{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CC3IYO5UGWJVQDTEL3AMKD3CMZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1d1ebe6c657f0e17cfa4287c17e3537f2b77dc67313f2499c95eac0fc7b349b1","cross_cats_sorted":["cs.AI","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T09:26:01Z","title_canon_sha256":"b533f44239a21dd564c9bac0fb2c5810afc238d1d6856738e0a4c393d3f7e2ff"},"schema_version":"1.0","source":{"id":"2505.17150","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17150","created_at":"2026-07-05T11:07:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17150v1","created_at":"2026-07-05T11:07:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17150","created_at":"2026-07-05T11:07:47Z"},{"alias_kind":"pith_short_12","alias_value":"CC3IYO5UGWJV","created_at":"2026-07-05T11:07:47Z"},{"alias_kind":"pith_short_16","alias_value":"CC3IYO5UGWJVQDTE","created_at":"2026-07-05T11:07:47Z"},{"alias_kind":"pith_short_8","alias_value":"CC3IYO5U","created_at":"2026-07-05T11:07:47Z"}],"graph_snapshots":[{"event_id":"sha256:4ac2979de565e8569a5dcad6ba920bddb860d27159e5713e4a3f5963e613af91","target":"graph","created_at":"2026-07-05T11:07:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.17150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a hierarchical, control theory inspired method for variational inference (VI) for neural stochastic differential equations (SDEs). While VI for neural SDEs is a promising avenue for uncertainty-aware reasoning in time-series, it is computationally challenging due to the iterative nature of maximizing the ELBO. In this work, we propose to decompose the control term into linear and residual non-linear components and derive an optimal control term for linear SDEs, using stochastic optimal control. Modeling the non-linear component by a neural network, we show how to efficiently train n","authors_text":"Guillaume Crevecoeur, Manfred Opper, Rembert Daems, Tolga Birdal","cross_cats":["cs.AI","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T09:26:01Z","title":"Efficient Training of Neural SDEs Using Stochastic Optimal Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17150","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0dccfbe5dfb72d50a9aa56d149f6ff0fd6da63c8bb8c9c25b93300a8eef115b2","target":"record","created_at":"2026-07-05T11:07:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1d1ebe6c657f0e17cfa4287c17e3537f2b77dc67313f2499c95eac0fc7b349b1","cross_cats_sorted":["cs.AI","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T09:26:01Z","title_canon_sha256":"b533f44239a21dd564c9bac0fb2c5810afc238d1d6856738e0a4c393d3f7e2ff"},"schema_version":"1.0","source":{"id":"2505.17150","kind":"arxiv","version":1}},"canonical_sha256":"10b68c3bb43593580e645ec0c50f6266797d08dd1381ea8cec907c29150d77a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10b68c3bb43593580e645ec0c50f6266797d08dd1381ea8cec907c29150d77a3","first_computed_at":"2026-07-05T11:07:47.887297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:47.887297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"is7phjp+vo0Jxzmueis5xn16oNpTI/eDoP7u2oNHufldMZx7ANQJYy+TVDXieN53xTavK/W9R0tpvB4YN8e2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:47.887811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17150","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dccfbe5dfb72d50a9aa56d149f6ff0fd6da63c8bb8c9c25b93300a8eef115b2","sha256:4ac2979de565e8569a5dcad6ba920bddb860d27159e5713e4a3f5963e613af91"],"state_sha256":"069222c003d115a023139c714c3509bc20c6167a9b2aea4883f57d9a81bbad29"}