{"id":"W7124958874","doi":"10.59275/j.melba.2025-5ce1","title":"The Trauma THOMPSON Dataset for Real-World Emergency AI","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"U.S. Army Medical Research and Development Command; National Science Foundation","keywords":"Action (physics); Benchmark (surveying); Object (grammar); Psychological intervention; Emergency response; Foundation (evidence); Visualization","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.004744148,0.0001920169,0.000265093,0.0002703996,0.00136872,0.0001723375,0.002387524,0.000036764,0.00001598548],"category_scores_gemma":[0.001376223,0.0001067802,0.0002026654,0.0007473485,0.0001934436,0.0002517292,0.0003057416,0.0009489017,0.000005018431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006775029,"about_ca_system_score_gemma":0.0001231961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002888716,"about_ca_topic_score_gemma":0.00003681351,"domain_scores_codex":[0.9977961,0.0003508232,0.0007788466,0.0002300579,0.0004096114,0.0004345134],"domain_scores_gemma":[0.9961441,0.002329913,0.0005930679,0.0005577145,0.000244791,0.0001304256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002423464,0.0001843742,0.005605468,0.0001045031,0.000215392,0.000003404384,0.0006120729,0.002586684,0.001535766,0.03822534,0.119126,0.8315586],"study_design_scores_gemma":[0.0006761426,0.00008598106,0.004281968,0.00004588225,0.00006768155,0.00002441959,0.00003388459,0.5303665,0.00007412684,0.007623364,0.4566203,0.00009973384],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001141494,0.0007531125,0.8617068,0.1348089,0.0008024495,0.0003818783,0.00005023788,0.00005965764,0.0002955],"genre_scores_gemma":[0.9284665,0.0004753999,0.06508455,0.002269173,0.0009663533,0.0001014254,0.00026731,0.00005911272,0.002310145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.927325,"threshold_uncertainty_score":0.9999313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01384478357073097,"score_gpt":0.3552164647173537,"score_spread":0.3413716811466227,"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."}}