{"id":"W4386560709","doi":"10.1007/s10639-023-12177-7","title":"Validating a novel digital performance-based assessment of data literacy: Psychometric and eye-tracking analyses","year":2023,"lang":"en","type":"article","venue":"Education and Information Technologies","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Eye tracking; Computer science; Educational technology; Literacy; Tracking (education); Digital literacy; Item response theory; Psychology; Psychometrics; Applied psychology; Data science; Mathematics education; Artificial intelligence; Pedagogy; World Wide Web; Clinical psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009002175,0.0001054292,0.0001957835,0.001252974,0.0003552544,0.00007863413,0.0002291977,0.0001420748,0.00001099552],"category_scores_gemma":[0.0009871083,0.00008908578,0.00001255456,0.001656795,0.00005642302,0.004027715,0.0001771467,0.0003115109,0.00001943609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001053069,"about_ca_system_score_gemma":0.0008046957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004126738,"about_ca_topic_score_gemma":0.00000194171,"domain_scores_codex":[0.998589,0.00003652417,0.0007590911,0.0001493867,0.0002008356,0.0002651552],"domain_scores_gemma":[0.9983646,0.0003386901,0.0005700064,0.0004295229,0.0002602495,0.00003687431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000004637967,0.00004114425,0.2377849,0.001683957,0.00001342733,1.094862e-8,0.001405128,0.00001380773,0.0001277059,0.001050159,0.001482974,0.7563922],"study_design_scores_gemma":[0.001237987,0.0002623617,0.6718054,0.001508338,0.00002842837,0.000003325051,0.06021918,0.1500311,0.0003968573,0.0002517376,0.1138827,0.0003725417],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9884588,0.0002778774,0.00449028,0.002268528,0.000399104,0.0006565991,0.00006913646,0.0006591519,0.002720568],"genre_scores_gemma":[0.9946167,0.000609314,0.003865445,0.0001555953,0.00003015447,0.0001170022,0.0005172295,0.000006622919,0.00008191106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7560197,"threshold_uncertainty_score":0.3632813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2076908494660303,"score_gpt":0.5556562711615043,"score_spread":0.347965421695474,"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."}}