{"id":"W4281661869","doi":"10.1190/tle41060400.1","title":"Downhole density estimation using multielement geochemistry and machine learning","year":2022,"lang":"en","type":"article","venue":"The Leading Edge","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Denison Mines (Canada); Geoscience BC; Ontario Tobacco Research Unit; CMC Microsystems (Canada); Hudbay Minerals (Canada); MRF Geosystems (Canada)","funders":"","keywords":"Borehole; Geology; Bulk density; Mineralogy; Soil science; Geotechnical engineering; Soil water","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":[0.0005622622,0.00008251127,0.00008369763,0.00001824067,0.0008388126,0.000061995,0.0003368233,0.00001958374,0.00004142293],"category_scores_gemma":[0.00008889433,0.00007017921,0.00001941792,0.0001350772,0.00003445187,0.00007648625,0.0006930515,0.0002967911,0.000005737824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004982926,"about_ca_system_score_gemma":0.00001752514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004178061,"about_ca_topic_score_gemma":0.000001126536,"domain_scores_codex":[0.9992946,0.00007499064,0.0001049994,0.0002144231,0.0001322567,0.000178758],"domain_scores_gemma":[0.9995576,0.00007465324,0.00007786805,0.0002361175,0.00002239359,0.00003133617],"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":[0.00003248373,0.0001541724,0.01865537,0.000213668,0.00008504734,0.00008410334,0.01402718,0.4252406,0.4462737,0.005964254,0.002957799,0.08631165],"study_design_scores_gemma":[0.0001399399,0.00001826937,0.0002416535,0.000007508457,0.000006886094,0.0001114334,0.0001149511,0.969013,0.02060628,0.001369349,0.008259093,0.0001115782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7796374,0.0002734229,0.2112131,0.003711935,0.0002357287,0.0001424402,0.000001965588,0.000205515,0.004578538],"genre_scores_gemma":[0.9922757,0.000002136225,0.005690487,0.0001449466,0.00003159804,0.000007337907,0.000005988736,0.000001922475,0.001839905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5437725,"threshold_uncertainty_score":0.6451553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02832842951490744,"score_gpt":0.2438667371108293,"score_spread":0.2155383075959218,"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."}}