{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UXYVNST4PKSRDAHYA25KA5J7JA","short_pith_number":"pith:UXYVNST4","schema_version":"1.0","canonical_sha256":"a5f156ca7c7aa51180f806baa0753f4803464568421b42920cec3e5805b736d7","source":{"kind":"arxiv","id":"2304.04757","version":1},"attestation_state":"computed","paper":{"title":"A new perspective on building efficient and expressive 3D equivariant graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Carla Gomes, Dieqiao Feng, Guifeng Wang, Limei Wang, Shuiwang Ji, Weitao Du, Yuanqi Du, Zhi-Ming Ma","submitted_at":"2023-04-07T18:08:27Z","abstract_excerpt":"Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these networks through a local-to-global analysis lacks today. In this paper, we propose a local hierarchy of 3D isomorphism to evaluate the expressive power of equivariant GNNs and investigate the process of representing global geometric information from local patches. Our work leads to two crucial modules for designing expressive and efficient geometric GNNs; namely l"},"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":"2304.04757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-07T18:08:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef5c3a1b197bfa78804be229216fdd6a653a3410f02c3bf5f7908640fe0b0d5a","abstract_canon_sha256":"774c3982134b6ffdbbea4d7e945969562269d9af41bbb1cfbd2958703647ce1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:51.418894Z","signature_b64":"oEDfHFpcofgYszKXNuwgxjl86Bx2ABWSxW7y8vTTmTyz56jXaslvcmK8riIG5j/sK/tDhHTXpY+QsKgar11BAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5f156ca7c7aa51180f806baa0753f4803464568421b42920cec3e5805b736d7","last_reissued_at":"2026-07-05T05:59:51.418456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:51.418456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A new perspective on building efficient and expressive 3D equivariant graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Carla Gomes, Dieqiao Feng, Guifeng Wang, Limei Wang, Shuiwang Ji, Weitao Du, Yuanqi Du, Zhi-Ming Ma","submitted_at":"2023-04-07T18:08:27Z","abstract_excerpt":"Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these networks through a local-to-global analysis lacks today. In this paper, we propose a local hierarchy of 3D isomorphism to evaluate the expressive power of equivariant GNNs and investigate the process of representing global geometric information from local patches. Our work leads to two crucial modules for designing expressive and efficient geometric GNNs; namely l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04757","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/2304.04757/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":"2304.04757","created_at":"2026-07-05T05:59:51.418523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04757v1","created_at":"2026-07-05T05:59:51.418523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04757","created_at":"2026-07-05T05:59:51.418523+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXYVNST4PKSR","created_at":"2026-07-05T05:59:51.418523+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXYVNST4PKSRDAHY","created_at":"2026-07-05T05:59:51.418523+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXYVNST4","created_at":"2026-07-05T05:59:51.418523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22990","citing_title":"Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23134","citing_title":"h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA","json":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA.json","graph_json":"https://pith.science/api/pith-number/UXYVNST4PKSRDAHYA25KA5J7JA/graph.json","events_json":"https://pith.science/api/pith-number/UXYVNST4PKSRDAHYA25KA5J7JA/events.json","paper":"https://pith.science/paper/UXYVNST4"},"agent_actions":{"view_html":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA","download_json":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA.json","view_paper":"https://pith.science/paper/UXYVNST4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04757&json=true","fetch_graph":"https://pith.science/api/pith-number/UXYVNST4PKSRDAHYA25KA5J7JA/graph.json","fetch_events":"https://pith.science/api/pith-number/UXYVNST4PKSRDAHYA25KA5J7JA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA/action/storage_attestation","attest_author":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA/action/author_attestation","sign_citation":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA/action/citation_signature","submit_replication":"https://pith.science/pith/UXYVNST4PKSRDAHYA25KA5J7JA/action/replication_record"}},"created_at":"2026-07-05T05:59:51.418523+00:00","updated_at":"2026-07-05T05:59:51.418523+00:00"}