{"id":"W2913766690","doi":"10.1093/mnras/stz2228","title":"A machine-learning approach for identifying the counterparts of submillimetre galaxies and applications to the GOODS-North field","year":2019,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institutes of Natural Sciences; Institut national des sciences de l'Univers; European Research Council; Science and Technology Facilities Council; National Research Council Canada; Ministry of Science and Technology, Taiwan; Jet Propulsion Laboratory; Natural Sciences and Engineering Research Council of Canada; National Astronomical Observatory of Japan; University of Hawai'i; California Institute of Technology; Korea Astronomy and Space Science Institute; National Aeronautics and Space Administration; Chinese Academy of Sciences; Ministry of Finance; National Science Foundation","keywords":"Physics; Galaxy; Millimeter; Angular resolution (graph drawing); Chandra Deep Field South; Sample (material); Astrophysics; Universe; Artificial neural network; Field (mathematics); Star formation; Deep learning; Artificial intelligence; Astronomy; Computer science","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":[0.001151753,0.0008133895,0.000383911,0.001441061,0.0005613455,0.000648938,0.001217342,0.0009628715,0.001342765],"category_scores_gemma":[0.002636815,0.0002723545,0.0004984325,0.0009333841,0.0004833706,0.0007637514,0.0007482643,0.0009555056,0.0004617201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009406229,"about_ca_system_score_gemma":0.0006076026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0208169,"about_ca_topic_score_gemma":0.018993,"domain_scores_codex":[0.9996966,0.0000841421,0.00001626112,0.0001111868,0.00005104941,0.00004092593],"domain_scores_gemma":[0.9989027,0.0004864565,0.0001232471,0.000153425,0.0002612495,0.00007292393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003059261,0.0004096124,0.0711619,0.00009725339,0.0001576713,0.0002658608,0.0001159487,0.5921838,0.01034863,0.002581606,0.00606205,0.3163098],"study_design_scores_gemma":[0.000009280363,0.0000197838,0.006630303,0.000006865194,0.000006374153,0.00001381117,0.00002289072,0.9900813,0.001488691,0.001331693,0.0003840435,0.000004878878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8226982,0.001294331,0.1641267,0.001404109,0.0001036522,0.0001075958,0.001289283,0.002743398,0.006232763],"genre_scores_gemma":[0.9168685,0.0001123076,0.07932016,0.000198639,0.00006143645,0.00005339901,0.001342219,0.00004912756,0.001994122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0208169,"threshold_uncertainty_score":0.04139143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008978286165100912,"score_gpt":0.2119572876608478,"score_spread":0.2029790014957469,"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."}}