{"id":"W4402905749","doi":"10.1167/jov.24.10.1317","title":"Fast-tracking improvements of metacognitive assessments of visual working memory","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Metacognition; Tracking (education); Cognitive psychology; Psychology; Eye tracking; Computer science; Artificial intelligence; Cognition; Neuroscience; Pedagogy","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":[0.000725607,0.0004766001,0.0004721889,0.0002785659,0.0001039656,0.0003575665,0.0003839682,0.0003197278,0.002599511],"category_scores_gemma":[0.003408105,0.0001984561,0.0002169133,0.0001520427,0.0001559154,0.0005393405,0.0006491848,0.0008972492,0.0004308478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001281595,"about_ca_system_score_gemma":0.0002497554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000664472,"about_ca_topic_score_gemma":0.001119386,"domain_scores_codex":[0.9996647,0.00004562999,0.00003242725,0.0001117344,0.00009132516,0.00005425283],"domain_scores_gemma":[0.9986595,0.0003764784,0.0003544408,0.0002462356,0.0002271773,0.0001362298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.003853203,0.002760788,0.01765533,0.0004918043,0.0001004375,0.00006326703,0.0007105283,0.001536608,0.7370683,0.0002379376,0.001032946,0.2344889],"study_design_scores_gemma":[0.0007505323,0.02461942,0.4917469,0.0001490959,0.0002793266,0.0004439117,0.0003724248,0.02262049,0.4511597,0.001884171,0.005824815,0.0001492806],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9857126,0.0003186574,0.01256027,0.0000510535,0.00004659885,0.00006754066,0.0001950507,0.0002051758,0.0008429521],"genre_scores_gemma":[0.9880708,0.0002104425,0.009569429,0.00003628854,0.00002482971,0.0001670423,0.0002958009,0.000029674,0.001595528],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002599511,"threshold_uncertainty_score":0.008696198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03092453816892759,"score_gpt":0.3590619516079246,"score_spread":0.328137413438997,"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."}}