{"id":"W4387893874","doi":"10.1177/17407745231203375","title":"The impact of feedback training on prediction of cancer clinical trial results","year":2023,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital; McGill University","funders":"","keywords":"Brier score; Randomized controlled trial; Confidence interval; Medicine; Sample size determination; Clinical trial; Physical therapy; Statistics; Medical physics; Internal medicine; Mathematics","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_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.7932209,0.0002359377,0.009309367,0.0002109006,0.0001226414,0.0002043992,0.001676889,0.0004187675,0.001388434],"category_scores_gemma":[0.8481673,0.00008064049,0.01241463,0.001845671,0.0003517832,0.00007896388,0.0001189646,0.0005012232,0.0008689455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001966329,"about_ca_system_score_gemma":0.000449887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002625962,"about_ca_topic_score_gemma":0.00001407828,"domain_scores_codex":[0.6413304,0.208276,0.1378289,0.002371985,0.00950274,0.0006899499],"domain_scores_gemma":[0.41316,0.5394948,0.03968299,0.005571038,0.001719075,0.0003721984],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02803339,0.0003124165,0.01509499,0.00001241754,0.002020446,0.000001577654,0.0002573061,0.0006100306,0.00002928869,0.0004193961,0.470071,0.4831378],"study_design_scores_gemma":[0.1002262,0.008358475,0.7301956,0.0004613044,0.002057575,0.000001002991,0.00135841,0.01963032,0.00004570121,0.02558159,0.1117082,0.0003756869],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9852565,0.0002565123,0.0001264183,0.001826372,0.005715347,0.002219929,0.0005910968,0.00001290861,0.003994909],"genre_scores_gemma":[0.9899692,0.00130669,0.0001181003,0.00006372111,0.002585034,0.00006153546,0.000013971,0.00001370721,0.005868074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7151006,"threshold_uncertainty_score":0.999909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9849873901837678,"score_gpt":0.769200980041683,"score_spread":0.2157864101420848,"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."}}