{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002089691,0.00125989,0.0008657934,0.0007657107,0.000533313,0.001102451,0.001253012,0.001292752,0.001237125],"category_scores_gemma":[0.004266992,0.0003696922,0.0009412805,0.0004542637,0.0003808126,0.0008751753,0.0006721824,0.001348544,0.000566347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009391203,"about_ca_system_score_gemma":0.001466093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02142668,"about_ca_topic_score_gemma":0.01448804,"domain_scores_codex":[0.999534,0.0001840248,0.0000321507,0.0001176628,0.00006754218,0.00006464835],"domain_scores_gemma":[0.9959651,0.002754537,0.0002489443,0.0002326938,0.0006585881,0.0001401077],"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":[0.001401017,0.000872666,0.01708128,0.0001169622,0.0002786421,0.00008602289,0.00007334108,0.8342446,0.003510002,0.0005245079,0.004149777,0.1376612],"study_design_scores_gemma":[0.00000782071,0.00003452062,0.0006049905,0.000003466582,0.0000139902,0.000005530176,0.00001031665,0.9983121,0.0007537508,0.000204126,0.00004632754,0.00000312573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.939716,0.001513837,0.0518855,0.0009306674,0.00025021,0.00006005709,0.0009750391,0.002052392,0.00261613],"genre_scores_gemma":[0.9927005,0.0001114729,0.005075183,0.00006337112,0.00003708198,0.00001787373,0.001019824,0.00002718233,0.000947553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02142668,"threshold_uncertainty_score":0.04260391,"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."}}