{"id":"W4396619646","doi":"10.1080/13588265.2024.2348397","title":"BConvLSTM: a deep learning-based technique for severity prediction of a traffic crash","year":2024,"lang":"en","type":"article","venue":"International Journal of Crashworthiness","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Crash; Poison control; Injury prevention; Computer science; Transport engineering; Forensic engineering; Engineering; Medical emergency; Medicine","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":[0.0004399795,0.0001283696,0.0001879905,0.0005068914,0.00002052951,0.00005959067,0.0002865347,0.0000918373,0.00003123365],"category_scores_gemma":[0.0000706,0.0001204548,0.000206018,0.0001667624,0.00003669693,0.0002947937,0.00001645912,0.0002778812,0.000001341792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001032408,"about_ca_system_score_gemma":0.00004730039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001168665,"about_ca_topic_score_gemma":0.000005671882,"domain_scores_codex":[0.9988652,0.00002113216,0.0005368678,0.000102435,0.0003676442,0.0001067313],"domain_scores_gemma":[0.9992735,0.00009577277,0.000118345,0.0000724509,0.0003925865,0.0000472869],"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":[0.0002273128,0.0002533,0.001066955,0.0009993138,0.001144844,0.0001196696,0.0004741137,0.7945579,0.01480662,0.001350618,0.0246709,0.1603284],"study_design_scores_gemma":[0.0007193219,0.0002026284,0.002537287,0.0006340859,0.00009932917,0.0001165744,0.00004020257,0.9292286,0.01043782,0.0004362541,0.05538367,0.0001642126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03526553,0.0003210409,0.9600974,0.0002683323,0.002321503,0.0002530991,0.00004166865,0.001104241,0.0003272144],"genre_scores_gemma":[0.9956489,0.0001407843,0.003723949,0.00003016881,0.0003185667,0.0000488712,0.0000209458,0.00003091294,0.00003685859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9603834,"threshold_uncertainty_score":0.4912002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007431146382020578,"score_gpt":0.2451640806573185,"score_spread":0.2377329342752979,"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."}}