{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZQ4WM6F3HKOJREW3CG3DKEDV7I","short_pith_number":"pith:ZQ4WM6F3","schema_version":"1.0","canonical_sha256":"cc396678bb3a9c9892db11b6351075fa2e08e6399ae007117178727a94759412","source":{"kind":"arxiv","id":"2008.08601","version":2},"attestation_state":"computed","paper":{"title":"Neural Networks and Quantum Field Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","hep-th","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anindita Maiti, James Halverson, Keegan Stoner","submitted_at":"2020-08-19T18:00:06Z","abstract_excerpt":"We propose a theoretical understanding of neural networks in terms of Wilsonian effective field theory. The correspondence relies on the fact that many asymptotic neural networks are drawn from Gaussian processes, the analog of non-interacting field theories. Moving away from the asymptotic limit yields a non-Gaussian process and corresponds to turning on particle interactions, allowing for the computation of correlation functions of neural network outputs with Feynman diagrams. Minimal non-Gaussian process likelihoods are determined by the most relevant non-Gaussian terms, according to the fl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.08601","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-19T18:00:06Z","cross_cats_sorted":["cond-mat.dis-nn","hep-th","stat.ML"],"title_canon_sha256":"17cc4c3b3f3df97319f7b010a3d895144c305801abac750e30f2cb5f69ffde65","abstract_canon_sha256":"0fed1458d25f135cde5e7b30197f1f0cbd990832730d16ce48fbae5890d55062"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:56.933221Z","signature_b64":"cBrQ1mNjai1IT3wSrN4GUzHNbfXYH8mgy1dgxQ5/fO4jbddgxlbdPLCNSfBgYKcLuH13FIb3qT0sLqNt5ycNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc396678bb3a9c9892db11b6351075fa2e08e6399ae007117178727a94759412","last_reissued_at":"2026-07-05T02:22:56.932762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:56.932762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Networks and Quantum Field Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","hep-th","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anindita Maiti, James Halverson, Keegan Stoner","submitted_at":"2020-08-19T18:00:06Z","abstract_excerpt":"We propose a theoretical understanding of neural networks in terms of Wilsonian effective field theory. The correspondence relies on the fact that many asymptotic neural networks are drawn from Gaussian processes, the analog of non-interacting field theories. Moving away from the asymptotic limit yields a non-Gaussian process and corresponds to turning on particle interactions, allowing for the computation of correlation functions of neural network outputs with Feynman diagrams. Minimal non-Gaussian process likelihoods are determined by the most relevant non-Gaussian terms, according to the fl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08601","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.08601/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.08601","created_at":"2026-07-05T02:22:56.932819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.08601v2","created_at":"2026-07-05T02:22:56.932819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08601","created_at":"2026-07-05T02:22:56.932819+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ4WM6F3HKOJ","created_at":"2026-07-05T02:22:56.932819+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ4WM6F3HKOJREW3","created_at":"2026-07-05T02:22:56.932819+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ4WM6F3","created_at":"2026-07-05T02:22:56.932819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.07946","citing_title":"Conformal Defects in Neural Network Field Theories","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02313","citing_title":"Topological Effects in Neural Network Field Theory","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12488","citing_title":"Anomalies in Neural Network Field Theory","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27050","citing_title":"Optimal Architecture and Fundamental Bounds in Neural Network Field Theory","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06394","citing_title":"Lecture Notes on Statistical Physics and Neural Networks","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18673","citing_title":"Neural Networks Reveal a Universal Bias in Conformal Correlators","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I","json":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I.json","graph_json":"https://pith.science/api/pith-number/ZQ4WM6F3HKOJREW3CG3DKEDV7I/graph.json","events_json":"https://pith.science/api/pith-number/ZQ4WM6F3HKOJREW3CG3DKEDV7I/events.json","paper":"https://pith.science/paper/ZQ4WM6F3"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I","download_json":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I.json","view_paper":"https://pith.science/paper/ZQ4WM6F3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.08601&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ4WM6F3HKOJREW3CG3DKEDV7I/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ4WM6F3HKOJREW3CG3DKEDV7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ4WM6F3HKOJREW3CG3DKEDV7I/action/replication_record"}},"created_at":"2026-07-05T02:22:56.932819+00:00","updated_at":"2026-07-05T02:22:56.932819+00:00"}