{"id":"W4401284752","doi":"10.1111/bjop.12724","title":"Plinko: Eliciting beliefs to build better models of statistical learning and mental model updating","year":2024,"lang":"en","type":"article","venue":"British Journal of Psychology","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Prior probability; Psychology; Bayesian probability; Bayesian inference; Cognitive psychology; Measure (data warehouse); Cognition; Artificial intelligence; Machine learning; Computer science; Data mining","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":[0.0006515072,0.00009835445,0.000242728,0.0001436501,0.00007972737,0.0001829233,0.0003254446,0.00007548618,0.00001219497],"category_scores_gemma":[0.00005870597,0.0001117131,0.00005050476,0.0001525755,0.00005699213,0.0003410831,0.0001328682,0.000532669,0.000003612276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000160984,"about_ca_system_score_gemma":0.00005083362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001567326,"about_ca_topic_score_gemma":0.000002972194,"domain_scores_codex":[0.9986372,0.00008762888,0.000537448,0.0002729666,0.0002223926,0.0002423592],"domain_scores_gemma":[0.9994259,0.0001056043,0.0001228734,0.000087436,0.0001149735,0.0001432487],"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":[0.00001949726,0.0000714527,0.0001850546,0.00006418181,0.00006887785,0.0004747211,0.002275098,0.01383974,0.008957336,0.03856355,0.004425528,0.9310549],"study_design_scores_gemma":[0.0002664602,0.0002624166,0.0001778881,0.0005281084,0.00001048755,0.003890282,0.00004558551,0.9252526,0.0001020708,0.06912716,0.0001914159,0.0001455594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1374624,0.001145355,0.8591663,0.001305984,0.0002251169,0.00003479538,0.00000828446,0.00002584943,0.0006259367],"genre_scores_gemma":[0.7589563,0.0001847509,0.2401325,0.0006052208,0.0000893195,0.000001122316,9.167464e-7,0.00001037381,0.00001953461],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9309094,"threshold_uncertainty_score":0.4555529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02354924035616306,"score_gpt":0.3326071516825843,"score_spread":0.3090579113264212,"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."}}