{"id":"W4407240674","doi":"10.1007/s11053-024-10438-x","title":"Pan-Canadian Predictive Modeling of Lithium–Cesium–Tantalum Pegmatites with Deep Learning and Natural Language Processing","year":2025,"lang":"en","type":"article","venue":"Natural Resources Research","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick; Manitoba Hydro; Laurentian University; Geological Survey of Canada; Natural Resources Canada","funders":"Natural Resources Canada","keywords":"Prospectivity mapping; Computer science; Interpretability; Artificial intelligence; Convolutional neural network; Machine learning; Geology","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":[0.0009133405,0.0001514105,0.0002035145,0.0004114782,0.0005480162,0.0002620428,0.0006865673,0.0001204162,0.000007455023],"category_scores_gemma":[0.0009166106,0.0001146103,0.0000320593,0.001161111,0.0002394864,0.0003058856,0.0003964524,0.001237046,0.000001788451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008205118,"about_ca_system_score_gemma":0.0002092836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003098392,"about_ca_topic_score_gemma":0.002073825,"domain_scores_codex":[0.9979329,0.0001968355,0.0002029449,0.000472209,0.0006024454,0.0005926809],"domain_scores_gemma":[0.9986441,0.0003283852,0.00006175308,0.0002332017,0.0006055639,0.0001270182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006358502,0.0001313211,0.06332458,0.003424203,0.0002955061,0.0003587712,0.07577143,0.01646644,0.03804787,0.004156812,0.000279491,0.7971077],"study_design_scores_gemma":[0.0002533509,0.00008788833,0.002786883,0.0003873289,0.0000057076,0.00002048531,0.005087126,0.9862278,0.00210726,0.000353706,0.002535653,0.0001468503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8821841,0.03570801,0.004208012,0.002488196,0.00007724241,0.0004496024,0.000002624105,0.0001533014,0.07472886],"genre_scores_gemma":[0.9922087,0.0000369573,0.002361909,0.00003719021,0.00003758537,0.00001335117,0.000004770842,0.000003595394,0.005295964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9697613,"threshold_uncertainty_score":0.5374417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01242914242357231,"score_gpt":0.2934952910299932,"score_spread":0.2810661486064209,"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."}}