{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004236028,0.0001659317,0.0003608474,0.00009234574,0.0001118944,0.0000314344,0.0003372402,0.000213074,0.00007795998],"category_scores_gemma":[0.0001338637,0.000147181,0.0004531936,0.0003548166,0.0003795395,0.00002923298,0.0007068373,0.0005797247,9.637606e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00020023,"about_ca_system_score_gemma":0.0001218164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004229812,"about_ca_topic_score_gemma":0.000001194336,"domain_scores_codex":[0.9984381,0.0000348401,0.0007764774,0.0003796026,0.0002398147,0.0001311198],"domain_scores_gemma":[0.9980263,0.00007442657,0.001081631,0.0005499419,0.0002208614,0.00004684579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002127515,0.0003829358,0.026409,0.0009155048,0.0005746673,3.134561e-10,0.000391761,0.1036558,0.8661366,0.0005502942,0.000103313,0.0008589509],"study_design_scores_gemma":[0.0002721609,0.00001602546,0.04783258,0.0001785242,0.001093757,0.000001661735,0.001002697,0.418747,0.5293977,0.00116183,0.00005781489,0.0002382449],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966593,0.0006905379,0.001024062,0.001200929,0.00007328559,0.0001189274,0.0001430553,0.000031626,0.00005820992],"genre_scores_gemma":[0.9955988,0.00004495534,0.003817209,0.000001133663,0.00007099101,0.00001364986,0.0001662803,0.0000171104,0.0002698795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3367388,"threshold_uncertainty_score":0.6001868,"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."}}