{"id":"W4212796401","doi":"10.1016/j.gexplo.2022.106959","title":"Performance of predictive supervised classification models of trace elements in magnetite for mineral exploration","year":2022,"lang":"en","type":"article","venue":"Journal of Geochemical Exploration","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Iron oxide copper gold ore deposits; Magnetite; Geology; Skarn; Naive Bayes classifier; Binary classification; Geochemistry; Random forest; Mineralogy; Support vector machine; Artificial intelligence; Quartz; Computer science; Fluid inclusions","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":[0.0007441969,0.00008671104,0.0002111392,0.0001401014,0.00004839543,0.00001100429,0.0003612711,0.00004797164,0.00001482147],"category_scores_gemma":[0.0001303569,0.000086912,0.00007642137,0.0003421951,0.0000273661,0.001475736,0.0000758653,0.0001606356,1.420857e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007225,"about_ca_system_score_gemma":0.00009436891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002181015,"about_ca_topic_score_gemma":7.43059e-7,"domain_scores_codex":[0.998468,0.00007105779,0.0007932488,0.0001517994,0.0003901017,0.0001257713],"domain_scores_gemma":[0.998513,0.00007339142,0.0007241076,0.0001628433,0.0004911801,0.00003547982],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006854054,0.0004979442,0.002026284,0.0001813443,0.00002213844,0.000001452531,0.004285205,0.2068281,0.7766141,0.002204083,0.000513953,0.006139987],"study_design_scores_gemma":[0.0009626712,0.0007301678,0.0005128227,0.00004053961,0.000009856157,0.000006270104,0.0007724014,0.8930085,0.09362701,0.01004741,0.0002050914,0.00007724296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8391895,0.00005701202,0.1584255,0.001709368,0.000112478,0.0002305676,0.000009722181,0.000007097557,0.0002588039],"genre_scores_gemma":[0.9869155,0.0000417811,0.01284429,0.00001764885,0.00004545841,0.00006004691,0.00003328418,0.000002354093,0.00003959116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6861804,"threshold_uncertainty_score":0.3544169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0504715591493711,"score_gpt":0.2497252089069436,"score_spread":0.1992536497575725,"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."}}