{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XUZH6E4TGDDFG6UX5P4PXOEXC2","short_pith_number":"pith:XUZH6E4T","schema_version":"1.0","canonical_sha256":"bd327f139330c6537a97ebf8fbb8971695cbfe7ab29533997e628ab3ef79f585","source":{"kind":"arxiv","id":"2203.17159","version":2},"attestation_state":"computed","paper":{"title":"Preventing Over-Smoothing for Hypergraph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guanzi Chen, Jiying Zhang, Xi Xiao, Yang Li","submitted_at":"2022-03-31T16:33:31Z","abstract_excerpt":"In recent years, hypergraph learning has attracted great attention due to its capacity in representing complex and high-order relationships. However, current neural network approaches designed for hypergraphs are mostly shallow, thus limiting their ability to extract information from high-order neighbors. In this paper, we show both theoretically and empirically, that the performance of hypergraph neural networks does not improve as the number of layers increases, which is known as the over-smoothing problem. To avoid this issue, we develop a new deep hypergraph convolutional network called De"},"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":"2203.17159","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T16:33:31Z","cross_cats_sorted":[],"title_canon_sha256":"fe530955e3fea48cb246e1c83844925c6b6bb85228bd6c9bc80b558b95fb3700","abstract_canon_sha256":"1f28f50a46a42553a5d2a041741f7e47672038b354d8a6b220b8d0bc8d8a7a18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:28.176875Z","signature_b64":"EQgJivdsYGV4krGPWdCPgJbcWE4VYBi1qe+VZE7HdxGmwrLooFJ5JJOLv5bQlOQ45k4PI0cEVTg1vvS9l7haCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd327f139330c6537a97ebf8fbb8971695cbfe7ab29533997e628ab3ef79f585","last_reissued_at":"2026-07-05T05:12:28.176349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:28.176349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preventing Over-Smoothing for Hypergraph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guanzi Chen, Jiying Zhang, Xi Xiao, Yang Li","submitted_at":"2022-03-31T16:33:31Z","abstract_excerpt":"In recent years, hypergraph learning has attracted great attention due to its capacity in representing complex and high-order relationships. However, current neural network approaches designed for hypergraphs are mostly shallow, thus limiting their ability to extract information from high-order neighbors. In this paper, we show both theoretically and empirically, that the performance of hypergraph neural networks does not improve as the number of layers increases, which is known as the over-smoothing problem. To avoid this issue, we develop a new deep hypergraph convolutional network called De"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17159","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/2203.17159/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":"2203.17159","created_at":"2026-07-05T05:12:28.176413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.17159v2","created_at":"2026-07-05T05:12:28.176413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17159","created_at":"2026-07-05T05:12:28.176413+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUZH6E4TGDDF","created_at":"2026-07-05T05:12:28.176413+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUZH6E4TGDDFG6UX","created_at":"2026-07-05T05:12:28.176413+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUZH6E4T","created_at":"2026-07-05T05:12:28.176413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20162","citing_title":"Implicit Semantic-Aware Communication Based on Hypergraph Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10955","citing_title":"Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2","json":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2.json","graph_json":"https://pith.science/api/pith-number/XUZH6E4TGDDFG6UX5P4PXOEXC2/graph.json","events_json":"https://pith.science/api/pith-number/XUZH6E4TGDDFG6UX5P4PXOEXC2/events.json","paper":"https://pith.science/paper/XUZH6E4T"},"agent_actions":{"view_html":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2","download_json":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2.json","view_paper":"https://pith.science/paper/XUZH6E4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.17159&json=true","fetch_graph":"https://pith.science/api/pith-number/XUZH6E4TGDDFG6UX5P4PXOEXC2/graph.json","fetch_events":"https://pith.science/api/pith-number/XUZH6E4TGDDFG6UX5P4PXOEXC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2/action/storage_attestation","attest_author":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2/action/author_attestation","sign_citation":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2/action/citation_signature","submit_replication":"https://pith.science/pith/XUZH6E4TGDDFG6UX5P4PXOEXC2/action/replication_record"}},"created_at":"2026-07-05T05:12:28.176413+00:00","updated_at":"2026-07-05T05:12:28.176413+00:00"}