{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U35Y7FYI2U4U6WXWLAFMIVIMW6","short_pith_number":"pith:U35Y7FYI","schema_version":"1.0","canonical_sha256":"a6fb8f9708d5394f5af6580ac4550cb7b106ce9826d1cb4aae063db7a2f6e6b4","source":{"kind":"arxiv","id":"2501.18871","version":1},"attestation_state":"computed","paper":{"title":"Neural SDEs as a Unified Approach to Continuous-Domain Sequence Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Cheng, Macheng Shen","submitted_at":"2025-01-31T03:47:22Z","abstract_excerpt":"Inspired by the ubiquitous use of differential equations to model continuous dynamics across diverse scientific and engineering domains, we propose a novel and intuitive approach to continuous sequence modeling. Our method interprets time-series data as \\textit{discrete samples from an underlying continuous dynamical system}, and models its time evolution using Neural Stochastic Differential Equation (Neural SDE), where both the flow (drift) and diffusion terms are parameterized by neural networks. We derive a principled maximum likelihood objective and a \\textit{simulation-free} scheme for ef"},"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":"2501.18871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T03:47:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7bd9491911ba5b2037da84bd322c581ee1b5dc1986a8b62e316a646f3ba5b915","abstract_canon_sha256":"4f026ec299a9193a4f6a1a32e4747c0f493977b8dc28ac642a11e046976b7d64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:52.916557Z","signature_b64":"Q3TGMWpMFrRMWMRRCkYm0oxIrxmc5a3O86HliiKWpYCqRvC9HcrTcD3mwXaLlO3FJTz7zZTxnrBLgUAnn/wSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6fb8f9708d5394f5af6580ac4550cb7b106ce9826d1cb4aae063db7a2f6e6b4","last_reissued_at":"2026-07-05T10:07:52.916065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:52.916065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural SDEs as a Unified Approach to Continuous-Domain Sequence Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Cheng, Macheng Shen","submitted_at":"2025-01-31T03:47:22Z","abstract_excerpt":"Inspired by the ubiquitous use of differential equations to model continuous dynamics across diverse scientific and engineering domains, we propose a novel and intuitive approach to continuous sequence modeling. Our method interprets time-series data as \\textit{discrete samples from an underlying continuous dynamical system}, and models its time evolution using Neural Stochastic Differential Equation (Neural SDE), where both the flow (drift) and diffusion terms are parameterized by neural networks. We derive a principled maximum likelihood objective and a \\textit{simulation-free} scheme for ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18871","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/2501.18871/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":"2501.18871","created_at":"2026-07-05T10:07:52.916123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18871v1","created_at":"2026-07-05T10:07:52.916123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18871","created_at":"2026-07-05T10:07:52.916123+00:00"},{"alias_kind":"pith_short_12","alias_value":"U35Y7FYI2U4U","created_at":"2026-07-05T10:07:52.916123+00:00"},{"alias_kind":"pith_short_16","alias_value":"U35Y7FYI2U4U6WXW","created_at":"2026-07-05T10:07:52.916123+00:00"},{"alias_kind":"pith_short_8","alias_value":"U35Y7FYI","created_at":"2026-07-05T10:07:52.916123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11007","citing_title":"The Transformer as a Polar State Estimator","ref_index":178,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6","json":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6.json","graph_json":"https://pith.science/api/pith-number/U35Y7FYI2U4U6WXWLAFMIVIMW6/graph.json","events_json":"https://pith.science/api/pith-number/U35Y7FYI2U4U6WXWLAFMIVIMW6/events.json","paper":"https://pith.science/paper/U35Y7FYI"},"agent_actions":{"view_html":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6","download_json":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6.json","view_paper":"https://pith.science/paper/U35Y7FYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18871&json=true","fetch_graph":"https://pith.science/api/pith-number/U35Y7FYI2U4U6WXWLAFMIVIMW6/graph.json","fetch_events":"https://pith.science/api/pith-number/U35Y7FYI2U4U6WXWLAFMIVIMW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6/action/storage_attestation","attest_author":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6/action/author_attestation","sign_citation":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6/action/citation_signature","submit_replication":"https://pith.science/pith/U35Y7FYI2U4U6WXWLAFMIVIMW6/action/replication_record"}},"created_at":"2026-07-05T10:07:52.916123+00:00","updated_at":"2026-07-05T10:07:52.916123+00:00"}