{"id":"W4200365875","doi":"10.22541/au.163827914.48781130/v1","title":"Empirical evaluation of fundamental principles of evidence-based medicine: a meta-epidemiological study","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Grading (engineering); Meta-analysis; Medicine; Odds ratio; Systematic review; Publication bias; Statistics; MEDLINE; Econometrics; Internal medicine; Mathematics; Chemistry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6150869,0.0007099667,0.01902652,0.0006777918,0.00005873214,0.0001956599,0.003190334,0.0003303995,0.1262787],"category_scores_gemma":[0.4582665,0.0002236306,0.007826623,0.001480878,0.0003234692,0.0001436395,0.001353288,0.0004650826,0.0000949844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000118468,"about_ca_system_score_gemma":0.0009585096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001907534,"about_ca_topic_score_gemma":0.0001701626,"domain_scores_codex":[0.6685302,0.2313733,0.05017403,0.004312873,0.04514855,0.0004610373],"domain_scores_gemma":[0.919193,0.0438893,0.01958191,0.007701922,0.009428367,0.0002054465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005161572,0.001752962,0.9328166,0.0006372071,0.0135885,0.000008244575,0.002013435,0.02840612,0.0001433058,0.000344413,0.01379862,0.006438973],"study_design_scores_gemma":[0.001103988,0.00104753,0.6511313,0.0010953,0.07185585,0.000005715953,0.01610683,0.2492686,0.0001652142,0.005452062,0.002141838,0.0006258084],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9561247,0.01255483,0.01817026,0.003660182,0.0004765991,0.005037684,0.00002010038,0.000007496889,0.003948111],"genre_scores_gemma":[0.9885376,0.00005183277,0.009326169,0.0003002619,0.00007584161,0.0004291352,0.00002526872,0.000009879439,0.001244003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2816853,"threshold_uncertainty_score":0.995537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9923385322462839,"score_gpt":0.7148133160779869,"score_spread":0.277525216168297,"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."}}