{"id":"W4408218699","doi":"10.21468/scipostphyscore.8.1.027","title":"Bayesian RG flow in neural network field theories","year":2025,"lang":"en","type":"article","venue":"SciPost Physics Core","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Perimeter Institute","funders":"University of Illinois at Urbana-Champaign; Institut Périmètre de physique théorique; Gordon and Betty Moore Foundation; National Science Foundation","keywords":"Artificial neural network; Field (mathematics); Bayesian network; Bayesian probability; Computer science; Flow (mathematics); Artificial intelligence; Econometrics; Mathematics; Pure mathematics; Geometry","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008203833,0.0001125167,0.0001280149,0.00002577578,0.0001654357,0.0001195643,0.0006749555,0.00003962161,0.000005573996],"category_scores_gemma":[0.000007681117,0.0001019573,0.00005386701,0.001044645,0.00004022267,0.0002197291,0.000275271,0.0001899456,0.00001150427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001406479,"about_ca_system_score_gemma":0.00003919487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001778392,"about_ca_topic_score_gemma":0.0000550767,"domain_scores_codex":[0.9991509,0.00002407263,0.0001480894,0.0002944991,0.000102167,0.0002802466],"domain_scores_gemma":[0.9992115,0.0001660102,0.00003719834,0.0005111183,0.00003381255,0.00004036349],"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":[0.000004761588,0.00003027837,0.002430711,0.000006056708,0.000005097361,0.000003987541,0.0001012836,0.02248192,0.00005611138,0.806466,0.007176622,0.1612371],"study_design_scores_gemma":[0.0001057846,0.00002342393,0.001608249,0.00003369667,0.000002795204,6.62739e-7,0.00000714162,0.5407227,0.0002382478,0.4554295,0.001719475,0.0001083175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01638841,0.0003556925,0.9543365,0.01112658,0.001295918,0.0004031031,0.000004272978,0.0002481347,0.01584142],"genre_scores_gemma":[0.9917945,0.00001088349,0.005108714,0.002406095,0.000287331,0.00003297196,0.000005064102,0.000005296134,0.0003491784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9754061,"threshold_uncertainty_score":0.4157699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01120427529848141,"score_gpt":0.2623864785078966,"score_spread":0.2511822032094152,"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."}}