{"id":"W4390562074","doi":"10.1093/mnras/stad3766","title":"Probing three-dimensional magnetic fields: II – an interpretable Convolutional Neural Network","year":2023,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Astrophysics and Star Formation Studies","field":"Physics and Astronomy","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Advanced Cyberinfrastructure; Universities Space Research Association; Alberta Livestock and Meat Agency; San Diego Supercomputer Center; National Aeronautics and Space Administration; National Science Foundation","keywords":"Physics; Magnetic field; Magnetohydrodynamics; Magnetization; Computational physics; Convolutional neural network; Molecular cloud; Astrophysics; Anisotropy; Turbulence; Orientation (vector space); Viewing angle; Geometry; Optics; Mechanics; Artificial intelligence; Quantum mechanics; Stars; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003038661,0.0007694323,0.0003268207,0.0002784517,0.0002233863,0.0005156983,0.001124299,0.0008591036,0.001242115],"category_scores_gemma":[0.000891805,0.0003237123,0.0004618224,0.0003140422,0.0004078631,0.0005042946,0.0004839944,0.000906026,0.0003065156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009871804,"about_ca_system_score_gemma":0.0005969879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02146905,"about_ca_topic_score_gemma":0.01627002,"domain_scores_codex":[0.9999214,0.00001411441,0.000002846427,0.0000250593,0.00001632613,0.00002017912],"domain_scores_gemma":[0.9998099,0.00008229898,0.00002323549,0.00002214105,0.00004475914,0.0000176387],"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":[0.0001096891,0.00007975028,0.002341361,0.00004229733,0.00006105225,0.00008542486,0.00002357875,0.9440517,0.00803468,0.002041274,0.001416991,0.04171208],"study_design_scores_gemma":[0.00000165772,0.000006166552,0.0001825799,0.000002171955,0.0000023737,0.000003449865,0.000001484344,0.9987969,0.0005044118,0.0004084194,0.00008866782,0.000001642142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.533532,0.001789702,0.4527326,0.00202864,0.0002217288,0.00009522561,0.001175862,0.002191591,0.006232732],"genre_scores_gemma":[0.9461514,0.0003315608,0.0491627,0.0001792634,0.00004635502,0.00006668716,0.00101943,0.00004517735,0.002997349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02146905,"threshold_uncertainty_score":0.04268819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009388092030316807,"score_gpt":0.2081419356348626,"score_spread":0.1987538436045457,"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."}}