{"id":"W4409212246","doi":"10.1111/1468-5973.70044","title":"Evaluating the Performance of Agreement Metrics in a Delphi Study on Chemical, Biological, Radiological and Nuclear Major Incidents Preparedness Using Classical and Machine Learning Approaches","year":2025,"lang":"en","type":"article","venue":"Journal of Contingencies and Crisis Management","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Radiological weapon; Preparedness; Delphi; Delphi method; Engineering; Computer science; Artificial intelligence; Chemistry; Political science; Radiochemistry","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":[0.007231128,0.0001381272,0.0005188536,0.0004211617,0.0002478382,0.0001677212,0.0003457897,0.00004946818,0.000009672209],"category_scores_gemma":[0.001014246,0.00007194502,0.00008659672,0.0007500824,0.0001535171,0.0001201805,0.0005169894,0.0002456495,1.78037e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004115902,"about_ca_system_score_gemma":0.00001203706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002550345,"about_ca_topic_score_gemma":0.000004957955,"domain_scores_codex":[0.9973117,0.00047048,0.0009918518,0.0002949478,0.0007659791,0.0001650123],"domain_scores_gemma":[0.9983424,0.0006667111,0.0006341471,0.0001682223,0.0001403305,0.00004821019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00127913,0.001022222,0.6326096,0.00009675664,0.0009351138,0.00003657353,0.0288436,0.007680472,0.001127336,0.0008886649,0.0002074059,0.3252731],"study_design_scores_gemma":[0.002352444,0.002302141,0.2846078,0.0001714228,0.0006174544,0.00001756237,0.332675,0.3753625,0.0000483379,0.001154203,0.0004512483,0.0002399292],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969689,0.001688737,0.0003889905,0.0005594282,0.00003920038,0.0002244598,5.798454e-7,0.000002567647,0.0001271212],"genre_scores_gemma":[0.9969903,0.001541821,0.001346925,0.00007619006,0.00001505587,0.00000241592,1.458327e-7,0.000002890785,0.00002430768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.367682,"threshold_uncertainty_score":0.2933833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2746546593058555,"score_gpt":0.4066631976442115,"score_spread":0.132008538338356,"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."}}