{"id":"W3191288094","doi":"10.20944/preprints202108.0067.v1","title":"3D Geophysical Post-Inversion Feature Extraction for Mineral Exploration Through Fast-ICA","year":2021,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Ministère de l'Énergie et des Ressources Naturelles","keywords":"Geology; Inversion (geology); Feature extraction; Geophysics; Physical property; Property (philosophy); Geologic map; Mineral exploration; Feature (linguistics); Induced polarization; Pattern recognition (psychology); Computer science; Artificial intelligence; Data mining; Seismology; Electrical resistivity and conductivity; Tectonics; Geomorphology; Materials science","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005326078,0.0004551523,0.0004781273,0.0001570682,0.0002176133,0.0002990326,0.001203787,0.0006924064,0.00006278223],"category_scores_gemma":[0.0002447775,0.0004929393,0.0003963641,0.0002775624,0.00005749726,0.002058296,0.002233957,0.001156651,0.0001851271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002274688,"about_ca_system_score_gemma":0.0003445699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001756267,"about_ca_topic_score_gemma":0.00003699755,"domain_scores_codex":[0.9966345,0.0002987119,0.0004770699,0.001608803,0.0005957864,0.0003851583],"domain_scores_gemma":[0.996669,0.0001411285,0.0004813123,0.001842136,0.0007480554,0.0001183634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007514358,0.003950237,0.01238559,0.001650378,0.0008969135,0.0001390894,0.0815017,0.0120397,0.7355019,0.07998896,0.01871364,0.0524804],"study_design_scores_gemma":[0.001837052,0.0003915254,0.05077993,0.0007911112,0.0002124106,0.00005269926,0.001304009,0.1454825,0.6884361,0.04972998,0.05795005,0.003032696],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.26144,0.0000472688,0.7256328,0.007659897,0.001157474,0.00125482,0.00001852463,0.0009101353,0.001879067],"genre_scores_gemma":[0.8270333,0.0001002415,0.1682557,0.001199481,0.000474973,0.0006541075,0.0005765898,0.00004980025,0.001655846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5655932,"threshold_uncertainty_score":0.9997522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1040687802258447,"score_gpt":0.3602724034280822,"score_spread":0.2562036232022375,"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."}}