{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UI7SVCUVVV5EW57QTLTKBCEV3Y","short_pith_number":"pith:UI7SVCUV","schema_version":"1.0","canonical_sha256":"a23f2a8a95ad7a4b77f09ae6a08895de28d69e286f42a4ce7deb9b2f63b6ca1f","source":{"kind":"arxiv","id":"1910.05513","version":4},"attestation_state":"computed","paper":{"title":"On Robustness of Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hanshu Yan, Jiashi Feng, Jiawei Du, Vincent Y. F. Tan","submitted_at":"2019-10-12T07:15:44Z","abstract_excerpt":"Neural ordinary differential equations (ODEs) have been attracting increasing attention in various research domains recently. There have been some works studying optimization issues and approximation capabilities of neural ODEs, but their robustness is still yet unclear. In this work, we fill this important gap by exploring robustness properties of neural ODEs both empirically and theoretically. We first present an empirical study on the robustness of the neural ODE-based networks (ODENets) by exposing them to inputs with various types of perturbations and subsequently investigating the change"},"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":"1910.05513","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T07:15:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"80a2ccfab9b0617db6726969cdd7628c77a72b816a834105d9848c45f35ea8bf","abstract_canon_sha256":"98c694a092ebf0c5513b3d092e76fa1e05116761d675f5228c4e23b144a2047c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:39.538489Z","signature_b64":"JvILcWBXi5zfhlgJnoxp2xJChLPVObI9nnNmmEQYocb/TP6S1+AD5TdXKFnNV5Bo6KIAgsPnNwRNzs08nZbsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a23f2a8a95ad7a4b77f09ae6a08895de28d69e286f42a4ce7deb9b2f63b6ca1f","last_reissued_at":"2026-07-05T04:01:39.538010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:39.538010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Robustness of Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hanshu Yan, Jiashi Feng, Jiawei Du, Vincent Y. F. Tan","submitted_at":"2019-10-12T07:15:44Z","abstract_excerpt":"Neural ordinary differential equations (ODEs) have been attracting increasing attention in various research domains recently. There have been some works studying optimization issues and approximation capabilities of neural ODEs, but their robustness is still yet unclear. In this work, we fill this important gap by exploring robustness properties of neural ODEs both empirically and theoretically. We first present an empirical study on the robustness of the neural ODE-based networks (ODENets) by exposing them to inputs with various types of perturbations and subsequently investigating the change"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05513","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/1910.05513/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":"1910.05513","created_at":"2026-07-05T04:01:39.538067+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.05513v4","created_at":"2026-07-05T04:01:39.538067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05513","created_at":"2026-07-05T04:01:39.538067+00:00"},{"alias_kind":"pith_short_12","alias_value":"UI7SVCUVVV5E","created_at":"2026-07-05T04:01:39.538067+00:00"},{"alias_kind":"pith_short_16","alias_value":"UI7SVCUVVV5EW57Q","created_at":"2026-07-05T04:01:39.538067+00:00"},{"alias_kind":"pith_short_8","alias_value":"UI7SVCUV","created_at":"2026-07-05T04:01:39.538067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02145","citing_title":"Hybrid Neural Ordinary Differential Equations for Data-Efficient Polymerization Modeling with Incomplete Kinetics","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16529","citing_title":"Multiscale Supervised Unbalanced Optimal Transport Flow Matching","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y","json":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y.json","graph_json":"https://pith.science/api/pith-number/UI7SVCUVVV5EW57QTLTKBCEV3Y/graph.json","events_json":"https://pith.science/api/pith-number/UI7SVCUVVV5EW57QTLTKBCEV3Y/events.json","paper":"https://pith.science/paper/UI7SVCUV"},"agent_actions":{"view_html":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y","download_json":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y.json","view_paper":"https://pith.science/paper/UI7SVCUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.05513&json=true","fetch_graph":"https://pith.science/api/pith-number/UI7SVCUVVV5EW57QTLTKBCEV3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/UI7SVCUVVV5EW57QTLTKBCEV3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y/action/storage_attestation","attest_author":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y/action/author_attestation","sign_citation":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y/action/citation_signature","submit_replication":"https://pith.science/pith/UI7SVCUVVV5EW57QTLTKBCEV3Y/action/replication_record"}},"created_at":"2026-07-05T04:01:39.538067+00:00","updated_at":"2026-07-05T04:01:39.538067+00:00"}