{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6ELBNBXEE3734XHQQ2W3WZHIOQ","short_pith_number":"pith:6ELBNBXE","schema_version":"1.0","canonical_sha256":"f1161686e426ffbe5cf086adbb64e87405757d4c189dfc9c803eab4ec7a62d58","source":{"kind":"arxiv","id":"2510.14007","version":2},"attestation_state":"computed","paper":{"title":"Conditional Clifford-Steerable CNNs for PDE Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"B\\'alint L\\'aszl\\'o Szarvas, Maksim Zhdanov","submitted_at":"2025-10-15T18:38:36Z","abstract_excerpt":"We introduce Conditional Clifford-Steerable CNNs (C-CSCNNs), a unified framework that incorporates equivariance to arbitrary pseudo-Euclidean groups and significantly improves the expressivity of standard CSCNNs. We show that the kernel basis of the standard formulation is incomplete, limiting model capacity. To address this, we augment the kernels with equivariant representations of the input feature field. We derive the equivariance constraint for these input-dependent kernels and show how it can be solved efficiently via implicit parameterization. We empirically validate on multiple PDE for"},"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":"2510.14007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-15T18:38:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c5f45ada152bbd8c6b7616df2055a0f7a2150fbc5f75c339090a3b57797d6da","abstract_canon_sha256":"c234ac1ba3d58c488abeb2b7a924ee737bf64bf1d12151d4cdf560dc7a10e72d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:11.966200Z","signature_b64":"cTVsfEo4kvl8nnjZh+YhJLCFZ9TZp0c93GG19bubXe1rns3ht9JoPHvIpD/CDcbkMsuvbQsibDf/cKkjWi3xBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1161686e426ffbe5cf086adbb64e87405757d4c189dfc9c803eab4ec7a62d58","last_reissued_at":"2026-07-07T02:17:11.965282Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:11.965282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Clifford-Steerable CNNs for PDE Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"B\\'alint L\\'aszl\\'o Szarvas, Maksim Zhdanov","submitted_at":"2025-10-15T18:38:36Z","abstract_excerpt":"We introduce Conditional Clifford-Steerable CNNs (C-CSCNNs), a unified framework that incorporates equivariance to arbitrary pseudo-Euclidean groups and significantly improves the expressivity of standard CSCNNs. We show that the kernel basis of the standard formulation is incomplete, limiting model capacity. To address this, we augment the kernels with equivariant representations of the input feature field. We derive the equivariance constraint for these input-dependent kernels and show how it can be solved efficiently via implicit parameterization. We empirically validate on multiple PDE for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14007","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/2510.14007/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":"2510.14007","created_at":"2026-07-07T02:17:11.965417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.14007v2","created_at":"2026-07-07T02:17:11.965417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14007","created_at":"2026-07-07T02:17:11.965417+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ELBNBXEE373","created_at":"2026-07-07T02:17:11.965417+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ELBNBXEE3734XHQ","created_at":"2026-07-07T02:17:11.965417+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ELBNBXE","created_at":"2026-07-07T02:17:11.965417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.25075","citing_title":"Solver Exactness, Learned Flexibility: Equivariant Boundary-Correction Operators for Stokes Flow","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ","json":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ.json","graph_json":"https://pith.science/api/pith-number/6ELBNBXEE3734XHQQ2W3WZHIOQ/graph.json","events_json":"https://pith.science/api/pith-number/6ELBNBXEE3734XHQQ2W3WZHIOQ/events.json","paper":"https://pith.science/paper/6ELBNBXE"},"agent_actions":{"view_html":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ","download_json":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ.json","view_paper":"https://pith.science/paper/6ELBNBXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.14007&json=true","fetch_graph":"https://pith.science/api/pith-number/6ELBNBXEE3734XHQQ2W3WZHIOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6ELBNBXEE3734XHQQ2W3WZHIOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ/action/storage_attestation","attest_author":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ/action/author_attestation","sign_citation":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ/action/citation_signature","submit_replication":"https://pith.science/pith/6ELBNBXEE3734XHQQ2W3WZHIOQ/action/replication_record"}},"created_at":"2026-07-07T02:17:11.965417+00:00","updated_at":"2026-07-07T02:17:11.965417+00:00"}