{"id":"W6959522140","doi":"10.1051/0004-6361/202451309/pdf","title":"Optimised sampling of SDSS-IV MaStar spectra for stellar classification using supervised models","year":2025,"lang":"en","type":"article","venue":"Springer Link (Chiba Institute of Technology)","topic":"Particle accelerators and beam dynamics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Lawrence Berkeley National Laboratory; Office of Science; Max-Planck-Institut für Astronomie; University of Colorado Boulder; Ministério da Ciência, Tecnologia e Inovação; University of Oxford; York University; Leibniz-Gemeinschaft; University of Notre Dame; Instituto de Astrofísica de Canarias; Carnegie Mellon University; Universidad Nacional Autónoma de México; Alfred P. Sloan Foundation; University of Washington; Johns Hopkins University; Carnegie Institution of Washington; University of Utah; Ohio State University; U.S. Department of Energy; Smithsonian Institution; New Mexico State University; University of Portsmouth; Vanderbilt University; Yale University; Max-Planck-Institut für Astrophysik","keywords":"Sampling (signal processing); Preprocessor; Feature (linguistics); Pattern recognition (psychology); Pipeline (software); Curse of dimensionality; Dimensionality reduction; Supervised learning; Oversampling; Random forest","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":[0.005242178,0.0009328404,0.001139906,0.001192024,0.0006663949,0.001401133,0.002302379,0.001615311,0.001367909],"category_scores_gemma":[0.01608152,0.0005257259,0.001420961,0.0007210929,0.001004573,0.001414534,0.001392912,0.001623993,0.00106032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001407641,"about_ca_system_score_gemma":0.001346488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005730978,"about_ca_topic_score_gemma":0.008706823,"domain_scores_codex":[0.998123,0.0008732511,0.00009176925,0.0005268953,0.0002590025,0.0001260588],"domain_scores_gemma":[0.9931415,0.003842534,0.0005919762,0.001021667,0.001131908,0.000270498],"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":[0.0004999375,0.0004427712,0.01461417,0.0002006994,0.0001873311,0.0001074952,0.0003827406,0.791407,0.005039198,0.003639973,0.006792775,0.1766859],"study_design_scores_gemma":[0.00002146422,0.00003102253,0.0005642265,0.000007842347,0.000008129841,0.00001412687,0.00002890132,0.9957249,0.001208767,0.001994218,0.000391603,0.00000470853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2608051,0.0006210296,0.7278152,0.0006209669,0.0001226292,0.0004245273,0.0007804797,0.005914014,0.002896148],"genre_scores_gemma":[0.7476153,0.00008668304,0.2468902,0.0003363234,0.0000947545,0.0003220839,0.002763739,0.0002955549,0.001595281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005730978,"threshold_uncertainty_score":0.02772367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04240561401946211,"score_gpt":0.2654708974333519,"score_spread":0.2230652834138898,"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."}}