{"id":"W4246712556","doi":"10.1037//0096-3445.130.2.208","title":"Using working memory theory to investigate the construct validity of multiple-choice reading comprehension tests such as the SAT.","year":2001,"lang":"en","type":"article","venue":"Journal of Experimental Psychology General","topic":"Reading and Literacy Development","field":"Psychology","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reading (process); Reading comprehension; Construct (python library); Test (biology); Construct validity; Psychology; Cognitive psychology; Comprehension; Test theory; Computer science; Working memory; Range (aeronautics); Developmental psychology; Psychometrics; Linguistics; Cognition","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":[0.001848771,0.0002882752,0.0004649648,0.0002266646,0.0003706717,0.00004737374,0.0006634349,0.0001548609,0.0003293026],"category_scores_gemma":[0.0002747951,0.0001765656,0.0002134914,0.000356589,0.0005034463,0.0001108425,0.0001244923,0.0006554407,0.00003509638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001117699,"about_ca_system_score_gemma":0.00006773785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078388,"about_ca_topic_score_gemma":0.000004660682,"domain_scores_codex":[0.9963762,0.001463455,0.0009985829,0.0003420492,0.0003595231,0.0004601886],"domain_scores_gemma":[0.9969808,0.001385265,0.0007613543,0.0005439044,0.0001324666,0.0001962421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001300397,0.0003860694,0.1844402,0.000004334285,0.0003774757,0.0001930975,0.02224256,0.0003540667,0.7766461,0.001355997,0.006327517,0.006372243],"study_design_scores_gemma":[0.01157811,0.002681168,0.6877335,0.0009309523,0.0003459548,0.03027279,0.02411507,0.0004227574,0.1634771,0.004872402,0.07203825,0.001531913],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885234,0.001222465,0.0003245163,0.001014572,0.004073,0.0002851911,0.000002226288,0.00001679468,0.004537894],"genre_scores_gemma":[0.9883782,0.00001872841,0.004865223,0.005487664,0.0007583988,0.000009353987,0.000002322279,0.00003512674,0.0004449845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.613169,"threshold_uncertainty_score":0.7200136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1440028474734239,"score_gpt":0.4223863955469895,"score_spread":0.2783835480735656,"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."}}