{"id":"W4391302154","doi":"10.2514/6.2024-1381","title":"Novel Methodology for Comparing Student Pilot Flight Performance with Instructor Pilot Expert Ratings","year":2024,"lang":"en","type":"article","venue":"","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Aeronautics; Multimedia; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01835535,0.001201689,0.0008876032,0.003916095,0.0005559879,0.001149125,0.001500818,0.0009221648,0.002903651],"category_scores_gemma":[0.04783661,0.0005512583,0.001003681,0.002908328,0.0007654356,0.001271131,0.001700233,0.001183035,0.0008995758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000582995,"about_ca_system_score_gemma":0.0007687719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00128199,"about_ca_topic_score_gemma":0.002348665,"domain_scores_codex":[0.9706172,0.0170882,0.002433767,0.002892055,0.006618169,0.0003505559],"domain_scores_gemma":[0.9539438,0.02466336,0.005515701,0.006925588,0.008404445,0.000547136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00162316,0.002358954,0.1154803,0.0009019304,0.001052226,0.0001405337,0.002280234,0.01189864,0.03542417,0.007275049,0.006011095,0.8155537],"study_design_scores_gemma":[0.001025874,0.02866379,0.4960485,0.0003591489,0.0006483115,0.002955488,0.002481887,0.3540693,0.06911416,0.01473516,0.0291001,0.0007983643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06247122,0.0001234853,0.9296392,0.00006962183,0.0001807042,0.002146028,0.0008055912,0.001357398,0.003206672],"genre_scores_gemma":[0.3227016,0.0001121525,0.6698531,0.00007913591,0.00008933268,0.004725692,0.0007245805,0.0001869666,0.001527423],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01835535,"threshold_uncertainty_score":0.09707355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2298847492854534,"score_gpt":0.4537138511828676,"score_spread":0.2238291018974142,"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."}}