{"id":"W4388973510","doi":"10.61089/aot2023.ttb8p367","title":"Analysis of vehicle pedestrian crash severity using advanced machine learning techniques","year":2023,"lang":"en","type":"article","venue":"Archives of Transport","topic":"Traffic and Road Safety","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Transport Canada","funders":"","keywords":"Pedestrian; Crash; Transport engineering; Machine learning; Artificial neural network; Computer science; Random forest; Artificial intelligence; Bayesian probability; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.00008397478,0.0001074409,0.0003225615,0.0003350475,0.00003881421,0.000001356924,0.0001242262,0.00003629012,0.00001873702],"category_scores_gemma":[0.000004392654,0.0001085974,0.0002120208,0.0007017787,0.00006516311,0.00005812853,0.000009666534,0.0001367671,7.154228e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005533336,"about_ca_system_score_gemma":0.00001286959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008861606,"about_ca_topic_score_gemma":0.0001203464,"domain_scores_codex":[0.9992839,0.00001618393,0.0002905775,0.0001261624,0.0001156297,0.0001675972],"domain_scores_gemma":[0.9996861,0.00006303386,0.00004636559,0.0001517145,0.000009221477,0.00004361895],"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":[0.00003872281,0.00002692523,0.3715346,0.0001965049,0.0005006372,0.000008357301,0.001330756,0.5412049,0.04342453,0.00002568288,0.000001084604,0.04170724],"study_design_scores_gemma":[0.000180351,0.00002583132,0.6768793,0.00004363788,0.00030119,4.955965e-7,0.00008774709,0.308836,0.01314252,0.00002730994,0.0003512967,0.0001242785],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890136,0.00008549961,0.008915187,0.00001050767,0.00002914176,0.00007793532,0.0000759768,0.0004454975,0.001346628],"genre_scores_gemma":[0.9945238,0.0003864393,0.004909906,0.000001734535,0.000009247737,0.000002321623,0.00009866887,0.00002075018,0.00004711628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3053447,"threshold_uncertainty_score":0.4428472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01057052677956678,"score_gpt":0.2326988209650866,"score_spread":0.2221282941855198,"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."}}