{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7PTWPT3CGEIUKNWU63XBTDSVU3","short_pith_number":"pith:7PTWPT3C","schema_version":"1.0","canonical_sha256":"fbe767cf6231114536d4f6ee198e55a6ecad6c7bdc89e83d054c86f3210b2ac8","source":{"kind":"arxiv","id":"2106.00694","version":1},"attestation_state":"computed","paper":{"title":"Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["hep-th","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anindita Maiti, James Halverson, Keegan Stoner","submitted_at":"2021-06-01T18:00:06Z","abstract_excerpt":"Parameter-space and function-space provide two different duality frames in which to study neural networks. We demonstrate that symmetries of network densities may be determined via dual computations of network correlation functions, even when the density is unknown and the network is not equivariant. Symmetry-via-duality relies on invariance properties of the correlation functions, which stem from the choice of network parameter distributions. Input and output symmetries of neural network densities are determined, which recover known Gaussian process results in the infinite width limit. The me"},"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":"2106.00694","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T18:00:06Z","cross_cats_sorted":["hep-th","stat.ML"],"title_canon_sha256":"83d8ebf300d40b9cf3d44992a54211ae62717c96e818427a48d9a4acef28c14e","abstract_canon_sha256":"0908e405d6106506e8718bf42a6c93239a47996962718991fea10d9ba1517c89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:39.108400Z","signature_b64":"QBwuWKkw+L1S1vuMtyo7srZxxxkglqBeoeOs6X+DksvhP+AKYS/C9/S7erFdjXw4jlq+HD5TRHPVQfNBTloUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbe767cf6231114536d4f6ee198e55a6ecad6c7bdc89e83d054c86f3210b2ac8","last_reissued_at":"2026-07-05T02:45:39.108040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:39.108040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["hep-th","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anindita Maiti, James Halverson, Keegan Stoner","submitted_at":"2021-06-01T18:00:06Z","abstract_excerpt":"Parameter-space and function-space provide two different duality frames in which to study neural networks. We demonstrate that symmetries of network densities may be determined via dual computations of network correlation functions, even when the density is unknown and the network is not equivariant. Symmetry-via-duality relies on invariance properties of the correlation functions, which stem from the choice of network parameter distributions. Input and output symmetries of neural network densities are determined, which recover known Gaussian process results in the infinite width limit. The me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00694","kind":"arxiv","version":1},"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/2106.00694/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":"2106.00694","created_at":"2026-07-05T02:45:39.108094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00694v1","created_at":"2026-07-05T02:45:39.108094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00694","created_at":"2026-07-05T02:45:39.108094+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PTWPT3CGEIU","created_at":"2026-07-05T02:45:39.108094+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PTWPT3CGEIUKNWU","created_at":"2026-07-05T02:45:39.108094+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PTWPT3C","created_at":"2026-07-05T02:45:39.108094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.07946","citing_title":"Conformal Defects in Neural Network Field Theories","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18948","citing_title":"Gauge-covariant stochastic neural fields: Stability and finite-width effects","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02313","citing_title":"Topological Effects in Neural Network Field Theory","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12488","citing_title":"Anomalies in Neural Network Field Theory","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27050","citing_title":"Optimal Architecture and Fundamental Bounds in Neural Network Field Theory","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3","json":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3.json","graph_json":"https://pith.science/api/pith-number/7PTWPT3CGEIUKNWU63XBTDSVU3/graph.json","events_json":"https://pith.science/api/pith-number/7PTWPT3CGEIUKNWU63XBTDSVU3/events.json","paper":"https://pith.science/paper/7PTWPT3C"},"agent_actions":{"view_html":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3","download_json":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3.json","view_paper":"https://pith.science/paper/7PTWPT3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00694&json=true","fetch_graph":"https://pith.science/api/pith-number/7PTWPT3CGEIUKNWU63XBTDSVU3/graph.json","fetch_events":"https://pith.science/api/pith-number/7PTWPT3CGEIUKNWU63XBTDSVU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3/action/storage_attestation","attest_author":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3/action/author_attestation","sign_citation":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3/action/citation_signature","submit_replication":"https://pith.science/pith/7PTWPT3CGEIUKNWU63XBTDSVU3/action/replication_record"}},"created_at":"2026-07-05T02:45:39.108094+00:00","updated_at":"2026-07-05T02:45:39.108094+00:00"}