{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5BSJ7RFFGPNDJGJMWXHOOVOI7C","short_pith_number":"pith:5BSJ7RFF","schema_version":"1.0","canonical_sha256":"e8649fc4a533da34992cb5cee755c8f8abaf85117945fd524fc45c48a799b70e","source":{"kind":"arxiv","id":"2304.00150","version":1},"attestation_state":"computed","paper":{"title":"E($3$) Equivariant Graph Neural Networks for Particle-Based Fluid Mechanics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Artur P. Toshev, Gianluca Galletti, Johannes Brandstetter, Nikolaus A. Adams, Stefan Adami","submitted_at":"2023-03-31T21:56:35Z","abstract_excerpt":"We contribute to the vastly growing field of machine learning for engineering systems by demonstrating that equivariant graph neural networks have the potential to learn more accurate dynamic-interaction models than their non-equivariant counterparts. We benchmark two well-studied fluid flow systems, namely the 3D decaying Taylor-Green vortex and the 3D reverse Poiseuille flow, and compare equivariant graph neural networks to their non-equivariant counterparts on different performance measures, such as kinetic energy or Sinkhorn distance. Such measures are typically used in engineering to vali"},"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":"2304.00150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-31T21:56:35Z","cross_cats_sorted":["physics.flu-dyn"],"title_canon_sha256":"a162ba4a339611ff28d9d6a39320faa2290f9673c873f974075f4ba9648c9592","abstract_canon_sha256":"5987c57a349da985abaa1e6719ec5d35ebe0abfe500038c8a2a7ee18d5860b4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:59.413507Z","signature_b64":"8BJm0u0fbz+qYChh/QYiVLkj7+/4cj0aGb+CTA/xeM8EGEkzePEshCjm1RQXrDdS3+1bx/Dfe6kTAPkAdUHqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8649fc4a533da34992cb5cee755c8f8abaf85117945fd524fc45c48a799b70e","last_reissued_at":"2026-07-05T05:56:59.413111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:59.413111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E($3$) Equivariant Graph Neural Networks for Particle-Based Fluid Mechanics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Artur P. Toshev, Gianluca Galletti, Johannes Brandstetter, Nikolaus A. Adams, Stefan Adami","submitted_at":"2023-03-31T21:56:35Z","abstract_excerpt":"We contribute to the vastly growing field of machine learning for engineering systems by demonstrating that equivariant graph neural networks have the potential to learn more accurate dynamic-interaction models than their non-equivariant counterparts. We benchmark two well-studied fluid flow systems, namely the 3D decaying Taylor-Green vortex and the 3D reverse Poiseuille flow, and compare equivariant graph neural networks to their non-equivariant counterparts on different performance measures, such as kinetic energy or Sinkhorn distance. Such measures are typically used in engineering to vali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00150","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/2304.00150/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":"2304.00150","created_at":"2026-07-05T05:56:59.413167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00150v1","created_at":"2026-07-05T05:56:59.413167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00150","created_at":"2026-07-05T05:56:59.413167+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BSJ7RFFGPND","created_at":"2026-07-05T05:56:59.413167+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BSJ7RFFGPNDJGJM","created_at":"2026-07-05T05:56:59.413167+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BSJ7RFF","created_at":"2026-07-05T05:56:59.413167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00626","citing_title":"Hierarchical equivariant graph neural networks for forecasting collective motion in vortex clusters and microswimmers","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C","json":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C.json","graph_json":"https://pith.science/api/pith-number/5BSJ7RFFGPNDJGJMWXHOOVOI7C/graph.json","events_json":"https://pith.science/api/pith-number/5BSJ7RFFGPNDJGJMWXHOOVOI7C/events.json","paper":"https://pith.science/paper/5BSJ7RFF"},"agent_actions":{"view_html":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C","download_json":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C.json","view_paper":"https://pith.science/paper/5BSJ7RFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00150&json=true","fetch_graph":"https://pith.science/api/pith-number/5BSJ7RFFGPNDJGJMWXHOOVOI7C/graph.json","fetch_events":"https://pith.science/api/pith-number/5BSJ7RFFGPNDJGJMWXHOOVOI7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C/action/storage_attestation","attest_author":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C/action/author_attestation","sign_citation":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C/action/citation_signature","submit_replication":"https://pith.science/pith/5BSJ7RFFGPNDJGJMWXHOOVOI7C/action/replication_record"}},"created_at":"2026-07-05T05:56:59.413167+00:00","updated_at":"2026-07-05T05:56:59.413167+00:00"}