{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OJ3XHDPDFK4SC5EMTX2ZHJXGCW","short_pith_number":"pith:OJ3XHDPD","schema_version":"1.0","canonical_sha256":"7277738de32ab921748c9df593a6e615bf7ddeeea652b11ffcab07181cb73236","source":{"kind":"arxiv","id":"2410.09590","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Sheaf Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"David L. Boothe, Ioannis Schizas, Layal Bou Hamdan, Patrick Gillespie, Vasileios Maroulas","submitted_at":"2024-10-12T16:46:48Z","abstract_excerpt":"Equipping graph neural networks with a convolution operation defined in terms of a cellular sheaf offers advantages for learning expressive representations of heterophilic graph data. The most flexible approach to constructing the sheaf is to learn it as part of the network as a function of the node features. However, this leaves the network potentially overly sensitive to the learned sheaf. As a counter-measure, we propose a variational approach to learning cellular sheaves within sheaf neural networks, yielding an architecture we refer to as a Bayesian sheaf neural network. As part of this w"},"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":"2410.09590","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T16:46:48Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"37d220c5f6f7b77fb4df4dc83ccd41fdc28d84231e98f268829a13e5383ec69d","abstract_canon_sha256":"5d6de07a9503a109a58ae9040f3c968f326fb7a4e6d0b3767522c3e426317fa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:10:53.580055Z","signature_b64":"ETonPCljK6R1mkkAaQdLAUf5RLuNu+XLbdrRra2ja970qN/1eaBHIlrH9xDPwTflwt1W3/ytfIYSUdp3DOwoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7277738de32ab921748c9df593a6e615bf7ddeeea652b11ffcab07181cb73236","last_reissued_at":"2026-07-05T12:10:53.579526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:10:53.579526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Sheaf Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"David L. Boothe, Ioannis Schizas, Layal Bou Hamdan, Patrick Gillespie, Vasileios Maroulas","submitted_at":"2024-10-12T16:46:48Z","abstract_excerpt":"Equipping graph neural networks with a convolution operation defined in terms of a cellular sheaf offers advantages for learning expressive representations of heterophilic graph data. The most flexible approach to constructing the sheaf is to learn it as part of the network as a function of the node features. However, this leaves the network potentially overly sensitive to the learned sheaf. As a counter-measure, we propose a variational approach to learning cellular sheaves within sheaf neural networks, yielding an architecture we refer to as a Bayesian sheaf neural network. As part of this w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09590","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/2410.09590/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":"2410.09590","created_at":"2026-07-05T12:10:53.579590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09590v2","created_at":"2026-07-05T12:10:53.579590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09590","created_at":"2026-07-05T12:10:53.579590+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJ3XHDPDFK4S","created_at":"2026-07-05T12:10:53.579590+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJ3XHDPDFK4SC5EM","created_at":"2026-07-05T12:10:53.579590+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJ3XHDPD","created_at":"2026-07-05T12:10:53.579590+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/OJ3XHDPDFK4SC5EMTX2ZHJXGCW","json":"https://pith.science/pith/OJ3XHDPDFK4SC5EMTX2ZHJXGCW.json","graph_json":"https://pith.science/api/pith-number/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/graph.json","events_json":"https://pith.science/api/pith-number/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/events.json","paper":"https://pith.science/paper/OJ3XHDPD"},"agent_actions":{"view_html":"https://pith.science/pith/OJ3XHDPDFK4SC5EMTX2ZHJXGCW","download_json":"https://pith.science/pith/OJ3XHDPDFK4SC5EMTX2ZHJXGCW.json","view_paper":"https://pith.science/paper/OJ3XHDPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09590&json=true","fetch_graph":"https://pith.science/api/pith-number/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/graph.json","fetch_events":"https://pith.science/api/pith-number/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/action/storage_attestation","attest_author":"https://pith.science/pith/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/action/author_attestation","sign_citation":"https://pith.science/pith/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/action/citation_signature","submit_replication":"https://pith.science/pith/OJ3XHDPDFK4SC5EMTX2ZHJXGCW/action/replication_record"}},"created_at":"2026-07-05T12:10:53.579590+00:00","updated_at":"2026-07-05T12:10:53.579590+00:00"}