{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P4SF54R67MRIOPLXL3LYVOZ4FW","short_pith_number":"pith:P4SF54R6","schema_version":"1.0","canonical_sha256":"7f245ef23efb22873d775ed78abb3c2da9b73e69739460647fd177c5084e7ee3","source":{"kind":"arxiv","id":"2408.04895","version":3},"attestation_state":"computed","paper":{"title":"Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chong-kwon Kim, Jiho Choi, Taewook Ko, Yoonhyuk Choi","submitted_at":"2024-08-09T06:46:06Z","abstract_excerpt":"Traditional Graph Neural Networks (GNNs) rely on network homophily, which can lead to performance degradation due to over-smoothing in many real-world heterophily scenarios. Recent studies analyze the smoothing effect (separability) after message-passing (MP), depending on the expectation of node features. Regarding separability gain, they provided theoretical backgrounds on over-smoothing caused by various propagation schemes, including positive, signed, and blocked MPs. More recently, by extending these theorems, some works have suggested improvements in signed propagation under multiple cla"},"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":"2408.04895","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T06:46:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65f69880a2f810b1ac6b8b5de4918178a0b745a036751bd2eba402885d93ef59","abstract_canon_sha256":"7ac0f0fea69f18f274f50035a32c2341975ac497585f3737c9a3ee9dd5492695"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:20.129729Z","signature_b64":"ZzqX75LAytZytxgV4RSApQxPYT94tIdg/hGlV9TltRHNhY4GkJRQ1RCNotgjWZ0JoI89L4SbStlVzxWcNSw8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f245ef23efb22873d775ed78abb3c2da9b73e69739460647fd177c5084e7ee3","last_reissued_at":"2026-07-05T09:30:20.129330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:20.129330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chong-kwon Kim, Jiho Choi, Taewook Ko, Yoonhyuk Choi","submitted_at":"2024-08-09T06:46:06Z","abstract_excerpt":"Traditional Graph Neural Networks (GNNs) rely on network homophily, which can lead to performance degradation due to over-smoothing in many real-world heterophily scenarios. Recent studies analyze the smoothing effect (separability) after message-passing (MP), depending on the expectation of node features. Regarding separability gain, they provided theoretical backgrounds on over-smoothing caused by various propagation schemes, including positive, signed, and blocked MPs. More recently, by extending these theorems, some works have suggested improvements in signed propagation under multiple cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04895","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/2408.04895/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":"2408.04895","created_at":"2026-07-05T09:30:20.129389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04895v3","created_at":"2026-07-05T09:30:20.129389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04895","created_at":"2026-07-05T09:30:20.129389+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4SF54R67MRI","created_at":"2026-07-05T09:30:20.129389+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4SF54R67MRIOPLX","created_at":"2026-07-05T09:30:20.129389+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4SF54R6","created_at":"2026-07-05T09:30:20.129389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16790","citing_title":"Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW","json":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW.json","graph_json":"https://pith.science/api/pith-number/P4SF54R67MRIOPLXL3LYVOZ4FW/graph.json","events_json":"https://pith.science/api/pith-number/P4SF54R67MRIOPLXL3LYVOZ4FW/events.json","paper":"https://pith.science/paper/P4SF54R6"},"agent_actions":{"view_html":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW","download_json":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW.json","view_paper":"https://pith.science/paper/P4SF54R6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04895&json=true","fetch_graph":"https://pith.science/api/pith-number/P4SF54R67MRIOPLXL3LYVOZ4FW/graph.json","fetch_events":"https://pith.science/api/pith-number/P4SF54R67MRIOPLXL3LYVOZ4FW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW/action/storage_attestation","attest_author":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW/action/author_attestation","sign_citation":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW/action/citation_signature","submit_replication":"https://pith.science/pith/P4SF54R67MRIOPLXL3LYVOZ4FW/action/replication_record"}},"created_at":"2026-07-05T09:30:20.129389+00:00","updated_at":"2026-07-05T09:30:20.129389+00:00"}