{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DHGZKOPTXFA2DNX5CD5MABE5G5","short_pith_number":"pith:DHGZKOPT","schema_version":"1.0","canonical_sha256":"19cd9539f3b941a1b6fd10fac0049d376b33c9a8eaf2f831575bbbbe4b43722a","source":{"kind":"arxiv","id":"2105.03688","version":1},"attestation_state":"computed","paper":{"title":"HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Guojie Song, Lingsheng Cai, Shuwen Yang, Ziyao Li","submitted_at":"2021-05-08T12:48:08Z","abstract_excerpt":"Well-designed molecular representations (fingerprints) are vital to combine medical chemistry and deep learning. Whereas incorporating 3D geometry of molecules (i.e. conformations) in their representations seems beneficial, current 3D algorithms are still in infancy. In this paper, we propose a novel molecular representation algorithm which preserves 3D conformations of molecules with a Molecular Hamiltonian Network (HamNet). In HamNet, implicit positions and momentums of atoms in a molecule interact in the Hamiltonian Engine following the discretized Hamiltonian equations. These implicit coor"},"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":"2105.03688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-08T12:48:08Z","cross_cats_sorted":["cs.CV","physics.chem-ph"],"title_canon_sha256":"216c2745906b046bd1afa0697676bb5f43720e69466a4a8c61716b66ae16bcd7","abstract_canon_sha256":"6d17b3c08f3dddd6fde24f4ff69b8ff0f788a71989b688e7b9979aee300c4149"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:38.034545Z","signature_b64":"xdtzXPUZ2aKfXdmXPk268P2dyj6cFuQW9l1HHrkmgoKAN9ZNMRbK6mA8NYoxWJIwUAXK/XVIJwNxVU1hgE8GAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19cd9539f3b941a1b6fd10fac0049d376b33c9a8eaf2f831575bbbbe4b43722a","last_reissued_at":"2026-07-05T02:38:38.034143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:38.034143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Guojie Song, Lingsheng Cai, Shuwen Yang, Ziyao Li","submitted_at":"2021-05-08T12:48:08Z","abstract_excerpt":"Well-designed molecular representations (fingerprints) are vital to combine medical chemistry and deep learning. Whereas incorporating 3D geometry of molecules (i.e. conformations) in their representations seems beneficial, current 3D algorithms are still in infancy. In this paper, we propose a novel molecular representation algorithm which preserves 3D conformations of molecules with a Molecular Hamiltonian Network (HamNet). In HamNet, implicit positions and momentums of atoms in a molecule interact in the Hamiltonian Engine following the discretized Hamiltonian equations. These implicit coor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03688","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/2105.03688/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":"2105.03688","created_at":"2026-07-05T02:38:38.034200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.03688v1","created_at":"2026-07-05T02:38:38.034200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03688","created_at":"2026-07-05T02:38:38.034200+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHGZKOPTXFA2","created_at":"2026-07-05T02:38:38.034200+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHGZKOPTXFA2DNX5","created_at":"2026-07-05T02:38:38.034200+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHGZKOPT","created_at":"2026-07-05T02:38:38.034200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06917","citing_title":"CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5","json":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5.json","graph_json":"https://pith.science/api/pith-number/DHGZKOPTXFA2DNX5CD5MABE5G5/graph.json","events_json":"https://pith.science/api/pith-number/DHGZKOPTXFA2DNX5CD5MABE5G5/events.json","paper":"https://pith.science/paper/DHGZKOPT"},"agent_actions":{"view_html":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5","download_json":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5.json","view_paper":"https://pith.science/paper/DHGZKOPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.03688&json=true","fetch_graph":"https://pith.science/api/pith-number/DHGZKOPTXFA2DNX5CD5MABE5G5/graph.json","fetch_events":"https://pith.science/api/pith-number/DHGZKOPTXFA2DNX5CD5MABE5G5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5/action/storage_attestation","attest_author":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5/action/author_attestation","sign_citation":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5/action/citation_signature","submit_replication":"https://pith.science/pith/DHGZKOPTXFA2DNX5CD5MABE5G5/action/replication_record"}},"created_at":"2026-07-05T02:38:38.034200+00:00","updated_at":"2026-07-05T02:38:38.034200+00:00"}