{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CZZVJH6MIXQDWEZACED5CL7QOX","short_pith_number":"pith:CZZVJH6M","schema_version":"1.0","canonical_sha256":"1673549fcc45e03b13201107d12ff075eb273a7f7d1aec9f7b597a34a722c9f3","source":{"kind":"arxiv","id":"2504.15773","version":2},"attestation_state":"computed","paper":{"title":"Clifford Group Equivariant Diffusion Models for 3D Molecular Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cong Liu, David Ruhe, Erik Bekkers, Patrick Forr\\'e, Sharvaree Vadgama","submitted_at":"2025-04-22T10:30:06Z","abstract_excerpt":"This paper explores leveraging the Clifford algebra's expressive power for $\\E(n)$-equivariant diffusion models. We utilize the geometric products between Clifford multivectors and the rich geometric information encoded in Clifford subspaces in \\emph{Clifford Diffusion Models} (CDMs). We extend the diffusion process beyond just Clifford one-vectors to incorporate all higher-grade multivector subspaces. The data is embedded in grade-$k$ subspaces, allowing us to apply latent diffusion across complete multivectors. This enables CDMs to capture the joint distribution across different subspaces of"},"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":"2504.15773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T10:30:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34deb4580762e8b48050688e58d250d4a998c36a31746b32d710b04bf36699e1","abstract_canon_sha256":"a7d0a195551cc9184a13d89af9dcb02afab6234b2e52e241bb28d8c046ccd35b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:18.388324Z","signature_b64":"NwX76m/ajBLLyczj/mlRPiiOCqOHPbKRrJHF3GhGR7vFiC44pIM6nLGPPpQgED0RfAIzb0hX3o5eyXAkfRvYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1673549fcc45e03b13201107d12ff075eb273a7f7d1aec9f7b597a34a722c9f3","last_reissued_at":"2026-07-05T10:53:18.387749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:18.387749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clifford Group Equivariant Diffusion Models for 3D Molecular Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cong Liu, David Ruhe, Erik Bekkers, Patrick Forr\\'e, Sharvaree Vadgama","submitted_at":"2025-04-22T10:30:06Z","abstract_excerpt":"This paper explores leveraging the Clifford algebra's expressive power for $\\E(n)$-equivariant diffusion models. We utilize the geometric products between Clifford multivectors and the rich geometric information encoded in Clifford subspaces in \\emph{Clifford Diffusion Models} (CDMs). We extend the diffusion process beyond just Clifford one-vectors to incorporate all higher-grade multivector subspaces. The data is embedded in grade-$k$ subspaces, allowing us to apply latent diffusion across complete multivectors. This enables CDMs to capture the joint distribution across different subspaces of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15773","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/2504.15773/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":"2504.15773","created_at":"2026-07-05T10:53:18.387808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15773v2","created_at":"2026-07-05T10:53:18.387808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15773","created_at":"2026-07-05T10:53:18.387808+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZZVJH6MIXQD","created_at":"2026-07-05T10:53:18.387808+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZZVJH6MIXQDWEZA","created_at":"2026-07-05T10:53:18.387808+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZZVJH6M","created_at":"2026-07-05T10:53:18.387808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12784","citing_title":"ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12784","citing_title":"ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX","json":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX.json","graph_json":"https://pith.science/api/pith-number/CZZVJH6MIXQDWEZACED5CL7QOX/graph.json","events_json":"https://pith.science/api/pith-number/CZZVJH6MIXQDWEZACED5CL7QOX/events.json","paper":"https://pith.science/paper/CZZVJH6M"},"agent_actions":{"view_html":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX","download_json":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX.json","view_paper":"https://pith.science/paper/CZZVJH6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15773&json=true","fetch_graph":"https://pith.science/api/pith-number/CZZVJH6MIXQDWEZACED5CL7QOX/graph.json","fetch_events":"https://pith.science/api/pith-number/CZZVJH6MIXQDWEZACED5CL7QOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX/action/storage_attestation","attest_author":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX/action/author_attestation","sign_citation":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX/action/citation_signature","submit_replication":"https://pith.science/pith/CZZVJH6MIXQDWEZACED5CL7QOX/action/replication_record"}},"created_at":"2026-07-05T10:53:18.387808+00:00","updated_at":"2026-07-05T10:53:18.387808+00:00"}