{"id":"W6910466240","doi":"10.48448/g86p-w039","title":"Association of Peer Review with Completeness of Reporting, Transparency for Risk of Bias, and Spin in Diagnostic Test Accuracy Studies Published in Imaging Journals","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Diagnostic accuracy; Transparency (behavior); Diagnostic test; Wilcoxon signed-rank test; Completeness (order theory); Test (biology); Medical imaging","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6583874,0.001193028,0.005013007,0.01487177,0.004629997,0.01450364,0.004973821,0.004704915,0.005232496],"category_scores_gemma":[0.9073446,0.002057742,0.005628322,0.02065682,0.01085446,0.01313617,0.009494359,0.004005068,0.0008431656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005765618,"about_ca_system_score_gemma":0.018868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002088714,"about_ca_topic_score_gemma":0.002294625,"domain_scores_codex":[0.1299341,0.4466379,0.3005514,0.02538866,0.09386297,0.003624924],"domain_scores_gemma":[0.01761625,0.6046241,0.2576133,0.06113233,0.05713255,0.00188159],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.008613952,0.0005492418,0.6806002,0.06001281,0.01923064,0.000773591,0.03036493,0.001517114,0.001003561,0.01019743,0.0125632,0.1745734],"study_design_scores_gemma":[0.004734589,0.005154441,0.7403277,0.06581543,0.01993799,0.005261015,0.01419529,0.01583076,0.006090732,0.05659289,0.06420437,0.001854888],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.449462,0.1798702,0.2158356,0.04148549,0.01037381,0.05712955,0.01324935,0.001283458,0.03131065],"genre_scores_gemma":[0.9092956,0.00639635,0.05897251,0.002469993,0.002432397,0.0178218,0.001437081,0.0003032196,0.0008710483],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3416126,"threshold_uncertainty_score":0.4212692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1062266965168701,"score_gpt":0.4020198503162805,"score_spread":0.2957931537994104,"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."}}