{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001248478,0.0001041904,0.0002857032,0.0003197248,0.00004196257,0.0001132392,0.0003317857,0.00004386825,0.000009488374],"category_scores_gemma":[0.00005835743,0.00007973399,0.000189946,0.0002929424,0.00001768068,0.0006901092,0.0001335811,0.0002724523,0.000003922313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005860785,"about_ca_system_score_gemma":0.0000951078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001014504,"about_ca_topic_score_gemma":3.549072e-7,"domain_scores_codex":[0.9982688,0.0001071976,0.0006854258,0.0001506984,0.0006412267,0.000146582],"domain_scores_gemma":[0.998652,0.0001759462,0.0006429641,0.0001005172,0.0003811049,0.00004744527],"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":[0.00002813063,0.0001555332,0.001007754,0.0001684164,0.0002601495,0.00009342325,0.001547447,0.0004065023,0.2641893,0.005226165,0.00003151872,0.7268857],"study_design_scores_gemma":[0.002012121,0.01006356,0.05991175,0.0312679,0.0003497617,0.0002902559,0.005063805,0.09300949,0.7798517,0.002263678,0.0150272,0.0008887979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3753585,0.001611458,0.6189605,0.00004558727,0.002530502,0.0001006615,6.959751e-7,0.00001912352,0.001372983],"genre_scores_gemma":[0.9915833,0.00003907027,0.007713368,0.00001231055,0.0001917966,4.218852e-7,1.869169e-7,0.000009491731,0.0004499994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7259969,"threshold_uncertainty_score":0.3251458,"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."}}