{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2000522,0.002455302,0.01332747,0.04295803,0.001532311,0.006696551,0.004301916,0.003177488,0.002348659],"category_scores_gemma":[0.567561,0.003434378,0.009043014,0.03072335,0.004006998,0.007064508,0.003192738,0.0018513,0.0004981706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00899259,"about_ca_system_score_gemma":0.01943693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006185446,"about_ca_topic_score_gemma":0.01492492,"domain_scores_codex":[0.73967,0.1309018,0.0949955,0.007031734,0.02632609,0.001074927],"domain_scores_gemma":[0.3918552,0.4947405,0.05963368,0.0110642,0.04152505,0.001181284],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0003178183,0.00002557815,0.003968664,0.8149716,0.0104904,0.0001523745,0.001254927,0.0001678559,0.0002296545,0.0009109087,0.0020166,0.1654936],"study_design_scores_gemma":[0.000392602,0.0003169277,0.01146131,0.9119914,0.04849047,0.0006546277,0.001488678,0.0002644461,0.0004330272,0.00225651,0.02214209,0.0001079346],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00196058,0.9918207,0.002824452,0.0009367202,0.0002908053,0.001258829,0.000449117,0.00002289672,0.0004359272],"genre_scores_gemma":[0.04689759,0.9183223,0.02430459,0.0008819983,0.0003143168,0.008404923,0.0006447216,0.00003620523,0.0001932008],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7999478,"threshold_uncertainty_score":0.986478,"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."}}