{"id":"W4376170986","doi":"10.2138/am-2022-8688","title":"Identifying serpentine minerals by their chemical compositions with machine learning","year":2023,"lang":"en","type":"article","venue":"American Mineralogist","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Geology; Geochemistry; Mineralogy; Ringwoodite; Chrysotile; Crust; Blueschist; Plagioclase; Subduction; Tectonics; Mantle (geology); Materials science; Quartz; Seismology; Paleontology","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":[0.0001716075,0.0002258403,0.0002866743,0.00007777418,0.0002293468,0.0001470322,0.0006805226,0.0000351225,0.0000357038],"category_scores_gemma":[0.0000747235,0.0001780516,0.00007189794,0.001258589,0.0003556045,0.0001780275,0.0003240917,0.0002745183,0.00007123834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002193192,"about_ca_system_score_gemma":0.00002003453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005299213,"about_ca_topic_score_gemma":0.00002070785,"domain_scores_codex":[0.9984775,0.00007601637,0.0002293838,0.0005238989,0.0002065827,0.000486623],"domain_scores_gemma":[0.9990545,0.0001461104,0.0001663825,0.0004241992,0.0000820339,0.0001268077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002036718,0.0001205545,0.01246385,0.00003956133,0.00008380448,0.0001689618,0.0006154365,0.001478774,0.9311643,0.00169602,0.04590992,0.006238507],"study_design_scores_gemma":[0.00295753,0.001000763,0.01043121,0.0002611979,0.00008257567,0.001175638,0.001684526,0.346969,0.1921465,0.002975739,0.4369501,0.003365267],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.83517,0.0001860886,0.09641847,0.03628433,0.0001779162,0.0003198676,0.00007411724,0.002200314,0.02916894],"genre_scores_gemma":[0.9824803,0.00002554225,0.007519726,0.0003972692,0.00005787814,0.00003385349,0.0003764674,0.000008279681,0.009100687],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7390178,"threshold_uncertainty_score":0.7260731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01551847291926166,"score_gpt":0.2388096277432085,"score_spread":0.2232911548239468,"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."}}