{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JHBXNJXHFSDVAOED34SEVZSRUT","short_pith_number":"pith:JHBXNJXH","schema_version":"1.0","canonical_sha256":"49c376a6e72c87503883df244ae651a4d8a9fee59f873f7278ee68e016f4a367","source":{"kind":"arxiv","id":"2111.13207","version":4},"attestation_state":"computed","paper":{"title":"Characteristic Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Hasan, Jie Ding, Khalil Elkhalil, Vahid Tarokh, Xingzi Xu","submitted_at":"2021-11-25T18:25:09Z","abstract_excerpt":"We propose Characteristic-Neural Ordinary Differential Equations (C-NODEs), a framework for extending Neural Ordinary Differential Equations (NODEs) beyond ODEs. While NODEs model the evolution of a latent variables as the solution to an ODE, C-NODE models the evolution of the latent variables as the solution of a family of first-order quasi-linear partial differential equations (PDEs) along curves on which the PDEs reduce to ODEs, referred to as characteristic curves. This in turn allows the application of the standard frameworks for solving ODEs, namely the adjoint method. Learning optimal c"},"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":"2111.13207","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-25T18:25:09Z","cross_cats_sorted":[],"title_canon_sha256":"57294e50f9a77fbd333c59b7f1094b8eccd4fc69dbd55ad3a5431a181f27a291","abstract_canon_sha256":"1d78250e1d52f74be89817af0e12739a5690c034a9a9b0e062bc6ce8a2a16d08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:32.159969Z","signature_b64":"fF0u5xbuzcKhPYPPdeTSho8VoIcCtpGyamsCLxiCZ4rqvpGlLCXyKX3N8d/PN3E4tExDSc4sltsFisz8aDbmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49c376a6e72c87503883df244ae651a4d8a9fee59f873f7278ee68e016f4a367","last_reissued_at":"2026-07-05T05:14:32.159519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:32.159519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characteristic Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Hasan, Jie Ding, Khalil Elkhalil, Vahid Tarokh, Xingzi Xu","submitted_at":"2021-11-25T18:25:09Z","abstract_excerpt":"We propose Characteristic-Neural Ordinary Differential Equations (C-NODEs), a framework for extending Neural Ordinary Differential Equations (NODEs) beyond ODEs. While NODEs model the evolution of a latent variables as the solution to an ODE, C-NODE models the evolution of the latent variables as the solution of a family of first-order quasi-linear partial differential equations (PDEs) along curves on which the PDEs reduce to ODEs, referred to as characteristic curves. This in turn allows the application of the standard frameworks for solving ODEs, namely the adjoint method. Learning optimal c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13207","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/2111.13207/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":"2111.13207","created_at":"2026-07-05T05:14:32.159594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13207v4","created_at":"2026-07-05T05:14:32.159594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13207","created_at":"2026-07-05T05:14:32.159594+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHBXNJXHFSDV","created_at":"2026-07-05T05:14:32.159594+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHBXNJXHFSDVAOED","created_at":"2026-07-05T05:14:32.159594+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHBXNJXH","created_at":"2026-07-05T05:14:32.159594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00692","citing_title":"Adjoint sharding for very long context training of state space models","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT","json":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT.json","graph_json":"https://pith.science/api/pith-number/JHBXNJXHFSDVAOED34SEVZSRUT/graph.json","events_json":"https://pith.science/api/pith-number/JHBXNJXHFSDVAOED34SEVZSRUT/events.json","paper":"https://pith.science/paper/JHBXNJXH"},"agent_actions":{"view_html":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT","download_json":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT.json","view_paper":"https://pith.science/paper/JHBXNJXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13207&json=true","fetch_graph":"https://pith.science/api/pith-number/JHBXNJXHFSDVAOED34SEVZSRUT/graph.json","fetch_events":"https://pith.science/api/pith-number/JHBXNJXHFSDVAOED34SEVZSRUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT/action/storage_attestation","attest_author":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT/action/author_attestation","sign_citation":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT/action/citation_signature","submit_replication":"https://pith.science/pith/JHBXNJXHFSDVAOED34SEVZSRUT/action/replication_record"}},"created_at":"2026-07-05T05:14:32.159594+00:00","updated_at":"2026-07-05T05:14:32.159594+00:00"}