{"id":"W4409074990","doi":"10.1016/j.ress.2025.111082","title":"Improving reliability of safety countermeasure evaluation at highway-rail grade crossings through aleatoric uncertainty modeling with machine learning techniques","year":2025,"lang":"en","type":"article","venue":"Reliability Engineering & System Safety","topic":"Traffic and Road Safety","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Countermeasure; Reliability (semiconductor); Engineering; Reliability engineering; Computer science; Transport engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003362073,0.0007544991,0.001136418,0.0002017849,0.0004655686,0.00006186737,0.0004521464,0.0004790212,0.00001526763],"category_scores_gemma":[0.0004062637,0.0006643078,0.0003059022,0.0009610995,0.0001442299,0.0004431811,0.0001344143,0.0009244657,0.000004816888],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004389035,"about_ca_system_score_gemma":0.0002628745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007326751,"about_ca_topic_score_gemma":0.00006944475,"domain_scores_codex":[0.9953829,0.0002448896,0.001682031,0.0009419266,0.0009809664,0.0007672762],"domain_scores_gemma":[0.9973706,0.0003614925,0.0002463409,0.001187138,0.0006895795,0.0001448272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002758208,0.00005409144,0.003645355,0.004646617,0.0001103559,0.000002324378,0.000504582,0.9847919,0.003853532,0.0004757289,0.00002036009,0.001619303],"study_design_scores_gemma":[0.001087932,0.00008508312,0.002885018,0.001560462,0.00022956,0.00001991319,0.0001730293,0.9871147,0.003127411,0.00002014537,0.003067311,0.0006294546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.401966,0.001659366,0.5870492,0.00009270496,0.001003845,0.0020072,0.0001313439,0.004048293,0.002041973],"genre_scores_gemma":[0.9911174,0.0001304183,0.008193766,0.000007210514,0.00009795123,0.0001412274,0.0001030802,0.0001222427,0.00008666315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5891514,"threshold_uncertainty_score":0.9995808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006552257959340377,"score_gpt":0.2089847933161003,"score_spread":0.2024325353567599,"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."}}