{"id":"W4200316362","doi":"10.31234/osf.io/5f9uc","title":"Flexibility in valenced reinforcement learning computations across development","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Mental Health; U.S. Department of Defense; National Defense Science and Engineering Graduate; York University; Jacobs Foundation; National Science Foundation","keywords":"Weighting; Reinforcement learning; Reinforcement; Flexibility (engineering); Psychology; Valence (chemistry); Context (archaeology); Exploratory analysis; Cognitive psychology; Developmental psychology; Computer science; Artificial intelligence; Social psychology; Statistics; Mathematics; Geography; Medicine; Data science","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000554127,0.0002975308,0.0004599696,0.00004575203,0.0002065991,0.00007595601,0.0002681621,0.0003694385,0.005259746],"category_scores_gemma":[0.00003463302,0.0002503836,0.0001277715,0.0001955808,0.0001030951,0.00002649673,0.0009902471,0.001135849,0.0002521237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001635791,"about_ca_system_score_gemma":0.00005253821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006464819,"about_ca_topic_score_gemma":0.0006040694,"domain_scores_codex":[0.9974865,0.0002206275,0.0007172038,0.0008576888,0.0002241265,0.0004938315],"domain_scores_gemma":[0.9991984,0.00009431375,0.0001578532,0.0003590987,0.0001089276,0.00008145745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001987787,0.002183686,0.4755352,0.0002667239,0.0004099674,0.0002756995,0.1108238,0.07188923,0.000052479,0.001008594,0.001373514,0.3359823],"study_design_scores_gemma":[0.0005715599,0.00006269318,0.9862241,0.0001250801,0.00001248152,0.000003164773,0.007559855,0.0001129696,0.00004820032,0.0002839518,0.004539522,0.0004564575],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9587653,0.0004827426,0.007610853,0.0002654041,0.001261018,0.0004606933,0.00000310603,0.0001598083,0.03099108],"genre_scores_gemma":[0.9864933,0.00003263584,0.002694615,0.0002537477,0.00004237867,0.000357744,0.0001573947,0.00001216322,0.009956002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5106888,"threshold_uncertainty_score":0.9999948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3446137764191203,"score_gpt":0.4416921586253916,"score_spread":0.09707838220627124,"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."}}