{"id":"W4395669421","doi":"10.1093/rasti/rzae017","title":"Reconstructing robust background integral field unit spectra using machine learning","year":2024,"lang":"en","type":"article","venue":"RAS Techniques and Instruments","topic":"Spectroscopy and Laser Applications","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Theoretical Astrophysics; University of Toronto; Mila - Quebec Artificial Intelligence Institute; Université Laval; Université de Montréal; Centre for Research in Astrophysics of Québec","funders":"Institut national des sciences de l'Univers; Natural Sciences and Engineering Research Council of Canada; Mitacs; Royal Astronomical Society; Horizon 2020 Framework Programme; Université de Montréal; Royal Society of Chemistry; National Science Foundation","keywords":"Physics; Data cube; Galaxy; Astrophysics; Emission spectrum; Principal component analysis; Astronomy; Artificial intelligence; Spectral line; Computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009580277,0.0001655059,0.0001405982,0.00008061897,0.0002152058,0.0001873724,0.0001130568,0.0001255905,0.001494156],"category_scores_gemma":[0.000009597339,0.0001576357,0.00005238414,0.0001562346,0.00005198883,0.0002007428,0.00007685803,0.0005241735,0.000008362635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007514407,"about_ca_system_score_gemma":0.00002965227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004099401,"about_ca_topic_score_gemma":0.00001433758,"domain_scores_codex":[0.9991603,0.00001095342,0.0002145222,0.0002992289,0.00009393466,0.0002210505],"domain_scores_gemma":[0.9996737,0.00004364,0.00004795798,0.0001565697,0.00001485217,0.0000633291],"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":[0.00007444756,0.0001091399,0.09818947,0.0007055196,0.0002604845,0.00007222242,0.0004519078,0.00001127147,0.5130013,0.02191496,0.0003746607,0.3648346],"study_design_scores_gemma":[0.0001681315,0.00007428975,0.00001982961,0.0005170544,0.00005552588,0.0003622168,0.0005236969,0.0400455,0.9008689,0.001749448,0.05529288,0.0003225405],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9586788,0.0003792128,0.001937107,0.0001080677,0.00006605096,0.00008169216,0.00001322229,0.0005946458,0.03814125],"genre_scores_gemma":[0.9762869,0.0003878594,0.02184939,0.00004229199,0.0001999953,0.00002159141,0.00003361676,0.00003282272,0.001145548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3878675,"threshold_uncertainty_score":0.9994186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03483296549302606,"score_gpt":0.3057248689121823,"score_spread":0.2708919034191562,"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."}}