{"id":"W4310883527","doi":"10.48550/arxiv.2212.02847","title":"Self-supervised component separation for the extragalactic submillimeter sky","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radio Astronomy Observations and Technology","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto; Canadian Institute for Theoretical Astrophysics; Compute Canada; Natural Sciences and Engineering Research Council of Canada; European Commission; Agence Nationale de la Recherche; Government of Ontario; Canadian Institute for Advanced Research","keywords":"Sky; Component (thermodynamics); Separation (statistics); Astronomy; Astrophysics; Artificial intelligence; Physics; Computer science; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001652796,0.0002464865,0.0002572597,0.0001190267,0.000490804,0.00006168528,0.0006812384,0.0001034159,0.0006529348],"category_scores_gemma":[0.000002586274,0.000249861,0.0003149074,0.0002298246,0.00006698131,0.0001180614,0.0004397361,0.0005165447,0.00001993091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602271,"about_ca_system_score_gemma":0.0001275308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001947027,"about_ca_topic_score_gemma":0.000009142637,"domain_scores_codex":[0.9988117,0.00007387393,0.0001958476,0.0005791881,0.00005422988,0.0002851374],"domain_scores_gemma":[0.9986688,0.0002034668,0.0002191354,0.0007750902,0.00008015452,0.0000532869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001424257,0.0007191381,0.09990409,0.000102955,0.001889108,0.00001191372,0.0004108103,0.2523705,0.0001053003,0.6357844,0.001695281,0.006864108],"study_design_scores_gemma":[0.001660013,0.0001308784,0.01277168,0.00001558029,0.0008673371,9.596419e-7,0.001126328,0.8820442,0.0002103635,0.03347345,0.06694164,0.0007575598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5728257,0.00005848055,0.4227859,0.0003232883,0.0005203657,0.00122447,0.0001551714,0.0001519473,0.001954663],"genre_scores_gemma":[0.9966842,0.00001493624,0.001799766,0.00003134703,0.000159131,0.00005235288,0.000309724,0.00002792407,0.000920605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6296737,"threshold_uncertainty_score":0.9999954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05948003764655841,"score_gpt":0.2055727345939602,"score_spread":0.1460926969474018,"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."}}