{"id":"W2102140188","doi":"10.1177/154193120504900344","title":"An Empirical Study of Calibration in Air Traffic Control Expert Judgment","year":2005,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Air traffic control; Probabilistic logic; Calibration; Control (management); Task (project management); Computer science; Aggregate (composite); Differential (mechanical device); Separation (statistics); Traffic conflict; Dempster–Shafer theory; Point (geometry); Mathematics; Statistics; Engineering; Artificial intelligence; Machine learning; Transport engineering; Traffic congestion","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01124281,0.0002353601,0.0002700053,0.0008545528,0.0004369408,0.001433964,0.0005388853,0.0008535165,0.001526948],"category_scores_gemma":[0.1889043,0.0003501394,0.0002282354,0.0006361064,0.001772236,0.001621758,0.001232342,0.0009828195,0.0001681702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004734204,"about_ca_system_score_gemma":0.0003140114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001134969,"about_ca_topic_score_gemma":0.001051282,"domain_scores_codex":[0.9908084,0.005463548,0.0006010634,0.001037376,0.001813641,0.0002759562],"domain_scores_gemma":[0.7226068,0.2392939,0.02034337,0.009563557,0.006804907,0.001387479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002268149,0.0008187613,0.8798831,0.000239531,0.0002912948,0.0005523862,0.03622082,0.007013493,0.01287098,0.001622668,0.0005239887,0.0576949],"study_design_scores_gemma":[0.00008053168,0.001388415,0.9574382,0.0001052306,0.00005773283,0.001213616,0.0107594,0.01912624,0.004640536,0.003425359,0.001629034,0.0001355916],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979006,0.00004763103,0.001037966,0.00002303633,0.000002474238,0.00001318497,0.00000952319,0.000002831174,0.0009626854],"genre_scores_gemma":[0.9994839,0.00002178503,0.0003879165,0.00001841231,0.000002945405,0.000008010284,0.00001628944,0.000001704545,0.00005893041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01124281,"threshold_uncertainty_score":0.05945837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06756849667941899,"score_gpt":0.3613776112737702,"score_spread":0.2938091145943512,"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."}}