{"id":"W2111648217","doi":"10.1111/j.1745-3992.2010.00181.x","title":"Developing Score Reports for Cognitive Diagnostic Assessments","year":2010,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Context (archaeology); Test (biology); Cognition; Diagnostic test; Hierarchy; Sample (material); Knowledge management; Data science; Psychology; Medicine","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":[0.08867823,0.002530017,0.00129406,0.02205593,0.001668036,0.00711185,0.003859992,0.001358146,0.00504693],"category_scores_gemma":[0.305648,0.0008466556,0.001797102,0.008175002,0.00175423,0.007168976,0.006005995,0.003022376,0.004346006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002569259,"about_ca_system_score_gemma":0.005630372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002391073,"about_ca_topic_score_gemma":0.002214763,"domain_scores_codex":[0.9008323,0.04256547,0.02196205,0.003385955,0.03004692,0.001207244],"domain_scores_gemma":[0.6628904,0.1465306,0.04205452,0.03220217,0.1138915,0.002430704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002417405,0.0002550644,0.02172922,0.001580567,0.0002010163,0.0003294584,0.005794339,0.006138311,0.004438039,0.09379523,0.04053209,0.8249649],"study_design_scores_gemma":[0.0003037456,0.00186447,0.03160755,0.005506775,0.0005169026,0.002657851,0.01169946,0.06775048,0.05689533,0.2650497,0.5551157,0.001031999],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009347145,0.0005963463,0.9661033,0.001167269,0.000483208,0.002588215,0.003194943,0.00552154,0.01099807],"genre_scores_gemma":[0.03763359,0.0004668282,0.9527227,0.0001775485,0.0001881627,0.003387114,0.003506862,0.0005264683,0.001390864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08867823,"threshold_uncertainty_score":0.4689809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.165780093144807,"score_gpt":0.4552123800807414,"score_spread":0.2894322869359344,"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."}}