{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002766606,0.0001561551,0.0001699181,0.0002073317,0.0006982924,0.0003364245,0.0003034465,0.0001319997,0.00006552644],"category_scores_gemma":[0.01135278,0.0001374429,0.00005792285,0.0005444637,0.0002056598,0.002331659,0.00009863017,0.0004452426,0.000006438774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002192161,"about_ca_system_score_gemma":0.00280768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001537609,"about_ca_topic_score_gemma":0.002459566,"domain_scores_codex":[0.9981667,0.000408867,0.0005237744,0.0002166098,0.0003367128,0.0003472974],"domain_scores_gemma":[0.9828265,0.01552949,0.0006018049,0.0002712926,0.0006609694,0.0001100038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00008061616,0.001351589,0.1726081,0.00004318819,0.00006532221,5.765668e-8,0.05189255,0.000003925003,0.00007360176,0.7408808,0.0008353708,0.03216486],"study_design_scores_gemma":[0.0008289103,0.00007522754,0.6145263,0.00003505056,0.00008254273,0.000001276393,0.05829775,0.00004811789,0.00000421243,0.002400313,0.3235689,0.0001314548],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5479867,0.0002252819,0.00292921,0.1355857,0.002199988,0.004179873,0.0002059455,0.00008172852,0.3066056],"genre_scores_gemma":[0.9870275,0.0009119121,0.008294825,0.001265766,0.0007343136,0.001030403,0.0001699097,0.00001185452,0.0005534856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7384805,"threshold_uncertainty_score":0.996975,"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."}}