{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02734997,0.0006495494,0.0005401817,0.003295137,0.0005193373,0.007009767,0.001203516,0.001346379,0.001359612],"category_scores_gemma":[0.1107205,0.0005837109,0.0006254528,0.001870962,0.009179497,0.009850972,0.002226168,0.001989328,0.0002381781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001215453,"about_ca_system_score_gemma":0.0007636339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001248842,"about_ca_topic_score_gemma":0.001425639,"domain_scores_codex":[0.9756699,0.018743,0.0005953014,0.001773026,0.002835916,0.0003828058],"domain_scores_gemma":[0.8143643,0.168916,0.007079685,0.005206371,0.003885445,0.0005483833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004850225,0.0008221492,0.1366886,0.00155044,0.00037915,0.0007410812,0.2894248,0.006169616,0.0366003,0.1701212,0.001154344,0.3558632],"study_design_scores_gemma":[0.0001798867,0.001616238,0.2452908,0.001030938,0.0003266637,0.002267285,0.07645,0.04680702,0.03385398,0.5738767,0.01776603,0.0005343136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7053012,0.001653818,0.2672206,0.004521044,0.00006019053,0.0002155796,0.00009362078,0.0002420642,0.0206918],"genre_scores_gemma":[0.9506222,0.0005449234,0.04762226,0.0004274304,0.00004773659,0.0001621682,0.00004708039,0.00005740225,0.0004688047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02734997,"threshold_uncertainty_score":0.1446422,"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."}}