{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4TGBLIDRWG5YMKCV2X3KXCRWUE","short_pith_number":"pith:4TGBLIDR","schema_version":"1.0","canonical_sha256":"e4cc15a071b1bb862855d5f6ab8a36a1264f577ee0fb84bf0457dfef38497aea","source":{"kind":"arxiv","id":"2202.13526","version":2},"attestation_state":"computed","paper":{"title":"Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Gene Cheung, Jin Zeng, Wei Hu, Yang Liu","submitted_at":"2022-02-28T03:39:48Z","abstract_excerpt":"A graph convolutional network (GCN) employs a graph filtering kernel tailored for data with irregular structures. However, simply stacking more GCN layers does not improve performance; instead, the output converges to an uninformative low-dimensional subspace, where the convergence rate is characterized by the graph spectrum -- this is the known over-smoothing problem in GCN. In this paper, we propose a sparse graph learning algorithm incorporating a new spectrum prior to compute a graph topology that circumvents over-smoothing while preserving pairwise correlations inherent in data. Specifica"},"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":"2202.13526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T03:39:48Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"e9af05cc8be45fb7744ff74eb45491cb5aa7fa6271a48cb44eb142ed6943e20e","abstract_canon_sha256":"4ce5c8de749e746e51b8559cd54bcb35e2db54c983c11583046646b51265c8cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:50.222838Z","signature_b64":"z5PxlGQZVJlLm+5DoXIV9DZvnlrvaVW8QXhNYPfL9gNTf2Tc5eiHQBs5FA9MAPWonMZnvFIswpAiPZ7T4CD0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4cc15a071b1bb862855d5f6ab8a36a1264f577ee0fb84bf0457dfef38497aea","last_reissued_at":"2026-07-05T05:12:50.222461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:50.222461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Gene Cheung, Jin Zeng, Wei Hu, Yang Liu","submitted_at":"2022-02-28T03:39:48Z","abstract_excerpt":"A graph convolutional network (GCN) employs a graph filtering kernel tailored for data with irregular structures. However, simply stacking more GCN layers does not improve performance; instead, the output converges to an uninformative low-dimensional subspace, where the convergence rate is characterized by the graph spectrum -- this is the known over-smoothing problem in GCN. In this paper, we propose a sparse graph learning algorithm incorporating a new spectrum prior to compute a graph topology that circumvents over-smoothing while preserving pairwise correlations inherent in data. Specifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13526","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/2202.13526/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":"2202.13526","created_at":"2026-07-05T05:12:50.222517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13526v2","created_at":"2026-07-05T05:12:50.222517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13526","created_at":"2026-07-05T05:12:50.222517+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TGBLIDRWG5Y","created_at":"2026-07-05T05:12:50.222517+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TGBLIDRWG5YMKCV","created_at":"2026-07-05T05:12:50.222517+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TGBLIDR","created_at":"2026-07-05T05:12:50.222517+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/4TGBLIDRWG5YMKCV2X3KXCRWUE","json":"https://pith.science/pith/4TGBLIDRWG5YMKCV2X3KXCRWUE.json","graph_json":"https://pith.science/api/pith-number/4TGBLIDRWG5YMKCV2X3KXCRWUE/graph.json","events_json":"https://pith.science/api/pith-number/4TGBLIDRWG5YMKCV2X3KXCRWUE/events.json","paper":"https://pith.science/paper/4TGBLIDR"},"agent_actions":{"view_html":"https://pith.science/pith/4TGBLIDRWG5YMKCV2X3KXCRWUE","download_json":"https://pith.science/pith/4TGBLIDRWG5YMKCV2X3KXCRWUE.json","view_paper":"https://pith.science/paper/4TGBLIDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13526&json=true","fetch_graph":"https://pith.science/api/pith-number/4TGBLIDRWG5YMKCV2X3KXCRWUE/graph.json","fetch_events":"https://pith.science/api/pith-number/4TGBLIDRWG5YMKCV2X3KXCRWUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TGBLIDRWG5YMKCV2X3KXCRWUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TGBLIDRWG5YMKCV2X3KXCRWUE/action/storage_attestation","attest_author":"https://pith.science/pith/4TGBLIDRWG5YMKCV2X3KXCRWUE/action/author_attestation","sign_citation":"https://pith.science/pith/4TGBLIDRWG5YMKCV2X3KXCRWUE/action/citation_signature","submit_replication":"https://pith.science/pith/4TGBLIDRWG5YMKCV2X3KXCRWUE/action/replication_record"}},"created_at":"2026-07-05T05:12:50.222517+00:00","updated_at":"2026-07-05T05:12:50.222517+00:00"}