{"id":"W4394001539","doi":"10.2139/ssrn.4782335","title":"Exploring Gem-Quality Beryl Global Geochemical Provenance Through Fingerprinting And Machine Learning Methods","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Mineralogy and Gemology Studies","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Provenance; Quality (philosophy); Geology; Geochemistry; Computer science; Philosophy; Epistemology","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":[0.002559988,0.000617622,0.0006443881,0.002086989,0.0005943315,0.002277888,0.0008670304,0.00114283,0.003295392],"category_scores_gemma":[0.01358456,0.0004104771,0.0005176105,0.00246764,0.0006984896,0.003316733,0.002480806,0.001341506,0.001224933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006153018,"about_ca_system_score_gemma":0.001131477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00583036,"about_ca_topic_score_gemma":0.008321856,"domain_scores_codex":[0.9993178,0.0001232531,0.00004987178,0.0002154086,0.0002111005,0.00008258547],"domain_scores_gemma":[0.9960913,0.0009082911,0.0005064138,0.001310692,0.001041935,0.0001412931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003680336,0.0002661693,0.2660142,0.001520916,0.000842758,0.001437327,0.001322954,0.2346563,0.08556007,0.04470453,0.02498402,0.3350104],"study_design_scores_gemma":[0.0002063291,0.0001777935,0.05403769,0.0002109633,0.0003220819,0.0004298936,0.0005432638,0.7785901,0.04862973,0.06689518,0.0498289,0.0001280766],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.59935,0.002654384,0.3608076,0.00181154,0.00116685,0.00006384379,0.0131321,0.01034232,0.01067151],"genre_scores_gemma":[0.9294969,0.0004578381,0.05963575,0.0001229942,0.00012904,0.00001416092,0.00706052,0.001458687,0.001624085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00583036,"threshold_uncertainty_score":0.01353866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09467542626720271,"score_gpt":0.338441400511929,"score_spread":0.2437659742447263,"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."}}