{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CPEK66QPAYRIEXRJ3UE6CEDGYP","short_pith_number":"pith:CPEK66QP","schema_version":"1.0","canonical_sha256":"13c8af7a0f0622825e29dd09e11066c3cc167a24992255ad24be2377cd5681ad","source":{"kind":"arxiv","id":"2310.11025","version":1},"attestation_state":"computed","paper":{"title":"SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Gaichao Li, Jinsong Chen, John E. Hopcroft, Kun He","submitted_at":"2023-10-17T06:42:11Z","abstract_excerpt":"The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a two-step aggregation operation on a fully connected graph. Due to the property of generating positive attention values, the self-attention mechanism is equal to conducting a smooth operation on all nodes, preserving the low-frequency information. However, only capturing the low-frequency information is inefficient in learning complex relations of nodes on divers"},"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":"2310.11025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-17T06:42:11Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"8e26506db4d049308f7ee938231a3615cd62ac1763278b8493f5f9844ba9cba4","abstract_canon_sha256":"a88193598e037d7eada2d8bb2636924b62a4836ffa5774c6c036529e4ea07777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:49.433183Z","signature_b64":"wMuqulNBt3U9rgGE7ltDQj1f94ncgJN4jaFHPOf1xWiJUg+0Wa5Deo4BO6tpLd3SCs/7r6GJGmrrBDCZxXyHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13c8af7a0f0622825e29dd09e11066c3cc167a24992255ad24be2377cd5681ad","last_reissued_at":"2026-07-05T07:01:49.432720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:49.432720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Gaichao Li, Jinsong Chen, John E. Hopcroft, Kun He","submitted_at":"2023-10-17T06:42:11Z","abstract_excerpt":"The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a two-step aggregation operation on a fully connected graph. Due to the property of generating positive attention values, the self-attention mechanism is equal to conducting a smooth operation on all nodes, preserving the low-frequency information. However, only capturing the low-frequency information is inefficient in learning complex relations of nodes on divers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11025","kind":"arxiv","version":1},"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/2310.11025/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":"2310.11025","created_at":"2026-07-05T07:01:49.432776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11025v1","created_at":"2026-07-05T07:01:49.432776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11025","created_at":"2026-07-05T07:01:49.432776+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPEK66QPAYRI","created_at":"2026-07-05T07:01:49.432776+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPEK66QPAYRIEXRJ","created_at":"2026-07-05T07:01:49.432776+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPEK66QP","created_at":"2026-07-05T07:01:49.432776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04833","citing_title":"Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP","json":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP.json","graph_json":"https://pith.science/api/pith-number/CPEK66QPAYRIEXRJ3UE6CEDGYP/graph.json","events_json":"https://pith.science/api/pith-number/CPEK66QPAYRIEXRJ3UE6CEDGYP/events.json","paper":"https://pith.science/paper/CPEK66QP"},"agent_actions":{"view_html":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP","download_json":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP.json","view_paper":"https://pith.science/paper/CPEK66QP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11025&json=true","fetch_graph":"https://pith.science/api/pith-number/CPEK66QPAYRIEXRJ3UE6CEDGYP/graph.json","fetch_events":"https://pith.science/api/pith-number/CPEK66QPAYRIEXRJ3UE6CEDGYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP/action/storage_attestation","attest_author":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP/action/author_attestation","sign_citation":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP/action/citation_signature","submit_replication":"https://pith.science/pith/CPEK66QPAYRIEXRJ3UE6CEDGYP/action/replication_record"}},"created_at":"2026-07-05T07:01:49.432776+00:00","updated_at":"2026-07-05T07:01:49.432776+00:00"}