{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BZR3IM26SURJCNX55VDWRSWQPM","short_pith_number":"pith:BZR3IM26","schema_version":"1.0","canonical_sha256":"0e63b4335e95229136fded4768cad07b316376444761d77fa27dfda2beee7c84","source":{"kind":"arxiv","id":"2506.17576","version":2},"attestation_state":"computed","paper":{"title":"Towards a deeper GCN: Alleviate over-smoothing with iterative training and fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Peng, Jinzhen Gao, Kang Liu, Sheng Wang, Xuan Lu, Yifan Huo","submitted_at":"2025-06-21T04:09:02Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) suffer from severe performance degradation in deep architectures due to over-smoothing. While existing studies primarily attribute the over-smoothing to repeated applications of graph Laplacian operators, our empirical analysis reveals a critical yet overlooked factor: trainable linear transformations in GCNs significantly exacerbate feature collapse, even at moderate depths (e.g., 8 layers). In contrast, Simplified Graph Convolution (SGC), which removes these transformations, maintains stable feature diversity up to 32 layers, highlighting linear transforma"},"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":"2506.17576","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T04:09:02Z","cross_cats_sorted":[],"title_canon_sha256":"2e4285eea9d830b39c700401d5cc824aed29a8ff2fa4e373fbf38f1206032004","abstract_canon_sha256":"89fe7b0a7ca6216c45092b9bfc4c82cb1d379a5229042427e43edf5e29d98433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:26.086142Z","signature_b64":"Pbzqimm/vVZfvPqTzxQeC58TxKqflriOu0cCoRVYVqsDVwAMpRKPfsRERVushgzM0kzvHWeaLquRNKzOwu76AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e63b4335e95229136fded4768cad07b316376444761d77fa27dfda2beee7c84","last_reissued_at":"2026-07-05T11:41:26.085611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:26.085611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a deeper GCN: Alleviate over-smoothing with iterative training and fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Peng, Jinzhen Gao, Kang Liu, Sheng Wang, Xuan Lu, Yifan Huo","submitted_at":"2025-06-21T04:09:02Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) suffer from severe performance degradation in deep architectures due to over-smoothing. While existing studies primarily attribute the over-smoothing to repeated applications of graph Laplacian operators, our empirical analysis reveals a critical yet overlooked factor: trainable linear transformations in GCNs significantly exacerbate feature collapse, even at moderate depths (e.g., 8 layers). In contrast, Simplified Graph Convolution (SGC), which removes these transformations, maintains stable feature diversity up to 32 layers, highlighting linear transforma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17576","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/2506.17576/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":"2506.17576","created_at":"2026-07-05T11:41:26.085689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17576v2","created_at":"2026-07-05T11:41:26.085689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17576","created_at":"2026-07-05T11:41:26.085689+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZR3IM26SURJ","created_at":"2026-07-05T11:41:26.085689+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZR3IM26SURJCNX5","created_at":"2026-07-05T11:41:26.085689+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZR3IM26","created_at":"2026-07-05T11:41:26.085689+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/BZR3IM26SURJCNX55VDWRSWQPM","json":"https://pith.science/pith/BZR3IM26SURJCNX55VDWRSWQPM.json","graph_json":"https://pith.science/api/pith-number/BZR3IM26SURJCNX55VDWRSWQPM/graph.json","events_json":"https://pith.science/api/pith-number/BZR3IM26SURJCNX55VDWRSWQPM/events.json","paper":"https://pith.science/paper/BZR3IM26"},"agent_actions":{"view_html":"https://pith.science/pith/BZR3IM26SURJCNX55VDWRSWQPM","download_json":"https://pith.science/pith/BZR3IM26SURJCNX55VDWRSWQPM.json","view_paper":"https://pith.science/paper/BZR3IM26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17576&json=true","fetch_graph":"https://pith.science/api/pith-number/BZR3IM26SURJCNX55VDWRSWQPM/graph.json","fetch_events":"https://pith.science/api/pith-number/BZR3IM26SURJCNX55VDWRSWQPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZR3IM26SURJCNX55VDWRSWQPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZR3IM26SURJCNX55VDWRSWQPM/action/storage_attestation","attest_author":"https://pith.science/pith/BZR3IM26SURJCNX55VDWRSWQPM/action/author_attestation","sign_citation":"https://pith.science/pith/BZR3IM26SURJCNX55VDWRSWQPM/action/citation_signature","submit_replication":"https://pith.science/pith/BZR3IM26SURJCNX55VDWRSWQPM/action/replication_record"}},"created_at":"2026-07-05T11:41:26.085689+00:00","updated_at":"2026-07-05T11:41:26.085689+00:00"}