{"id":"W4300979517","doi":"10.1038/s41467-022-33388-5","title":"Reconstructing Earth’s atmospheric oxygenation history using machine learning","year":2022,"lang":"en","type":"article","venue":"Nature Communications","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada","funders":"Science Mission Directorate; State Key Laboratory of Geological Processes and Mineral Resources; NASA Astrobiology Institute; National Natural Science Foundation of China; National Aeronautics and Space Administration","keywords":"Atmospheric oxygen; Mantle (geology); Earth (classical element); Mafic; Billion years; Proxy (statistics); Earth science; Geology; Environmental science; Astrobiology; Oxygen; Chemistry; Geophysics; Geochemistry; Computer science; Physics; Machine learning; Astrophysics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006682987,0.0003875273,0.0002840093,0.001389285,0.0002388781,0.0007097577,0.0005252481,0.0005371944,0.0006675957],"category_scores_gemma":[0.00207923,0.000161127,0.000392804,0.0009169355,0.0003486634,0.0006373006,0.0005511685,0.0005593152,0.0002584518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004962868,"about_ca_system_score_gemma":0.0004149339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004848506,"about_ca_topic_score_gemma":0.005605989,"domain_scores_codex":[0.9998386,0.00005075349,0.000007804008,0.00005536385,0.00002201775,0.00002541166],"domain_scores_gemma":[0.9992315,0.0003847438,0.0001363447,0.0001077833,0.00008722285,0.00005244815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001294718,0.00021225,0.1511492,0.00008475119,0.0003410324,0.0001360601,0.0000874299,0.674408,0.009355608,0.002323016,0.003428712,0.1583444],"study_design_scores_gemma":[0.00000377472,0.000008619797,0.01162896,0.000006665698,0.000009157944,0.000009426337,0.00001891635,0.9834965,0.0008254882,0.003554261,0.0004314889,0.000006574039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8711201,0.001243654,0.1196654,0.001516814,0.0000947098,0.00002243704,0.00153567,0.0009931519,0.003808001],"genre_scores_gemma":[0.9838052,0.0001191251,0.01469119,0.0000745186,0.00004357913,0.000008794679,0.0008805132,0.00001310267,0.000363901],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004848506,"threshold_uncertainty_score":0.009640574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.029652418278621,"score_gpt":0.2469102198776282,"score_spread":0.2172578015990072,"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."}}