{"id":"W2803387226","doi":"10.1186/s13063-018-2654-z","title":"Outcome pre-specification requires sufficient detail to guard against outcome switching in clinical trials: a case study","year":2018,"lang":"en","type":"article","venue":"Trials","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University Hospital","funders":"","keywords":"Medicine; Outcome (game theory); Confidence interval; Clinical trial; Odds ratio; Guard (computer science); Odds; Internal medicine; Logistic regression","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","research_integrity"],"domain":"reporting","study_design":"case_report","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.758987,0.002377414,0.008153074,0.004202649,0.002767766,0.01053101,0.005129877,0.01476356,0.003643936],"category_scores_gemma":[0.8584684,0.002060187,0.01334031,0.007289325,0.009150727,0.0140352,0.006651537,0.01362417,0.001007729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00944752,"about_ca_system_score_gemma":0.01507126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001542954,"about_ca_topic_score_gemma":0.001431832,"domain_scores_codex":[0.09407691,0.7980387,0.07876974,0.00529303,0.02180891,0.002012733],"domain_scores_gemma":[0.03133798,0.8537781,0.05301136,0.04694672,0.0140128,0.0009130192],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"case_report","study_design_scores_codex":[0.04120853,0.001358639,0.08766413,0.09522448,0.01925162,0.01029374,0.02903305,0.02023664,0.003320498,0.1630611,0.03044894,0.4988986],"study_design_scores_gemma":[0.02648672,0.02176161,0.05772137,0.1785343,0.03436195,0.02252879,0.006744924,0.04776174,0.01608087,0.3405859,0.2454264,0.002005339],"study_design_candidate":"case_report","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1420932,0.1404902,0.4955739,0.1573712,0.006720779,0.03383756,0.002517784,0.001007564,0.02038777],"genre_scores_gemma":[0.5915397,0.01151668,0.3221436,0.03267348,0.002975071,0.03670647,0.001046022,0.0005268148,0.0008721862],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.241013,"threshold_uncertainty_score":0.297212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9745720513411243,"score_gpt":0.7350387175842116,"score_spread":0.2395333337569128,"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."}}