{"id":"W4409743627","doi":"10.1002/cjce.25700","title":"Chemical process safety domain knowledge graph‐enhanced <scp>LLM</scp> for efficient emergency response decision support","year":2025,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Science and Technology Planning Project of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Emergency response; Process (computing); Graph; Decision process; Domain (mathematical analysis); Process management; Engineering; Medical emergency; Medicine; Theoretical computer science; Operating system; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005232015,0.0002459278,0.0005682154,0.0007939227,0.0002362139,0.0001162829,0.001552635,0.0001761818,0.00008312324],"category_scores_gemma":[0.01458098,0.0001671933,0.0005888107,0.002127008,0.0001193731,0.0001163158,0.0000546302,0.000479515,0.00001595468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003018801,"about_ca_system_score_gemma":0.00123378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003284109,"about_ca_topic_score_gemma":0.0001373456,"domain_scores_codex":[0.9968503,0.00008523584,0.00141146,0.0003280329,0.0007302815,0.0005946904],"domain_scores_gemma":[0.994121,0.003480128,0.0003097544,0.000477248,0.0009240041,0.0006879379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002196993,0.0002857858,0.000454783,0.0001427959,0.0007586893,0.0001018366,0.01037549,0.3213245,0.5531802,0.006725951,0.04957571,0.05487729],"study_design_scores_gemma":[0.004522527,0.0002696759,0.001406728,0.000663262,0.0005080103,0.000194702,0.001738571,0.08789566,0.6705042,0.1055353,0.1260324,0.0007289459],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8537205,0.0007405176,0.1422866,0.001571363,0.0007717061,0.0001930638,0.00002687801,0.00001488619,0.0006744569],"genre_scores_gemma":[0.9973726,0.00001322631,0.002002353,0.00005054897,0.0001599987,0.00001051168,0.000002442171,0.00001977623,0.0003685265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2334289,"threshold_uncertainty_score":0.9937196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01651386059589308,"score_gpt":0.3068938228672535,"score_spread":0.2903799622713604,"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."}}