{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AHSSUJJ4NK4XY26SPTDGW54EA4","short_pith_number":"pith:AHSSUJJ4","schema_version":"1.0","canonical_sha256":"01e52a253c6ab97c6bd27cc66b7784070d1e6ec8040af031780d5ce1c9cb0e17","source":{"kind":"arxiv","id":"2203.00128","version":1},"attestation_state":"computed","paper":{"title":"Learning Neural Hamiltonian Dynamics: A Methodological Overview","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongyuan Zha, Junchi Yan, Mingquan Feng, Zhijie Chen","submitted_at":"2022-02-28T22:54:39Z","abstract_excerpt":"The past few years have witnessed an increased interest in learning Hamiltonian dynamics in deep learning frameworks. As an inductive bias based on physical laws, Hamiltonian dynamics endow neural networks with accurate long-term prediction, interpretability, and data-efficient learning. However, Hamiltonian dynamics also bring energy conservation or dissipation assumptions on the input data and additional computational overhead. In this paper, we systematically survey recently proposed Hamiltonian neural network models, with a special emphasis on methodologies. In general, we discuss the majo"},"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":"2203.00128","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T22:54:39Z","cross_cats_sorted":[],"title_canon_sha256":"8b2f6457e0a5dbd0353985993cb7bcdbbfa52ed23e1b2d259196dff7a40d32d2","abstract_canon_sha256":"b542ece564711cdc1fa58050db9b491aa8a236a8ca9e0737ac7f04b6893a76f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:14.016349Z","signature_b64":"VRDPFwsilMPUrDxz2DDM6Sq9fJeaJ2hzHogJSlH9IL/VT/kt5rF2LwUi8x3QRVGdRegcEX0lpKZjHOqUmI+fCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e52a253c6ab97c6bd27cc66b7784070d1e6ec8040af031780d5ce1c9cb0e17","last_reissued_at":"2026-07-05T04:01:14.015849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:14.015849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Neural Hamiltonian Dynamics: A Methodological Overview","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongyuan Zha, Junchi Yan, Mingquan Feng, Zhijie Chen","submitted_at":"2022-02-28T22:54:39Z","abstract_excerpt":"The past few years have witnessed an increased interest in learning Hamiltonian dynamics in deep learning frameworks. As an inductive bias based on physical laws, Hamiltonian dynamics endow neural networks with accurate long-term prediction, interpretability, and data-efficient learning. However, Hamiltonian dynamics also bring energy conservation or dissipation assumptions on the input data and additional computational overhead. In this paper, we systematically survey recently proposed Hamiltonian neural network models, with a special emphasis on methodologies. In general, we discuss the majo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00128","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/2203.00128/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":"2203.00128","created_at":"2026-07-05T04:01:14.015910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.00128v1","created_at":"2026-07-05T04:01:14.015910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00128","created_at":"2026-07-05T04:01:14.015910+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHSSUJJ4NK4X","created_at":"2026-07-05T04:01:14.015910+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHSSUJJ4NK4XY26S","created_at":"2026-07-05T04:01:14.015910+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHSSUJJ4","created_at":"2026-07-05T04:01:14.015910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10778","citing_title":"SlotPi: Physics-informed Object-centric Reasoning Models","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4","json":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4.json","graph_json":"https://pith.science/api/pith-number/AHSSUJJ4NK4XY26SPTDGW54EA4/graph.json","events_json":"https://pith.science/api/pith-number/AHSSUJJ4NK4XY26SPTDGW54EA4/events.json","paper":"https://pith.science/paper/AHSSUJJ4"},"agent_actions":{"view_html":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4","download_json":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4.json","view_paper":"https://pith.science/paper/AHSSUJJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.00128&json=true","fetch_graph":"https://pith.science/api/pith-number/AHSSUJJ4NK4XY26SPTDGW54EA4/graph.json","fetch_events":"https://pith.science/api/pith-number/AHSSUJJ4NK4XY26SPTDGW54EA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4/action/storage_attestation","attest_author":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4/action/author_attestation","sign_citation":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4/action/citation_signature","submit_replication":"https://pith.science/pith/AHSSUJJ4NK4XY26SPTDGW54EA4/action/replication_record"}},"created_at":"2026-07-05T04:01:14.015910+00:00","updated_at":"2026-07-05T04:01:14.015910+00:00"}