{"id":"W4387762598","doi":"10.1016/j.stueduc.2023.101309","title":"Predicting reading comprehension performance based on student characteristics and item properties","year":2023,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Reading and Literacy Development","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of Alberta","funders":"","keywords":"Reading comprehension; Reading (process); Affect (linguistics); Test (biology); Psychology; Multilingualism; Comprehension; Mathematics education; Cognition; Computer science; Cognitive psychology; Linguistics; Pedagogy; Communication","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":[0.001338717,0.0001089857,0.0001383054,0.0002458255,0.0001994944,0.00002172224,0.00005683206,0.00003223302,0.00004950771],"category_scores_gemma":[0.0005188575,0.0000939316,0.00001291123,0.0002656982,0.00006100549,0.00006866206,0.00003655904,0.0001005409,0.00008430984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002318369,"about_ca_system_score_gemma":0.00008675364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007174378,"about_ca_topic_score_gemma":0.000001964018,"domain_scores_codex":[0.9986784,0.0001619421,0.0003051885,0.0002656367,0.0004206934,0.0001681073],"domain_scores_gemma":[0.9990157,0.0005091775,0.00009852648,0.0001287471,0.0002237388,0.00002413723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005881385,0.0001586625,0.921593,0.00009146996,0.00005017628,8.027949e-7,0.04995685,0.0009177314,0.00009736781,0.0003183778,0.001394798,0.025362],"study_design_scores_gemma":[0.0003665015,0.00006350585,0.9583269,0.0004408898,0.00001523455,0.00000188112,0.005471965,0.03480263,0.00001448093,0.0000793892,0.0003198937,0.00009674886],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940193,0.0002625234,0.000001596245,0.001089198,0.001974434,0.0003907902,0.000002570505,0.00003937833,0.002220192],"genre_scores_gemma":[0.9978892,0.00008728525,0.0001092668,0.000160591,0.0002051288,0.0004802535,0.00007674286,0.00001075467,0.000980768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04448488,"threshold_uncertainty_score":0.3830419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1548524743564766,"score_gpt":0.4384727952419538,"score_spread":0.2836203208854772,"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."}}