{"id":"W2009513741","doi":"10.1007/s10979-010-9227-3","title":"Individual confidence intervals do not inform decision-makers about the accuracy of risk assessment evaluations.","year":2010,"lang":"en","type":"article","venue":"Law and Human Behavior","topic":"Psychopathy, Forensic Psychiatry, Sexual Offending","field":"Psychology","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; Public Safety Canada","funders":"","keywords":"Recidivism; Confidence interval; Psychology; Statistics; Outcome (game theory); Risk assessment; Social psychology; Clinical psychology; Mathematics; Computer science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001368349,0.0002417643,0.0003072786,0.0001156165,0.0004798335,0.0001869072,0.0005915143,0.0001788216,0.002242116],"category_scores_gemma":[0.0001435214,0.0001802337,0.0001201364,0.0001264539,0.0006366957,0.0002551019,0.0001457091,0.0007188859,0.00006799993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002078145,"about_ca_system_score_gemma":0.00005417661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006806259,"about_ca_topic_score_gemma":0.001453673,"domain_scores_codex":[0.9979013,0.0001204354,0.0006963564,0.0003910978,0.0005598639,0.0003310121],"domain_scores_gemma":[0.9973722,0.0008816655,0.0005428274,0.0009128953,0.0001604448,0.0001300068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001014903,0.0005286866,0.09886635,0.00001390201,0.0001270339,0.000009647992,0.009267542,8.002903e-7,0.002369975,0.7673947,0.01590811,0.1054117],"study_design_scores_gemma":[0.001427295,0.0002667314,0.9772055,0.0000741017,0.0003370273,0.00003532128,0.001915938,0.000002486189,0.0001453756,0.007095326,0.01123893,0.0002560027],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9619524,0.00009229709,0.00008595701,0.0001098923,0.01958081,0.0006052567,0.0001648789,0.00004295033,0.01736549],"genre_scores_gemma":[0.9978254,0.000008856204,0.000856598,0.0005788889,0.0004045692,0.000150929,0.00002651858,0.00002688524,0.0001213469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8783391,"threshold_uncertainty_score":0.99867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05116656771464605,"score_gpt":0.4218178756069128,"score_spread":0.3706513078922667,"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."}}