{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SKITPXJE255DB4MA3O63NY63GP","short_pith_number":"pith:SKITPXJE","schema_version":"1.0","canonical_sha256":"929137dd24d77a30f180dbbdb6e3db33eb8c3f8c06451ad0fa85029e7aaac0d6","source":{"kind":"arxiv","id":"2110.02905","version":3},"attestation_state":"computed","paper":{"title":"Geometric and Physical Quantities Improve E(3) Equivariant Message Passing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elise van der Pol, Erik J Bekkers, Johannes Brandstetter, Max Welling, Rob Hesselink","submitted_at":"2021-10-06T16:34:26Z","abstract_excerpt":"Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that generalise equivariant graph networks, such that node and edge attributes are not restricted to invariant scalars, but can contain covariant information, such as vectors or tensors. This model, composed of steerable MLPs, is able to incorporate geometric and physical information in both the message and update functions. Through the definition of steerable node attributes, the MLP"},"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":"2110.02905","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T16:34:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9ac22fc291c255b2e7b7fb0722e5a5ce17e0d30399ffed973866fd8c3d781815","abstract_canon_sha256":"65f622fe2fd42590c4c97743bb0756a6addef2482b64f030fdbed0ec920aa1af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:40.454257Z","signature_b64":"bLhl3rv0wJTuq/XCGAz2NMalEUuhMAKRhfjGP2QtAG3CRZzpOt0Sym2bFVGiWp09qYwEEX7q3Qxa9AV32NtiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"929137dd24d77a30f180dbbdb6e3db33eb8c3f8c06451ad0fa85029e7aaac0d6","last_reissued_at":"2026-07-05T04:08:40.453833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:40.453833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometric and Physical Quantities Improve E(3) Equivariant Message Passing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elise van der Pol, Erik J Bekkers, Johannes Brandstetter, Max Welling, Rob Hesselink","submitted_at":"2021-10-06T16:34:26Z","abstract_excerpt":"Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that generalise equivariant graph networks, such that node and edge attributes are not restricted to invariant scalars, but can contain covariant information, such as vectors or tensors. This model, composed of steerable MLPs, is able to incorporate geometric and physical information in both the message and update functions. Through the definition of steerable node attributes, the MLP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02905","kind":"arxiv","version":3},"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/2110.02905/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":"2110.02905","created_at":"2026-07-05T04:08:40.453915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02905v3","created_at":"2026-07-05T04:08:40.453915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02905","created_at":"2026-07-05T04:08:40.453915+00:00"},{"alias_kind":"pith_short_12","alias_value":"SKITPXJE255D","created_at":"2026-07-05T04:08:40.453915+00:00"},{"alias_kind":"pith_short_16","alias_value":"SKITPXJE255DB4MA","created_at":"2026-07-05T04:08:40.453915+00:00"},{"alias_kind":"pith_short_8","alias_value":"SKITPXJE","created_at":"2026-07-05T04:08:40.453915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19133","citing_title":"Equivariant Graph Neural Networks Improve Optical Spectra Prediction for Materials Screening","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19374","citing_title":"Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09432","citing_title":"Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24886","citing_title":"Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03046","citing_title":"Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15073","citing_title":"Fast contracted Clebsch--Gordan tensor products for equivariant graph neural networks","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP","json":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP.json","graph_json":"https://pith.science/api/pith-number/SKITPXJE255DB4MA3O63NY63GP/graph.json","events_json":"https://pith.science/api/pith-number/SKITPXJE255DB4MA3O63NY63GP/events.json","paper":"https://pith.science/paper/SKITPXJE"},"agent_actions":{"view_html":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP","download_json":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP.json","view_paper":"https://pith.science/paper/SKITPXJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02905&json=true","fetch_graph":"https://pith.science/api/pith-number/SKITPXJE255DB4MA3O63NY63GP/graph.json","fetch_events":"https://pith.science/api/pith-number/SKITPXJE255DB4MA3O63NY63GP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP/action/storage_attestation","attest_author":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP/action/author_attestation","sign_citation":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP/action/citation_signature","submit_replication":"https://pith.science/pith/SKITPXJE255DB4MA3O63NY63GP/action/replication_record"}},"created_at":"2026-07-05T04:08:40.453915+00:00","updated_at":"2026-07-05T04:08:40.453915+00:00"}