{"id":"W799664100","doi":"10.1017/cbo9780511996276.006","title":"Putting It All Together: Cognitive Models to Inform the Design and Development of Large-Scale Educational Assessment","year":2011,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Scale (ratio); Cognition; Computer science; Psychology; Cognitive science; Geography; Neuroscience; Cartography","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":[0.02961772,0.001133395,0.0007304567,0.003694515,0.001071062,0.009659276,0.002985788,0.001680565,0.004844363],"category_scores_gemma":[0.1145398,0.0008046799,0.001069274,0.002123689,0.002892956,0.01014454,0.004046937,0.003419926,0.0009439785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004010179,"about_ca_system_score_gemma":0.004905724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004003962,"about_ca_topic_score_gemma":0.007588605,"domain_scores_codex":[0.981937,0.01265053,0.001003762,0.001016744,0.003091411,0.0003005219],"domain_scores_gemma":[0.9208564,0.05733745,0.003728118,0.006723995,0.01003054,0.001323547],"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":[0.0002178446,0.0008539101,0.0210686,0.001671721,0.0002579999,0.0003175928,0.01755332,0.06319107,0.004509479,0.3293318,0.01075796,0.5502687],"study_design_scores_gemma":[0.0001770402,0.0007176824,0.01062853,0.002842693,0.0001974286,0.0002937183,0.007672831,0.4069595,0.005645755,0.4778816,0.08671737,0.0002659414],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.021389,0.0008257748,0.959196,0.002569004,0.0001235938,0.001567982,0.0002192482,0.001428632,0.01268084],"genre_scores_gemma":[0.1190559,0.0003333589,0.8775455,0.0002726005,0.00002185129,0.001596257,0.0002380838,0.0001255832,0.0008109082],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02961772,"threshold_uncertainty_score":0.1566354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1396910555132541,"score_gpt":0.3343148166578936,"score_spread":0.1946237611446395,"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."}}