{"id":"W4390145132","doi":"10.1177/03611981231212162","title":"Machine Learning Approach to Enhance Highway Railroad Grade Crossing Safety by Analyzing Crash Data and Identifying Hotspot Crash Locations","year":2023,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Hotspot (geology); Crash; Transport engineering; Cluster analysis; Train; Collision; Forensic engineering; Engineering; Computer science; Geography; Computer security; Cartography; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004960683,0.0003013255,0.0004582653,0.001222798,0.00151738,0.0005147982,0.001360458,0.0001654715,0.00003508154],"category_scores_gemma":[0.0002509293,0.000256138,0.0001514346,0.003302173,0.0004035503,0.001037318,0.00003498645,0.002674868,0.00001706035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002394279,"about_ca_system_score_gemma":0.0002180217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001902209,"about_ca_topic_score_gemma":0.004367979,"domain_scores_codex":[0.9943941,0.0005149783,0.001223668,0.000560453,0.00220322,0.001103615],"domain_scores_gemma":[0.9970466,0.0006095889,0.0002089982,0.0006376321,0.001067672,0.0004294669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007676382,0.0002242422,0.4486053,0.002131492,0.0007981357,0.0001662649,0.02178088,0.24929,0.1619294,0.00086955,0.03601417,0.07742295],"study_design_scores_gemma":[0.001176122,0.0001866195,0.9016653,0.0009293951,0.00009591981,0.000002449929,0.003826433,0.0288837,0.009120315,0.0009000804,0.05263841,0.0005752653],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9399682,0.000684811,0.05634765,0.001075687,0.00065446,0.0007254825,0.0002256062,0.0001710346,0.0001471102],"genre_scores_gemma":[0.9917465,0.002932309,0.004060665,0.00001707246,0.0002533679,0.00004446508,0.0002160719,0.00009823811,0.0006312848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.45306,"threshold_uncertainty_score":0.9999891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06874134827501226,"score_gpt":0.3773744326445148,"score_spread":0.3086330843695025,"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."}}