{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001856226,0.0001838046,0.0004640894,0.0000888006,0.0002592705,0.00009850122,0.0006283064,0.0001178107,0.000008336465],"category_scores_gemma":[0.0001889333,0.0001220551,0.0001896582,0.0002151805,0.0001312824,0.0007043547,0.0001569412,0.0001900461,4.706285e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009095157,"about_ca_system_score_gemma":0.00002671936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009160682,"about_ca_topic_score_gemma":0.0001107608,"domain_scores_codex":[0.9978971,0.00003260714,0.001039686,0.0004377532,0.0003788723,0.0002139374],"domain_scores_gemma":[0.9986644,0.000257372,0.0006475794,0.0001714713,0.0001770802,0.00008213778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001257659,0.001359229,0.8553245,0.000009609453,0.00003168913,7.960173e-8,0.1130929,0.01050479,0.004939603,0.00006622018,0.0009703467,0.01357527],"study_design_scores_gemma":[0.003220849,0.001202031,0.5631232,0.0001265287,0.00006305335,0.000002166314,0.3731248,0.05194792,0.004420731,0.001461407,0.0006999834,0.0006073859],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9993318,0.0000301718,0.000005166839,0.0001704967,0.00009218755,0.0002825434,0.00001658776,0.00001598854,0.00005505786],"genre_scores_gemma":[0.9994339,0.000006239351,0.0003233471,0.0001189189,0.00008105767,0.000006947088,6.66003e-7,0.0000135632,0.00001531126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2922014,"threshold_uncertainty_score":0.4977262,"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."}}