{"id":"W2791660821","doi":"10.1136/bmjebm-2017-110852","title":"Assessing the validity of surrogate endpoints in the context of a controversy about the measurement of effectiveness of hepatitis C virus treatment","year":2018,"lang":"en","type":"article","venue":"BMJ evidence-based medicine","topic":"Hepatitis C virus research","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"National Health and Medical Research Council","keywords":"Surrogate endpoint; Medicine; Clinical endpoint; Intensive care medicine; Context (archaeology); Endpoint Determination; Randomized controlled trial; Clinical trial; 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":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0170533,0.0002512142,0.001155924,0.0002075951,0.00008431553,0.0000082788,0.0004487843,0.00009132137,0.0001450465],"category_scores_gemma":[0.01096321,0.0001090995,0.0002179374,0.0007038626,0.002296031,0.0001334463,0.00005026376,0.0002437109,0.000003335314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003842796,"about_ca_system_score_gemma":0.001280991,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03087585,"about_ca_topic_score_gemma":0.005155687,"domain_scores_codex":[0.9922953,0.003382418,0.001203498,0.0002963742,0.002478185,0.000344256],"domain_scores_gemma":[0.9860871,0.01024262,0.00078798,0.001090453,0.001702853,0.00008902744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004599491,0.001058711,0.6362983,0.00281432,0.0004949382,0.00007179138,0.005905801,0.00001772842,0.3070533,0.0004202412,0.0003721265,0.04089331],"study_design_scores_gemma":[0.006563286,0.005791358,0.5083423,0.01680978,0.0004159405,0.000007051784,0.001268029,0.0005123401,0.4597163,0.00008261966,0.0004031472,0.00008786864],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890643,0.002155816,0.0004916464,0.003541201,0.0001849899,0.003702877,0.00003858948,0.000008064625,0.0008125433],"genre_scores_gemma":[0.9978935,0.001318741,0.00005297632,0.00032416,0.0001660329,0.0002115047,0.000006850593,0.00001892781,0.000007352857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.152663,"threshold_uncertainty_score":0.9973679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2545075038471375,"score_gpt":0.4540353686146979,"score_spread":0.1995278647675604,"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."}}