{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2ZAKWQ25AM3PIUORI3GXSLHT7L","short_pith_number":"pith:2ZAKWQ25","schema_version":"1.0","canonical_sha256":"d640ab435d0336f451d146cd792cf3fae9316cf61d896921392a04eaeaa1cab7","source":{"kind":"arxiv","id":"2009.08295","version":4},"attestation_state":"computed","paper":{"title":"Neural Rough Differential Equations for Long Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cristopher Salvi, James Foster, James Morrill, Patrick Kidger, Terry Lyons","submitted_at":"2020-09-17T13:43:47Z","abstract_excerpt":"Neural controlled differential equations (CDEs) are the continuous-time analogue of recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory-efficient continuous-time way to model functions of potentially irregular time series. Existing methods for computing the forward pass of a Neural CDE involve embedding the incoming time series into path space, often via interpolation, and using evaluations of this path to drive the hidden state. Here, we use rough path theory to extend this formulation. Instead of directly embedding into path space, we instead represent the "},"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":"2009.08295","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-17T13:43:47Z","cross_cats_sorted":["cs.AI","math.DS","stat.ML"],"title_canon_sha256":"bad4379b7940597e7ccf936b999594796432a204d2f41af48a709787c46f2506","abstract_canon_sha256":"770f1f063c3f81ec8bf4373a03656d22515f2a6963ae85254fac44f802a52238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:41.013382Z","signature_b64":"DiOlLH2kS34NJjcTaFWgaSzBOo86wC7R5Bol2cJ+/E2xeM9aBWL5L0brm5c+NDK7QA+R3UdAxKr0/d65QEd4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d640ab435d0336f451d146cd792cf3fae9316cf61d896921392a04eaeaa1cab7","last_reissued_at":"2026-07-05T02:50:41.012976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:41.012976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Rough Differential Equations for Long Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cristopher Salvi, James Foster, James Morrill, Patrick Kidger, Terry Lyons","submitted_at":"2020-09-17T13:43:47Z","abstract_excerpt":"Neural controlled differential equations (CDEs) are the continuous-time analogue of recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory-efficient continuous-time way to model functions of potentially irregular time series. Existing methods for computing the forward pass of a Neural CDE involve embedding the incoming time series into path space, often via interpolation, and using evaluations of this path to drive the hidden state. Here, we use rough path theory to extend this formulation. Instead of directly embedding into path space, we instead represent the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.08295","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/2009.08295/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":"2009.08295","created_at":"2026-07-05T02:50:41.013034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.08295v4","created_at":"2026-07-05T02:50:41.013034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.08295","created_at":"2026-07-05T02:50:41.013034+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZAKWQ25AM3P","created_at":"2026-07-05T02:50:41.013034+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZAKWQ25AM3PIUOR","created_at":"2026-07-05T02:50:41.013034+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZAKWQ25","created_at":"2026-07-05T02:50:41.013034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21021","citing_title":"Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13913","citing_title":"Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05008","citing_title":"Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04662","citing_title":"Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L","json":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L.json","graph_json":"https://pith.science/api/pith-number/2ZAKWQ25AM3PIUORI3GXSLHT7L/graph.json","events_json":"https://pith.science/api/pith-number/2ZAKWQ25AM3PIUORI3GXSLHT7L/events.json","paper":"https://pith.science/paper/2ZAKWQ25"},"agent_actions":{"view_html":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L","download_json":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L.json","view_paper":"https://pith.science/paper/2ZAKWQ25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.08295&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZAKWQ25AM3PIUORI3GXSLHT7L/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZAKWQ25AM3PIUORI3GXSLHT7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L/action/storage_attestation","attest_author":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L/action/author_attestation","sign_citation":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L/action/citation_signature","submit_replication":"https://pith.science/pith/2ZAKWQ25AM3PIUORI3GXSLHT7L/action/replication_record"}},"created_at":"2026-07-05T02:50:41.013034+00:00","updated_at":"2026-07-05T02:50:41.013034+00:00"}