{"id":"W4388574245","doi":"10.1111/jedm.12380","title":"Incorporating Test‐Taking Engagement into Multistage Adaptive Testing Design for Large‐Scale Assessments","year":2023,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Operationalization; Computerized adaptive testing; Test (biology); Item response theory; Premise; Scale (ratio); Computer science; Test design; Reliability (semiconductor); Psychology; Applied psychology; Reliability engineering; Psychometrics; Statistics; Test method; Mathematics; Engineering; Clinical 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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05667346,0.0001905845,0.0004038898,0.0009897898,0.0006091819,0.0002646892,0.0007596324,0.00005671128,0.0001024974],"category_scores_gemma":[0.3496663,0.0001461823,0.0001706395,0.002572598,0.00003266046,0.0003834127,0.0001349397,0.0002986209,0.00002728157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005020077,"about_ca_system_score_gemma":0.001058621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001080212,"about_ca_topic_score_gemma":0.00000762559,"domain_scores_codex":[0.9934541,0.0008953885,0.001609396,0.0003814826,0.003267982,0.0003916512],"domain_scores_gemma":[0.9104707,0.08028877,0.003507366,0.0003349282,0.005177811,0.0002204175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002539931,0.001599948,0.6261827,0.00008904078,0.0003316661,0.00001809686,0.003654623,0.02319495,0.03623732,0.002528484,0.05043581,0.2554734],"study_design_scores_gemma":[0.002373858,0.001847803,0.6918802,0.0006326229,0.0001087484,0.0000441738,0.01641327,0.07280599,0.001679935,0.2075657,0.004099534,0.0005481233],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07395511,0.0003500554,0.9180561,0.002275494,0.003142479,0.0007315764,0.00001534141,0.00003264646,0.001441255],"genre_scores_gemma":[0.5209432,0.000002339123,0.4783773,0.00007950716,0.0004355258,0.00003613986,0.000001157821,0.00001195869,0.0001128372],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4469881,"threshold_uncertainty_score":0.9713532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8135852760237042,"score_gpt":0.547201763889805,"score_spread":0.2663835121338992,"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."}}