{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03964259,0.001035428,0.001418287,0.003099415,0.0005250961,0.001521105,0.001678885,0.001125457,0.001857446],"category_scores_gemma":[0.1131489,0.0005403416,0.0008575427,0.002082913,0.000981523,0.001810733,0.001349593,0.001774012,0.0004709092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009587625,"about_ca_system_score_gemma":0.001662758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001755182,"about_ca_topic_score_gemma":0.003218368,"domain_scores_codex":[0.9770939,0.01822634,0.001024304,0.001243223,0.002126922,0.0002853375],"domain_scores_gemma":[0.8586547,0.1240624,0.00521726,0.003905155,0.007043929,0.001116461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001533262,0.00128397,0.1409973,0.0004133955,0.000641449,0.0001023556,0.0008911873,0.08301967,0.004839596,0.003648366,0.001441276,0.7611881],"study_design_scores_gemma":[0.0002591106,0.001281035,0.03628886,0.0001664674,0.000160558,0.00008154375,0.0002111047,0.9466958,0.005813603,0.007769854,0.001178564,0.00009352434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2642927,0.0003310356,0.7316007,0.0003585262,0.00003710019,0.001061494,0.0001137742,0.001059289,0.001145408],"genre_scores_gemma":[0.6008786,0.00007787329,0.3976533,0.0001054348,0.00001785786,0.0007349714,0.0001807098,0.00004276593,0.0003084618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03964259,"threshold_uncertainty_score":0.2096525,"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."}}