{"id":"W1978227392","doi":"10.1080/09695940903565362","title":"Teacher beliefs about the cognitive diagnostic information of classroom‐ versus large‐scale tests: implications for assessment literacy","year":2010,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Smiths Detection (Canada); University of Alberta","funders":"","keywords":"Test (biology); Mathematics education; Scale (ratio); Psychology; Literacy; Pedagogy","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":[0.01806175,0.0001351053,0.0003152725,0.0008998394,0.0007124273,0.002100859,0.0003819063,0.0005893644,0.001641075],"category_scores_gemma":[0.09956048,0.0001864146,0.0002370216,0.0005637105,0.002684751,0.00167242,0.001195022,0.001235263,0.0002026775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001463088,"about_ca_system_score_gemma":0.002002553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004040514,"about_ca_topic_score_gemma":0.005678851,"domain_scores_codex":[0.9862849,0.009205063,0.0006611623,0.0005382682,0.002781196,0.0005295246],"domain_scores_gemma":[0.8462662,0.1257316,0.01490018,0.002664201,0.007589693,0.002848247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003199617,0.000556424,0.8799813,0.0001750006,0.00004423654,0.0002092822,0.05179688,0.0001787413,0.001265468,0.002176912,0.0004372369,0.06285856],"study_design_scores_gemma":[0.00005866946,0.0009721441,0.9119956,0.0004627797,0.00007213419,0.0003476619,0.07655937,0.001305666,0.001896404,0.003248692,0.003044775,0.00003611574],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918861,0.0002430131,0.001165182,0.001953559,0.000009878112,0.00003279307,0.00001531575,0.000005557,0.004688581],"genre_scores_gemma":[0.9993843,0.00008268609,0.0002588815,0.0001090259,0.000004612682,0.00001385766,0.000006010136,0.000001405375,0.0001392302],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01806175,"threshold_uncertainty_score":0.09552073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05055241862711323,"score_gpt":0.48032179247732,"score_spread":0.4297693738502068,"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."}}