{"id":"W2900297252","doi":"10.48550/arxiv.1811.03390","title":"Bayesian Deep Learning for Exoplanet Atmospheric Retrieval","year":2018,"lang":"en","type":"preprint","venue":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Population and Public Health","funders":"National Aeronautics and Space Administration; NASA Astrobiology Institute; Secretário de Ciência, Tecnologia e Ensino Superior, Governo do Estado de Parana; Goddard Space Flight Center; Nvidia; Ames Research Center","keywords":"Exoplanet; Computer science; Planet; Terrestrial planet; Atmospheric composition; Atmosphere (unit); Astrobiology; Artificial intelligence; Meteorology; Physics; Astronomy","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":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.001919287,0.0003917185,0.0009117837,0.0002936007,0.001516375,0.00003524202,0.006054567,0.0008856458,0.0006958694],"category_scores_gemma":[0.0002403144,0.0005017689,0.0006153825,0.001165608,0.002414614,0.0003433735,0.005838937,0.001945269,0.00001607303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002255304,"about_ca_system_score_gemma":0.000685876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003343129,"about_ca_topic_score_gemma":0.001499193,"domain_scores_codex":[0.9961893,0.0006860749,0.0002656011,0.00103909,0.001023233,0.0007967329],"domain_scores_gemma":[0.9946849,0.0008845012,0.0007989091,0.001478823,0.00184641,0.000306411],"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":[0.02438193,0.007979091,0.03310125,0.02142435,0.009619721,0.002676644,0.3253997,0.2748672,0.01208344,0.01638674,0.1499541,0.1221258],"study_design_scores_gemma":[0.006207077,0.002403466,0.009319537,0.001756303,0.0006764769,0.00004297094,0.1527309,0.5409714,0.0004728993,0.004373456,0.2792278,0.001817671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2227789,0.0008044537,0.7354845,0.01589181,0.0004553947,0.002090513,0.0004273225,0.0003281712,0.02173896],"genre_scores_gemma":[0.8966138,0.001835446,0.07397331,0.00001968448,0.000134312,2.850405e-8,0.0003209817,0.00001768302,0.02708479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6738349,"threshold_uncertainty_score":0.9997835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03509883636397196,"score_gpt":0.2481105486884368,"score_spread":0.2130117123244649,"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."}}