{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OBTRLNQN2AA24AZVLXKRYE6K5X","short_pith_number":"pith:OBTRLNQN","schema_version":"1.0","canonical_sha256":"706715b60dd001ae03355dd51c13caedf1be3a50c6bfc70d43bdded11a7a9ec4","source":{"kind":"arxiv","id":"2307.03223","version":2},"attestation_state":"computed","paper":{"title":"Neural Network Field Theories: Non-Gaussianity, Actions, and Locality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"hep-th","authors_text":"Anindita Maiti, James Halverson, Keegan Stoner, Matthew D. Schwartz, Mehmet Demirtas","submitted_at":"2023-07-06T18:00:01Z","abstract_excerpt":"Both the path integral measure in field theory and ensembles of neural networks describe distributions over functions. When the central limit theorem can be applied in the infinite-width (infinite-$N$) limit, the ensemble of networks corresponds to a free field theory. Although an expansion in $1/N$ corresponds to interactions in the field theory, others, such as in a small breaking of the statistical independence of network parameters, can also lead to interacting theories. These other expansions can be advantageous over the $1/N$-expansion, for example by improved behavior with respect to th"},"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":"2307.03223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-th","submitted_at":"2023-07-06T18:00:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4adb855109f95bcb100302cf4c7ec424498b6bee0ec39073e94960b4bcb93b4d","abstract_canon_sha256":"03caed6ac7da2ae08a212b4ee6effb80899571c886ca98ec8d2e5659ce35a61a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:58.715725Z","signature_b64":"3aaL83c6TvO4tAtVp7WNNLtZdQ4rsQbyTqJGN8nPaG9hXdkMcLg9h+EgbonR/M0Mdv6krXzNMLDG2xWaCSYgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"706715b60dd001ae03355dd51c13caedf1be3a50c6bfc70d43bdded11a7a9ec4","last_reissued_at":"2026-07-05T07:23:58.715144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:58.715144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Field Theories: Non-Gaussianity, Actions, and Locality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"hep-th","authors_text":"Anindita Maiti, James Halverson, Keegan Stoner, Matthew D. Schwartz, Mehmet Demirtas","submitted_at":"2023-07-06T18:00:01Z","abstract_excerpt":"Both the path integral measure in field theory and ensembles of neural networks describe distributions over functions. When the central limit theorem can be applied in the infinite-width (infinite-$N$) limit, the ensemble of networks corresponds to a free field theory. Although an expansion in $1/N$ corresponds to interactions in the field theory, others, such as in a small breaking of the statistical independence of network parameters, can also lead to interacting theories. These other expansions can be advantageous over the $1/N$-expansion, for example by improved behavior with respect to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03223","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/2307.03223/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":"2307.03223","created_at":"2026-07-05T07:23:58.715207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03223v2","created_at":"2026-07-05T07:23:58.715207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03223","created_at":"2026-07-05T07:23:58.715207+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBTRLNQN2AA2","created_at":"2026-07-05T07:23:58.715207+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBTRLNQN2AA24AZV","created_at":"2026-07-05T07:23:58.715207+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBTRLNQN","created_at":"2026-07-05T07:23:58.715207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.03810","citing_title":"Viability of perturbative expansion for quantum field theories on neurons","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07946","citing_title":"Conformal Defects in Neural Network Field Theories","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02313","citing_title":"Topological Effects in Neural Network Field Theory","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12488","citing_title":"Anomalies in Neural Network Field Theory","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27050","citing_title":"Optimal Architecture and Fundamental Bounds in Neural Network Field Theory","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18673","citing_title":"Neural Networks Reveal a Universal Bias in Conformal Correlators","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X","json":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X.json","graph_json":"https://pith.science/api/pith-number/OBTRLNQN2AA24AZVLXKRYE6K5X/graph.json","events_json":"https://pith.science/api/pith-number/OBTRLNQN2AA24AZVLXKRYE6K5X/events.json","paper":"https://pith.science/paper/OBTRLNQN"},"agent_actions":{"view_html":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X","download_json":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X.json","view_paper":"https://pith.science/paper/OBTRLNQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03223&json=true","fetch_graph":"https://pith.science/api/pith-number/OBTRLNQN2AA24AZVLXKRYE6K5X/graph.json","fetch_events":"https://pith.science/api/pith-number/OBTRLNQN2AA24AZVLXKRYE6K5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X/action/storage_attestation","attest_author":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X/action/author_attestation","sign_citation":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X/action/citation_signature","submit_replication":"https://pith.science/pith/OBTRLNQN2AA24AZVLXKRYE6K5X/action/replication_record"}},"created_at":"2026-07-05T07:23:58.715207+00:00","updated_at":"2026-07-05T07:23:58.715207+00:00"}