{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3GMLAK2AFYIU4ZLR27CD7KF6MC","short_pith_number":"pith:3GMLAK2A","schema_version":"1.0","canonical_sha256":"d998b02b402e114e6571d7c43fa8be60a864456a89cb4a604196a73cf151d74e","source":{"kind":"arxiv","id":"2012.06333","version":1},"attestation_state":"computed","paper":{"title":"Sheaf Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT"],"primary_cat":"cs.LG","authors_text":"Jakob Hansen, Thomas Gebhart","submitted_at":"2020-12-08T01:19:48Z","abstract_excerpt":"We present a generalization of graph convolutional networks by generalizing the diffusion operation underlying this class of graph neural networks. These sheaf neural networks are based on the sheaf Laplacian, a generalization of the graph Laplacian that encodes additional relational structure parameterized by the underlying graph. The sheaf Laplacian and associated matrices provide an extended version of the diffusion operation in graph convolutional networks, providing a proper generalization for domains where relations between nodes are non-constant, asymmetric, and varying in dimension. We"},"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":"2012.06333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T01:19:48Z","cross_cats_sorted":["math.AT"],"title_canon_sha256":"975c65dadfc04acc5c8b345d0dbfc8d92d6f72c3fa791e1c3adb06c2cdb42e72","abstract_canon_sha256":"d563a92da48ed84ddbcb90a2c24b72481bf6352895dfe9c655348427a07ef3ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:50.529670Z","signature_b64":"bQMs58KswmUPNBlcIj4r/oef8bHBk/HIVaz7K7V2kz1fNL5AjdxAyAKmwATX+7O31cgWplFH+kXt0OLY3Qx2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d998b02b402e114e6571d7c43fa8be60a864456a89cb4a604196a73cf151d74e","last_reissued_at":"2026-07-05T01:58:50.529241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:50.529241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sheaf Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT"],"primary_cat":"cs.LG","authors_text":"Jakob Hansen, Thomas Gebhart","submitted_at":"2020-12-08T01:19:48Z","abstract_excerpt":"We present a generalization of graph convolutional networks by generalizing the diffusion operation underlying this class of graph neural networks. These sheaf neural networks are based on the sheaf Laplacian, a generalization of the graph Laplacian that encodes additional relational structure parameterized by the underlying graph. The sheaf Laplacian and associated matrices provide an extended version of the diffusion operation in graph convolutional networks, providing a proper generalization for domains where relations between nodes are non-constant, asymmetric, and varying in dimension. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06333","kind":"arxiv","version":1},"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/2012.06333/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":"2012.06333","created_at":"2026-07-05T01:58:50.529300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.06333v1","created_at":"2026-07-05T01:58:50.529300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06333","created_at":"2026-07-05T01:58:50.529300+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GMLAK2AFYIU","created_at":"2026-07-05T01:58:50.529300+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GMLAK2AFYIU4ZLR","created_at":"2026-07-05T01:58:50.529300+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GMLAK2A","created_at":"2026-07-05T01:58:50.529300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20932","citing_title":"Hierarchical Pooling for Sheaf Neural Networks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09806","citing_title":"Topological Neural Operators","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03270","citing_title":"Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06395","citing_title":"Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19324","citing_title":"BrainDyn: A Sheaf Neural ODE for Generative Brain Dynamics","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06395","citing_title":"Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC","json":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC.json","graph_json":"https://pith.science/api/pith-number/3GMLAK2AFYIU4ZLR27CD7KF6MC/graph.json","events_json":"https://pith.science/api/pith-number/3GMLAK2AFYIU4ZLR27CD7KF6MC/events.json","paper":"https://pith.science/paper/3GMLAK2A"},"agent_actions":{"view_html":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC","download_json":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC.json","view_paper":"https://pith.science/paper/3GMLAK2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.06333&json=true","fetch_graph":"https://pith.science/api/pith-number/3GMLAK2AFYIU4ZLR27CD7KF6MC/graph.json","fetch_events":"https://pith.science/api/pith-number/3GMLAK2AFYIU4ZLR27CD7KF6MC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC/action/storage_attestation","attest_author":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC/action/author_attestation","sign_citation":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC/action/citation_signature","submit_replication":"https://pith.science/pith/3GMLAK2AFYIU4ZLR27CD7KF6MC/action/replication_record"}},"created_at":"2026-07-05T01:58:50.529300+00:00","updated_at":"2026-07-05T01:58:50.529300+00:00"}