{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:74K3TB34IJIND3TMHGZ4K2BEH7","short_pith_number":"pith:74K3TB34","schema_version":"1.0","canonical_sha256":"ff15b9877c4250d1ee6c39b3c568243ffb44244b0df9e40063749b1ebc81a745","source":{"kind":"arxiv","id":"2107.07562","version":1},"attestation_state":"computed","paper":{"title":"On universal approximation and error bounds for Fourier Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Nikola Kovachki, Samuel Lanthaler, Siddhartha Mishra","submitted_at":"2021-07-15T18:49:20Z","abstract_excerpt":"Fourier neural operators (FNOs) have recently been proposed as an effective framework for learning operators that map between infinite-dimensional spaces. We prove that FNOs are universal, in the sense that they can approximate any continuous operator to desired accuracy. Moreover, we suggest a mechanism by which FNOs can approximate operators associated with PDEs efficiently. Explicit error bounds are derived to show that the size of the FNO, approximating operators associated with a Darcy type elliptic PDE and with the incompressible Navier-Stokes equations of fluid dynamics, only increases "},"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":"2107.07562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2021-07-15T18:49:20Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"d2f18dd1ca3fdd0f5647de302f29180dc18dbd7c72c1920ceeb142e506ebaa06","abstract_canon_sha256":"8fc5a01c727107f249a3603a27311821c4bbb43f4fe93f598ccab360155b6901"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:02.552349Z","signature_b64":"vqECsvGrDgRHIYV5BsWTnxai5MebYQZFjPcPS77/AR3XT8X28xO3/4k1WqY0+BlEF7TPcWo3pAKDGil11kt5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff15b9877c4250d1ee6c39b3c568243ffb44244b0df9e40063749b1ebc81a745","last_reissued_at":"2026-07-05T03:42:02.551925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:02.551925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On universal approximation and error bounds for Fourier Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Nikola Kovachki, Samuel Lanthaler, Siddhartha Mishra","submitted_at":"2021-07-15T18:49:20Z","abstract_excerpt":"Fourier neural operators (FNOs) have recently been proposed as an effective framework for learning operators that map between infinite-dimensional spaces. We prove that FNOs are universal, in the sense that they can approximate any continuous operator to desired accuracy. Moreover, we suggest a mechanism by which FNOs can approximate operators associated with PDEs efficiently. Explicit error bounds are derived to show that the size of the FNO, approximating operators associated with a Darcy type elliptic PDE and with the incompressible Navier-Stokes equations of fluid dynamics, only increases "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07562","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/2107.07562/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":"2107.07562","created_at":"2026-07-05T03:42:02.551982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.07562v1","created_at":"2026-07-05T03:42:02.551982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07562","created_at":"2026-07-05T03:42:02.551982+00:00"},{"alias_kind":"pith_short_12","alias_value":"74K3TB34IJIN","created_at":"2026-07-05T03:42:02.551982+00:00"},{"alias_kind":"pith_short_16","alias_value":"74K3TB34IJIND3TM","created_at":"2026-07-05T03:42:02.551982+00:00"},{"alias_kind":"pith_short_8","alias_value":"74K3TB34","created_at":"2026-07-05T03:42:02.551982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18905","citing_title":"Stability and Discretization Error of State Space Model Neural Operators","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7","json":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7.json","graph_json":"https://pith.science/api/pith-number/74K3TB34IJIND3TMHGZ4K2BEH7/graph.json","events_json":"https://pith.science/api/pith-number/74K3TB34IJIND3TMHGZ4K2BEH7/events.json","paper":"https://pith.science/paper/74K3TB34"},"agent_actions":{"view_html":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7","download_json":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7.json","view_paper":"https://pith.science/paper/74K3TB34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.07562&json=true","fetch_graph":"https://pith.science/api/pith-number/74K3TB34IJIND3TMHGZ4K2BEH7/graph.json","fetch_events":"https://pith.science/api/pith-number/74K3TB34IJIND3TMHGZ4K2BEH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7/action/storage_attestation","attest_author":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7/action/author_attestation","sign_citation":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7/action/citation_signature","submit_replication":"https://pith.science/pith/74K3TB34IJIND3TMHGZ4K2BEH7/action/replication_record"}},"created_at":"2026-07-05T03:42:02.551982+00:00","updated_at":"2026-07-05T03:42:02.551982+00:00"}