{"id":"W4416540833","doi":"10.2139/ssrn.5786802","title":"Tractable approximate Gaussian inference for interpretable mineral prospectivity modelling","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Prospectivity mapping; Inference; Robustness (evolution); Bayesian inference; Bayesian probability; Gaussian; Benchmark (surveying); Artificial neural network; Monte Carlo method","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":[0.005468745,0.001400115,0.004377564,0.001475667,0.0008888197,0.00348107,0.004751203,0.003802512,0.00630153],"category_scores_gemma":[0.03869329,0.001987288,0.002242402,0.00270494,0.003022393,0.004737446,0.003679391,0.005033565,0.0009983291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003655578,"about_ca_system_score_gemma":0.003012399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02149412,"about_ca_topic_score_gemma":0.02165634,"domain_scores_codex":[0.9975995,0.001165687,0.0001307763,0.0005150936,0.0003584612,0.0002304363],"domain_scores_gemma":[0.9681481,0.02865674,0.000859617,0.001347827,0.0006946403,0.0002931216],"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":[0.0001468996,0.00006970812,0.0007235876,0.0001415794,0.00008424136,0.0001112327,0.00009736968,0.8810808,0.0002190461,0.09701645,0.002374603,0.01793463],"study_design_scores_gemma":[0.00001303998,0.000005421477,0.00006669099,0.000008272365,0.000008128455,0.00001017141,0.000008477539,0.8879106,0.00005628133,0.1116725,0.000234759,0.000005706149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01337829,0.0006893013,0.9813673,0.001239336,0.00004097666,0.00004723934,0.0008553871,0.0005356236,0.001846465],"genre_scores_gemma":[0.7757359,0.001423942,0.2060445,0.0007128742,0.000438153,0.00040971,0.00336562,0.0004381488,0.01143109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02149412,"threshold_uncertainty_score":0.04273802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01803526463311969,"score_gpt":0.261622381600197,"score_spread":0.2435871169670773,"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."}}