{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WR3BTZYKGJTNEOZQCGM7WWP7OA","short_pith_number":"pith:WR3BTZYK","schema_version":"1.0","canonical_sha256":"b47619e70a3266d23b301199fb59ff700006fb69348e1d05adf1fc55ce3eff76","source":{"kind":"arxiv","id":"1906.02355","version":1},"attestation_state":"computed","paper":{"title":"Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Qin Cao, Sanjiv Kumar, Si Si, Tesi Xiao, Xuanqing Liu","submitted_at":"2019-06-05T23:19:50Z","abstract_excerpt":"Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g. dropout, Gaussian noise) are missing in current Neural ODE networks. In this paper, we propose a new continuous neural network framework called Neural Stochastic Differential Equation (Neural SDE) network, which naturally incorporates various commonly used regularization mechanisms based on random noise injection. Our framework can model various types of noise injection frequently used in di"},"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":"1906.02355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T23:19:50Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"51495cfe50cfe4782c86c65db8fa84749cc0c8dc21ca072887e75193a9a04e80","abstract_canon_sha256":"452ee6c7dbabfbbc9d4164ded20e48a39d65ad8613decdf67bd15834cd3b1145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:01.484753Z","signature_b64":"Gd0sCkBJNBOpNALWxqhstWAzeQOj973IWFF1EnbR1oYOsRcgHS1MTek+zo0alhJM2uXcjBsLA/f/2qfeI2qzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b47619e70a3266d23b301199fb59ff700006fb69348e1d05adf1fc55ce3eff76","last_reissued_at":"2026-05-17T23:44:01.484211Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:01.484211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Qin Cao, Sanjiv Kumar, Si Si, Tesi Xiao, Xuanqing Liu","submitted_at":"2019-06-05T23:19:50Z","abstract_excerpt":"Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g. dropout, Gaussian noise) are missing in current Neural ODE networks. In this paper, we propose a new continuous neural network framework called Neural Stochastic Differential Equation (Neural SDE) network, which naturally incorporates various commonly used regularization mechanisms based on random noise injection. Our framework can model various types of noise injection frequently used in di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02355","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":""},"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":"1906.02355","created_at":"2026-05-17T23:44:01.484290+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02355v1","created_at":"2026-05-17T23:44:01.484290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02355","created_at":"2026-05-17T23:44:01.484290+00:00"},{"alias_kind":"pith_short_12","alias_value":"WR3BTZYKGJTN","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WR3BTZYKGJTNEOZQ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WR3BTZYK","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2504.13228","citing_title":"Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic Differential Equations","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18118","citing_title":"Functional Whole-Brain Models: A New Framework for Unifying Brain Structure and Cognitive Function","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2510.12916","citing_title":"Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22208","citing_title":"Finite Expression Method with TranNet-based Function Learning for High-Dimensional Partial Differential Equations","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA","json":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA.json","graph_json":"https://pith.science/api/pith-number/WR3BTZYKGJTNEOZQCGM7WWP7OA/graph.json","events_json":"https://pith.science/api/pith-number/WR3BTZYKGJTNEOZQCGM7WWP7OA/events.json","paper":"https://pith.science/paper/WR3BTZYK"},"agent_actions":{"view_html":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA","download_json":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA.json","view_paper":"https://pith.science/paper/WR3BTZYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02355&json=true","fetch_graph":"https://pith.science/api/pith-number/WR3BTZYKGJTNEOZQCGM7WWP7OA/graph.json","fetch_events":"https://pith.science/api/pith-number/WR3BTZYKGJTNEOZQCGM7WWP7OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA/action/storage_attestation","attest_author":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA/action/author_attestation","sign_citation":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA/action/citation_signature","submit_replication":"https://pith.science/pith/WR3BTZYKGJTNEOZQCGM7WWP7OA/action/replication_record"}},"created_at":"2026-05-17T23:44:01.484290+00:00","updated_at":"2026-05-17T23:44:01.484290+00:00"}