{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LZ2SPHJNCGZTVUZC2S2TD6ZHZC","short_pith_number":"pith:LZ2SPHJN","schema_version":"1.0","canonical_sha256":"5e75279d2d11b33ad322d4b531fb27c8bedaaceb1adc140b45cf458b6e5f232a","source":{"kind":"arxiv","id":"2305.13290","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty and Structure in Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Katharina Ott, Michael Tiemann, Philipp Hennig","submitted_at":"2023-05-22T17:50:42Z","abstract_excerpt":"Neural ordinary differential equations (ODEs) are an emerging class of deep learning models for dynamical systems. They are particularly useful for learning an ODE vector field from observed trajectories (i.e., inverse problems). We here consider aspects of these models relevant for their application in science and engineering. Scientific predictions generally require structured uncertainty estimates. As a first contribution, we show that basic and lightweight Bayesian deep learning techniques like the Laplace approximation can be applied to neural ODEs to yield structured and meaningful uncer"},"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":"2305.13290","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T17:50:42Z","cross_cats_sorted":[],"title_canon_sha256":"230afc1cc46065e8cc3a7d45a126e228bccbdcde58c64c77d6a62505c487b5a7","abstract_canon_sha256":"afad5e4646117a3fea026eae1133158e5257983f152b032fe45f28b0a440284c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:28.675472Z","signature_b64":"U2Y3ISD4TC1+fYV0BgceweDhay/CtOVn71WGFpBmVGcYOLyG6+VhohOrLkLJLEMWB0Pogxukx8eaJc5FHZVAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e75279d2d11b33ad322d4b531fb27c8bedaaceb1adc140b45cf458b6e5f232a","last_reissued_at":"2026-07-05T06:12:28.674983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:28.674983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty and Structure in Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Katharina Ott, Michael Tiemann, Philipp Hennig","submitted_at":"2023-05-22T17:50:42Z","abstract_excerpt":"Neural ordinary differential equations (ODEs) are an emerging class of deep learning models for dynamical systems. They are particularly useful for learning an ODE vector field from observed trajectories (i.e., inverse problems). We here consider aspects of these models relevant for their application in science and engineering. Scientific predictions generally require structured uncertainty estimates. As a first contribution, we show that basic and lightweight Bayesian deep learning techniques like the Laplace approximation can be applied to neural ODEs to yield structured and meaningful uncer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13290","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.13290/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":"2305.13290","created_at":"2026-07-05T06:12:28.675040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13290v1","created_at":"2026-07-05T06:12:28.675040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13290","created_at":"2026-07-05T06:12:28.675040+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZ2SPHJNCGZT","created_at":"2026-07-05T06:12:28.675040+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZ2SPHJNCGZTVUZC","created_at":"2026-07-05T06:12:28.675040+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZ2SPHJN","created_at":"2026-07-05T06:12:28.675040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09053","citing_title":"Safe Active Learning for Gaussian Differential Equations","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC","json":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC.json","graph_json":"https://pith.science/api/pith-number/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/graph.json","events_json":"https://pith.science/api/pith-number/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/events.json","paper":"https://pith.science/paper/LZ2SPHJN"},"agent_actions":{"view_html":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC","download_json":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC.json","view_paper":"https://pith.science/paper/LZ2SPHJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13290&json=true","fetch_graph":"https://pith.science/api/pith-number/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/graph.json","fetch_events":"https://pith.science/api/pith-number/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/action/storage_attestation","attest_author":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/action/author_attestation","sign_citation":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/action/citation_signature","submit_replication":"https://pith.science/pith/LZ2SPHJNCGZTVUZC2S2TD6ZHZC/action/replication_record"}},"created_at":"2026-07-05T06:12:28.675040+00:00","updated_at":"2026-07-05T06:12:28.675040+00:00"}