{"paper":{"title":"Using Active Learning to Improve Quasar Identification for the DESI Spectra Processing Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.CO"],"primary_cat":"astro-ph.IM","authors_text":"A. Bault, A. Brodzeller, A. de la Macorra, A. D. Myers, A. Font-Ribera, A. Kremin, A. Lambert, A. Meisner, B. A. Weaver, C. Saulder, David Kirkby, D. Bianchi, D. Brooks, D. M. Alexander, D. Schlegel, D. Sprayberry, Dylan Green, E. Armengaud, E. Gazta\\~naga, E. Sanchez, F. Prada, F. Sinigaglia, G. Gutierrez, G. Rossi, G. Tarl\\'e, H. Seo, H. Zou, I. P\\'erez-R\\`afols, J. Aguilar, J. E. Forero-Romero, J. Moustakas, J. Yu, L. Le Guillou, M. E. Levi, M. Ishak, M. Landriau, M. Manera, M. Schubnell, N. Palanque-Delabrouille, P. Doel, R. de Belsunce, R. Kehoe, R. Miquel, R. Zhou, S. Ahlen, S. Bailey, S. Ferraro, S. Gontcho A Gontcho, S. Juneau, S. Youles, T. Claybaugh, T. Kisner, T. Tan, V. A. Fawcett","submitted_at":"2025-05-02T21:40:05Z","abstract_excerpt":"The Dark Energy Spectroscopic Instrument (DESI) survey uses an automatic spectral classification pipeline to classify spectra. QuasarNET is a convolutional neural network used as part of this pipeline originally trained using data from the Baryon Oscillation Spectroscopic Survey (BOSS). In this paper we implement an active learning algorithm to optimally select spectra to use for training a new version of the QuasarNET weights file using only DESI data, specifically to improve classification accuracy. This active learning algorithm includes a novel outlier rejection step using a Self-Organizin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01596","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.01596/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}