{"id":"W2124548530","doi":"10.1136/ebm.12.2.59","title":"Simon S. Statistical evidence in medical trials: what do the data really tell us? Oxford: Oxford University Press, 2006.","year":2007,"lang":"en","type":"article","venue":"Evidence-Based Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"London Health Sciences Centre","funders":"","keywords":"History; Psychology","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"],"domain":"methods","study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5390321,0.0005465989,0.004920404,0.0006056709,0.0002530855,0.0006810614,0.009027162,0.0002962766,0.01965436],"category_scores_gemma":[0.608431,0.0002295518,0.0006054008,0.002848685,0.000948982,0.002516208,0.0007370962,0.000850151,0.0002428388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001907611,"about_ca_system_score_gemma":0.0009912888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006466056,"about_ca_topic_score_gemma":0.001527339,"domain_scores_codex":[0.902591,0.04599719,0.02007768,0.003582677,0.02642295,0.001328454],"domain_scores_gemma":[0.596495,0.3729384,0.009567676,0.01700185,0.00235101,0.001646045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00087087,0.0001731667,0.06511322,0.0002644837,0.0001882106,0.0008696736,0.0003850952,0.0002129126,0.00002145654,0.003223427,0.6255031,0.3031744],"study_design_scores_gemma":[0.001211025,0.0002696511,0.02487856,0.007338959,0.0007684604,0.00001722412,0.002982031,0.02379881,0.00001438257,0.000554849,0.937845,0.0003210667],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02757953,0.1388835,0.6787223,0.1385665,0.003320251,0.006121688,0.0001835901,0.00006159483,0.006561028],"genre_scores_gemma":[0.8032107,0.1472983,0.01573107,0.01715511,0.004221512,0.00004632954,0.0002756891,0.00009638518,0.01196499],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7756311,"threshold_uncertainty_score":0.9963345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7886856891919887,"score_gpt":0.5482014631040504,"score_spread":0.2404842260879383,"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."}}