{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:65XSKYNWVK72EVMWB3P4W2OE4A","short_pith_number":"pith:65XSKYNW","schema_version":"1.0","canonical_sha256":"f76f2561b6aabfa255960edfcb69c4e031c446dd8c7da76f0628af46acad46c8","source":{"kind":"arxiv","id":"2303.02262","version":3},"attestation_state":"computed","paper":{"title":"Locally Regularized Neural Differential Equations: Some Black Boxes Were Meant to Remain Closed!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Alan Edelman, Avik Pal, Chris Rackauckas","submitted_at":"2023-03-03T23:31:15Z","abstract_excerpt":"Implicit layer deep learning techniques, like Neural Differential Equations, have become an important modeling framework due to their ability to adapt to new problems automatically. Training a neural differential equation is effectively a search over a space of plausible dynamical systems. However, controlling the computational cost for these models is difficult since it relies on the number of steps the adaptive solver takes. Most prior works have used higher-order methods to reduce prediction timings while greatly increasing training time or reducing both training and prediction timings by r"},"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":"2303.02262","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T23:31:15Z","cross_cats_sorted":["cs.AI","cs.NA","math.NA"],"title_canon_sha256":"39e167560e0b245aecfafecac5b0c0a3e213e1f789548d44f99915c824ed6442","abstract_canon_sha256":"d20b1cbb88994e24f41998bac7e8e4c0afc830cea5f460e175ce36a911a504b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:49.343671Z","signature_b64":"o1IUVOe/NPmKrtsqYV85javao3RhcCuVfq9+xZcz4Ek3YLm37eVdT5I3btu8x42MRToIA+Q3MdjM5K8UP9ifCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f76f2561b6aabfa255960edfcb69c4e031c446dd8c7da76f0628af46acad46c8","last_reissued_at":"2026-07-05T06:16:49.343261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:49.343261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locally Regularized Neural Differential Equations: Some Black Boxes Were Meant to Remain Closed!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Alan Edelman, Avik Pal, Chris Rackauckas","submitted_at":"2023-03-03T23:31:15Z","abstract_excerpt":"Implicit layer deep learning techniques, like Neural Differential Equations, have become an important modeling framework due to their ability to adapt to new problems automatically. Training a neural differential equation is effectively a search over a space of plausible dynamical systems. However, controlling the computational cost for these models is difficult since it relies on the number of steps the adaptive solver takes. Most prior works have used higher-order methods to reduce prediction timings while greatly increasing training time or reducing both training and prediction timings by r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02262","kind":"arxiv","version":3},"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/2303.02262/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":"2303.02262","created_at":"2026-07-05T06:16:49.343325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02262v3","created_at":"2026-07-05T06:16:49.343325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02262","created_at":"2026-07-05T06:16:49.343325+00:00"},{"alias_kind":"pith_short_12","alias_value":"65XSKYNWVK72","created_at":"2026-07-05T06:16:49.343325+00:00"},{"alias_kind":"pith_short_16","alias_value":"65XSKYNWVK72EVMW","created_at":"2026-07-05T06:16:49.343325+00:00"},{"alias_kind":"pith_short_8","alias_value":"65XSKYNW","created_at":"2026-07-05T06:16:49.343325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01181","citing_title":"Training Stiff Neural Ordinary Differential Equations with Explicit Exponential Integration Methods","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A","json":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A.json","graph_json":"https://pith.science/api/pith-number/65XSKYNWVK72EVMWB3P4W2OE4A/graph.json","events_json":"https://pith.science/api/pith-number/65XSKYNWVK72EVMWB3P4W2OE4A/events.json","paper":"https://pith.science/paper/65XSKYNW"},"agent_actions":{"view_html":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A","download_json":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A.json","view_paper":"https://pith.science/paper/65XSKYNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02262&json=true","fetch_graph":"https://pith.science/api/pith-number/65XSKYNWVK72EVMWB3P4W2OE4A/graph.json","fetch_events":"https://pith.science/api/pith-number/65XSKYNWVK72EVMWB3P4W2OE4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A/action/storage_attestation","attest_author":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A/action/author_attestation","sign_citation":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A/action/citation_signature","submit_replication":"https://pith.science/pith/65XSKYNWVK72EVMWB3P4W2OE4A/action/replication_record"}},"created_at":"2026-07-05T06:16:49.343325+00:00","updated_at":"2026-07-05T06:16:49.343325+00:00"}