{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PTYTZHTERFDW6W7WDTEFWD4CW7","short_pith_number":"pith:PTYTZHTE","schema_version":"1.0","canonical_sha256":"7cf13c9e6489476f5bf61cc85b0f82b7f87c76f5f87228f78ed47889cd89d70d","source":{"kind":"arxiv","id":"2103.12413","version":2},"attestation_state":"computed","paper":{"title":"Neural ODE Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Norcliffe, Ben Day, Cristian Bodnar, Jacob Moss, Pietro Li\\`o","submitted_at":"2021-03-23T09:32:06Z","abstract_excerpt":"Neural Ordinary Differential Equations (NODEs) use a neural network to model the instantaneous rate of change in the state of a system. However, despite their apparent suitability for dynamics-governed time-series, NODEs present a few disadvantages. First, they are unable to adapt to incoming data points, a fundamental requirement for real-time applications imposed by the natural direction of time. Second, time series are often composed of a sparse set of measurements that could be explained by many possible underlying dynamics. NODEs do not capture this uncertainty. In contrast, Neural Proces"},"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":"2103.12413","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-23T09:32:06Z","cross_cats_sorted":[],"title_canon_sha256":"110c47a6444855f31130d25f2f22899a256118cef99deadfcd533d178f99481a","abstract_canon_sha256":"a58705b139ac417e05bbc349da85d04f47855ff8120452c60dc6b42889a09b5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:22.180049Z","signature_b64":"mlKRH9O9pvA3cEYxry1Zx6b4y0GvaOWkqYNxEJc3mif+cgu8VydoiwARFs55s4cb3T+a+v6V3GOl6QOPJe3kDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf13c9e6489476f5bf61cc85b0f82b7f87c76f5f87228f78ed47889cd89d70d","last_reissued_at":"2026-07-05T03:06:22.179671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:22.179671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural ODE Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Norcliffe, Ben Day, Cristian Bodnar, Jacob Moss, Pietro Li\\`o","submitted_at":"2021-03-23T09:32:06Z","abstract_excerpt":"Neural Ordinary Differential Equations (NODEs) use a neural network to model the instantaneous rate of change in the state of a system. However, despite their apparent suitability for dynamics-governed time-series, NODEs present a few disadvantages. First, they are unable to adapt to incoming data points, a fundamental requirement for real-time applications imposed by the natural direction of time. Second, time series are often composed of a sparse set of measurements that could be explained by many possible underlying dynamics. NODEs do not capture this uncertainty. In contrast, Neural Proces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12413","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/2103.12413/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":"2103.12413","created_at":"2026-07-05T03:06:22.179726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12413v2","created_at":"2026-07-05T03:06:22.179726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12413","created_at":"2026-07-05T03:06:22.179726+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTYTZHTERFDW","created_at":"2026-07-05T03:06:22.179726+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTYTZHTERFDW6W7W","created_at":"2026-07-05T03:06:22.179726+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTYTZHTE","created_at":"2026-07-05T03:06:22.179726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.00203","citing_title":"Estimating Parameter Fields in Multi-Physics PDEs from Scarce Measurements","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13913","citing_title":"Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11007","citing_title":"The Transformer as a Polar State Estimator","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7","json":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7.json","graph_json":"https://pith.science/api/pith-number/PTYTZHTERFDW6W7WDTEFWD4CW7/graph.json","events_json":"https://pith.science/api/pith-number/PTYTZHTERFDW6W7WDTEFWD4CW7/events.json","paper":"https://pith.science/paper/PTYTZHTE"},"agent_actions":{"view_html":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7","download_json":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7.json","view_paper":"https://pith.science/paper/PTYTZHTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12413&json=true","fetch_graph":"https://pith.science/api/pith-number/PTYTZHTERFDW6W7WDTEFWD4CW7/graph.json","fetch_events":"https://pith.science/api/pith-number/PTYTZHTERFDW6W7WDTEFWD4CW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7/action/storage_attestation","attest_author":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7/action/author_attestation","sign_citation":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7/action/citation_signature","submit_replication":"https://pith.science/pith/PTYTZHTERFDW6W7WDTEFWD4CW7/action/replication_record"}},"created_at":"2026-07-05T03:06:22.179726+00:00","updated_at":"2026-07-05T03:06:22.179726+00:00"}