{"id":"W2142171035","doi":"10.1186/1472-6963-5-25","title":"Systems for grading the quality of evidence and the strength of recommendations II: Pilot study of a new system","year":2005,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":327,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Health informatics; Nursing research; Health administration; Grading (engineering); Public health; Nursing; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.450885,0.001944259,0.004995323,0.01496916,0.00419919,0.01192997,0.004917785,0.005174396,0.005195462],"category_scores_gemma":[0.6766576,0.003228179,0.009413768,0.01815224,0.004105953,0.01297113,0.01072705,0.00856515,0.001623064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01373799,"about_ca_system_score_gemma":0.0257829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006445869,"about_ca_topic_score_gemma":0.009937816,"domain_scores_codex":[0.5071402,0.2930605,0.1284921,0.009678612,0.05891547,0.002713116],"domain_scores_gemma":[0.2388516,0.4917836,0.05165964,0.04234929,0.1719227,0.003433189],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.006463257,0.002046898,0.04458639,0.05063425,0.003367784,0.0003091225,0.01926092,0.003357311,0.003841154,0.01106121,0.0280133,0.8270584],"study_design_scores_gemma":[0.02406785,0.03781335,0.2686769,0.139754,0.02749716,0.004591416,0.03265673,0.08054379,0.02330301,0.07003863,0.2859826,0.005074563],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1685937,0.02282956,0.5098324,0.02371526,0.009606203,0.2246812,0.007834704,0.003137693,0.02976927],"genre_scores_gemma":[0.0843994,0.003282856,0.847781,0.0007782209,0.0002554979,0.06139372,0.001208804,0.0002004109,0.0007001213],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5491149,"threshold_uncertainty_score":0.6771565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9429551293519843,"score_gpt":0.694466003944852,"score_spread":0.2484891254071323,"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."}}