{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03044758,0.0003226675,0.001771597,0.001837375,0.00009102435,0.0000532015,0.0006397546,0.00006525166,0.000256214],"category_scores_gemma":[0.4049791,0.0002579547,0.00008965519,0.003536819,0.0007469994,0.0005392751,0.0001580026,0.0004215256,5.339624e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005017404,"about_ca_system_score_gemma":0.0009104765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001829181,"about_ca_topic_score_gemma":0.009592393,"domain_scores_codex":[0.9926838,0.0003299289,0.003552178,0.0006665578,0.002314174,0.0004533836],"domain_scores_gemma":[0.9439557,0.0133617,0.03715153,0.0009498976,0.004450568,0.0001306422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001178182,0.000286452,0.975557,0.003749665,0.0000752417,0.000009161416,0.0004558811,0.000129851,0.0003645621,0.00002078894,0.01705668,0.002282952],"study_design_scores_gemma":[0.006918197,0.0009608941,0.8623604,0.0925782,0.002008632,0.00006466899,0.004398387,0.003768592,0.00060399,0.002024243,0.02261917,0.001694635],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.2384945,0.6784886,0.001863444,0.01808584,0.001526499,0.02688812,0.01666074,0.0004058048,0.01758643],"genre_scores_gemma":[0.8880752,0.08962,0.01544431,0.0001864513,0.0001340599,0.0005588422,0.0004256072,0.0007606905,0.004794884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6495807,"threshold_uncertainty_score":0.9999872,"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."}}