{"id":"W2889900146","doi":"10.2217/cer-2018-0035","title":"Some issues for the evaluation of noninferiority trials","year":2018,"lang":"en","type":"article","venue":"Journal of Comparative Effectiveness Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"H2020 European Research Council","keywords":"Medicine; Confidence interval; Margin (machine learning); Adjuvant therapy; Placebo; Medical physics; Cancer; Internal medicine; Alternative 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":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","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":["metaresearch"],"category_scores_codex":[0.2842236,0.0001452267,0.001753953,0.0002310255,0.0002521859,0.00005779297,0.0005548968,0.0001165718,0.0001806135],"category_scores_gemma":[0.4086082,0.00007936214,0.0003993058,0.0004503566,0.001073901,0.0001726127,0.0001003304,0.0005589482,0.00000883433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001876135,"about_ca_system_score_gemma":0.000588053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009569658,"about_ca_topic_score_gemma":0.000003974391,"domain_scores_codex":[0.9504216,0.0446459,0.001796629,0.0002056293,0.002614726,0.0003154732],"domain_scores_gemma":[0.4651242,0.5198521,0.001251096,0.0003792912,0.01329419,0.00009913244],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.03106114,0.002489796,0.001435524,0.00132292,0.004294687,0.000005519691,0.004498716,0.0003143568,0.05888393,0.7738841,0.01480195,0.1070074],"study_design_scores_gemma":[0.00315368,0.002616234,0.00962351,0.0003268665,0.0003226359,0.000003346976,0.0002650128,0.002927869,0.1135697,0.866661,0.0004565947,0.00007349693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6369655,0.002307911,0.3516888,0.0006761304,0.002194868,0.005594792,0.00006218144,0.000009866429,0.0004999484],"genre_scores_gemma":[0.913784,0.0000696138,0.08309387,0.000005416146,0.002853018,0.0001539631,1.878253e-7,0.00001559685,0.00002430861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4852974,"threshold_uncertainty_score":0.7370424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9613010515836794,"score_gpt":0.7999582645757043,"score_spread":0.1613427870079751,"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."}}