{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:247HM66ZSQ7JTLB3LNX35BWHQ4","short_pith_number":"pith:247HM66Z","schema_version":"1.0","canonical_sha256":"d73e767bd9943e99ac3b5b6fbe86c78738cb367867b9ed7450917b5d04b50b7b","source":{"kind":"arxiv","id":"2601.22123","version":4},"attestation_state":"computed","paper":{"title":"Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank No\\'e, Gregor Lied, Klaus-Robert M\\\"uller, Michael Plainer, Oliver T. Unke, Stefan Chmiela, Thorben Frank, Winfried Ripken","submitted_at":"2026-01-29T18:47:46Z","abstract_excerpt":"Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome this constraint, we introduce a framework to learn Hamiltonian Flow Maps by predicting the mean phase-space evolution over a chosen time span, enabling stable large-timestep updates far beyond the stability limits of classical integrators. To this end, we impose a Mean Flow consistency condition for time-averaged Hamiltonian dynamics. Unlike prior approaches, this allows training on independent phase-space samples without access to future states, av"},"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":"2601.22123","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T18:47:46Z","cross_cats_sorted":[],"title_canon_sha256":"896ac38c0325a8a48a6dfd3a94a14606f7d2a5f1216d9d0c5a611f30aef5009a","abstract_canon_sha256":"9ba6720aac97bc66b382284af6afd0fb3b82a17733e5e51d20e6f55928e69b4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:46.392506Z","signature_b64":"8ksAtx84qmu8E/oJH/tJGKTDFg+RPaUOf8aoatJFlW+RLISGdD5lxDDBG54Xxq+fTWsK5GTD+WLnIy0NrAIJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d73e767bd9943e99ac3b5b6fbe86c78738cb367867b9ed7450917b5d04b50b7b","last_reissued_at":"2026-07-01T01:17:46.391948Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:46.391948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank No\\'e, Gregor Lied, Klaus-Robert M\\\"uller, Michael Plainer, Oliver T. Unke, Stefan Chmiela, Thorben Frank, Winfried Ripken","submitted_at":"2026-01-29T18:47:46Z","abstract_excerpt":"Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome this constraint, we introduce a framework to learn Hamiltonian Flow Maps by predicting the mean phase-space evolution over a chosen time span, enabling stable large-timestep updates far beyond the stability limits of classical integrators. To this end, we impose a Mean Flow consistency condition for time-averaged Hamiltonian dynamics. Unlike prior approaches, this allows training on independent phase-space samples without access to future states, av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22123","kind":"arxiv","version":4},"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/2601.22123/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":"2601.22123","created_at":"2026-07-01T01:17:46.392020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22123v4","created_at":"2026-07-01T01:17:46.392020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22123","created_at":"2026-07-01T01:17:46.392020+00:00"},{"alias_kind":"pith_short_12","alias_value":"247HM66ZSQ7J","created_at":"2026-07-01T01:17:46.392020+00:00"},{"alias_kind":"pith_short_16","alias_value":"247HM66ZSQ7JTLB3","created_at":"2026-07-01T01:17:46.392020+00:00"},{"alias_kind":"pith_short_8","alias_value":"247HM66Z","created_at":"2026-07-01T01:17:46.392020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.19050","citing_title":"Generative Pseudo-Force Fields for Molecular Generation","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25244","citing_title":"Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4","json":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4.json","graph_json":"https://pith.science/api/pith-number/247HM66ZSQ7JTLB3LNX35BWHQ4/graph.json","events_json":"https://pith.science/api/pith-number/247HM66ZSQ7JTLB3LNX35BWHQ4/events.json","paper":"https://pith.science/paper/247HM66Z"},"agent_actions":{"view_html":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4","download_json":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4.json","view_paper":"https://pith.science/paper/247HM66Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22123&json=true","fetch_graph":"https://pith.science/api/pith-number/247HM66ZSQ7JTLB3LNX35BWHQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/247HM66ZSQ7JTLB3LNX35BWHQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4/action/storage_attestation","attest_author":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4/action/author_attestation","sign_citation":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4/action/citation_signature","submit_replication":"https://pith.science/pith/247HM66ZSQ7JTLB3LNX35BWHQ4/action/replication_record"}},"created_at":"2026-07-01T01:17:46.392020+00:00","updated_at":"2026-07-01T01:17:46.392020+00:00"}