{"id":"W3100984816","doi":"10.31234/osf.io/mktgj","title":"Effect of Confidence Interval Construction on Judgment Accuracy","year":2020,"lang":"en","type":"article","venue":"","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Confidence interval; Univariate; Statistics; Range (aeronautics); Skepticism; Interval (graph theory); Psychology; Expert elicitation; Mathematics; Social psychology; Engineering; Multivariate statistics; Epistemology","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":["insufficient_payload"],"category_scores_codex":[0.00129119,0.0001099625,0.0003246278,0.00008878443,0.0000415879,0.0001233829,0.0005024585,0.00005014199,0.001724979],"category_scores_gemma":[0.004321064,0.00006893303,0.000142169,0.0002486062,0.0001048035,0.0002032932,0.0001197424,0.0001074241,0.001235879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002104291,"about_ca_system_score_gemma":0.0000274577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001607254,"about_ca_topic_score_gemma":0.000002468878,"domain_scores_codex":[0.9982022,0.0001526762,0.000604243,0.0003724131,0.0005561398,0.0001123312],"domain_scores_gemma":[0.996103,0.003076585,0.0002699724,0.0003328083,0.0001053551,0.0001122149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002618335,0.00001907973,0.002406011,0.000003187443,0.000004357049,0.000004076965,0.0001174613,0.0001257156,0.001229509,0.001612124,0.004342414,0.9898742],"study_design_scores_gemma":[0.005163921,0.02024687,0.005978604,0.0003542865,0.0001368269,0.00009303274,0.003347373,0.02806135,0.7926285,0.07685158,0.06587164,0.001265989],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9878936,0.000007297961,0.003390611,0.001170207,0.0005422907,0.0001399864,0.000007571111,0.00003273372,0.006815703],"genre_scores_gemma":[0.9986753,0.000003096304,0.0006343645,0.0005478372,0.00004458416,0.000002867612,6.8414e-7,0.000004702484,0.00008649779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9886082,"threshold_uncertainty_score":0.9995418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1453684563854634,"score_gpt":0.4286088685024013,"score_spread":0.2832404121169378,"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."}}