{"id":"W2035397104","doi":"10.1046/j.1365-2923.2001.00005.x","title":"The reproducibility of assessing radiological reporting: studies from the development of the General Medical Council’s Performance Procedures","year":2001,"lang":"en","type":"article","venue":"Medical Education","topic":"Radiology practices and education","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Protocol (science); Generalizability theory; Radiological weapon; Reliability (semiconductor); Reproducibility; Medical physics; Sample (material); Cohen's kappa; Medicine; Medical education; Psychology; Computer science; Statistics; Radiology; Alternative medicine; 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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3745455,0.0007917213,0.0009326088,0.002361204,0.001376255,0.002277906,0.003340113,0.00169271,0.00142969],"category_scores_gemma":[0.6962891,0.001109387,0.001871491,0.002569043,0.005336466,0.002414734,0.003127558,0.001589627,0.0005472536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002804467,"about_ca_system_score_gemma":0.003332174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003710745,"about_ca_topic_score_gemma":0.004377653,"domain_scores_codex":[0.510105,0.3503423,0.03908037,0.01402753,0.08484513,0.001599613],"domain_scores_gemma":[0.1158287,0.6898404,0.07042459,0.05565017,0.06727812,0.0009779994],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.007265075,0.00113698,0.5905848,0.008853459,0.005846307,0.000235303,0.04474227,0.003010741,0.004525735,0.003001742,0.003302587,0.3274949],"study_design_scores_gemma":[0.0007670798,0.009994258,0.9434096,0.003469946,0.00210839,0.001142282,0.005893417,0.00601929,0.009627403,0.002153649,0.01509274,0.000321915],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8807129,0.01537582,0.07822184,0.001316632,0.0008430651,0.004140525,0.000579468,0.0002188191,0.01859092],"genre_scores_gemma":[0.9757408,0.001132197,0.02026807,0.0004201971,0.0002955276,0.001171961,0.0003112963,0.0001333364,0.0005265501],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6254545,"threshold_uncertainty_score":0.7712968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1568577815366753,"score_gpt":0.4327873194181923,"score_spread":0.275929537881517,"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."}}