{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DJQLZFDKPCHEJVRKYZCWZD67YV","short_pith_number":"pith:DJQLZFDK","schema_version":"1.0","canonical_sha256":"1a60bc946a788e44d62ac6456c8fdfc55573f39c7122b575f9c77b0ead513cbd","source":{"kind":"arxiv","id":"2305.11141","version":5},"attestation_state":"computed","paper":{"title":"Clifford Group Equivariant Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Ruhe, Johannes Brandstetter, Patrick Forr\\'e","submitted_at":"2023-05-18T17:35:35Z","abstract_excerpt":"We introduce Clifford Group Equivariant Neural Networks: a novel approach for constructing $\\mathrm{O}(n)$- and $\\mathrm{E}(n)$-equivariant models. We identify and study the $\\textit{Clifford group}$, a subgroup inside the Clifford algebra tailored to achieve several favorable properties. Primarily, the group's action forms an orthogonal automorphism that extends beyond the typical vector space to the entire Clifford algebra while respecting the multivector grading. This leads to several non-equivalent subrepresentations corresponding to the multivector decomposition. Furthermore, we prove tha"},"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":"2305.11141","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T17:35:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cdf5e84fe05dd7da1cbee45c825fb522c0ee86b96b04b819da1ca808e14d4a36","abstract_canon_sha256":"d0f7ea74f43c58636e1330b48a4ae7a2c2e38114dd801b34964b0b1dd606206d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:24.841323Z","signature_b64":"RSkcMrqXCJnUU6A4ICmBeeb9gz/dKP1DkcSzmUFl8gF+PlI841VCEosFw0hDNtCmb7MLO3cE+twsFG6KI48YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a60bc946a788e44d62ac6456c8fdfc55573f39c7122b575f9c77b0ead513cbd","last_reissued_at":"2026-07-05T07:03:24.840850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:24.840850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clifford Group Equivariant Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Ruhe, Johannes Brandstetter, Patrick Forr\\'e","submitted_at":"2023-05-18T17:35:35Z","abstract_excerpt":"We introduce Clifford Group Equivariant Neural Networks: a novel approach for constructing $\\mathrm{O}(n)$- and $\\mathrm{E}(n)$-equivariant models. We identify and study the $\\textit{Clifford group}$, a subgroup inside the Clifford algebra tailored to achieve several favorable properties. Primarily, the group's action forms an orthogonal automorphism that extends beyond the typical vector space to the entire Clifford algebra while respecting the multivector grading. This leads to several non-equivalent subrepresentations corresponding to the multivector decomposition. Furthermore, we prove tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11141","kind":"arxiv","version":5},"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/2305.11141/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":"2305.11141","created_at":"2026-07-05T07:03:24.840904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11141v5","created_at":"2026-07-05T07:03:24.840904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11141","created_at":"2026-07-05T07:03:24.840904+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJQLZFDKPCHE","created_at":"2026-07-05T07:03:24.840904+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJQLZFDKPCHEJVRK","created_at":"2026-07-05T07:03:24.840904+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJQLZFDK","created_at":"2026-07-05T07:03:24.840904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.18104","citing_title":"Adaptive Domain Models: Bayesian Evolution, Warm Rotation, and Principled Training for Geometric and Neuromorphic AI","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17627","citing_title":"The Program Hypergraph: Multi-Way Relational Structure for Geometric Algebra, Spatial Compute, and Physics-Aware Compilation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV","json":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV.json","graph_json":"https://pith.science/api/pith-number/DJQLZFDKPCHEJVRKYZCWZD67YV/graph.json","events_json":"https://pith.science/api/pith-number/DJQLZFDKPCHEJVRKYZCWZD67YV/events.json","paper":"https://pith.science/paper/DJQLZFDK"},"agent_actions":{"view_html":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV","download_json":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV.json","view_paper":"https://pith.science/paper/DJQLZFDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11141&json=true","fetch_graph":"https://pith.science/api/pith-number/DJQLZFDKPCHEJVRKYZCWZD67YV/graph.json","fetch_events":"https://pith.science/api/pith-number/DJQLZFDKPCHEJVRKYZCWZD67YV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV/action/storage_attestation","attest_author":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV/action/author_attestation","sign_citation":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV/action/citation_signature","submit_replication":"https://pith.science/pith/DJQLZFDKPCHEJVRKYZCWZD67YV/action/replication_record"}},"created_at":"2026-07-05T07:03:24.840904+00:00","updated_at":"2026-07-05T07:03:24.840904+00:00"}