{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001208064,0.00005586563,0.0001221804,0.00008283158,0.00007709688,0.0001634285,0.0002369489,0.00002738282,0.000007501022],"category_scores_gemma":[0.0007202711,0.00004235057,0.0000310785,0.0001588149,0.00001192981,0.0002987338,0.0001423653,0.0001356916,0.000008671809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001619833,"about_ca_system_score_gemma":0.00003146887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003309841,"about_ca_topic_score_gemma":0.000003594807,"domain_scores_codex":[0.9991153,0.0001143862,0.0002602527,0.0001156414,0.0003097923,0.00008465967],"domain_scores_gemma":[0.999295,0.00005634711,0.0001976357,0.0001165239,0.0002112485,0.0001232585],"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":[0.00005868658,0.0002827832,0.01603398,0.00007105894,0.00002820028,0.00001101774,0.001617303,0.002012971,0.01625171,0.0157688,0.005044584,0.9428189],"study_design_scores_gemma":[0.001510895,0.002907289,0.05643649,0.0005019011,0.00002989554,0.000117943,0.00009335536,0.7814354,0.0009407082,0.006140698,0.1495096,0.0003758177],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04500174,0.00001983451,0.9533459,0.001183276,0.0001316493,0.00003795558,3.252499e-7,0.00001459581,0.0002647356],"genre_scores_gemma":[0.9627696,0.000008179238,0.0368203,0.0002498462,0.0001112923,1.502701e-7,6.188176e-7,0.000003381336,0.00003662067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9424431,"threshold_uncertainty_score":0.1727006,"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."}}