{"id":"W2103899236","doi":"10.1136/bmjopen-2012-001368","title":"Inter-rater and test–retest reliability of quality assessments by novice student raters using the Jadad and Newcastle–Ottawa Scales","year":2012,"lang":"en","type":"article","venue":"BMJ Open","topic":"Electroconvulsive Therapy Studies","field":"Medicine","cited_by":208,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; McMaster University","funders":"","keywords":"Jadad scale; Intraclass correlation; Medicine; Inter-rater reliability; Reliability (semiconductor); Test (biology); Observational study; Clinical psychology; Rating scale; Physical therapy; Randomized controlled trial; Psychometrics; Psychology; Internal medicine; Developmental psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002085414,0.0001644746,0.000425488,0.00002330499,0.0001155409,0.00005676755,0.0001797742,0.00004316294,0.000021888],"category_scores_gemma":[0.000302944,0.0001014702,0.00002808078,0.00009328184,0.0002641288,0.0002533103,0.0004775641,0.0001354261,0.00000181407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007187241,"about_ca_system_score_gemma":0.00004423571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007135532,"about_ca_topic_score_gemma":0.0001226147,"domain_scores_codex":[0.9986016,0.0002721305,0.0003989124,0.0002348686,0.0002333061,0.000259156],"domain_scores_gemma":[0.9986484,0.0005047894,0.0002067763,0.0003912728,0.0001541421,0.00009461669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000194254,0.0002081001,0.9429202,0.0001120515,0.00009910707,8.455621e-7,0.00121105,1.193825e-7,0.05387061,0.00001890104,0.0006489417,0.0007157964],"study_design_scores_gemma":[0.001614283,0.000481726,0.9838056,0.0001571946,0.000100657,0.00002121055,0.00221434,0.00002216629,0.01065171,0.00003565579,0.0007396964,0.0001557454],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935396,0.0004111735,0.00006069914,0.002144912,0.00005194883,0.003183028,0.0000169243,0.00000915963,0.0005824952],"genre_scores_gemma":[0.9977392,0.00002520369,0.0008109847,0.000972028,0.00005005645,0.0001124759,0.000004901362,0.00001614151,0.0002689899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04321889,"threshold_uncertainty_score":0.4137836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1192619632601358,"score_gpt":0.5071182900183459,"score_spread":0.3878563267582101,"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."}}