{"id":"W3212807346","doi":"10.3847/1538-4357/ac5019","title":"GWSkyNet-Multi: A Machine-learning Multiclass Classifier for LIGO–Virgo Public Alerts","year":2022,"lang":"en","type":"preprint","venue":"The Astrophysical Journal","topic":"Pulsars and Gravitational Waves Research","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; McGill University","funders":"Science and Technology Facilities Council; Natural Sciences and Engineering Research Council of Canada; Istituto Nazionale di Fisica Nucleare; Centre National de la Recherche Scientifique; Canada Research Chairs; Max-Planck-Gesellschaft; National Science Foundation","keywords":"LIGO; Gravitational wave; Physics; Neutron star; Binary black hole; Binary number; Classifier (UML); Binary classification; Astrophysics; Astronomy; Artificial intelligence; Computer science; Support vector machine","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":[0.002448235,0.002573278,0.001278167,0.003482623,0.0007562371,0.001232554,0.002758011,0.00315884,0.003778823],"category_scores_gemma":[0.004348757,0.0004470869,0.001145691,0.001293183,0.0005132097,0.001803181,0.00194845,0.002198927,0.002472885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001335679,"about_ca_system_score_gemma":0.001245522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01047892,"about_ca_topic_score_gemma":0.008826372,"domain_scores_codex":[0.9989939,0.0002156146,0.00009258728,0.0002975251,0.0002301748,0.0001702462],"domain_scores_gemma":[0.9980982,0.0007720935,0.0001919323,0.0003391428,0.0003782167,0.0002204104],"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":[0.001776373,0.001850522,0.0391153,0.0004782579,0.0006084801,0.0005279715,0.0001602283,0.2068964,0.006577937,0.00240465,0.09844349,0.6411604],"study_design_scores_gemma":[0.00006955156,0.0001873983,0.003031066,0.00002942121,0.00003632923,0.00005647614,0.00005124259,0.9877836,0.003492816,0.002402272,0.002830428,0.00002947732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7656513,0.003895091,0.1339016,0.002694469,0.001290456,0.0008553614,0.02292019,0.05727438,0.01151718],"genre_scores_gemma":[0.8739786,0.000325955,0.0856945,0.0007346505,0.0002493176,0.0003905843,0.0316234,0.0004477055,0.006555288],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01047892,"threshold_uncertainty_score":0.02083582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04551384880903381,"score_gpt":0.351375687283201,"score_spread":0.3058618384741671,"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."}}