{"id":"W1917342880","doi":"10.1111/j.1365-2753.2011.01649.x","title":"Development of a Farsi translation of the AGREE instrument, and the effects of group discussion on improving the reliability of the scores","year":2011,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Ministry of Health and Medical Education","keywords":"Reliability (semiconductor); Fluency; Guideline; Psychology; Class (philosophy); Natural language processing; Medicine; Computer science; Artificial intelligence; Mathematics education; Pathology","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":[0.1231008,0.0009451683,0.00104814,0.00394328,0.001206336,0.002012495,0.00125019,0.0008345402,0.004377429],"category_scores_gemma":[0.2231371,0.000764265,0.002072608,0.002819741,0.001469763,0.002015942,0.002471235,0.001638819,0.00105349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002048974,"about_ca_system_score_gemma":0.006799705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001185426,"about_ca_topic_score_gemma":0.002827262,"domain_scores_codex":[0.9064229,0.05863419,0.01485398,0.001945296,0.01703894,0.001104783],"domain_scores_gemma":[0.7826955,0.1086715,0.0175343,0.01363451,0.07575206,0.001712235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001898858,0.002133057,0.1742617,0.003978335,0.0003944514,0.000392727,0.0223442,0.002524297,0.009950953,0.006087973,0.01651617,0.7595174],"study_design_scores_gemma":[0.00260077,0.01485743,0.7584208,0.007139969,0.0009805744,0.001833828,0.0292825,0.02631334,0.03992963,0.0171373,0.1007299,0.0007738376],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6964128,0.001596282,0.2182333,0.003976587,0.001320971,0.04995014,0.003120462,0.001004155,0.02438532],"genre_scores_gemma":[0.3864197,0.0006504525,0.5423539,0.0005586709,0.0001696857,0.06595728,0.001651086,0.0002807426,0.001958437],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1231008,"threshold_uncertainty_score":0.6510268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2709013351580075,"score_gpt":0.507067147106021,"score_spread":0.2361658119480135,"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."}}