{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:USWLWGJ7BTAJNBABSZ4O7MB4MD","short_pith_number":"pith:USWLWGJ7","schema_version":"1.0","canonical_sha256":"a4acbb193f0cc09684019678efb03c60c0953aef56032931934e107b1f83a4c9","source":{"kind":"arxiv","id":"2407.20471","version":2},"attestation_state":"computed","paper":{"title":"Relaxed Equivariant Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elyssa Hofgard, Robin Walters, Rui Wang, Tess Smidt","submitted_at":"2024-07-30T00:16:50Z","abstract_excerpt":"3D Euclidean symmetry equivariant neural networks have demonstrated notable success in modeling complex physical systems. We introduce a framework for relaxed $E(3)$ graph equivariant neural networks that can learn and represent symmetry breaking within continuous groups. Building on the existing e3nn framework, we propose the use of relaxed weights to allow for controlled symmetry breaking. We show empirically that these relaxed weights learn the correct amount of symmetry breaking."},"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":"2407.20471","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-30T00:16:50Z","cross_cats_sorted":[],"title_canon_sha256":"fdc026b3cab51d44d58565747732fce8c21ca5d91b6c219725fcc81b72925f03","abstract_canon_sha256":"b8cb271fde842f3deef9d158b89abd75c0513c514739911b9e4157187c3bad68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:49.758838Z","signature_b64":"WEyo9KfAMvumClGZeo80NbDuci7TvGkFjSJYYVHh/lcv/l0RyI7rji9hgtbvDceGjppN6++wj5QMM9wMrUnuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4acbb193f0cc09684019678efb03c60c0953aef56032931934e107b1f83a4c9","last_reissued_at":"2026-07-05T09:46:49.758360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:49.758360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relaxed Equivariant Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elyssa Hofgard, Robin Walters, Rui Wang, Tess Smidt","submitted_at":"2024-07-30T00:16:50Z","abstract_excerpt":"3D Euclidean symmetry equivariant neural networks have demonstrated notable success in modeling complex physical systems. We introduce a framework for relaxed $E(3)$ graph equivariant neural networks that can learn and represent symmetry breaking within continuous groups. Building on the existing e3nn framework, we propose the use of relaxed weights to allow for controlled symmetry breaking. We show empirically that these relaxed weights learn the correct amount of symmetry breaking."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20471","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/2407.20471/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":"2407.20471","created_at":"2026-07-05T09:46:49.758426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.20471v2","created_at":"2026-07-05T09:46:49.758426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20471","created_at":"2026-07-05T09:46:49.758426+00:00"},{"alias_kind":"pith_short_12","alias_value":"USWLWGJ7BTAJ","created_at":"2026-07-05T09:46:49.758426+00:00"},{"alias_kind":"pith_short_16","alias_value":"USWLWGJ7BTAJNBAB","created_at":"2026-07-05T09:46:49.758426+00:00"},{"alias_kind":"pith_short_8","alias_value":"USWLWGJ7","created_at":"2026-07-05T09:46:49.758426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07327","citing_title":"Six Open Questions in Machine-Learned Interatomic Potential Foundation Models","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD","json":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD.json","graph_json":"https://pith.science/api/pith-number/USWLWGJ7BTAJNBABSZ4O7MB4MD/graph.json","events_json":"https://pith.science/api/pith-number/USWLWGJ7BTAJNBABSZ4O7MB4MD/events.json","paper":"https://pith.science/paper/USWLWGJ7"},"agent_actions":{"view_html":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD","download_json":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD.json","view_paper":"https://pith.science/paper/USWLWGJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.20471&json=true","fetch_graph":"https://pith.science/api/pith-number/USWLWGJ7BTAJNBABSZ4O7MB4MD/graph.json","fetch_events":"https://pith.science/api/pith-number/USWLWGJ7BTAJNBABSZ4O7MB4MD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD/action/storage_attestation","attest_author":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD/action/author_attestation","sign_citation":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD/action/citation_signature","submit_replication":"https://pith.science/pith/USWLWGJ7BTAJNBABSZ4O7MB4MD/action/replication_record"}},"created_at":"2026-07-05T09:46:49.758426+00:00","updated_at":"2026-07-05T09:46:49.758426+00:00"}