{"id":"W2056109249","doi":"10.1080/00016470412331294445","title":"How reliable are reliability studies of fracture classifications?A systematic review of their methodologies","year":2004,"lang":"en","type":"review","venue":"Acta Orthopaedica Scandinavica","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":184,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; McMaster University Medical Centre","funders":"","keywords":"Checklist; Medicine; Reliability (semiconductor); Kappa; Cohen's kappa; MEDLINE; Statistics; Sample size determination; Medical physics; Data mining; Computer science; Mathematics; Psychology; Cognitive psychology","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","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03297559,0.001061327,0.01164354,0.0005983827,0.0002825702,0.0001483779,0.003706552,0.0007016168,0.0001521223],"category_scores_gemma":[0.104112,0.0005488904,0.003017348,0.002986034,0.001245539,0.0004181942,0.0006461345,0.001054215,0.00002738791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005567155,"about_ca_system_score_gemma":0.001083206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001648936,"about_ca_topic_score_gemma":0.00000671254,"domain_scores_codex":[0.9813682,0.005176373,0.006532552,0.001725344,0.004578433,0.0006190836],"domain_scores_gemma":[0.9618553,0.01625462,0.01230188,0.005852583,0.003470611,0.0002650033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000009375584,0.0002024773,0.00006945527,0.9754391,0.0005787341,0.000003351079,0.0001365575,0.000002584139,0.000001095375,0.0001483253,0.008458263,0.01495067],"study_design_scores_gemma":[0.0001255918,0.0001323019,0.00003088827,0.6429625,0.002544132,0.00001207205,0.001014108,4.884353e-7,0.000007906009,0.004710937,0.3480912,0.0003679447],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000005939002,0.9886809,0.0003195693,0.004711944,0.0005466359,0.005126765,0.0002513237,0.00006688498,0.0002900293],"genre_scores_gemma":[0.0004052568,0.9949648,0.002864145,0.0002213549,0.00007818227,0.0007394561,0.00005089731,0.00004831462,0.0006275662],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3396329,"threshold_uncertainty_score":0.9996963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3789064394489871,"score_gpt":0.4667575180918639,"score_spread":0.08785107864287689,"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."}}