{"id":"W4401825009","doi":"10.3847/1538-4357/ad496a","title":"GWSkyNet. II. A Refined Machine-learning Pipeline for Real-time Classification of Public Gravitational Wave Alerts","year":2024,"lang":"en","type":"article","venue":"The Astrophysical Journal","topic":"Pulsars and Gravitational Waves Research","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Indo-US Science and Technology Forum; Canada Research Chairs; McGill University; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Physics; Gravitational wave; Classifier (UML); LIGO; False alarm; Artificial intelligence; Sky; Constant false alarm rate; Snapshot (computer storage); Pipeline (software); Machine learning; Astronomy; Computer science; Real-time computing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001491042,0.001655243,0.0007053978,0.001690126,0.000515733,0.001236597,0.002833475,0.001458603,0.007855863],"category_scores_gemma":[0.004226463,0.000642653,0.0007019878,0.0009063166,0.0005102178,0.002233682,0.001416399,0.001598041,0.006064496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001024769,"about_ca_system_score_gemma":0.001511034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01350026,"about_ca_topic_score_gemma":0.0157603,"domain_scores_codex":[0.9993144,0.00009232226,0.00004621582,0.0002692072,0.0001764644,0.0001014209],"domain_scores_gemma":[0.9988148,0.0003494244,0.00008523749,0.0003029313,0.0003424833,0.0001051865],"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":[0.00187476,0.0008088907,0.01730683,0.0004738694,0.0003414628,0.0003956093,0.0002813909,0.09566157,0.02705804,0.003521294,0.1606424,0.6916339],"study_design_scores_gemma":[0.00009505338,0.0001773795,0.003500481,0.00002171875,0.00002533436,0.00005210305,0.00004081985,0.97004,0.01195206,0.003424851,0.01063117,0.00003895563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.1660176,0.0008229461,0.3503925,0.0008806214,0.0007803369,0.0008286933,0.01633023,0.4559453,0.00800178],"genre_scores_gemma":[0.5806261,0.0002227455,0.3391489,0.0009869789,0.0001807454,0.0008846842,0.05850045,0.005018793,0.01443066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01350026,"threshold_uncertainty_score":0.02684331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03093823712933271,"score_gpt":0.3265369608811294,"score_spread":0.2955987237517967,"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."}}