{"id":"W4382403947","doi":"10.1093/rasti/rzad023","title":"A machine learning approach to galactic emission-line region classification","year":2023,"lang":"en","type":"article","venue":"RAS Techniques and Instruments","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Université de Montréal; Centre for Research in Astrophysics of Québec","funders":"Natural Sciences and Engineering Research Council of Canada; College of Natural Resources and Sciences, Humboldt State University; Fundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina; Fonds de recherche du Québec – Nature et technologies; Université de Montréal; National Research Council; Newton Fund; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Royal Society","keywords":"Doubly ionized oxygen; Astrophysics; Line (geometry); Luminosity; Emission spectrum; Physics; Photoionization; Supernova; Artificial intelligence; Planetary nebula; Machine learning; Artificial neural network; Computer science; Astronomy; Spectral line; Mathematics; Galaxy; Stars; Geometry; Ionization","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000182915,0.0001460434,0.0001398985,0.0001758518,0.0002593933,0.00005970223,0.0001057963,0.00004526435,0.00002665076],"category_scores_gemma":[0.000008664925,0.0001362623,0.00003553394,0.0003831111,0.00002532386,0.0002725007,0.00008762552,0.0001531981,0.00003463291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005987918,"about_ca_system_score_gemma":0.0000206951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009548022,"about_ca_topic_score_gemma":2.590603e-7,"domain_scores_codex":[0.9990885,0.00003878331,0.0002499341,0.0002419085,0.0001595144,0.0002213882],"domain_scores_gemma":[0.999527,0.000009298607,0.000125332,0.0001813046,0.00004873344,0.0001083169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001331421,0.00006438688,0.9784594,0.00002298576,0.00001586093,1.347176e-8,0.0003734646,0.00000495281,0.0005098535,0.00456524,0.001083692,0.0148868],"study_design_scores_gemma":[0.0005343085,0.0002023924,0.9234335,0.00008872658,0.00002517473,0.000008755831,0.0006098984,0.04417878,0.003325857,0.005010755,0.0221865,0.0003953797],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893451,0.00001020761,0.002386512,0.0002269833,0.00004100422,0.0003919861,0.000005190642,0.0003823979,0.00721067],"genre_scores_gemma":[0.9956352,0.00004583873,0.001794934,0.000004831976,0.0001082418,0.0001291236,0.0002465976,0.00002166745,0.00201359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05502597,"threshold_uncertainty_score":0.5556616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02341598067587988,"score_gpt":0.2567581827243963,"score_spread":0.2333422020485164,"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."}}