{"id":"W4408436068","doi":"10.5194/egusphere-egu25-7327","title":"Canada-wide Modelling &amp;#8211; Analysis of Model Accuracy to Drive Appropriate Use and Risk Reduction Program Development","year":2025,"lang":"en","type":"preprint","venue":"","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Safety Canada","funders":"","keywords":"Reduction (mathematics); Computer science; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002662552,0.0003863897,0.0009503918,0.001909726,0.0002442147,0.0005098433,0.000663181,0.0002639135,0.00001936891],"category_scores_gemma":[0.002624749,0.0003140056,0.0002660573,0.002441177,0.00005459346,0.000245849,0.0007162448,0.000432692,0.000002265759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001711742,"about_ca_system_score_gemma":0.00256818,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.4631263,"about_ca_topic_score_gemma":0.5263162,"domain_scores_codex":[0.9943801,0.0002281243,0.00178215,0.001415862,0.001842945,0.0003508664],"domain_scores_gemma":[0.995118,0.0008652714,0.0008505501,0.001156202,0.001707629,0.0003023899],"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":[0.00004244186,0.00005810144,0.003361458,0.00002304246,0.0007716076,2.627593e-7,0.001547956,0.944576,0.000006272241,0.0001410991,0.0007580383,0.04871378],"study_design_scores_gemma":[0.00009847282,0.000009089104,0.001398393,0.00007177499,0.0009714487,2.41595e-7,0.0005254975,0.9895587,0.00005632578,0.005705276,0.001276636,0.0003281668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4855992,0.00004467095,0.5132606,0.0001586861,0.000137766,0.0004790883,0.0001177187,0.00004610039,0.0001561581],"genre_scores_gemma":[0.6079109,0.0004399278,0.3892692,0.0000825278,0.00001136123,0.0001359811,0.0001561204,0.00001187112,0.001982135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1239914,"threshold_uncertainty_score":0.9999312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1921410029475143,"score_gpt":0.3848843078091519,"score_spread":0.1927433048616376,"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."}}