{"id":"W2026404479","doi":"10.1167/14.10.881","title":"Plinko: A spatial probability task to measure learning and updating.","year":2014,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Task (project management); Probability distribution; Computer science; Statistics; Ball (mathematics); Event (particle physics); Artificial intelligence; Matching (statistics); Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00218642,0.001641203,0.0006718699,0.001800466,0.0003478069,0.001279299,0.001590028,0.001202923,0.008294022],"category_scores_gemma":[0.0363254,0.000635926,0.0005372162,0.000871007,0.0005744729,0.004777593,0.002565429,0.0009796931,0.001904393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004844363,"about_ca_system_score_gemma":0.0006714736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002220387,"about_ca_topic_score_gemma":0.00237068,"domain_scores_codex":[0.9981516,0.0003944106,0.0002410125,0.0004874428,0.0006131616,0.000112328],"domain_scores_gemma":[0.9862257,0.007155595,0.003444776,0.001138892,0.00111227,0.0009227428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.008452441,0.003344022,0.1128824,0.003767265,0.0008384224,0.0007622218,0.002919751,0.02482525,0.141388,0.01070145,0.04125143,0.6488674],"study_design_scores_gemma":[0.002023576,0.008786179,0.4537723,0.0004887087,0.0006623284,0.003974492,0.001002004,0.3100902,0.06863347,0.07399345,0.07569569,0.000877631],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4690787,0.00188137,0.4642436,0.0006418033,0.0004887413,0.005648631,0.01437531,0.01185485,0.03178698],"genre_scores_gemma":[0.7478747,0.0006946671,0.229107,0.000730075,0.0001505908,0.005673605,0.007932674,0.001151835,0.006684921],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008294022,"threshold_uncertainty_score":0.02774626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01730257704136275,"score_gpt":0.3062568750239014,"score_spread":0.2889542979825387,"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."}}