{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004180037,0.0001423715,0.0001714765,0.00009318678,0.000818818,0.0003327182,0.0003716655,0.0001830754,0.0001789348],"category_scores_gemma":[0.0003209733,0.0001104971,0.00007792346,0.0001127705,0.0002067415,0.0001120797,0.000435298,0.0002749186,0.00007716673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001018919,"about_ca_system_score_gemma":0.001116454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002409616,"about_ca_topic_score_gemma":0.001098908,"domain_scores_codex":[0.9984795,0.0003169663,0.0002232619,0.0003694766,0.0002843249,0.0003264666],"domain_scores_gemma":[0.9969269,0.002533369,0.0001324513,0.0002112136,0.0001238031,0.00007225326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006000264,0.000157599,0.01979177,0.0006230465,0.0004127188,0.000004710954,0.4275467,0.0004435698,0.001430036,0.16686,0.3582541,0.02387577],"study_design_scores_gemma":[0.0007291357,0.0001580528,0.05120072,0.001163003,0.0002538742,0.000002731271,0.2330178,0.002857257,0.0001498212,0.2683721,0.4403582,0.001737288],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7742717,0.001449788,0.002887266,0.131886,0.006912867,0.005872212,0.0001118586,0.0009213077,0.07568695],"genre_scores_gemma":[0.5902143,0.0007108826,0.0140349,0.0006393777,0.005038729,0.0006962933,0.0001640809,0.0001033567,0.3883981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3127112,"threshold_uncertainty_score":0.6297768,"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."}}