{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WTT5IQ7TRO4UN6J5IYRYTQ4VNN","short_pith_number":"pith:WTT5IQ7T","schema_version":"1.0","canonical_sha256":"b4e7d443f38bb946f93d462389c3956b7c56ae6ddb2d158c1a45b6fbd998e02b","source":{"kind":"arxiv","id":"2002.09405","version":2},"attestation_state":"computed","paper":{"title":"Learning to Simulate Complex Physics with Graph Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvaro Sanchez-Gonzalez, Jonathan Godwin, Jure Leskovec, Peter W. Battaglia, Rex Ying, Tobias Pfaff","submitted_at":"2020-02-21T16:44:28Z","abstract_excerpt":"Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another. Our framework---which we term \"Graph Network-based Simulators\" (GNS)---represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions,"},"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":"2002.09405","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-21T16:44:28Z","cross_cats_sorted":["physics.comp-ph","stat.ML"],"title_canon_sha256":"9cbe0c9b7906ca6e9560433933d4b6727ef569409a3832bd851398881f53e86f","abstract_canon_sha256":"dce1740773d2f1449ecd3753e2fe28512eddcda2c296740aaa021e73c45e6a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:52.189354Z","signature_b64":"R56NEE2ItwGu8J9ySMM+3eWn4gfQ17MPF6twXL8SIlEpAkcHaXB3Gb9AZaazOWp5a3RCsP6+jEFtUuHvwTJrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4e7d443f38bb946f93d462389c3956b7c56ae6ddb2d158c1a45b6fbd998e02b","last_reissued_at":"2026-07-05T01:34:52.188917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:52.188917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Simulate Complex Physics with Graph Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvaro Sanchez-Gonzalez, Jonathan Godwin, Jure Leskovec, Peter W. Battaglia, Rex Ying, Tobias Pfaff","submitted_at":"2020-02-21T16:44:28Z","abstract_excerpt":"Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another. Our framework---which we term \"Graph Network-based Simulators\" (GNS)---represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09405","kind":"arxiv","version":2},"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/2002.09405/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":"2002.09405","created_at":"2026-07-05T01:34:52.188975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09405v2","created_at":"2026-07-05T01:34:52.188975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09405","created_at":"2026-07-05T01:34:52.188975+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTT5IQ7TRO4U","created_at":"2026-07-05T01:34:52.188975+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTT5IQ7TRO4UN6J5","created_at":"2026-07-05T01:34:52.188975+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTT5IQ7T","created_at":"2026-07-05T01:34:52.188975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25909","citing_title":"R5DGS: Semantic-Aware 4D Gaussian Splatting with Rigid Body Constraints for Efficient Dynamic Scene Reconstruction","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30429","citing_title":"Attention-based optimizer for symmetry finding","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23251","citing_title":"Attention mechanism for scalable mesh-based neural surrogates of free-surface fluids","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04233","citing_title":"PAINET: A Principled Efficient Transformer for 3D Dynamics Modeling","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN","json":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN.json","graph_json":"https://pith.science/api/pith-number/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/graph.json","events_json":"https://pith.science/api/pith-number/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/events.json","paper":"https://pith.science/paper/WTT5IQ7T"},"agent_actions":{"view_html":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN","download_json":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN.json","view_paper":"https://pith.science/paper/WTT5IQ7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09405&json=true","fetch_graph":"https://pith.science/api/pith-number/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/graph.json","fetch_events":"https://pith.science/api/pith-number/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/action/storage_attestation","attest_author":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/action/author_attestation","sign_citation":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/action/citation_signature","submit_replication":"https://pith.science/pith/WTT5IQ7TRO4UN6J5IYRYTQ4VNN/action/replication_record"}},"created_at":"2026-07-05T01:34:52.188975+00:00","updated_at":"2026-07-05T01:34:52.188975+00:00"}