{"id":"W2086203028","doi":"10.1080/10627190802602384","title":"Identifying Potential Test Item Misalignment Using Student Verbal Reports","year":2008,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Educational Strategies and Epistemologies","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of Alberta","funders":"","keywords":"Ambiguity; Psychology; Cognition; Construct (python library); Test (biology); Item analysis; Confidence interval; Cognitive psychology; Applied psychology; Psychometrics; Statistics; Developmental psychology; Computer science; Mathematics","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":[0.05404278,0.0009933667,0.001154457,0.004345702,0.0004572688,0.003007892,0.001043239,0.0007894047,0.00100204],"category_scores_gemma":[0.3248609,0.0004942814,0.0006451857,0.003979544,0.0009466823,0.002374246,0.002074054,0.001084017,0.0003525895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006401995,"about_ca_system_score_gemma":0.0008559712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004899047,"about_ca_topic_score_gemma":0.0005945046,"domain_scores_codex":[0.9312668,0.03541249,0.01432599,0.002643793,0.01551628,0.0008344899],"domain_scores_gemma":[0.5858323,0.2939548,0.07054771,0.02123011,0.02727257,0.001162469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001338268,0.0004583326,0.7828666,0.0006248938,0.0004159256,0.0006908351,0.01089888,0.002349365,0.007441176,0.001720978,0.0007234465,0.1904713],"study_design_scores_gemma":[0.0001534656,0.004153951,0.8740264,0.0009243317,0.0004846578,0.003218679,0.01457736,0.046421,0.03994861,0.009946895,0.005823719,0.00032084],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9472997,0.0003707129,0.04944824,0.0001477177,0.00007271369,0.000431522,0.0002037751,0.0001930848,0.001832506],"genre_scores_gemma":[0.9745072,0.0001553443,0.02415849,0.00006773815,0.00003572717,0.0004420841,0.0003155747,0.00003492233,0.0002829187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05404278,"threshold_uncertainty_score":0.2858089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08693562939927937,"score_gpt":0.4388979660022925,"score_spread":0.3519623366030131,"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."}}