{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZKCAPVX367ZKF4HGM2VBTBQBZK","short_pith_number":"pith:ZKCAPVX3","schema_version":"1.0","canonical_sha256":"ca8407d6fbf7f2a2f0e666aa198601cabb7b5a86923e09572431938a8eb11307","source":{"kind":"arxiv","id":"2210.03466","version":2},"attestation_state":"computed","paper":{"title":"Latent Neural ODEs with Sparse Bayesian Multiple Shooting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cagatay Yildiz, Harri L\\\"ahdesm\\\"aki, Markus Heinonen, Valerii Iakovlev","submitted_at":"2022-10-07T11:36:29Z","abstract_excerpt":"Training dynamic models, such as neural ODEs, on long trajectories is a hard problem that requires using various tricks, such as trajectory splitting, to make model training work in practice. These methods are often heuristics with poor theoretical justifications, and require iterative manual tuning. We propose a principled multiple shooting technique for neural ODEs that splits the trajectories into manageable short segments, which are optimised in parallel, while ensuring probabilistic control on continuity over consecutive segments. We derive variational inference for our shooting-based lat"},"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":"2210.03466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T11:36:29Z","cross_cats_sorted":[],"title_canon_sha256":"d632095fe5a75edecb174b6bbe052a33e68450f69b823e562503c014df64f985","abstract_canon_sha256":"d73f7ee71f2d7555fb9fd26c07430ba991fc6e7065169b3b394d23ae607bb688"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:53.659006Z","signature_b64":"VehjpbYqcyjY1DWhOjoXN2qVWYrctnVEoYa/ftqz6SaXbSpRuYINJMI2KjdxwTIpS3Qwqh9Cm0DCNqCxCz8MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca8407d6fbf7f2a2f0e666aa198601cabb7b5a86923e09572431938a8eb11307","last_reissued_at":"2026-07-05T05:39:53.658545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:53.658545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Neural ODEs with Sparse Bayesian Multiple Shooting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cagatay Yildiz, Harri L\\\"ahdesm\\\"aki, Markus Heinonen, Valerii Iakovlev","submitted_at":"2022-10-07T11:36:29Z","abstract_excerpt":"Training dynamic models, such as neural ODEs, on long trajectories is a hard problem that requires using various tricks, such as trajectory splitting, to make model training work in practice. These methods are often heuristics with poor theoretical justifications, and require iterative manual tuning. We propose a principled multiple shooting technique for neural ODEs that splits the trajectories into manageable short segments, which are optimised in parallel, while ensuring probabilistic control on continuity over consecutive segments. We derive variational inference for our shooting-based lat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03466","kind":"arxiv","version":2},"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/2210.03466/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":"2210.03466","created_at":"2026-07-05T05:39:53.658605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03466v2","created_at":"2026-07-05T05:39:53.658605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03466","created_at":"2026-07-05T05:39:53.658605+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKCAPVX367ZK","created_at":"2026-07-05T05:39:53.658605+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKCAPVX367ZKF4HG","created_at":"2026-07-05T05:39:53.658605+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKCAPVX3","created_at":"2026-07-05T05:39:53.658605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06351","citing_title":"Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK","json":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK.json","graph_json":"https://pith.science/api/pith-number/ZKCAPVX367ZKF4HGM2VBTBQBZK/graph.json","events_json":"https://pith.science/api/pith-number/ZKCAPVX367ZKF4HGM2VBTBQBZK/events.json","paper":"https://pith.science/paper/ZKCAPVX3"},"agent_actions":{"view_html":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK","download_json":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK.json","view_paper":"https://pith.science/paper/ZKCAPVX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03466&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKCAPVX367ZKF4HGM2VBTBQBZK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKCAPVX367ZKF4HGM2VBTBQBZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK/action/storage_attestation","attest_author":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK/action/author_attestation","sign_citation":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK/action/citation_signature","submit_replication":"https://pith.science/pith/ZKCAPVX367ZKF4HGM2VBTBQBZK/action/replication_record"}},"created_at":"2026-07-05T05:39:53.658605+00:00","updated_at":"2026-07-05T05:39:53.658605+00:00"}