{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LSUXUV5JIFBPMXA3IOXMUF3SUZ","short_pith_number":"pith:LSUXUV5J","schema_version":"1.0","canonical_sha256":"5ca97a57a94142f65c1b43aeca1772a669fb0e760bc91f399b9b0045b58fbc8c","source":{"kind":"arxiv","id":"2004.13830","version":1},"attestation_state":"computed","paper":{"title":"Deep Hamiltonian networks based on symplectic integrators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Aiqing Zhu, Pengzhan Jin, Yifa Tang","submitted_at":"2020-04-23T06:27:16Z","abstract_excerpt":"HNets is a class of neural networks on grounds of physical prior for learning Hamiltonian systems. This paper explains the influences of different integrators as hyper-parameters on the HNets through error analysis. If we define the network target as the map with zero empirical loss on arbitrary training data, then the non-symplectic integrators cannot guarantee the existence of the network targets of HNets. We introduce the inverse modified equations for HNets and prove that the HNets based on symplectic integrators possess network targets and the differences between the network targets and t"},"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":"2004.13830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2020-04-23T06:27:16Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"cec38542c00b2495daa87ba0ad94ac3f44a74c311c0aa7b5dfbc0363bac9f2b2","abstract_canon_sha256":"d078a28f24b1bf5a46faef2dc7feb90506810be9002572053bafde33243a3166"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:04.502493Z","signature_b64":"TgUVAc5EVbEIdWomMKtpr0C5VxWbMV6DgUDuUYaGSXZNzI2RhwRH74YfQJiXnSDNHAoHEafTF6nvahGL27u1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ca97a57a94142f65c1b43aeca1772a669fb0e760bc91f399b9b0045b58fbc8c","last_reissued_at":"2026-07-05T00:59:04.502122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:04.502122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Hamiltonian networks based on symplectic integrators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Aiqing Zhu, Pengzhan Jin, Yifa Tang","submitted_at":"2020-04-23T06:27:16Z","abstract_excerpt":"HNets is a class of neural networks on grounds of physical prior for learning Hamiltonian systems. This paper explains the influences of different integrators as hyper-parameters on the HNets through error analysis. If we define the network target as the map with zero empirical loss on arbitrary training data, then the non-symplectic integrators cannot guarantee the existence of the network targets of HNets. We introduce the inverse modified equations for HNets and prove that the HNets based on symplectic integrators possess network targets and the differences between the network targets and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13830","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/2004.13830/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":"2004.13830","created_at":"2026-07-05T00:59:04.502178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.13830v1","created_at":"2026-07-05T00:59:04.502178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13830","created_at":"2026-07-05T00:59:04.502178+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSUXUV5JIFBP","created_at":"2026-07-05T00:59:04.502178+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSUXUV5JIFBPMXA3","created_at":"2026-07-05T00:59:04.502178+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSUXUV5J","created_at":"2026-07-05T00:59:04.502178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23510","citing_title":"Learning partially observed systems with neural Hamiltonian ordinary differential equations","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ","json":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ.json","graph_json":"https://pith.science/api/pith-number/LSUXUV5JIFBPMXA3IOXMUF3SUZ/graph.json","events_json":"https://pith.science/api/pith-number/LSUXUV5JIFBPMXA3IOXMUF3SUZ/events.json","paper":"https://pith.science/paper/LSUXUV5J"},"agent_actions":{"view_html":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ","download_json":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ.json","view_paper":"https://pith.science/paper/LSUXUV5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.13830&json=true","fetch_graph":"https://pith.science/api/pith-number/LSUXUV5JIFBPMXA3IOXMUF3SUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LSUXUV5JIFBPMXA3IOXMUF3SUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ/action/storage_attestation","attest_author":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ/action/author_attestation","sign_citation":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ/action/citation_signature","submit_replication":"https://pith.science/pith/LSUXUV5JIFBPMXA3IOXMUF3SUZ/action/replication_record"}},"created_at":"2026-07-05T00:59:04.502178+00:00","updated_at":"2026-07-05T00:59:04.502178+00:00"}