{"id":"W4383227026","doi":"10.31234/osf.io/zc98s","title":"Utilizing Response Time for Scoring the TIMSS 2019 Problem Solving and Inquiry Tasks","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Psychology; Normative; Item response theory; Time limit; Polytomous Rasch model; Mathematics education; Computer science; Psychometrics; Developmental psychology","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":[0.01452484,0.001594566,0.0007887777,0.003436474,0.0005098712,0.001380842,0.001107805,0.0009564128,0.005007319],"category_scores_gemma":[0.06856191,0.0003890855,0.001442645,0.002201713,0.0004779577,0.001551001,0.001198436,0.00139882,0.003980753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009587365,"about_ca_system_score_gemma":0.001555562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00213418,"about_ca_topic_score_gemma":0.005303052,"domain_scores_codex":[0.9833624,0.00655281,0.003179536,0.001605134,0.004846983,0.0004532141],"domain_scores_gemma":[0.9417008,0.02695847,0.01138448,0.004904221,0.0141948,0.0008572847],"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":[0.002829809,0.001807129,0.237693,0.001127167,0.0004267285,0.0002277619,0.002859245,0.015424,0.02921817,0.004450263,0.01666375,0.687273],"study_design_scores_gemma":[0.0005720468,0.006130693,0.7100453,0.0005019795,0.0003131271,0.0009209086,0.001772927,0.142315,0.07584699,0.009316561,0.05148845,0.0007759614],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5848315,0.0003862515,0.3681283,0.0003345321,0.0004705921,0.009268056,0.00655151,0.004601866,0.02542748],"genre_scores_gemma":[0.5981731,0.0004596372,0.3633637,0.0002919376,0.0001386181,0.02159568,0.006479131,0.00073492,0.008763263],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01452484,"threshold_uncertainty_score":0.07681555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2003486351706198,"score_gpt":0.4571740379790052,"score_spread":0.2568254028083853,"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."}}