{"id":"W3011084809","doi":"10.1051/0004-6361/201936866","title":"Cataloging accreted stars within<i>Gaia</i>DR2 using deep learning","year":2020,"lang":"en","type":"article","venue":"Astronomy and Astrophysics","topic":"Gamma-ray bursts and supernovae","field":"Physics and Astronomy","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Australian Astronomical Optics-Macquarie; Leibniz-Gemeinschaft; Natural Sciences and Engineering Research Council of Canada; Istituto Nazionale di Astrofisica; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Javna Agencija za Raziskovalno Dejavnost RS; Nuclear Safety and Security Commission; U.S. Department of Energy; University of California, Davis; W. M. Keck Foundation; Macquarie University; Agence Nationale de la Recherche; Australian Research Council; Space Telescope Science Institute; Deutsche Forschungsgemeinschaft; CERN; Munich Institute for Astro- and Particle Physics; European Space Agency; Johns Hopkins University; Flatiron Health; Australian National University; University of Oregon; Aspen Center for Physics; California Institute of Technology; National Aeronautics and Space Administration; Research Corporation for Science Advancement; National Science Foundation","keywords":"Milky Way; Stars; Metallicity; Deep learning; Set (abstract data type); Galaxy formation and evolution","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005631282,0.0005607463,0.0002807699,0.00189895,0.0002981437,0.0009604462,0.0007915105,0.0004282193,0.0008513777],"category_scores_gemma":[0.001354822,0.0001915359,0.0004577063,0.001160015,0.0002144047,0.0007639796,0.00107514,0.0004362959,0.0008301233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006183942,"about_ca_system_score_gemma":0.0005256327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008594599,"about_ca_topic_score_gemma":0.01624798,"domain_scores_codex":[0.9998333,0.0000281355,0.00001054335,0.0000680962,0.00003215904,0.00002766746],"domain_scores_gemma":[0.9992746,0.00008575104,0.0002150789,0.0001945191,0.0001336796,0.00009636579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002629226,0.0001916338,0.6875959,0.0001166329,0.0003069483,0.0002810501,0.000202781,0.09352146,0.01833384,0.002540468,0.00658235,0.190064],"study_design_scores_gemma":[0.00005081126,0.0001683733,0.2890351,0.00004934593,0.00009646863,0.0003463211,0.0002839922,0.6740174,0.01652676,0.005832733,0.01354004,0.00005270265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9312215,0.0004981468,0.05674784,0.0002703879,0.00002898484,0.00006932443,0.004005018,0.002972169,0.004186734],"genre_scores_gemma":[0.9452916,0.000104949,0.04388798,0.0001083449,0.00002266437,0.00002770765,0.008794899,0.00008647851,0.001675434],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008594599,"threshold_uncertainty_score":0.01708913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01456813190068071,"score_gpt":0.214293767069037,"score_spread":0.1997256351683563,"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."}}