{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZXPO3ZRAAUWWPAEHTESXFPVNFH","short_pith_number":"pith:ZXPO3ZRA","schema_version":"1.0","canonical_sha256":"cddeede620052d678087992572bead29df1af810f04e5d736b8aeb724ccb27bd","source":{"kind":"arxiv","id":"2607.05280","version":1},"attestation_state":"computed","paper":{"title":"Advances in Neural Controlled Differential Equations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Walker","submitted_at":"2026-07-06T16:25:03Z","abstract_excerpt":"Many real-world systems evolve continuously, yet most machine learning models interpret time series as discrete sequences. Continuous-time approaches instead treat time series as samples from an underlying input path, a formulation that naturally accommodates irregularly sampled or oversampled data. Among these, Neural Controlled Differential Equations (NCDEs) are a maximally expressive class of models that parametrise a vector field using a neural network and evolve their hidden state by solving a dynamical system driven by the input path. NCDEs typically use a non-linear vector field, so 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":"2607.05280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T16:25:03Z","cross_cats_sorted":[],"title_canon_sha256":"544e79b5a3f66ea3b40a014beb253c767626f4193b3ca3a06fe9cb7f5b315731","abstract_canon_sha256":"36e74bba53d83018fca89ae38c76dc2cffe9e3dedc77202b637cce31c348c3a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:21.809470Z","signature_b64":"2ZT/idHarhJiBvatti7evelhAh5FVk3KdpEL9/7v6ISEjB9Bq2CEABXTNDhVxHHBqzn4B9dtgmi11xIZwJn+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cddeede620052d678087992572bead29df1af810f04e5d736b8aeb724ccb27bd","last_reissued_at":"2026-07-07T03:19:21.808995Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:21.808995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advances in Neural Controlled Differential Equations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Walker","submitted_at":"2026-07-06T16:25:03Z","abstract_excerpt":"Many real-world systems evolve continuously, yet most machine learning models interpret time series as discrete sequences. Continuous-time approaches instead treat time series as samples from an underlying input path, a formulation that naturally accommodates irregularly sampled or oversampled data. Among these, Neural Controlled Differential Equations (NCDEs) are a maximally expressive class of models that parametrise a vector field using a neural network and evolve their hidden state by solving a dynamical system driven by the input path. NCDEs typically use a non-linear vector field, so the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05280","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/2607.05280/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":"2607.05280","created_at":"2026-07-07T03:19:21.809066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05280v1","created_at":"2026-07-07T03:19:21.809066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05280","created_at":"2026-07-07T03:19:21.809066+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXPO3ZRAAUWW","created_at":"2026-07-07T03:19:21.809066+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXPO3ZRAAUWWPAEH","created_at":"2026-07-07T03:19:21.809066+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXPO3ZRA","created_at":"2026-07-07T03:19:21.809066+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/ZXPO3ZRAAUWWPAEHTESXFPVNFH","json":"https://pith.science/pith/ZXPO3ZRAAUWWPAEHTESXFPVNFH.json","graph_json":"https://pith.science/api/pith-number/ZXPO3ZRAAUWWPAEHTESXFPVNFH/graph.json","events_json":"https://pith.science/api/pith-number/ZXPO3ZRAAUWWPAEHTESXFPVNFH/events.json","paper":"https://pith.science/paper/ZXPO3ZRA"},"agent_actions":{"view_html":"https://pith.science/pith/ZXPO3ZRAAUWWPAEHTESXFPVNFH","download_json":"https://pith.science/pith/ZXPO3ZRAAUWWPAEHTESXFPVNFH.json","view_paper":"https://pith.science/paper/ZXPO3ZRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05280&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXPO3ZRAAUWWPAEHTESXFPVNFH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXPO3ZRAAUWWPAEHTESXFPVNFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXPO3ZRAAUWWPAEHTESXFPVNFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXPO3ZRAAUWWPAEHTESXFPVNFH/action/storage_attestation","attest_author":"https://pith.science/pith/ZXPO3ZRAAUWWPAEHTESXFPVNFH/action/author_attestation","sign_citation":"https://pith.science/pith/ZXPO3ZRAAUWWPAEHTESXFPVNFH/action/citation_signature","submit_replication":"https://pith.science/pith/ZXPO3ZRAAUWWPAEHTESXFPVNFH/action/replication_record"}},"created_at":"2026-07-07T03:19:21.809066+00:00","updated_at":"2026-07-07T03:19:21.809066+00:00"}