{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VCBDYQBDGXP7466IIPJQ67P4A2","short_pith_number":"pith:VCBDYQBD","schema_version":"1.0","canonical_sha256":"a8823c402335dffe7bc843d30f7dfc06a6a3fc32e33e51f412a1722f3ebafb86","source":{"kind":"arxiv","id":"2412.11301","version":1},"attestation_state":"computed","paper":{"title":"Semi-Implicit Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hong Zhang, Romit Maulik, Ying Liu","submitted_at":"2024-12-15T20:21:02Z","abstract_excerpt":"Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning. We present a semi-implicit neural ODE approach that exploits the partitionable structure of the underlying dynamics. Our technique leads to an implicit neural network with significant computational advantages over existing approaches because of enhanced stability and efficient linear solves during time integration. We show that our approach outperforms existing approac"},"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":"2412.11301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-15T20:21:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94daad23589a673b44a61e5cb222d15cc5d813b9c120687dcaa5f4d36f30b60e","abstract_canon_sha256":"4f84237db4cf66d3403d7f53bdd9995e049083e922b09f61f4f3d6cb58f6ed23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:30.294101Z","signature_b64":"XSs8u5er0NvbRrrqu7kOXxP57vNfCriusIXiHPcEWsAJvGhoho5cYS+8aAbec9IYf0vJSmSA0DCgFyfgzIrpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8823c402335dffe7bc843d30f7dfc06a6a3fc32e33e51f412a1722f3ebafb86","last_reissued_at":"2026-07-05T09:49:30.293665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:30.293665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Implicit Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hong Zhang, Romit Maulik, Ying Liu","submitted_at":"2024-12-15T20:21:02Z","abstract_excerpt":"Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning. We present a semi-implicit neural ODE approach that exploits the partitionable structure of the underlying dynamics. Our technique leads to an implicit neural network with significant computational advantages over existing approaches because of enhanced stability and efficient linear solves during time integration. We show that our approach outperforms existing approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11301","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/2412.11301/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":"2412.11301","created_at":"2026-07-05T09:49:30.293718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11301v1","created_at":"2026-07-05T09:49:30.293718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11301","created_at":"2026-07-05T09:49:30.293718+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCBDYQBDGXP7","created_at":"2026-07-05T09:49:30.293718+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCBDYQBDGXP7466I","created_at":"2026-07-05T09:49:30.293718+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCBDYQBD","created_at":"2026-07-05T09:49:30.293718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2","json":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2.json","graph_json":"https://pith.science/api/pith-number/VCBDYQBDGXP7466IIPJQ67P4A2/graph.json","events_json":"https://pith.science/api/pith-number/VCBDYQBDGXP7466IIPJQ67P4A2/events.json","paper":"https://pith.science/paper/VCBDYQBD"},"agent_actions":{"view_html":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2","download_json":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2.json","view_paper":"https://pith.science/paper/VCBDYQBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11301&json=true","fetch_graph":"https://pith.science/api/pith-number/VCBDYQBDGXP7466IIPJQ67P4A2/graph.json","fetch_events":"https://pith.science/api/pith-number/VCBDYQBDGXP7466IIPJQ67P4A2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2/action/storage_attestation","attest_author":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2/action/author_attestation","sign_citation":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2/action/citation_signature","submit_replication":"https://pith.science/pith/VCBDYQBDGXP7466IIPJQ67P4A2/action/replication_record"}},"created_at":"2026-07-05T09:49:30.293718+00:00","updated_at":"2026-07-05T09:49:30.293718+00:00"}