{"id":"W4413466260","doi":"10.1016/j.oregeorev.2025.106844","title":"A generative neural network approach to uncertainty and risk-return analysis in mineral prospectivity modelling","year":2025,"lang":"en","type":"article","venue":"Ore Geology Reviews","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Prospectivity mapping; Geology; Generative grammar; Artificial neural network; Mineral; Geochemistry; Mineral deposit; Mining engineering; Machine learning; Artificial intelligence; Geomorphology; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.00122223,0.0002092086,0.0006883019,0.0001375851,0.0001500466,0.00004521631,0.0004312897,0.0001201003,0.000006171682],"category_scores_gemma":[0.0001896235,0.0001648269,0.0001237911,0.0020629,0.00007525841,0.0000951357,0.0003953681,0.0003188776,0.000002892727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003167788,"about_ca_system_score_gemma":0.00003009434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002374405,"about_ca_topic_score_gemma":0.0004635498,"domain_scores_codex":[0.9979202,0.0004694335,0.0003882232,0.0007492147,0.00006561318,0.0004073823],"domain_scores_gemma":[0.9990947,0.00009322274,0.0001516385,0.0005218922,0.00006629781,0.00007228116],"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":[0.000008182808,0.00003765722,0.2518781,0.00004110162,0.00007941868,0.000003995513,0.0004443972,0.7348707,0.00001215546,0.005323228,0.0008387297,0.006462335],"study_design_scores_gemma":[0.0001414825,0.00002035096,0.01277036,0.00002031451,0.00007469518,0.000005852058,0.00001057198,0.9703221,0.000005853261,0.006456907,0.0100107,0.0001608761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1450508,0.007031319,0.8357258,0.00293927,0.0001290427,0.0007092835,0.000001298423,0.0000525838,0.00836053],"genre_scores_gemma":[0.8694393,0.001188527,0.1255466,0.001113009,0.0001169137,0.0002736542,0.00001554093,0.000002546001,0.002303906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7243885,"threshold_uncertainty_score":0.6721446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0255269440280645,"score_gpt":0.2573541254984559,"score_spread":0.2318271814703914,"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."}}