{"id":"W4404198666","doi":"10.1177/17407745241290729","title":"Pragmatic monitoring of emerging efficacy data in randomized controlled trials","year":2024,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; Impact; McMaster University; Population Health Research Institute","funders":"","keywords":"Randomized controlled trial; Medicine; 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","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7429408,0.0005487765,0.0357248,0.0004649225,0.0000493001,0.0001996048,0.001422211,0.0006908263,0.0009382004],"category_scores_gemma":[0.9933407,0.000326395,0.005071483,0.000761732,0.0006025265,0.0002140322,0.0005704436,0.001266064,0.00008017245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004903267,"about_ca_system_score_gemma":0.0004265856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001194621,"about_ca_topic_score_gemma":0.000001247514,"domain_scores_codex":[0.5752973,0.337715,0.08024097,0.002921351,0.002530194,0.001295183],"domain_scores_gemma":[0.01117351,0.9802506,0.005655864,0.002388977,0.0002171659,0.0003138781],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.39519,0.002970291,0.0005768191,0.003031418,0.01307694,0.0002043129,0.0004701218,0.00002978816,0.0004797938,0.2366032,0.006594254,0.3407731],"study_design_scores_gemma":[0.3549507,0.0001098155,0.00004803737,0.002951163,0.004241491,0.000001553079,0.0000658121,0.00497699,0.000132285,0.6319307,0.0003132577,0.0002781277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0952856,0.02686813,0.706262,0.00877337,0.08338855,0.06705075,0.001936347,0.001751832,0.008683443],"genre_scores_gemma":[0.1407949,0.003821306,0.8459755,0.00008023842,0.007990045,0.0007234671,0.00001959548,0.0001679401,0.0004269895],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6425356,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8746604636711833,"score_gpt":0.7229113298889603,"score_spread":0.151749133782223,"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."}}