{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UIU5Y5BT7LPA6W5NOPRJ4NIDTC","short_pith_number":"pith:UIU5Y5BT","schema_version":"1.0","canonical_sha256":"a229dc7433fade0f5bad73e29e350398b9aa39bace36fb61c23511b3228da50b","source":{"kind":"arxiv","id":"2605.21435","version":1},"attestation_state":"computed","paper":{"title":"Gaussian Sheaf Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","math.CT"],"primary_cat":"cs.LG","authors_text":"Ana Luiza Ten\\'orio, Andr\\'e Ribeiro, Diego Mesquita, Tiago da Silva","submitted_at":"2026-05-20T17:26:32Z","abstract_excerpt":"Graph Neural Networks (GNNs) have become the de facto standard for learning on relational data. While traditional GNNs' message passing is well suited for vector-valued node features, there are cases in which node features are better represented by probability distributions than real vectors. Concretely, when node features are Gaussians, characterized by a mean and a covariance matrix, naively concatenating their parameters into a single vector and applying standard message passing discards the geometric and algebraic structure that governs means and covariances. We propose Gaussian Sheaf Neur"},"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":"2605.21435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T17:26:32Z","cross_cats_sorted":["math.AT","math.CT"],"title_canon_sha256":"3556794c7088a4f41027310072ae6221d3eda2dcc3480f3e22e7c050aa5750da","abstract_canon_sha256":"43e268b94d6eba724c3521d6c751d0a560e5b8116066a08939bb179993ca3a6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:34.624172Z","signature_b64":"jDMusJQ72AbfhZakMvKVesrSF+ZhrvpWmHAn00xWgSdp8xTkknjAOzwrqIjJ5yCqPnMLWHLNr4fte2d9GzM7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a229dc7433fade0f5bad73e29e350398b9aa39bace36fb61c23511b3228da50b","last_reissued_at":"2026-05-21T02:05:34.623391Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:34.623391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Sheaf Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","math.CT"],"primary_cat":"cs.LG","authors_text":"Ana Luiza Ten\\'orio, Andr\\'e Ribeiro, Diego Mesquita, Tiago da Silva","submitted_at":"2026-05-20T17:26:32Z","abstract_excerpt":"Graph Neural Networks (GNNs) have become the de facto standard for learning on relational data. While traditional GNNs' message passing is well suited for vector-valued node features, there are cases in which node features are better represented by probability distributions than real vectors. Concretely, when node features are Gaussians, characterized by a mean and a covariance matrix, naively concatenating their parameters into a single vector and applying standard message passing discards the geometric and algebraic structure that governs means and covariances. We propose Gaussian Sheaf Neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21435","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/2605.21435/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":"2605.21435","created_at":"2026-05-21T02:05:34.623527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21435v1","created_at":"2026-05-21T02:05:34.623527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21435","created_at":"2026-05-21T02:05:34.623527+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIU5Y5BT7LPA","created_at":"2026-05-21T02:05:34.623527+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIU5Y5BT7LPA6W5N","created_at":"2026-05-21T02:05:34.623527+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIU5Y5BT","created_at":"2026-05-21T02:05:34.623527+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/UIU5Y5BT7LPA6W5NOPRJ4NIDTC","json":"https://pith.science/pith/UIU5Y5BT7LPA6W5NOPRJ4NIDTC.json","graph_json":"https://pith.science/api/pith-number/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/graph.json","events_json":"https://pith.science/api/pith-number/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/events.json","paper":"https://pith.science/paper/UIU5Y5BT"},"agent_actions":{"view_html":"https://pith.science/pith/UIU5Y5BT7LPA6W5NOPRJ4NIDTC","download_json":"https://pith.science/pith/UIU5Y5BT7LPA6W5NOPRJ4NIDTC.json","view_paper":"https://pith.science/paper/UIU5Y5BT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21435&json=true","fetch_graph":"https://pith.science/api/pith-number/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/graph.json","fetch_events":"https://pith.science/api/pith-number/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/action/storage_attestation","attest_author":"https://pith.science/pith/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/action/author_attestation","sign_citation":"https://pith.science/pith/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/action/citation_signature","submit_replication":"https://pith.science/pith/UIU5Y5BT7LPA6W5NOPRJ4NIDTC/action/replication_record"}},"created_at":"2026-05-21T02:05:34.623527+00:00","updated_at":"2026-05-21T02:05:34.623527+00:00"}