{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QLRVF7KDL6TMZYSXFM4OTXC4GJ","short_pith_number":"pith:QLRVF7KD","schema_version":"1.0","canonical_sha256":"82e352fd435fa6cce2572b38e9dc5c32663d9478fad9cc13c855bfdf1fbe64cf","source":{"kind":"arxiv","id":"1905.12374","version":2},"attestation_state":"computed","paper":{"title":"GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Arany, Edward De Brouwer, Jaak Simm, Yves Moreau","submitted_at":"2019-05-29T12:25:49Z","abstract_excerpt":"Modeling real-world multidimensional time series can be particularly challenging when these are sporadically observed (i.e., sampling is irregular both in time and across dimensions)-such as in the case of clinical patient data. To address these challenges, we propose (1) a continuous-time version of the Gated Recurrent Unit, building upon the recent Neural Ordinary Differential Equations (Chen et al., 2018), and (2) a Bayesian update network that processes the sporadic observations. We bring these two ideas together in our GRU-ODE-Bayes method. We then demonstrate that the proposed method enc"},"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":"1905.12374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T12:25:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"37957ba89f85884a1486155e7e32cd60d6dc2e9e3063e450a98b7d890bf686b5","abstract_canon_sha256":"a399ba313c6967df2660b3890825642ffeb8ce5a9ae37b196217443938d9fbd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:39.590453Z","signature_b64":"32gZbV8OIpDffE+PlSqD2FZIphWQIXDfHC0Sy8rDDGJfLheKB53mxx0MTMmU0OoACKCKs4LHRXcYhUnt+qIBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82e352fd435fa6cce2572b38e9dc5c32663d9478fad9cc13c855bfdf1fbe64cf","last_reissued_at":"2026-07-05T00:22:39.589949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:39.589949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Arany, Edward De Brouwer, Jaak Simm, Yves Moreau","submitted_at":"2019-05-29T12:25:49Z","abstract_excerpt":"Modeling real-world multidimensional time series can be particularly challenging when these are sporadically observed (i.e., sampling is irregular both in time and across dimensions)-such as in the case of clinical patient data. To address these challenges, we propose (1) a continuous-time version of the Gated Recurrent Unit, building upon the recent Neural Ordinary Differential Equations (Chen et al., 2018), and (2) a Bayesian update network that processes the sporadic observations. We bring these two ideas together in our GRU-ODE-Bayes method. We then demonstrate that the proposed method enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12374","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/1905.12374/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":"1905.12374","created_at":"2026-07-05T00:22:39.590002+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12374v2","created_at":"2026-07-05T00:22:39.590002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12374","created_at":"2026-07-05T00:22:39.590002+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLRVF7KDL6TM","created_at":"2026-07-05T00:22:39.590002+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLRVF7KDL6TMZYSX","created_at":"2026-07-05T00:22:39.590002+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLRVF7KD","created_at":"2026-07-05T00:22:39.590002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21021","citing_title":"Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ","json":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ.json","graph_json":"https://pith.science/api/pith-number/QLRVF7KDL6TMZYSXFM4OTXC4GJ/graph.json","events_json":"https://pith.science/api/pith-number/QLRVF7KDL6TMZYSXFM4OTXC4GJ/events.json","paper":"https://pith.science/paper/QLRVF7KD"},"agent_actions":{"view_html":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ","download_json":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ.json","view_paper":"https://pith.science/paper/QLRVF7KD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12374&json=true","fetch_graph":"https://pith.science/api/pith-number/QLRVF7KDL6TMZYSXFM4OTXC4GJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QLRVF7KDL6TMZYSXFM4OTXC4GJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ/action/storage_attestation","attest_author":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ/action/author_attestation","sign_citation":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ/action/citation_signature","submit_replication":"https://pith.science/pith/QLRVF7KDL6TMZYSXFM4OTXC4GJ/action/replication_record"}},"created_at":"2026-07-05T00:22:39.590002+00:00","updated_at":"2026-07-05T00:22:39.590002+00:00"}