{"id":"W4280532161","doi":"10.1136/bmj-2021-069155","title":"Validity of data extraction in evidence synthesis practice of adverse events: reproducibility study","year":2022,"lang":"en","type":"article","venue":"BMJ","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Institute of Mental Health; U.S. National Library of Medicine; National Health and Medical Research Council; Medical Research Council; National Institutes of Health","keywords":"Data extraction; Meta-analysis; Systematic review; Medicine; Randomized controlled trial; MEDLINE; Data mining; Computer science; Internal medicine","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","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6067145,0.0001166845,0.001809322,0.0002386705,0.00007174646,0.00001497163,0.002704173,0.00002047719,0.006485505],"category_scores_gemma":[0.6739826,0.00006979697,0.0003870853,0.001778782,0.00002667571,0.001187361,0.0009967767,0.0001546188,0.00009760252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005772908,"about_ca_system_score_gemma":0.0001283874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003703964,"about_ca_topic_score_gemma":0.0001007579,"domain_scores_codex":[0.7702903,0.1727547,0.02934386,0.006335472,0.02090795,0.0003677511],"domain_scores_gemma":[0.8397867,0.0792321,0.02530595,0.05327776,0.002287145,0.0001103327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001601281,0.002489914,0.9616008,0.0001165603,0.0001711256,0.00001566844,0.001417037,0.001066782,0.0002439307,0.00002831344,0.02102337,0.01166642],"study_design_scores_gemma":[0.0002935478,0.0002607336,0.9211749,0.0001021269,0.001142793,0.00003062313,0.03787246,0.005743645,0.0001942481,0.0007867698,0.03218503,0.0002131059],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993484,0.0002455711,0.001143825,0.001466793,0.0002790006,0.002152137,0.00006276721,0.000002385785,0.001163542],"genre_scores_gemma":[0.9955955,0.00001108808,0.003673083,0.00002490984,0.00002596893,0.0001096749,0.00000225964,0.000003712259,0.0005538043],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09352261,"threshold_uncertainty_score":0.9944227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8833574908081807,"score_gpt":0.6284029396064584,"score_spread":0.2549545512017223,"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."}}