{"id":"W3047457928","doi":"","title":"Validity and Inter-Rater Reliability Testing of Quality Assessment Instruments [Internet]","year":2012,"lang":"en","type":"article","venue":"","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Inter-rater reliability; Meta-analysis; Kappa; Statistics; Reliability (semiconductor); Medicine; Quality Score; Psychology; Mathematics; Rating scale; Internal medicine; Metric (unit)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.5859243,0.001563273,0.004643717,0.01633358,0.002578406,0.005676972,0.003761188,0.002464131,0.004819694],"category_scores_gemma":[0.7838981,0.001603121,0.008660084,0.01451179,0.004790698,0.004901752,0.005840597,0.00278458,0.001344732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005053068,"about_ca_system_score_gemma":0.0135711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003186633,"about_ca_topic_score_gemma":0.003620245,"domain_scores_codex":[0.3031672,0.3963009,0.2045682,0.01649769,0.0774457,0.002020309],"domain_scores_gemma":[0.129699,0.5338976,0.09640733,0.04845409,0.1903846,0.001157419],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003305162,0.0006141519,0.1678945,0.148881,0.02835041,0.0003645974,0.01881446,0.003940396,0.003468947,0.02560693,0.02480159,0.5739578],"study_design_scores_gemma":[0.005098596,0.004219305,0.4263896,0.2262998,0.02929183,0.002006841,0.007183885,0.03626688,0.01341234,0.06976218,0.1783474,0.001721322],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08923956,0.07621108,0.6436478,0.009081209,0.004034942,0.1199144,0.01300386,0.00205462,0.04281265],"genre_scores_gemma":[0.3595553,0.01048255,0.4870357,0.002320761,0.0007841141,0.1332704,0.004887216,0.0005316975,0.001132208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4140757,"threshold_uncertainty_score":0.5106291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.868285073652717,"score_gpt":0.5874881910494772,"score_spread":0.2807968826032398,"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."}}