{"id":"W2996376220","doi":"10.1002/jqs.3170","title":"Machine learning classifiers for attributing tephra to source volcanoes: an evaluation of methods for Alaska tephras","year":2019,"lang":"en","type":"article","venue":"Journal of Quaternary Science","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tephra; Volcano; Geology; Holocene; Pleistocene; Chronology; Tephrochronology; Artificial intelligence; Machine learning; Geochemistry; Archaeology; Physical geography; Paleontology; Computer science; Geography","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":[0.01643791,0.0001327161,0.0002945982,0.0002442606,0.0002308032,0.0001268788,0.001557326,0.00005444597,0.0000129541],"category_scores_gemma":[0.002917978,0.0001080198,0.0001300565,0.0005851629,0.00009551748,0.001030928,0.0001933199,0.000177836,0.000002182017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108995,"about_ca_system_score_gemma":0.0004735592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001116162,"about_ca_topic_score_gemma":7.811727e-7,"domain_scores_codex":[0.9977801,0.0002160061,0.0005801878,0.0003610843,0.0006688409,0.0003937883],"domain_scores_gemma":[0.9964201,0.0004789109,0.0008084521,0.0003320988,0.001762214,0.0001981547],"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":[0.0001252289,0.0001043061,0.03036631,0.0001194267,0.00003574797,0.000001229003,0.004050405,0.1531949,0.4878965,0.0008664679,0.0001011281,0.3231384],"study_design_scores_gemma":[0.0007167087,0.0009995339,0.002235206,0.00009479404,0.00002388502,0.00005559361,0.0005838225,0.9199256,0.06418661,0.00278661,0.008237357,0.0001543357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.396404,0.00005415696,0.6017876,0.0009194009,0.0003925569,0.0002770939,0.000001058433,0.00001117287,0.0001529491],"genre_scores_gemma":[0.7566611,0.000003105891,0.2428184,0.0001071407,0.00007563597,0.000007319175,8.891147e-7,0.000003023817,0.0003233281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7667307,"threshold_uncertainty_score":0.5697083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08029582090672344,"score_gpt":0.3860298657644839,"score_spread":0.3057340448577605,"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."}}