{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:C5AVLITPSTRWI2FFMSIAHAAP4V","short_pith_number":"pith:C5AVLITP","schema_version":"1.0","canonical_sha256":"174155a26f94e36468a5649003800fe57398e331567841672536d680cfa0473b","source":{"kind":"arxiv","id":"1711.08920","version":2},"attestation_state":"computed","paper":{"title":"SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frank Weichert, Heinrich M\\\"uller, Jan Eric Lenssen, Matthias Fey","submitted_at":"2017-11-24T10:33:05Z","abstract_excerpt":"We present Spline-based Convolutional Neural Networks (SplineCNNs), a variant of deep neural networks for irregular structured and geometric input, e.g., graphs or meshes. Our main contribution is a novel convolution operator based on B-splines, that makes the computation time independent from the kernel size due to the local support property of the B-spline basis functions. As a result, we obtain a generalization of the traditional CNN convolution operator by using continuous kernel functions parametrized by a fixed number of trainable weights. In contrast to related approaches that filter in"},"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":"1711.08920","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-24T10:33:05Z","cross_cats_sorted":[],"title_canon_sha256":"78e238dd4a969aa61103fb1519e94592c5f27323394badb2eee4cbbeebc0522f","abstract_canon_sha256":"f1aab101e2ddb6ec6c7e1973bb66fea1ccf9bcbb2fc70e1087a472f66278e222"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.982297Z","signature_b64":"HWNrVCabLfo1esxLYb7UCM65roAcRH/tK0XL27SLtq+BnoBW73qprh9uxa0cHyRvp5BVauUR/8HiSPxC/3CwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"174155a26f94e36468a5649003800fe57398e331567841672536d680cfa0473b","last_reissued_at":"2026-05-18T00:15:09.981528Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.981528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frank Weichert, Heinrich M\\\"uller, Jan Eric Lenssen, Matthias Fey","submitted_at":"2017-11-24T10:33:05Z","abstract_excerpt":"We present Spline-based Convolutional Neural Networks (SplineCNNs), a variant of deep neural networks for irregular structured and geometric input, e.g., graphs or meshes. Our main contribution is a novel convolution operator based on B-splines, that makes the computation time independent from the kernel size due to the local support property of the B-spline basis functions. As a result, we obtain a generalization of the traditional CNN convolution operator by using continuous kernel functions parametrized by a fixed number of trainable weights. In contrast to related approaches that filter in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08920","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":""},"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":"1711.08920","created_at":"2026-05-18T00:15:09.981637+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08920v2","created_at":"2026-05-18T00:15:09.981637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08920","created_at":"2026-05-18T00:15:09.981637+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5AVLITPSTRW","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5AVLITPSTRWI2FF","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5AVLITP","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V","json":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V.json","graph_json":"https://pith.science/api/pith-number/C5AVLITPSTRWI2FFMSIAHAAP4V/graph.json","events_json":"https://pith.science/api/pith-number/C5AVLITPSTRWI2FFMSIAHAAP4V/events.json","paper":"https://pith.science/paper/C5AVLITP"},"agent_actions":{"view_html":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V","download_json":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V.json","view_paper":"https://pith.science/paper/C5AVLITP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08920&json=true","fetch_graph":"https://pith.science/api/pith-number/C5AVLITPSTRWI2FFMSIAHAAP4V/graph.json","fetch_events":"https://pith.science/api/pith-number/C5AVLITPSTRWI2FFMSIAHAAP4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V/action/storage_attestation","attest_author":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V/action/author_attestation","sign_citation":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V/action/citation_signature","submit_replication":"https://pith.science/pith/C5AVLITPSTRWI2FFMSIAHAAP4V/action/replication_record"}},"created_at":"2026-05-18T00:15:09.981637+00:00","updated_at":"2026-05-18T00:15:09.981637+00:00"}