{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XD5TS7Z76TKPVTTQN2EG3X3C2P","short_pith_number":"pith:XD5TS7Z7","schema_version":"1.0","canonical_sha256":"b8fb397f3ff4d4face706e886ddf62d3f4598ef3848c3178be9f9275e545edb1","source":{"kind":"arxiv","id":"1907.03907","version":1},"attestation_state":"computed","paper":{"title":"Latent ODEs for Irregularly-Sampled Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Ricky T. Q. Chen, Yulia Rubanova","submitted_at":"2019-07-08T23:21:32Z","abstract_excerpt":"Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace the recognition network of the recently-proposed Latent ODE model. Both ODE-RNNs and Latent ODEs can naturally handle arbitrary time gaps between observations, and can explicitly model the probability of observation times using Poisson processes. We show experimentally that these "},"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":"1907.03907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-08T23:21:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"394d1100f5c5b60a42af752f16ce4d699c2833e3b2ce0fa8eddef8e2794df121","abstract_canon_sha256":"1a296a3160b9d63fa8c8c4015f6aa9d5649a8a41d86dfc7c1e6969920b7f29de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:06.439574Z","signature_b64":"pdwwjSrTqWBIlTE5BbiMfC1NHdaYUq/dwjyD4LWMLs/hD68u6lT3Ex7KZaEXuFgAyX+dwwOlZhmFKxzORvNMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8fb397f3ff4d4face706e886ddf62d3f4598ef3848c3178be9f9275e545edb1","last_reissued_at":"2026-05-17T23:41:06.438968Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:06.438968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent ODEs for Irregularly-Sampled Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Ricky T. Q. Chen, Yulia Rubanova","submitted_at":"2019-07-08T23:21:32Z","abstract_excerpt":"Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace the recognition network of the recently-proposed Latent ODE model. Both ODE-RNNs and Latent ODEs can naturally handle arbitrary time gaps between observations, and can explicitly model the probability of observation times using Poisson processes. We show experimentally that these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03907","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":"1907.03907","created_at":"2026-05-17T23:41:06.439068+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03907v1","created_at":"2026-05-17T23:41:06.439068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03907","created_at":"2026-05-17T23:41:06.439068+00:00"},{"alias_kind":"pith_short_12","alias_value":"XD5TS7Z76TKP","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XD5TS7Z76TKPVTTQ","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XD5TS7Z7","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2001.04385","citing_title":"Universal Differential Equations for Scientific Machine Learning","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2512.12116","citing_title":"Neural CDEs as Correctors for Learned Time Series Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11007","citing_title":"RT-Transformer: The Transformer Block as a Spherical State Estimator","ref_index":164,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P","json":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P.json","graph_json":"https://pith.science/api/pith-number/XD5TS7Z76TKPVTTQN2EG3X3C2P/graph.json","events_json":"https://pith.science/api/pith-number/XD5TS7Z76TKPVTTQN2EG3X3C2P/events.json","paper":"https://pith.science/paper/XD5TS7Z7"},"agent_actions":{"view_html":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P","download_json":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P.json","view_paper":"https://pith.science/paper/XD5TS7Z7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03907&json=true","fetch_graph":"https://pith.science/api/pith-number/XD5TS7Z76TKPVTTQN2EG3X3C2P/graph.json","fetch_events":"https://pith.science/api/pith-number/XD5TS7Z76TKPVTTQN2EG3X3C2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P/action/storage_attestation","attest_author":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P/action/author_attestation","sign_citation":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P/action/citation_signature","submit_replication":"https://pith.science/pith/XD5TS7Z76TKPVTTQN2EG3X3C2P/action/replication_record"}},"created_at":"2026-05-17T23:41:06.439068+00:00","updated_at":"2026-05-17T23:41:06.439068+00:00"}