{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005310736,0.001352593,0.0004852761,0.0004617561,0.000385983,0.00159859,0.001680487,0.001047576,0.007589406],"category_scores_gemma":[0.04231095,0.0006198821,0.0007123894,0.0002516235,0.001616194,0.003393687,0.002595775,0.002390922,0.0008835694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006580998,"about_ca_system_score_gemma":0.0007016049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001081989,"about_ca_topic_score_gemma":0.001842894,"domain_scores_codex":[0.9976149,0.001372649,0.0001406032,0.0003939822,0.0003497615,0.0001281625],"domain_scores_gemma":[0.9749026,0.01974148,0.001845512,0.002455184,0.0005138343,0.0005413548],"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":[0.006798913,0.003608907,0.05087995,0.002716783,0.0007798488,0.001563778,0.0207431,0.1157858,0.1798872,0.2459881,0.01607599,0.3551717],"study_design_scores_gemma":[0.0008544205,0.001495829,0.01394321,0.0002285219,0.0001958307,0.0005998736,0.0007854577,0.670171,0.03994906,0.2467524,0.02475153,0.0002729819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2080324,0.00009816204,0.7777042,0.0009993992,0.00009675961,0.0007581849,0.0008116756,0.003255654,0.008243566],"genre_scores_gemma":[0.6367956,0.00009160047,0.3579609,0.0003500388,0.00002221169,0.001157446,0.0005661203,0.0003585736,0.002697524],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007589406,"threshold_uncertainty_score":0.02808619,"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."}}