{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04193265,0.0001091956,0.00046253,0.00006167461,0.0000777147,0.000005972625,0.0002481384,0.0001049822,0.00002549311],"category_scores_gemma":[0.1803841,0.00003849049,0.0002677789,0.0003165813,0.0004920907,0.0003737247,0.0001046345,0.0007424644,2.708543e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006868143,"about_ca_system_score_gemma":0.0005735859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001225295,"about_ca_topic_score_gemma":0.0001054615,"domain_scores_codex":[0.9899116,0.004067724,0.00426646,0.0001585543,0.001500131,0.00009552727],"domain_scores_gemma":[0.9578929,0.0322155,0.007977996,0.0005534992,0.001315578,0.00004454703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0216571,0.003311957,0.145952,0.0007683632,0.0003954356,0.00000106262,0.01250005,0.0001596396,0.0107872,0.0006826263,0.0001150654,0.8036695],"study_design_scores_gemma":[0.01074611,0.001290862,0.971691,0.001049054,0.00161905,0.00001810563,0.002721203,0.002251013,0.005695072,0.00261751,0.0002432721,0.00005779088],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851202,0.0001486015,0.0006427122,0.01173787,0.0006240013,0.001527701,0.000001587134,0.000001194463,0.0001960793],"genre_scores_gemma":[0.9918697,0.0001563675,0.007468767,0.0004149929,0.0000678615,0.000009776022,8.02083e-7,0.000007802423,0.000003954397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.825739,"threshold_uncertainty_score":0.986532,"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."}}