{"id":"W4390511336","doi":"10.1016/j.acags.2023.100149","title":"GeoCoDA: Recognizing and validating structural processes in geochemical data. A workflow on compositional data analysis in lithogeochemistry","year":2024,"lang":"en","type":"article","venue":"Applied Computing and Geosciences","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; Geological Survey of Canada; University of Waterloo","funders":"","keywords":"Compositional data; Workflow; Geology; Geochemistry; Computer science; Data mining; Database; Machine learning","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":[0.001334676,0.000212918,0.0002923443,0.0002244251,0.0002294934,0.0006450105,0.00148974,0.00009011582,0.000005064844],"category_scores_gemma":[0.0002494589,0.0001888762,0.00001648655,0.002223888,0.0001935845,0.0004019772,0.001989979,0.0003583731,0.000001218108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001797709,"about_ca_system_score_gemma":0.0001175434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001038633,"about_ca_topic_score_gemma":0.00006264756,"domain_scores_codex":[0.9972787,0.00003916441,0.0003680493,0.001582493,0.0003048597,0.0004266699],"domain_scores_gemma":[0.9983143,0.0007780448,0.00008294809,0.0007030866,0.00003283424,0.00008878045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009947318,0.0004314776,0.2083776,0.003564525,0.0004951676,0.0006097187,0.01102102,0.03923843,0.02174848,0.03619797,0.0006786431,0.6775375],"study_design_scores_gemma":[0.0001837606,0.00001444258,0.008341885,0.0002803273,0.00002778373,0.00005349289,0.0002536771,0.9799747,0.001021431,0.009058267,0.000462682,0.0003275292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9768938,0.0009673198,0.01674514,0.0025683,0.0001117711,0.0001527927,0.00004945034,0.0001487353,0.002362658],"genre_scores_gemma":[0.972653,0.00002067572,0.02689015,0.00009980744,0.00007624365,0.00000439977,0.0002309427,0.000002286295,0.00002253189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9407363,"threshold_uncertainty_score":0.7702148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03658029191266851,"score_gpt":0.2922814459141251,"score_spread":0.2557011540014565,"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."}}