{"id":"W4394972048","doi":"10.1093/pasj/psae037","title":"Efficient identification of broad absorption line quasars using dimensionality reduction and machine learning","year":2024,"lang":"en","type":"preprint","venue":"Publications of the Astronomical Society of Japan","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Lawrence Berkeley National Laboratory; Smithsonian Astrophysical Observatory; University of Colorado Boulder; Office of Science; Max-Planck-Institut für Astronomie; Ministério da Ciência, Tecnologia e Inovação; U.S. Department of Energy; Smithsonian Institution; National Natural Science Foundation of China; University of Oxford; York University; Leibniz-Gemeinschaft; University of Notre Dame; Instituto de Astrofísica de Canarias; Astronomical Society of Japan; 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; New Mexico State University; University of Portsmouth; Vanderbilt University; Yale University; Max-Planck-Institut für Astrophysik","keywords":"Quasar; Dimensionality reduction; Artificial intelligence; Isomap; Computer science; Machine learning; Principal component analysis; Supermassive black hole; Astrophysics; Physics; Pattern recognition (psychology); Galaxy; Nonlinear dimensionality reduction","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":[0.002185695,0.001047921,0.001218678,0.001948104,0.0007042936,0.001601642,0.001351411,0.0008955355,0.0009075621],"category_scores_gemma":[0.006854553,0.0003065036,0.001220341,0.001524382,0.0005525855,0.001791989,0.001259295,0.001442842,0.001139738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006305739,"about_ca_system_score_gemma":0.001198008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003986371,"about_ca_topic_score_gemma":0.003910583,"domain_scores_codex":[0.9984922,0.0006590312,0.0001075837,0.0002954199,0.0003076077,0.0001381758],"domain_scores_gemma":[0.9972208,0.00122221,0.0002881417,0.0006170212,0.0005484896,0.0001034024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002754173,0.000724829,0.02407338,0.0003517169,0.0002675928,0.0002168039,0.0003399594,0.2415705,0.01134676,0.008744178,0.01854551,0.6935433],"study_design_scores_gemma":[0.00001709471,0.00005653192,0.002091913,0.00001728166,0.00001686384,0.00004190356,0.00007974051,0.9887782,0.00209587,0.005318752,0.00147253,0.00001339228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2511038,0.002656209,0.7346925,0.001590824,0.0002353362,0.0003422771,0.001498563,0.004907506,0.002973087],"genre_scores_gemma":[0.5486767,0.0004854068,0.444464,0.0002881023,0.0001626492,0.0002432896,0.004417429,0.0001239814,0.001138481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003986371,"threshold_uncertainty_score":0.01155913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03074476721909728,"score_gpt":0.2921514767399181,"score_spread":0.2614067095208208,"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."}}