{"id":"W2560833249","doi":"10.1056/nejmra1510065","title":"Interpreting Geographic Variations in Results of Randomized, Controlled Trials","year":2016,"lang":"en","type":"article","venue":"New England Journal of Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"","keywords":"Medicine; Randomized controlled trial; MEDLINE; Surgery","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03383323,0.0001324144,0.003564628,0.0005709852,0.00001245985,0.000003900926,0.0001632373,0.0000694919,0.0001091857],"category_scores_gemma":[0.2055742,0.00005417341,0.0003297953,0.0001600036,0.0001416745,0.0001166423,0.00001766098,0.0001998213,3.254211e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003036487,"about_ca_system_score_gemma":0.00008618119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004490397,"about_ca_topic_score_gemma":0.00002902465,"domain_scores_codex":[0.9941248,0.001573401,0.003671576,0.00008655669,0.0004059475,0.0001377023],"domain_scores_gemma":[0.9515885,0.04428358,0.003480017,0.0001675417,0.0003841371,0.00009624984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.6310316,0.0002366109,0.001085306,0.00007878034,0.001342811,0.00008930288,0.005149804,0.00001282088,0.04533719,0.1460517,0.004409894,0.1651742],"study_design_scores_gemma":[0.5979286,0.00029959,0.00002190151,0.002180542,0.000262711,0.00003539433,0.00004648218,0.0000268815,0.0008939859,0.3980888,0.0001705676,0.00004454647],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08986741,0.001679962,0.8793791,0.02086082,0.0007571114,0.001619053,0.00001097024,0.0000547229,0.005770871],"genre_scores_gemma":[0.9768465,0.0009400652,0.02128539,0.00005320638,0.000719012,0.000008765854,4.192208e-7,0.00001037108,0.0001362982],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.886979,"threshold_uncertainty_score":0.994872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08639357282908044,"score_gpt":0.4075397463559389,"score_spread":0.3211461735268585,"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."}}