{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZVDVUWEWQ2V2AIQXKZW63L35AY","short_pith_number":"pith:ZVDVUWEW","schema_version":"1.0","canonical_sha256":"cd475a589686aba02217566dedaf7d06360cac9c3caa24312f2cc4747f42b134","source":{"kind":"arxiv","id":"2305.16791","version":4},"attestation_state":"computed","paper":{"title":"On the Generalization and Approximation Capacities of Neural Controlled Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Agathe Guilloux, Linus Bleistein","submitted_at":"2023-05-26T10:02:32Z","abstract_excerpt":"Neural Controlled Differential Equations (NCDEs) are a state-of-the-art tool for supervised learning with irregularly sampled time series (Kidger, 2020). However, no theoretical analysis of their performance has been provided yet, and it remains unclear in particular how the irregularity of the time series affects their predictions. By merging the rich theory of controlled differential equations (CDE) and Lipschitz-based measures of the complexity of deep neural nets, we take a first step towards the theoretical understanding of NCDE. Our first result is a generalization bound for this class o"},"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":"2305.16791","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-26T10:02:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"db60d914208ee2f65ea93e325eb42f01cc333b7b1a3a05936a285cb11a50271d","abstract_canon_sha256":"8bd32beff9ccf43ea696710cbb9b0d00268625d963910c4d14714271d02ce4ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:51.969358Z","signature_b64":"DYbX9xZwoHtFdMJX8otg6SIGO7emGG9LpHSjooRmywc+nA2mFcqDpw1AeZ/ojPPCl36FV6r0OY9P0f4eDnwIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd475a589686aba02217566dedaf7d06360cac9c3caa24312f2cc4747f42b134","last_reissued_at":"2026-07-05T08:38:51.968850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:51.968850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Generalization and Approximation Capacities of Neural Controlled Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Agathe Guilloux, Linus Bleistein","submitted_at":"2023-05-26T10:02:32Z","abstract_excerpt":"Neural Controlled Differential Equations (NCDEs) are a state-of-the-art tool for supervised learning with irregularly sampled time series (Kidger, 2020). However, no theoretical analysis of their performance has been provided yet, and it remains unclear in particular how the irregularity of the time series affects their predictions. By merging the rich theory of controlled differential equations (CDE) and Lipschitz-based measures of the complexity of deep neural nets, we take a first step towards the theoretical understanding of NCDE. Our first result is a generalization bound for this class o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16791","kind":"arxiv","version":4},"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/2305.16791/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":"2305.16791","created_at":"2026-07-05T08:38:51.968912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16791v4","created_at":"2026-07-05T08:38:51.968912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16791","created_at":"2026-07-05T08:38:51.968912+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVDVUWEWQ2V2","created_at":"2026-07-05T08:38:51.968912+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVDVUWEWQ2V2AIQX","created_at":"2026-07-05T08:38:51.968912+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVDVUWEW","created_at":"2026-07-05T08:38:51.968912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.09742","citing_title":"Upper Generalization Bounds for Neural Oscillators","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY","json":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY.json","graph_json":"https://pith.science/api/pith-number/ZVDVUWEWQ2V2AIQXKZW63L35AY/graph.json","events_json":"https://pith.science/api/pith-number/ZVDVUWEWQ2V2AIQXKZW63L35AY/events.json","paper":"https://pith.science/paper/ZVDVUWEW"},"agent_actions":{"view_html":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY","download_json":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY.json","view_paper":"https://pith.science/paper/ZVDVUWEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16791&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVDVUWEWQ2V2AIQXKZW63L35AY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVDVUWEWQ2V2AIQXKZW63L35AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY/action/storage_attestation","attest_author":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY/action/author_attestation","sign_citation":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY/action/citation_signature","submit_replication":"https://pith.science/pith/ZVDVUWEWQ2V2AIQXKZW63L35AY/action/replication_record"}},"created_at":"2026-07-05T08:38:51.968912+00:00","updated_at":"2026-07-05T08:38:51.968912+00:00"}