{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HNDNR74BJDMTPLXCOJ7DIPHUND","short_pith_number":"pith:HNDNR74B","schema_version":"1.0","canonical_sha256":"3b46d8ff8148d937aee2727e343cf468d81b829611bc7a8c5ff33cf5f7628f8e","source":{"kind":"arxiv","id":"2309.03139","version":1},"attestation_state":"computed","paper":{"title":"Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carmelo Gonzales, Daniel Levy, Santiago Miret, S\\'ekou-Oumar Kaba, Siamak Ravanbakhsh","submitted_at":"2023-09-06T16:24:26Z","abstract_excerpt":"We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node. We formulate the extension and show that it improves performance across different physical systems benchmark tasks, with minimal differences in runtime or number of parameters. The proposed multichannel EGNN outperforms the standard singlechannel EGNN on N-body charged particle dynamics, molecular property predictions, and predicting the trajectories of solar system bodies. Given the additional benefits and minimal additional cost of multi-channel EGNN, we suggest that this"},"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":"2309.03139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-06T16:24:26Z","cross_cats_sorted":[],"title_canon_sha256":"f4554c3d3e398ed70546206b669202b5d9d6968bbd2d3c073b0f8020d4a132fb","abstract_canon_sha256":"a32566e8cb79f9ccf80f3255d0d481af5ba54b9a128b43a29db91f3b37d94a7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:21.375073Z","signature_b64":"cfrhmE7S1vGKjRh+VI85Jbgop8UGq162bv7JUdXRMvCHdjje54Mq/yr3hE/HIbSmyG+hGHD7SJYLJXiZVqbHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b46d8ff8148d937aee2727e343cf468d81b829611bc7a8c5ff33cf5f7628f8e","last_reissued_at":"2026-07-05T06:48:21.374672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:21.374672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carmelo Gonzales, Daniel Levy, Santiago Miret, S\\'ekou-Oumar Kaba, Siamak Ravanbakhsh","submitted_at":"2023-09-06T16:24:26Z","abstract_excerpt":"We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node. We formulate the extension and show that it improves performance across different physical systems benchmark tasks, with minimal differences in runtime or number of parameters. The proposed multichannel EGNN outperforms the standard singlechannel EGNN on N-body charged particle dynamics, molecular property predictions, and predicting the trajectories of solar system bodies. Given the additional benefits and minimal additional cost of multi-channel EGNN, we suggest that this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03139","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/2309.03139/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":"2309.03139","created_at":"2026-07-05T06:48:21.374728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.03139v1","created_at":"2026-07-05T06:48:21.374728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03139","created_at":"2026-07-05T06:48:21.374728+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNDNR74BJDMT","created_at":"2026-07-05T06:48:21.374728+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNDNR74BJDMTPLXC","created_at":"2026-07-05T06:48:21.374728+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNDNR74B","created_at":"2026-07-05T06:48:21.374728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27613","citing_title":"AMGenC: Generating Charge Balanced Amorphous Materials","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08172","citing_title":"Augmented Equivariant Mesh Networks for Anatomical Segmentation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND","json":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND.json","graph_json":"https://pith.science/api/pith-number/HNDNR74BJDMTPLXCOJ7DIPHUND/graph.json","events_json":"https://pith.science/api/pith-number/HNDNR74BJDMTPLXCOJ7DIPHUND/events.json","paper":"https://pith.science/paper/HNDNR74B"},"agent_actions":{"view_html":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND","download_json":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND.json","view_paper":"https://pith.science/paper/HNDNR74B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.03139&json=true","fetch_graph":"https://pith.science/api/pith-number/HNDNR74BJDMTPLXCOJ7DIPHUND/graph.json","fetch_events":"https://pith.science/api/pith-number/HNDNR74BJDMTPLXCOJ7DIPHUND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND/action/storage_attestation","attest_author":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND/action/author_attestation","sign_citation":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND/action/citation_signature","submit_replication":"https://pith.science/pith/HNDNR74BJDMTPLXCOJ7DIPHUND/action/replication_record"}},"created_at":"2026-07-05T06:48:21.374728+00:00","updated_at":"2026-07-05T06:48:21.374728+00:00"}