{"id":"W2015957719","doi":"10.1002/jrsm.41","title":"Reliability and validity of three quality rating instruments for systematic reviews of observational studies","year":2011,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":172,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Observational study; Intraclass correlation; Reliability (semiconductor); Validity; Inter-rater reliability; Rating scale; Sign (mathematics); Statistics; Psychology; Medicine; Clinical psychology; Psychometrics; Mathematics; Physics","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8087921,0.0002438605,0.007864277,0.0003951731,0.0002196585,0.00008880193,0.001474592,0.00009546765,0.0007492912],"category_scores_gemma":[0.8840745,0.000111877,0.001442443,0.001342688,0.0004512875,0.0002822269,0.0003930293,0.0001596035,0.00002149129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005588288,"about_ca_system_score_gemma":0.0001114482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000384255,"about_ca_topic_score_gemma":0.0000224045,"domain_scores_codex":[0.5890741,0.366683,0.03072841,0.001930612,0.01090412,0.0006796982],"domain_scores_gemma":[0.1892415,0.7585156,0.02201451,0.01058866,0.01923829,0.0004014155],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000185965,0.0008039449,0.3942699,0.3074568,0.002673974,6.421349e-7,0.008264499,0.000008647678,0.01198852,0.05010824,0.004045944,0.2201929],"study_design_scores_gemma":[0.0005196415,0.0004694738,0.318418,0.01394123,0.00139547,0.000004573428,0.01137795,0.01290175,0.04205131,0.5954186,0.002810207,0.0006917478],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6903123,0.005514963,0.2899273,0.0002601046,0.000203417,0.01129269,0.00007946771,0.000006649392,0.00240313],"genre_scores_gemma":[0.3204356,0.0002322615,0.6780772,0.000009174619,0.00002208668,0.0009794317,7.134355e-7,0.000009180136,0.0002343434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5453104,"threshold_uncertainty_score":0.8204213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9900024069594315,"score_gpt":0.7477755849671291,"score_spread":0.2422268219923024,"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."}}