{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01158183,0.0005338567,0.0004569031,0.002007617,0.0006144339,0.002233575,0.0007396255,0.001210544,0.002029072],"category_scores_gemma":[0.03307193,0.0003157841,0.001025446,0.001148024,0.0007368104,0.002182559,0.002162054,0.0009924939,0.0007164386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009110416,"about_ca_system_score_gemma":0.001438053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001969887,"about_ca_topic_score_gemma":0.003323472,"domain_scores_codex":[0.9907478,0.002708781,0.001606187,0.001199737,0.003400295,0.0003371503],"domain_scores_gemma":[0.9625898,0.01808514,0.006486577,0.00238135,0.009421314,0.001035847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001328178,0.004355577,0.815694,0.0004815604,0.0004131712,0.00009638889,0.002587145,0.001720769,0.01306932,0.00127515,0.001817293,0.1571614],"study_design_scores_gemma":[0.0002538507,0.0062979,0.9593679,0.0002006964,0.0003269706,0.0004676617,0.001843118,0.009754322,0.01480747,0.001067069,0.005502312,0.0001107003],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.977515,0.0001429395,0.01291864,0.0002160409,0.00005815582,0.001141531,0.0007727969,0.0001605121,0.007074375],"genre_scores_gemma":[0.9660234,0.0001694415,0.02802097,0.0003143499,0.00004061433,0.001717226,0.001098297,0.00004070429,0.002575011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01158183,"threshold_uncertainty_score":0.06125134,"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."}}