{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OGTM3MNLSDHUM7MTEGD5JIKPKW","short_pith_number":"pith:OGTM3MNL","schema_version":"1.0","canonical_sha256":"71a6cdb1ab90cf467d932187d4a14f55bd7d4f4d3d85020be27e570096c2460a","source":{"kind":"arxiv","id":"1905.09905","version":1},"attestation_state":"computed","paper":{"title":"Neural ODEs with stochastic vector field mixtures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Micha{\\l} Koz{\\l}owski, Niall Twomey, Ra\\'ul Santos-Rodr\\'iguez","submitted_at":"2019-05-23T20:14:39Z","abstract_excerpt":"It was recently shown that neural ordinary differential equation models cannot solve fundamental and seemingly straightforward tasks even with high-capacity vector field representations. This paper introduces two other fundamental tasks to the set that baseline methods cannot solve, and proposes mixtures of stochastic vector fields as a model class that is capable of solving these essential problems. Dynamic vector field selection is of critical importance for our model, and our approach is to propagate component uncertainty over the integration interval with a technique based on forward filte"},"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":"1905.09905","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T20:14:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"05e951712bdbedfbf940564fc34639f220bf3b54fb7ec15276a22ea13398ce8d","abstract_canon_sha256":"a8a5b7c14633829e2e2485e08dc2ec5fab123f9481e2c3e40a08ae5bf7ba1f9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:14.074487Z","signature_b64":"ohl8MHTYdj2WiclsegT/D2hN4MZXqZsL6XzAYTIim3f7ujLcEYjeOHmwYA/Wc9BpRkAa6VQIcId3itfSR0scBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71a6cdb1ab90cf467d932187d4a14f55bd7d4f4d3d85020be27e570096c2460a","last_reissued_at":"2026-05-17T23:45:14.073820Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:14.073820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural ODEs with stochastic vector field mixtures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Micha{\\l} Koz{\\l}owski, Niall Twomey, Ra\\'ul Santos-Rodr\\'iguez","submitted_at":"2019-05-23T20:14:39Z","abstract_excerpt":"It was recently shown that neural ordinary differential equation models cannot solve fundamental and seemingly straightforward tasks even with high-capacity vector field representations. This paper introduces two other fundamental tasks to the set that baseline methods cannot solve, and proposes mixtures of stochastic vector fields as a model class that is capable of solving these essential problems. Dynamic vector field selection is of critical importance for our model, and our approach is to propagate component uncertainty over the integration interval with a technique based on forward filte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09905","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":"1905.09905","created_at":"2026-05-17T23:45:14.073919+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09905v1","created_at":"2026-05-17T23:45:14.073919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09905","created_at":"2026-05-17T23:45:14.073919+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGTM3MNLSDHU","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGTM3MNLSDHUM7MT","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGTM3MNL","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW","json":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW.json","graph_json":"https://pith.science/api/pith-number/OGTM3MNLSDHUM7MTEGD5JIKPKW/graph.json","events_json":"https://pith.science/api/pith-number/OGTM3MNLSDHUM7MTEGD5JIKPKW/events.json","paper":"https://pith.science/paper/OGTM3MNL"},"agent_actions":{"view_html":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW","download_json":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW.json","view_paper":"https://pith.science/paper/OGTM3MNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09905&json=true","fetch_graph":"https://pith.science/api/pith-number/OGTM3MNLSDHUM7MTEGD5JIKPKW/graph.json","fetch_events":"https://pith.science/api/pith-number/OGTM3MNLSDHUM7MTEGD5JIKPKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW/action/storage_attestation","attest_author":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW/action/author_attestation","sign_citation":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW/action/citation_signature","submit_replication":"https://pith.science/pith/OGTM3MNLSDHUM7MTEGD5JIKPKW/action/replication_record"}},"created_at":"2026-05-17T23:45:14.073919+00:00","updated_at":"2026-05-17T23:45:14.073919+00:00"}