{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MGJHKIEF73PIKX4E4U6KW2RF76","short_pith_number":"pith:MGJHKIEF","schema_version":"1.0","canonical_sha256":"6192752085fede855f84e53cab6a25ffa2203e4cfc585afdbce97b5f29e38bc5","source":{"kind":"arxiv","id":"2412.15302","version":2},"attestation_state":"computed","paper":{"title":"Tokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Leong Hou U, Pak Lon Ip, Rongqin Chen, Shenghui Zhang, Xuekai Wei, Zhaoqi Lu, Zijie Zhou","submitted_at":"2024-12-19T10:44:18Z","abstract_excerpt":"Graph Neural Networks (GNNs) are widely used in graph data mining tasks. Traditional GNNs follow a message passing scheme that can effectively utilize local and structural information. However, the phenomena of over-smoothing and over-squashing limit the receptive field in message passing processes. Graph Transformers were introduced to address these issues, achieving a global receptive field but suffering from the noise of irrelevant nodes and loss of structural information. Therefore, drawing inspiration from fine-grained token-based representation learning in Natural Language Processing (NL"},"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":"2412.15302","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:44:18Z","cross_cats_sorted":[],"title_canon_sha256":"2feecdff157592cceb284874f2c53f241e21c61e2387467353e0066db74aaae5","abstract_canon_sha256":"19fd128ba5ea100714adb3571f9c43235f67425e22a2a9f6a97c8d91651a8850"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:34.822802Z","signature_b64":"VHZAmT4df6R1wNHrFXnzXhdgqtjaimMdwEzSeik+2GKOh5IHCjrOHAFeZqBDIe6+6AjYLvZB1XkfvzSePpgTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6192752085fede855f84e53cab6a25ffa2203e4cfc585afdbce97b5f29e38bc5","last_reissued_at":"2026-07-05T10:47:34.822341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:34.822341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Leong Hou U, Pak Lon Ip, Rongqin Chen, Shenghui Zhang, Xuekai Wei, Zhaoqi Lu, Zijie Zhou","submitted_at":"2024-12-19T10:44:18Z","abstract_excerpt":"Graph Neural Networks (GNNs) are widely used in graph data mining tasks. Traditional GNNs follow a message passing scheme that can effectively utilize local and structural information. However, the phenomena of over-smoothing and over-squashing limit the receptive field in message passing processes. Graph Transformers were introduced to address these issues, achieving a global receptive field but suffering from the noise of irrelevant nodes and loss of structural information. Therefore, drawing inspiration from fine-grained token-based representation learning in Natural Language Processing (NL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15302","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/2412.15302/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":"2412.15302","created_at":"2026-07-05T10:47:34.822400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15302v2","created_at":"2026-07-05T10:47:34.822400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15302","created_at":"2026-07-05T10:47:34.822400+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGJHKIEF73PI","created_at":"2026-07-05T10:47:34.822400+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGJHKIEF73PIKX4E","created_at":"2026-07-05T10:47:34.822400+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGJHKIEF","created_at":"2026-07-05T10:47:34.822400+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/MGJHKIEF73PIKX4E4U6KW2RF76","json":"https://pith.science/pith/MGJHKIEF73PIKX4E4U6KW2RF76.json","graph_json":"https://pith.science/api/pith-number/MGJHKIEF73PIKX4E4U6KW2RF76/graph.json","events_json":"https://pith.science/api/pith-number/MGJHKIEF73PIKX4E4U6KW2RF76/events.json","paper":"https://pith.science/paper/MGJHKIEF"},"agent_actions":{"view_html":"https://pith.science/pith/MGJHKIEF73PIKX4E4U6KW2RF76","download_json":"https://pith.science/pith/MGJHKIEF73PIKX4E4U6KW2RF76.json","view_paper":"https://pith.science/paper/MGJHKIEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15302&json=true","fetch_graph":"https://pith.science/api/pith-number/MGJHKIEF73PIKX4E4U6KW2RF76/graph.json","fetch_events":"https://pith.science/api/pith-number/MGJHKIEF73PIKX4E4U6KW2RF76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGJHKIEF73PIKX4E4U6KW2RF76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGJHKIEF73PIKX4E4U6KW2RF76/action/storage_attestation","attest_author":"https://pith.science/pith/MGJHKIEF73PIKX4E4U6KW2RF76/action/author_attestation","sign_citation":"https://pith.science/pith/MGJHKIEF73PIKX4E4U6KW2RF76/action/citation_signature","submit_replication":"https://pith.science/pith/MGJHKIEF73PIKX4E4U6KW2RF76/action/replication_record"}},"created_at":"2026-07-05T10:47:34.822400+00:00","updated_at":"2026-07-05T10:47:34.822400+00:00"}