{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OPILBUYWX5CBODKUUE4O72CSNA","short_pith_number":"pith:OPILBUYW","schema_version":"1.0","canonical_sha256":"73d0b0d316bf44170d54a138efe852681a2555254c7f6b6db894072d5d9b182a","source":{"kind":"arxiv","id":"1906.01563","version":3},"attestation_state":"computed","paper":{"title":"Hamiltonian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Jason Yosinski, Misko Dzamba, Sam Greydanus","submitted_at":"2019-06-04T16:27:55Z","abstract_excerpt":"Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? In this paper, we draw inspiration from Hamiltonian mechanics to train models that learn and respect exact conservation laws in an unsupervised manner. We evaluate our models on problems where conservation of energy is important, including the two-body problem and pixel observations of a pendulum. Our model trains faster and generalizes better than a regular neural network. An interesting side effect is that our model is perfectly rever"},"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":"1906.01563","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-04T16:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"84c562e75574692394d08b8dc57965930c6d97250b078bef7332acd4784ad5d6","abstract_canon_sha256":"f64f99020d55accd3627c3451000dcef5ca22e2ad53780c4f8a289a3c2573a3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:27.361501Z","signature_b64":"SYO9FB3L7tZxUROllPL/izxrS+cOfEn1ipIpdEUm6kSGIkMR8zuFEiccNrjiSBUW6+iM3oLrSTwtcqDuR1aKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73d0b0d316bf44170d54a138efe852681a2555254c7f6b6db894072d5d9b182a","last_reissued_at":"2026-07-05T00:02:27.360958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:27.360958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hamiltonian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Jason Yosinski, Misko Dzamba, Sam Greydanus","submitted_at":"2019-06-04T16:27:55Z","abstract_excerpt":"Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? In this paper, we draw inspiration from Hamiltonian mechanics to train models that learn and respect exact conservation laws in an unsupervised manner. We evaluate our models on problems where conservation of energy is important, including the two-body problem and pixel observations of a pendulum. Our model trains faster and generalizes better than a regular neural network. An interesting side effect is that our model is perfectly rever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01563","kind":"arxiv","version":3},"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/1906.01563/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":"1906.01563","created_at":"2026-07-05T00:02:27.361026+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01563v3","created_at":"2026-07-05T00:02:27.361026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01563","created_at":"2026-07-05T00:02:27.361026+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPILBUYWX5CB","created_at":"2026-07-05T00:02:27.361026+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPILBUYWX5CBODKU","created_at":"2026-07-05T00:02:27.361026+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPILBUYW","created_at":"2026-07-05T00:02:27.361026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24945","citing_title":"When Do Conservation Laws Survive Learned Representations? Certified Horizons for Latent World Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24945","citing_title":"When Do Conservation Laws Survive Learned Representations? Certified Horizons for Latent World Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18386","citing_title":"Reconstructing Galactic Gravitational Potentials from Stellar Kinematics with Physics-Informed Neural Networks","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15015","citing_title":"NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09929","citing_title":"Between Amnesia and Chaos: A Memory Stability Expressivity Trilemma for Trainable Dissipative Oscillator Networks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30318","citing_title":"Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00089","citing_title":"Can Predicted Dynamics Exist in the Physical World?","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24868","citing_title":"A comparative study of accuracy and rollout stability of temporal surrogate models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30117","citing_title":"Gravitational Duals from Equations of State II: Large Hierarchies and False Vacua","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25313","citing_title":"UWM-JEPA: Predictive World Models That Imagine in Belief Space","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28452","citing_title":"Physics-constrained identification of graph-based thermal networks for spacecraft digital twins","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11251","citing_title":"Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18937","citing_title":"Symplecticity-preserving prediction of parameter-dependent Hamiltonian dynamics by Generalized Kernel Interpolation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20107","citing_title":"Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19589","citing_title":"Physics-Informed Graph Neural Network Surrogates for Turbulent Nanoparticle Dispersion in Dental Clinical Environments","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15881","citing_title":"Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2001.04385","citing_title":"Universal Differential Equations for Scientific Machine Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09100","citing_title":"Area Scaling of Dynamical Degrees of Freedom in Regularised Scalar Field Theory","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25435","citing_title":"PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices","ref_index":25,"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":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA","json":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA.json","graph_json":"https://pith.science/api/pith-number/OPILBUYWX5CBODKUUE4O72CSNA/graph.json","events_json":"https://pith.science/api/pith-number/OPILBUYWX5CBODKUUE4O72CSNA/events.json","paper":"https://pith.science/paper/OPILBUYW"},"agent_actions":{"view_html":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA","download_json":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA.json","view_paper":"https://pith.science/paper/OPILBUYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01563&json=true","fetch_graph":"https://pith.science/api/pith-number/OPILBUYWX5CBODKUUE4O72CSNA/graph.json","fetch_events":"https://pith.science/api/pith-number/OPILBUYWX5CBODKUUE4O72CSNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA/action/storage_attestation","attest_author":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA/action/author_attestation","sign_citation":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA/action/citation_signature","submit_replication":"https://pith.science/pith/OPILBUYWX5CBODKUUE4O72CSNA/action/replication_record"}},"created_at":"2026-07-05T00:02:27.361026+00:00","updated_at":"2026-07-05T00:02:27.361026+00:00"}