0.001063748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004282354,"about_ca_system_score_gemma":0.000638686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002655763,"about_ca_topic_score_gemma":0.002429412,"domain_scores_codex":[0.9996741,0.0001010736,0.00001465438,0.0001245698,0.00005196865,0.00003361536],"domain_scores_gemma":[0.9964383,0.00205552,0.0003831417,0.0004641951,0.0004260672,0.0002327668],"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":[0.002300484,0.001057289,0.06639468,0.0003955744,0.0003579888,0.0004269278,0.002223516,0.1501458,0.1189414,0.07447998,0.0164094,0.566867],"study_design_scores_gemma":[0.0001370185,0.0005535002,0.04654825,0.00008371496,0.0001100699,0.0001770507,0.0003542889,0.8154123,0.02053615,0.1101092,0.005880625,0.00009789053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6685362,0.0005198143,0.2957838,0.001386869,0.0003796979,0.00008762444,0.0003434429,0.001314829,0.0316477],"genre_scores_gemma":[0.9853411,0.0000740071,0.01127882,0.00007491212,0.00001519371,0.00002022127,0.0001011775,0.0001055317,0.002988998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00569427,"threshold_uncertainty_score":0.01904923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1644300741039804,"score_gpt":0.4243602209578892,"score_spread":0.2599301468539088,"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."}}