{"id":"W3123314203","doi":"10.3390/app11030994","title":"Dynamic Railway Derailment Risk Analysis with Text-Data-Based Bayesian Network","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Safety Warnings and Signage","field":"Psychology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Derailment; Computer science; Bayesian probability; Data mining; Bayesian network; Process (computing); Artificial intelligence; Machine learning; Track (disk drive)","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":[0.001086198,0.000172742,0.0002941282,0.0001279886,0.0005740799,0.0001275841,0.0006575556,0.00006756624,0.003297733],"category_scores_gemma":[0.00001666028,0.0001286296,0.00007318106,0.002740867,0.0003545891,0.00006527945,0.0001042683,0.0001763113,0.000160325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002272748,"about_ca_system_score_gemma":0.0001381209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001180249,"about_ca_topic_score_gemma":0.0009510515,"domain_scores_codex":[0.9977937,0.000130773,0.0002366726,0.0009225168,0.0004089063,0.0005074795],"domain_scores_gemma":[0.9985767,0.0002921853,0.0001852252,0.0008041586,0.00003316614,0.0001085585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0004945567,0.0009868856,0.3801188,0.00003072047,0.004547124,0.0004552123,0.004667727,0.3858714,0.001613312,0.07079597,0.02050908,0.1299092],"study_design_scores_gemma":[0.004048798,0.0005716727,0.665215,0.00005015514,0.003517786,0.0000317275,0.01157494,0.2519642,0.0004415778,0.005981692,0.05451325,0.002089204],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3009903,0.001723328,0.4647524,0.002589923,0.0006490505,0.0006083979,0.0001033396,0.0003054281,0.2282778],"genre_scores_gemma":[0.9832729,0.000008013562,0.01520942,0.0007236352,0.00005518783,0.00003424444,0.00008812179,0.0000115586,0.0005968946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6822826,"threshold_uncertainty_score":0.9976134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01853046547846462,"score_gpt":0.29366671880873,"score_spread":0.2751362533302654,"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."}}