{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01359565,0.0001060681,0.0002948862,0.00001151929,0.0004035881,0.00001091516,0.0003148039,0.0001497235,0.00009656167],"category_scores_gemma":[0.1832446,0.0000420169,0.00006888269,0.000218653,0.0007951979,0.00007650567,0.00008357212,0.000419384,0.000001776328],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002418023,"about_ca_system_score_gemma":0.01517995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000964178,"about_ca_topic_score_gemma":0.0001330726,"domain_scores_codex":[0.9965059,0.0002946754,0.001286813,0.0004141986,0.001314343,0.0001840948],"domain_scores_gemma":[0.9939997,0.001521586,0.001881466,0.001449353,0.001010883,0.0001369997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001330631,0.0006062959,0.8362368,0.0001110398,0.0001634437,0.00000122496,0.00981451,0.000003197894,0.0003770191,0.00008528051,0.023518,0.1289501],"study_design_scores_gemma":[0.0001961286,0.00004394742,0.964619,0.0003321937,0.0000751121,0.0001598392,0.004781643,0.0003112407,0.0005947817,0.0001886159,0.02864423,0.00005325223],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9287852,0.004432973,0.00002162181,0.06449377,0.001495175,0.0002871392,1.755026e-7,0.0000121688,0.0004717826],"genre_scores_gemma":[0.9946119,0.001344046,0.0008045997,0.001719559,0.001104499,0.00006228345,0.000009633293,0.000005968865,0.0003374887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1696489,"threshold_uncertainty_score":0.9904031,"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."}}