{"id":"W2155682078","doi":"10.1191/0265532206lt337oa","title":"How assessing reading comprehension with multiple-choice questions shapes the construct: a cognitive processing perspective","year":2006,"lang":"en","type":"article","venue":"Language Testing","topic":"Reading and Literacy Development","field":"Psychology","cited_by":243,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Construct (python library); Reading comprehension; Psychology; Variety (cybernetics); Comprehension; Cognitive psychology; Cognition; Multiple choice; Perspective (graphical); Test (biology); Reading (process); Selection (genetic algorithm); Task (project management); Computer science; Linguistics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002283761,0.0002434074,0.0002156308,0.0001108192,0.0007084723,0.000548546,0.0001376334,0.00006991483,0.0000238625],"category_scores_gemma":[0.00131618,0.0001635571,0.00003497804,0.0004912741,0.0002089865,0.0003127529,0.00004413012,0.0003785491,0.00001102192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001057574,"about_ca_system_score_gemma":0.00007505581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003125566,"about_ca_topic_score_gemma":0.0002443612,"domain_scores_codex":[0.9984963,0.0001797195,0.000218231,0.0004625499,0.0002217411,0.0004214444],"domain_scores_gemma":[0.9963829,0.00279183,0.0002582659,0.0001552328,0.0003582245,0.00005355005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007025608,0.0002364359,0.6751266,0.0000966199,0.0001497225,0.0006212133,0.1068639,0.00009739653,0.01403943,0.003832681,0.0001840682,0.1986817],"study_design_scores_gemma":[0.001487748,0.0001023093,0.8128787,0.00221474,0.0001468411,0.001063438,0.1757799,0.004787926,0.0003559259,0.0002948716,0.0003223631,0.0005651739],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665036,0.00098653,0.004748041,0.0004993891,0.0001062971,0.0003523188,0.000009116025,0.0004097635,0.02638495],"genre_scores_gemma":[0.983562,1.685733e-7,0.01454108,0.0002099199,0.000345125,0.00005791464,0.00001782621,0.0000418845,0.001224067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1981165,"threshold_uncertainty_score":0.6669666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02646085463337262,"score_gpt":0.3216621472035859,"score_spread":0.2952012925702133,"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."}}