{"id":"W4384942374","doi":"10.1186/s40536-023-00177-5","title":"Incorporating test-taking engagement into the item selection algorithm in low-stakes computerized adaptive tests","year":2023,"lang":"en","type":"article","venue":"Large-scale Assessments in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computerized adaptive testing; Test (biology); Selection (genetic algorithm); Psychology; Computer science; Trait; Machine learning; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01407781,0.000213548,0.0003393969,0.001265616,0.0004059202,0.0003604055,0.0007245248,0.0001067016,0.00004951039],"category_scores_gemma":[0.02325436,0.000160615,0.00006336316,0.00912062,0.00005017805,0.0005403825,0.0002808244,0.0005002024,0.00004263187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000397177,"about_ca_system_score_gemma":0.000406474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003796664,"about_ca_topic_score_gemma":0.0004709535,"domain_scores_codex":[0.995218,0.001500358,0.001047131,0.0007287934,0.001030548,0.0004751189],"domain_scores_gemma":[0.9764963,0.02179012,0.0008792846,0.0004760729,0.0002884004,0.00006980212],"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":[0.000006795857,0.000335582,0.467436,0.000007495893,0.000006207496,0.000002244031,0.002794293,0.0009741139,0.0002856888,0.0001810277,0.0004704804,0.5275],"study_design_scores_gemma":[0.0003787735,0.00007571436,0.6898748,0.0001148638,0.000004088748,0.000002052246,0.01880105,0.274985,0.00007480349,0.01492445,0.0006138769,0.0001504761],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8694857,0.00008672995,0.123967,0.0006881715,0.002685391,0.0007779659,0.000006555131,0.0001475382,0.002154988],"genre_scores_gemma":[0.7597377,0.00001795944,0.2393305,0.000209192,0.0002083132,0.0001912189,0.00002429381,0.00001715325,0.0002636486],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5273496,"threshold_uncertainty_score":0.9849732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2262113854356192,"score_gpt":0.4864308640796258,"score_spread":0.2602194786440065,"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."}}