{"id":"W2101047548","doi":"10.1093/mnras/stv1608","title":"A hybrid ensemble learning approach to star–galaxy classification","year":2015,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Center for Advanced Study, University of Illinois at Urbana-Champaign; Institut national des sciences de l'Univers; Natural Sciences and Engineering Research Council of Canada; Office of Science; University of Illinois at Urbana-Champaign; Centre National de la Recherche Scientifique; Canadian Space Agency; Alfred P. Sloan Foundation; U.S. Department of Energy; National Science Foundation","keywords":"Random forest; Machine learning; Artificial intelligence; Bayesian probability; Galaxy; Ensemble learning; Classifier (UML); Supervised learning; Physics; Pattern recognition (psychology); Computer science; Artificial neural network; Astrophysics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002314242,0.0001743098,0.0002884434,0.0000178135,0.0001200127,0.00004625503,0.000544109,0.00009084598,0.00007846384],"category_scores_gemma":[0.0001463571,0.0001343843,0.000331679,0.000162254,0.0001080335,0.00006191878,0.0002200355,0.0003457084,0.00002529744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002641738,"about_ca_system_score_gemma":0.00006937073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001965285,"about_ca_topic_score_gemma":0.000002154515,"domain_scores_codex":[0.9987429,0.00003060383,0.0002978859,0.0003291838,0.0002838761,0.0003155455],"domain_scores_gemma":[0.9990849,0.00007517319,0.0002125199,0.0003572724,0.0000744447,0.0001956685],"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":[0.00007990921,0.0002760107,0.0316568,0.00005423566,0.0002268444,4.780346e-8,0.0007519461,0.9569239,0.002736991,0.00005772157,0.006721097,0.0005144883],"study_design_scores_gemma":[0.0007852509,0.00007486458,0.01720867,0.00001863978,0.0003255556,3.70515e-8,0.004163017,0.8980851,0.07449728,0.00004093913,0.004451642,0.0003490141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821512,0.0001081638,0.0006025165,0.0002622136,0.0000450455,0.00007546884,0.00001474287,0.00005133838,0.0166893],"genre_scores_gemma":[0.9871033,9.264202e-8,0.01018458,0.00003465331,0.0001571362,0.0000174946,0.00002113493,0.00001997926,0.00246164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0717603,"threshold_uncertainty_score":0.5480033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02564637418064466,"score_gpt":0.2418891626217066,"score_spread":0.2162427884410619,"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."}}