{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01085804,0.001013867,0.0005908154,0.003529397,0.0004170885,0.002040679,0.0009504727,0.001004889,0.002593878],"category_scores_gemma":[0.05847776,0.0003345936,0.001380746,0.002307812,0.002141214,0.002975426,0.001871224,0.002528808,0.0006801388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004625,"about_ca_system_score_gemma":0.00123433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002249778,"about_ca_topic_score_gemma":0.001616466,"domain_scores_codex":[0.9964092,0.002240594,0.0001806889,0.0003876775,0.000651794,0.0001300585],"domain_scores_gemma":[0.9273993,0.06118962,0.004887344,0.003054667,0.002772987,0.0006959594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008799492,0.004545953,0.4816545,0.001074209,0.00252177,0.0009943593,0.01356204,0.008379879,0.00522369,0.183742,0.005453937,0.2919677],"study_design_scores_gemma":[0.001112934,0.007636704,0.4724042,0.00112639,0.001764128,0.003228655,0.009937425,0.07201649,0.0114415,0.3945544,0.02448368,0.0002935218],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8103175,0.004931571,0.1429244,0.003824215,0.0005415209,0.0006307247,0.0006870273,0.0001791027,0.03596383],"genre_scores_gemma":[0.9622537,0.0017199,0.03107291,0.0008123526,0.0001387785,0.0007647448,0.0005876091,0.00002549297,0.002624478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01085804,"threshold_uncertainty_score":0.05742353,"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."}}