{"id":"W1907101914","doi":"10.1027/2192-0923/a000041","title":"Understanding Variance in Pilot Performance Ratings","year":2013,"lang":"en","type":"article","venue":"Aviation Psychology and Applied Human Factors","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Applied psychology; Psychology; Statistics; Variance (accounting); Rating scale; Reliability (semiconductor); Mathematics","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":[0.000195258,0.0001703883,0.0001891285,0.0002326911,0.000283809,0.00004841069,0.0001113218,0.0001418226,0.009624772],"category_scores_gemma":[0.000007676733,0.0001666102,0.00002339235,0.0001640947,0.0001068925,0.0002266488,0.00001714283,0.0003146616,0.0007774291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006276205,"about_ca_system_score_gemma":0.00000571578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004065501,"about_ca_topic_score_gemma":0.00002637274,"domain_scores_codex":[0.9987713,0.00007372021,0.0004144955,0.0003789861,0.00009536891,0.0002661454],"domain_scores_gemma":[0.9994128,0.00009602016,0.0001844688,0.0002152668,0.00002342723,0.00006805366],"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":[0.0001052355,0.0004310774,0.2309004,0.00002495547,0.00007030333,0.000001578424,0.01632608,0.00002069953,0.009081814,0.7283518,0.01189985,0.002786194],"study_design_scores_gemma":[0.00126921,0.0001234073,0.9859244,0.00001050459,0.000005045157,0.000003818672,0.001051666,0.00004168399,0.00006795737,0.01021574,0.001087107,0.0001994701],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8598277,0.00001177511,0.00240688,0.0003100213,0.0004771389,0.0003177162,0.000001754601,0.0001081264,0.1365389],"genre_scores_gemma":[0.9970833,0.000007040266,0.00005924729,0.001157102,0.00005893615,0.0001260564,0.00003322509,0.00001722749,0.00145788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.755024,"threshold_uncertainty_score":0.9992538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1166949241889494,"score_gpt":0.3581434269031571,"score_spread":0.2414485027142077,"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."}}