{"id":"W2150519824","doi":"10.1080/01421590601032427","title":"Composition of the panel of reference for concordance tests: Do teaching functions have an impact on examinees’ ranks and absolute scores?","year":2007,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Concordance; Ranking (information retrieval); Test (biology); Medicine; Ambiguity; Family medicine; Psychology; Statistics; Mathematics; Computer science; Internal medicine; Artificial intelligence","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":[0.06276204,0.0005617764,0.0008050171,0.002038626,0.0009845486,0.001641829,0.0009403461,0.000935114,0.002105095],"category_scores_gemma":[0.2546383,0.0003601935,0.0006680497,0.001346368,0.001756057,0.001287469,0.001353339,0.0007042113,0.0007857502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00068099,"about_ca_system_score_gemma":0.0009353506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001097078,"about_ca_topic_score_gemma":0.001357073,"domain_scores_codex":[0.9328213,0.0431314,0.003990367,0.004019293,0.01491461,0.001123094],"domain_scores_gemma":[0.7040512,0.227835,0.02626687,0.01728959,0.02014137,0.004416006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001936946,0.0002843807,0.9003624,0.0001754411,0.0003344444,0.0001596773,0.002988628,0.0007385487,0.004796584,0.0002715295,0.000776428,0.08717492],"study_design_scores_gemma":[0.00005120822,0.001239651,0.9866354,0.00009425535,0.0001756944,0.0005669107,0.0008741366,0.002690929,0.006218872,0.0003659301,0.001052783,0.0000343449],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9843482,0.0006360052,0.01171986,0.0002738915,0.00008871582,0.0001381808,0.00009045075,0.00009254293,0.002612206],"genre_scores_gemma":[0.9939429,0.0000665856,0.005475307,0.00004790221,0.00003560218,0.00008895135,0.0001031072,0.00003498443,0.0002048012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06276204,"threshold_uncertainty_score":0.3319213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0828956857860335,"score_gpt":0.4049771565153758,"score_spread":0.3220814707293423,"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."}}