{"id":"W2382198149","doi":"10.1111/bioe.12260","title":"Do We Know Whether Researchers and Reviewers are Estimating Risk and Benefit Accurately?","year":2016,"lang":"en","type":"article","venue":"Bioethics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Estimation; Actuarial science; Risk analysis (engineering); Measure (data warehouse); Work (physics); Quality (philosophy); Computer science; Psychology; Economics; Medicine; Epistemology; Data mining; Management","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"],"consensus_categories":[],"category_scores_codex":[0.02302789,0.0001832776,0.0006482609,0.0001910406,0.0002931689,0.0001429132,0.0001831413,0.000279433,0.0002290275],"category_scores_gemma":[0.01386045,0.0001676193,0.00005710834,0.0001378033,0.0004203797,0.0004000059,0.0001123484,0.0003357692,0.0005945576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002024916,"about_ca_system_score_gemma":0.00006988797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005759071,"about_ca_topic_score_gemma":0.0001978176,"domain_scores_codex":[0.9968446,0.00031986,0.001739606,0.0005973491,0.0001093498,0.0003891822],"domain_scores_gemma":[0.9947719,0.00285967,0.00152069,0.000474761,0.0001120942,0.0002609035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004512283,0.00007450202,0.4120397,0.002594216,0.0001771383,0.000003115607,0.00737957,0.00002954697,0.00001270478,0.4104925,0.02194048,0.1452114],"study_design_scores_gemma":[0.001844557,0.0001762998,0.037088,0.003506448,0.00002485903,0.00001306399,0.004483872,0.003842423,0.00001311685,0.3148336,0.6332138,0.0009600354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2451365,0.2543427,0.009426197,0.4841858,0.00124831,0.001686435,0.001128257,0.0001679906,0.002677771],"genre_scores_gemma":[0.4512405,0.4509554,0.07629769,0.01219658,0.001681358,0.0002769879,0.00001454246,0.0002344535,0.007102534],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.6112732,"threshold_uncertainty_score":0.9944462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7003927520154161,"score_gpt":0.5213886242829595,"score_spread":0.1790041277324566,"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."}}