{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5SEYV3VESLE7FMUJRPP7E2MQIM","short_pith_number":"pith:5SEYV3VE","schema_version":"1.0","canonical_sha256":"ec898aeea492c9f2b2898bdff269904337d3de3ed77eecb6cb016455d8ace375","source":{"kind":"arxiv","id":"2012.07244","version":4},"attestation_state":"computed","paper":{"title":"Bayesian Neural Ordinary Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aslan Garcia-Valadez, Chris Rackauckas, Karen Chung, Krishna Vishal Vemula, Mohamed Tarek, Raj Dandekar, Vaibhav Dixit","submitted_at":"2020-12-14T04:05:26Z","abstract_excerpt":"Recently, Neural Ordinary Differential Equations has emerged as a powerful framework for modeling physical simulations without explicitly defining the ODEs governing the system, but instead learning them via machine learning. However, the question: \"Can Bayesian learning frameworks be integrated with Neural ODE's to robustly quantify the uncertainty in the weights of a Neural ODE?\" remains unanswered. In an effort to address this question, we primarily evaluate the following categories of inference methods: (a) The No-U-Turn MCMC sampler (NUTS), (b) Stochastic Gradient Hamiltonian Monte Carlo "},"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":"2012.07244","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T04:05:26Z","cross_cats_sorted":[],"title_canon_sha256":"14785f7d96e1313b38d08d67df0e8daab299308549000b1a2cfdc94fe39f213f","abstract_canon_sha256":"75dfcc1453211ac30518eb85778f3220aa0b8690fc1d78b4daaad6ff39ddf458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:18.828768Z","signature_b64":"ScYFKjHldSg4egVTInaYQ8gWab0+i4yQK06gQx3G3ITTsRppxho+6WC9Rmvisc0unura7Ed8JaaBN+TpzVdoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec898aeea492c9f2b2898bdff269904337d3de3ed77eecb6cb016455d8ace375","last_reissued_at":"2026-07-05T03:54:18.828355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:18.828355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Neural Ordinary Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aslan Garcia-Valadez, Chris Rackauckas, Karen Chung, Krishna Vishal Vemula, Mohamed Tarek, Raj Dandekar, Vaibhav Dixit","submitted_at":"2020-12-14T04:05:26Z","abstract_excerpt":"Recently, Neural Ordinary Differential Equations has emerged as a powerful framework for modeling physical simulations without explicitly defining the ODEs governing the system, but instead learning them via machine learning. However, the question: \"Can Bayesian learning frameworks be integrated with Neural ODE's to robustly quantify the uncertainty in the weights of a Neural ODE?\" remains unanswered. In an effort to address this question, we primarily evaluate the following categories of inference methods: (a) The No-U-Turn MCMC sampler (NUTS), (b) Stochastic Gradient Hamiltonian Monte Carlo "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07244","kind":"arxiv","version":4},"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/2012.07244/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":"2012.07244","created_at":"2026-07-05T03:54:18.828416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.07244v4","created_at":"2026-07-05T03:54:18.828416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07244","created_at":"2026-07-05T03:54:18.828416+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SEYV3VESLE7","created_at":"2026-07-05T03:54:18.828416+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SEYV3VESLE7FMUJ","created_at":"2026-07-05T03:54:18.828416+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SEYV3VE","created_at":"2026-07-05T03:54:18.828416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11988","citing_title":"What Uncertainties Do We Need for Dynamical Systems?","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06351","citing_title":"Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30289","citing_title":"Structural functional identifiability and model discovery in differential equation models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00203","citing_title":"Estimating Parameter Fields in Multi-Physics PDEs from Scarce Measurements","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01231","citing_title":"Experimental Design for Missing Physics","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM","json":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM.json","graph_json":"https://pith.science/api/pith-number/5SEYV3VESLE7FMUJRPP7E2MQIM/graph.json","events_json":"https://pith.science/api/pith-number/5SEYV3VESLE7FMUJRPP7E2MQIM/events.json","paper":"https://pith.science/paper/5SEYV3VE"},"agent_actions":{"view_html":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM","download_json":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM.json","view_paper":"https://pith.science/paper/5SEYV3VE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.07244&json=true","fetch_graph":"https://pith.science/api/pith-number/5SEYV3VESLE7FMUJRPP7E2MQIM/graph.json","fetch_events":"https://pith.science/api/pith-number/5SEYV3VESLE7FMUJRPP7E2MQIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM/action/storage_attestation","attest_author":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM/action/author_attestation","sign_citation":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM/action/citation_signature","submit_replication":"https://pith.science/pith/5SEYV3VESLE7FMUJRPP7E2MQIM/action/replication_record"}},"created_at":"2026-07-05T03:54:18.828416+00:00","updated_at":"2026-07-05T03:54:18.828416+00:00"}