{"id":"W4383873581","doi":"10.20944/preprints202307.0192.v2","title":"Examining the Potential of Generative Language Models for Aviation Safety Analysis: Case Study and Insights using the Aviation Safety Reporting System (ASRS)","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"General Fusion (Canada)","funders":"","keywords":"Aviation; Computer science; Crew; Similarity (geometry); Aviation safety; Aviation accident; Process (computing); Generative grammar; Risk analysis (engineering); Operations research; Aeronautics; Engineering; Artificial intelligence; Business","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008371213,0.001129106,0.0003651355,0.00251531,0.0006693521,0.002515407,0.001147033,0.001273423,0.001608648],"category_scores_gemma":[0.03690469,0.0003851786,0.001191916,0.001529891,0.001322955,0.002859782,0.001897044,0.001663744,0.0006136125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001642589,"about_ca_system_score_gemma":0.001376362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006728755,"about_ca_topic_score_gemma":0.009833276,"domain_scores_codex":[0.9910615,0.007135522,0.0002391258,0.0007243161,0.000663971,0.0001756198],"domain_scores_gemma":[0.9340737,0.05943439,0.001524681,0.002950547,0.001605771,0.0004108009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00201791,0.00171975,0.1237074,0.003300539,0.0006813103,0.005607834,0.04776081,0.3545563,0.02563875,0.06004735,0.01595557,0.3590065],"study_design_scores_gemma":[0.0001195863,0.000654192,0.01303248,0.0004398614,0.0001880102,0.001342929,0.00971183,0.9032928,0.01061728,0.0355059,0.02494296,0.0001523049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6432797,0.001353033,0.3374038,0.00401543,0.0001891537,0.0006339872,0.003184752,0.00257736,0.007362644],"genre_scores_gemma":[0.8310571,0.000363492,0.1631249,0.0003456465,0.0000627636,0.0002693361,0.003229555,0.0002895828,0.001257494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008371213,"threshold_uncertainty_score":0.04427177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4517070882426561,"score_gpt":0.5252554654343733,"score_spread":0.0735483771917172,"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."}}