{"id":"W2757022617","doi":"10.1093/mnras/stx3298","title":"An application of deep learning in the analysis of stellar spectra","year":2017,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Stellar, planetary, and galactic studies","field":"Physics and Astronomy","cited_by":121,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; Herzberg Institute of Astrophysics","funders":"","keywords":"Physics; Spectral line; Metallicity; Astronomical spectroscopy; Artificial neural network; Synthetic data; Surface gravity; Stellar classification; Range (aeronautics); Pipeline (software); Convolutional neural network; Pattern recognition (psychology); Artificial intelligence; Astrophysics; Stars; Computer science; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003416272,0.0001090521,0.0003522775,0.00001565798,0.0001772171,0.00002297807,0.0006681123,0.00003624789,0.00003402738],"category_scores_gemma":[0.00001195802,0.00007011506,0.0003827568,0.00008146262,0.0002310389,0.0000525987,0.00008499837,0.000164172,8.691487e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001272058,"about_ca_system_score_gemma":0.00001054753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002800328,"about_ca_topic_score_gemma":0.000185517,"domain_scores_codex":[0.9991397,0.00008112325,0.0003085719,0.000164504,0.0001563926,0.0001497009],"domain_scores_gemma":[0.9986507,0.0002026918,0.0005690319,0.0005230117,0.00003217518,0.00002244245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001152604,0.00007927586,0.6132306,0.000006013317,0.0003343697,5.760509e-9,0.0007694397,0.3827979,0.000005953448,0.00005093387,0.00000489392,0.002709051],"study_design_scores_gemma":[0.0001391898,0.00002319928,0.6651971,0.000003367331,0.0003880271,4.598097e-10,0.0009355259,0.33305,0.0001750308,0.00001692205,0.00002933281,0.00004228763],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956411,0.00006125321,0.0002828179,0.000091733,0.0000318863,0.0001353261,0.00001432124,0.00000270844,0.003738926],"genre_scores_gemma":[0.9992755,2.215657e-7,0.0005989339,0.000004307269,0.00007913467,0.000004670178,0.00001881253,0.000005072239,0.00001335172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05196648,"threshold_uncertainty_score":0.4233277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007871186514893313,"score_gpt":0.2270105373405596,"score_spread":0.2191393508256663,"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."}}