{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6XLMCZKXVC77XEUTHDMBWI4E6Z","short_pith_number":"pith:6XLMCZKX","schema_version":"1.0","canonical_sha256":"f5d6c16557a8bffb929338d81b2384f67a2f08d9c44364cc47be9904fc2a5c3b","source":{"kind":"arxiv","id":"2304.00352","version":2},"attestation_state":"computed","paper":{"title":"Universal approximation of flows of control systems by recurrent neural networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Amritam Das, Karl H. Johansson, Miguel Aguiar","submitted_at":"2023-04-01T16:13:49Z","abstract_excerpt":"We consider the problem of approximating flow functions of continuous-time dynamical systems with inputs. It is well-known that continuous-time recurrent neural networks are universal approximators of this type of system. In this paper, we prove that an architecture based on discrete-time recurrent neural networks universally approximates flows of continuous-time dynamical systems with inputs. The required assumptions are shown to hold for systems whose dynamics are well-behaved ordinary differential equations and with practically relevant classes of input signals. This enables the use of off-"},"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":"2304.00352","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.SY","submitted_at":"2023-04-01T16:13:49Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"45f01129b4e6f9fa7b079f267dc471af5a61c01dbd77746d49f11884779acc26","abstract_canon_sha256":"8a9e93d4c8714b8692115a9da4db69c191e3c33438f716c0278082e6c9c74c15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:03.357589Z","signature_b64":"6UTlUg0V+7brMgR0HEtqur6I8cMGtLriEScqXsgmU06OGKIEG2+WT3QrdXCAEHer6CkdQCWFQHomJG9F4IBhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5d6c16557a8bffb929338d81b2384f67a2f08d9c44364cc47be9904fc2a5c3b","last_reissued_at":"2026-07-05T06:52:03.357101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:03.357101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal approximation of flows of control systems by recurrent neural networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Amritam Das, Karl H. Johansson, Miguel Aguiar","submitted_at":"2023-04-01T16:13:49Z","abstract_excerpt":"We consider the problem of approximating flow functions of continuous-time dynamical systems with inputs. It is well-known that continuous-time recurrent neural networks are universal approximators of this type of system. In this paper, we prove that an architecture based on discrete-time recurrent neural networks universally approximates flows of continuous-time dynamical systems with inputs. The required assumptions are shown to hold for systems whose dynamics are well-behaved ordinary differential equations and with practically relevant classes of input signals. This enables the use of off-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00352","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/2304.00352/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":"2304.00352","created_at":"2026-07-05T06:52:03.357164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00352v2","created_at":"2026-07-05T06:52:03.357164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00352","created_at":"2026-07-05T06:52:03.357164+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XLMCZKXVC77","created_at":"2026-07-05T06:52:03.357164+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XLMCZKXVC77XEUT","created_at":"2026-07-05T06:52:03.357164+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XLMCZKX","created_at":"2026-07-05T06:52:03.357164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z","json":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z.json","graph_json":"https://pith.science/api/pith-number/6XLMCZKXVC77XEUTHDMBWI4E6Z/graph.json","events_json":"https://pith.science/api/pith-number/6XLMCZKXVC77XEUTHDMBWI4E6Z/events.json","paper":"https://pith.science/paper/6XLMCZKX"},"agent_actions":{"view_html":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z","download_json":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z.json","view_paper":"https://pith.science/paper/6XLMCZKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00352&json=true","fetch_graph":"https://pith.science/api/pith-number/6XLMCZKXVC77XEUTHDMBWI4E6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/6XLMCZKXVC77XEUTHDMBWI4E6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z/action/storage_attestation","attest_author":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z/action/author_attestation","sign_citation":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z/action/citation_signature","submit_replication":"https://pith.science/pith/6XLMCZKXVC77XEUTHDMBWI4E6Z/action/replication_record"}},"created_at":"2026-07-05T06:52:03.357164+00:00","updated_at":"2026-07-05T06:52:03.357164+00:00"}