{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FQ7Y437IFWSAHR23LRRNIC76ND","short_pith_number":"pith:FQ7Y437I","schema_version":"1.0","canonical_sha256":"2c3f8e6fe82da403c75b5c62d40bfe68fba687be493ce8cc8dc1d68c6f31d53b","source":{"kind":"arxiv","id":"1909.12790","version":1},"attestation_state":"computed","paper":{"title":"Hamiltonian Graph Networks with ODE Integrators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Alvaro Sanchez-Gonzalez, Kyle Cranmer, Peter Battaglia, Victor Bapst","submitted_at":"2019-09-27T16:54:04Z","abstract_excerpt":"We introduce an approach for imposing physically informed inductive biases in learned simulation models. We combine graph networks with a differentiable ordinary differential equation integrator as a mechanism for predicting future states, and a Hamiltonian as an internal representation. We find that our approach outperforms baselines without these biases in terms of predictive accuracy, energy accuracy, and zero-shot generalization to time-step sizes and integrator orders not experienced during training. This advances the state-of-the-art of learned simulation, and in principle is applicable "},"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":"1909.12790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-27T16:54:04Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"d7c87674de67e007c6049c240909ad0fce75fcec746385589531f78bd91b410b","abstract_canon_sha256":"f108340f9521bc11865a997f27c890537571cbf94681cabd8b3d34932e3bfa55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:42.736796Z","signature_b64":"GbScn5nd5XEwDq9Fsx+f3O7MBVBGb0bwcUuh0HzcA4+2tMLCEwO0B6l3e7soJbYk/deux1ZFC5oCvCj8eUy+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c3f8e6fe82da403c75b5c62d40bfe68fba687be493ce8cc8dc1d68c6f31d53b","last_reissued_at":"2026-07-05T00:07:42.736330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:42.736330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hamiltonian Graph Networks with ODE Integrators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Alvaro Sanchez-Gonzalez, Kyle Cranmer, Peter Battaglia, Victor Bapst","submitted_at":"2019-09-27T16:54:04Z","abstract_excerpt":"We introduce an approach for imposing physically informed inductive biases in learned simulation models. We combine graph networks with a differentiable ordinary differential equation integrator as a mechanism for predicting future states, and a Hamiltonian as an internal representation. We find that our approach outperforms baselines without these biases in terms of predictive accuracy, energy accuracy, and zero-shot generalization to time-step sizes and integrator orders not experienced during training. This advances the state-of-the-art of learned simulation, and in principle is applicable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12790","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/1909.12790/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":"1909.12790","created_at":"2026-07-05T00:07:42.736394+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12790v1","created_at":"2026-07-05T00:07:42.736394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12790","created_at":"2026-07-05T00:07:42.736394+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQ7Y437IFWSA","created_at":"2026-07-05T00:07:42.736394+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQ7Y437IFWSAHR23","created_at":"2026-07-05T00:07:42.736394+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQ7Y437I","created_at":"2026-07-05T00:07:42.736394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09432","citing_title":"Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23510","citing_title":"Learning partially observed systems with neural Hamiltonian ordinary differential equations","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23606","citing_title":"Hamiltonian Graph Inference Networks: Joint structure discovery and dynamics prediction for lattice Hamiltonian systems from trajectory data","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND","json":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND.json","graph_json":"https://pith.science/api/pith-number/FQ7Y437IFWSAHR23LRRNIC76ND/graph.json","events_json":"https://pith.science/api/pith-number/FQ7Y437IFWSAHR23LRRNIC76ND/events.json","paper":"https://pith.science/paper/FQ7Y437I"},"agent_actions":{"view_html":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND","download_json":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND.json","view_paper":"https://pith.science/paper/FQ7Y437I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12790&json=true","fetch_graph":"https://pith.science/api/pith-number/FQ7Y437IFWSAHR23LRRNIC76ND/graph.json","fetch_events":"https://pith.science/api/pith-number/FQ7Y437IFWSAHR23LRRNIC76ND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND/action/storage_attestation","attest_author":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND/action/author_attestation","sign_citation":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND/action/citation_signature","submit_replication":"https://pith.science/pith/FQ7Y437IFWSAHR23LRRNIC76ND/action/replication_record"}},"created_at":"2026-07-05T00:07:42.736394+00:00","updated_at":"2026-07-05T00:07:42.736394+00:00"}