{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FIEMQ53HNCSU545YQOFSIXDVGB","short_pith_number":"pith:FIEMQ53H","schema_version":"1.0","canonical_sha256":"2a08c8776768a54ef3b8838b245c7530576dbaa466c1ac7475acb6599756d7c3","source":{"kind":"arxiv","id":"2005.10224","version":2},"attestation_state":"computed","paper":{"title":"The Random Feature Model for Input-Output Maps between Banach Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","physics.comp-ph","stat.ML"],"primary_cat":"math.NA","authors_text":"Andrew M. Stuart, Nicholas H. Nelsen","submitted_at":"2020-05-20T17:41:40Z","abstract_excerpt":"Well known to the machine learning community, the random feature model is a parametric approximation to kernel interpolation or regression methods. It is typically used to approximate functions mapping a finite-dimensional input space to the real line. In this paper, we instead propose a methodology for use of the random feature model as a data-driven surrogate for operators that map an input Banach space to an output Banach space. Although the methodology is quite general, we consider operators defined by partial differential equations (PDEs); here, the inputs and outputs are themselves funct"},"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":"2005.10224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2020-05-20T17:41:40Z","cross_cats_sorted":["cs.LG","cs.NA","physics.comp-ph","stat.ML"],"title_canon_sha256":"59594b746b2903d6b083cf05e0de5ff64b14f8ac29ee2b72ffbe1fea1b187313","abstract_canon_sha256":"838e404ef27f217fe025f68d7d83dabb0e314c182425ff1e1101739ce8d44eb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:49.633695Z","signature_b64":"6lhJhmfQivN7ii1QOdqXYbe+lxAD/3T2H2QzJ+N33JRjsGZC8FhvehYwc1dzNT2cbC+dFoMoFgCsoU7VubCKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a08c8776768a54ef3b8838b245c7530576dbaa466c1ac7475acb6599756d7c3","last_reissued_at":"2026-07-05T04:33:49.633180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:49.633180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Random Feature Model for Input-Output Maps between Banach Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","physics.comp-ph","stat.ML"],"primary_cat":"math.NA","authors_text":"Andrew M. Stuart, Nicholas H. Nelsen","submitted_at":"2020-05-20T17:41:40Z","abstract_excerpt":"Well known to the machine learning community, the random feature model is a parametric approximation to kernel interpolation or regression methods. It is typically used to approximate functions mapping a finite-dimensional input space to the real line. In this paper, we instead propose a methodology for use of the random feature model as a data-driven surrogate for operators that map an input Banach space to an output Banach space. Although the methodology is quite general, we consider operators defined by partial differential equations (PDEs); here, the inputs and outputs are themselves funct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10224","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/2005.10224/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":"2005.10224","created_at":"2026-07-05T04:33:49.633239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.10224v2","created_at":"2026-07-05T04:33:49.633239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10224","created_at":"2026-07-05T04:33:49.633239+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIEMQ53HNCSU","created_at":"2026-07-05T04:33:49.633239+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIEMQ53HNCSU545Y","created_at":"2026-07-05T04:33:49.633239+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIEMQ53H","created_at":"2026-07-05T04:33:49.633239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2010.08895","citing_title":"Fourier Neural Operator for Parametric Partial Differential Equations","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB","json":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB.json","graph_json":"https://pith.science/api/pith-number/FIEMQ53HNCSU545YQOFSIXDVGB/graph.json","events_json":"https://pith.science/api/pith-number/FIEMQ53HNCSU545YQOFSIXDVGB/events.json","paper":"https://pith.science/paper/FIEMQ53H"},"agent_actions":{"view_html":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB","download_json":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB.json","view_paper":"https://pith.science/paper/FIEMQ53H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.10224&json=true","fetch_graph":"https://pith.science/api/pith-number/FIEMQ53HNCSU545YQOFSIXDVGB/graph.json","fetch_events":"https://pith.science/api/pith-number/FIEMQ53HNCSU545YQOFSIXDVGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB/action/storage_attestation","attest_author":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB/action/author_attestation","sign_citation":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB/action/citation_signature","submit_replication":"https://pith.science/pith/FIEMQ53HNCSU545YQOFSIXDVGB/action/replication_record"}},"created_at":"2026-07-05T04:33:49.633239+00:00","updated_at":"2026-07-05T04:33:49.633239+00:00"}