{"id":"W4410049575","doi":"10.1007/s11053-025-10468-z","title":"Class Label Representativeness in Machine Learning-Based Mineral Prospectivity Mapping","year":2025,"lang":"en","type":"article","venue":"Natural Resources Research","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada; Natural Resources Canada","funders":"Natural Resources Canada","keywords":"Prospectivity mapping; Mineral exploration; Mineral resource classification; Artificial intelligence; Representativeness heuristic; Class (philosophy); Boosting (machine learning); Computer science; Machine learning; Pattern recognition (psychology); Geology; Mathematics; Geochemistry; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002523782,0.0001667325,0.0002424618,0.0005452777,0.0003740731,0.0002385445,0.001291377,0.0001456234,0.00002342397],"category_scores_gemma":[0.002877983,0.0001448703,0.0000603793,0.002915129,0.000217586,0.0001987191,0.0008952031,0.001915401,0.00001456575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001887545,"about_ca_system_score_gemma":0.0001480645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005318946,"about_ca_topic_score_gemma":0.0001890646,"domain_scores_codex":[0.9966732,0.000844932,0.0002601629,0.0007540301,0.0007411444,0.000726539],"domain_scores_gemma":[0.9978577,0.001066194,0.0000590011,0.0005415641,0.0003966985,0.00007878509],"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":[0.0006642099,0.0009111943,0.7677811,0.001029819,0.0001005966,0.0007284773,0.005031653,0.0176069,0.09631185,0.02115873,0.0047501,0.08392531],"study_design_scores_gemma":[0.001522337,0.00008445709,0.1142263,0.0002285429,0.000001383543,0.000005824457,0.0002608428,0.7428526,0.01160044,0.004782917,0.1241607,0.000273576],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.893199,0.001983804,0.004098037,0.02396614,0.0002342914,0.0006702366,0.00000246227,0.0002702291,0.07557575],"genre_scores_gemma":[0.9697509,0.000007979421,0.001166506,0.000109635,0.00004072534,0.00005819453,0.000006420067,0.000002734354,0.0288569],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7252457,"threshold_uncertainty_score":0.8321571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04539881329855538,"score_gpt":0.3540391425883438,"score_spread":0.3086403292897885,"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."}}