{"id":"W2973195436","doi":"10.1093/mnras/staa3344","title":"Cleaning our own dust: simulating and separating galactic dust foregrounds with neural networks","year":2020,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Radio Astronomy Observations and Technology","field":"Physics and Astronomy","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Science Foundation","keywords":"Physics; Cosmic microwave background; Planck; Generalization; Gaussian; Cosmic dust; Artificial neural network; Convolutional neural network; Astrophysics; Interstellar medium; Astronomy; Statistical physics; Galaxy; Artificial intelligence; Optics; Computer science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001063802,0.0002337078,0.0003329592,0.000008450274,0.0003281338,0.00008813928,0.0003106581,0.00007815693,0.0000224053],"category_scores_gemma":[0.000009869687,0.0001700597,0.0002115543,0.0001376823,0.0001465929,0.0001807954,0.0002445051,0.0004930455,9.509732e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003309051,"about_ca_system_score_gemma":0.0000269916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002041801,"about_ca_topic_score_gemma":0.000007169194,"domain_scores_codex":[0.9987882,0.00004222095,0.0003433462,0.0003353394,0.0001125092,0.0003784029],"domain_scores_gemma":[0.9991786,0.00009770186,0.0003516558,0.0002210686,0.00003759234,0.0001134188],"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":[0.00001754479,0.00001984673,0.3762251,0.000006392795,0.00008661396,4.238735e-8,0.0001572581,0.6203034,0.000003942635,0.0001408332,0.00007651876,0.002962475],"study_design_scores_gemma":[0.0005610192,0.0001104499,0.1003931,0.00001881076,0.00008308292,1.412666e-8,0.002210182,0.8963017,0.00004611143,0.000008769784,0.0001130206,0.0001537879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931723,0.00002921937,0.004454728,0.001704803,0.00005468443,0.0002218898,0.00001284046,0.00004266063,0.0003068783],"genre_scores_gemma":[0.9915268,1.205237e-8,0.007946956,0.00006440159,0.000376766,0.0000131924,0.00001101596,0.0000268793,0.0000340131],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2759983,"threshold_uncertainty_score":0.6934834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01242897953310697,"score_gpt":0.214432968563811,"score_spread":0.202003989030704,"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."}}