{"id":"W4400328941","doi":"10.3389/esss.2024.10109","title":"Geospatial Data and Deep Learning Expose ESG Risks to Critical Raw Materials Supply: The Case of Lithium","year":2024,"lang":"en","type":"article","venue":"Earth Science Systems and Society","topic":"Mining and Resource Management","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada; Natural Resources Canada","funders":"Natural Resources Canada; Natural Environment Research Council; Sight Research UK","keywords":"Geospatial analysis; Population; Deep learning; Supply chain; Computer science; Artificial intelligence; Machine learning; Engineering; Cartography; Geography; Business","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":[],"consensus_categories":[],"category_scores_codex":[0.00129849,0.00008156385,0.0001238125,0.00002615432,0.0002840522,0.0004139315,0.0001632025,0.00003510841,0.000009921915],"category_scores_gemma":[0.00006957068,0.00005319568,0.00001749936,0.0001760996,0.0002607616,0.0001157239,0.0002488482,0.0001045428,0.000003525919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006069862,"about_ca_system_score_gemma":0.00001173187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003202005,"about_ca_topic_score_gemma":0.000009799312,"domain_scores_codex":[0.9992052,0.00003536631,0.0001614147,0.0002416428,0.0001500419,0.0002063765],"domain_scores_gemma":[0.9995368,0.0001067606,0.00001127543,0.0002374007,0.00002082777,0.00008700666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000251486,0.00009816215,0.003844776,0.01245736,0.0005216171,0.001731516,0.536746,0.1070772,0.1215871,0.03536954,0.01971484,0.1608268],"study_design_scores_gemma":[0.0001127083,0.00009003779,0.001788203,0.0003188909,0.00003772882,0.0004156025,0.03411221,0.9426258,0.001080523,0.000007498512,0.01920176,0.0002090437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908273,0.001852669,0.005885987,0.00008627111,0.0006982289,0.0001607016,0.00002307928,0.0000734457,0.0003923405],"genre_scores_gemma":[0.9992679,0.0001003448,0.0002992983,0.00001195659,0.00014471,0.000006160579,0.000001831985,0.000008154188,0.0001596525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8355486,"threshold_uncertainty_score":0.3991551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02368484764338676,"score_gpt":0.2796869626346586,"score_spread":0.2560021149912719,"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."}}