{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ILGBHASOKU3CWQZ6TV3JABCCGX","short_pith_number":"pith:ILGBHASO","schema_version":"1.0","canonical_sha256":"42cc13824e55362b433e9d7690044235f4f2b3203f74e00dde57b6dbbcd01760","source":{"kind":"arxiv","id":"2512.00242","version":3},"attestation_state":"computed","paper":{"title":"Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessio Borgi, Fabrizio Silvestri, Pietro Li\\`o","submitted_at":"2025-11-28T23:10:54Z","abstract_excerpt":"Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a linear learnable restriction/transport maps to nodes and edges, yielding an edge-aware inductive bias that handles heterophily and limits oversmoothing. However, common Neural Sheaf Diffusion implementations rely on SVD-based sheaf normalization and dense per-edge restriction maps, which scale with stalk dimension, require frequent Laplacian rebuilds, and yield brittle gradients. To address these limitations, we introduce Polynomial Neural Sheaf Diffusion ("},"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":"2512.00242","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-28T23:10:54Z","cross_cats_sorted":["cs.AI","cs.ET","stat.ML"],"title_canon_sha256":"e35594ffcde7fd2e566cc0c1b4c079f8ea88db71a11513c6001fafeb3d616930","abstract_canon_sha256":"3a2f94f74f9352ab5534606cf9c14f1e11a294fa16af09a1d62a591e2ba350bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:28.997368Z","signature_b64":"/6JhK9Tn+xhUNd2BBPvx+QVSWB1ELvSy6FmO0OYhFNrJPtpKkuDX3zh/UM0hY76+20D/vcgi2Z5trGh/UEl/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42cc13824e55362b433e9d7690044235f4f2b3203f74e00dde57b6dbbcd01760","last_reissued_at":"2026-05-20T00:00:28.996610Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:28.996610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessio Borgi, Fabrizio Silvestri, Pietro Li\\`o","submitted_at":"2025-11-28T23:10:54Z","abstract_excerpt":"Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a linear learnable restriction/transport maps to nodes and edges, yielding an edge-aware inductive bias that handles heterophily and limits oversmoothing. However, common Neural Sheaf Diffusion implementations rely on SVD-based sheaf normalization and dense per-edge restriction maps, which scale with stalk dimension, require frequent Laplacian rebuilds, and yield brittle gradients. To address these limitations, we introduce Polynomial Neural Sheaf Diffusion ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.00242","kind":"arxiv","version":3},"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/2512.00242/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":"2512.00242","created_at":"2026-05-20T00:00:28.996735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.00242v3","created_at":"2026-05-20T00:00:28.996735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.00242","created_at":"2026-05-20T00:00:28.996735+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILGBHASOKU3C","created_at":"2026-05-20T00:00:28.996735+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILGBHASOKU3CWQZ6","created_at":"2026-05-20T00:00:28.996735+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILGBHASO","created_at":"2026-05-20T00:00:28.996735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19021","citing_title":"Deep Neural Sheaf Diffusion","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX","json":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX.json","graph_json":"https://pith.science/api/pith-number/ILGBHASOKU3CWQZ6TV3JABCCGX/graph.json","events_json":"https://pith.science/api/pith-number/ILGBHASOKU3CWQZ6TV3JABCCGX/events.json","paper":"https://pith.science/paper/ILGBHASO"},"agent_actions":{"view_html":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX","download_json":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX.json","view_paper":"https://pith.science/paper/ILGBHASO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.00242&json=true","fetch_graph":"https://pith.science/api/pith-number/ILGBHASOKU3CWQZ6TV3JABCCGX/graph.json","fetch_events":"https://pith.science/api/pith-number/ILGBHASOKU3CWQZ6TV3JABCCGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX/action/storage_attestation","attest_author":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX/action/author_attestation","sign_citation":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX/action/citation_signature","submit_replication":"https://pith.science/pith/ILGBHASOKU3CWQZ6TV3JABCCGX/action/replication_record"}},"created_at":"2026-05-20T00:00:28.996735+00:00","updated_at":"2026-05-20T00:00:28.996735+00:00"}