{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RCJSMCOD2XZSD65UN4SHQ3EXC4","short_pith_number":"pith:RCJSMCOD","schema_version":"1.0","canonical_sha256":"88932609c3d5f321fbb46f24786c97172098fdbc8f8412a437c6ddf30695c2f4","source":{"kind":"arxiv","id":"2206.04910","version":4},"attestation_state":"computed","paper":{"title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaichao Li, Jinsong Chen, Kaiyuan Gao, Kun He","submitted_at":"2022-06-10T07:23:51Z","abstract_excerpt":"The graph Transformer emerges as a new architecture and has shown superior performance on various graph mining tasks. In this work, we observe that existing graph Transformers treat nodes as independent tokens and construct a single long sequence composed of all node tokens so as to train the Transformer model, causing it hard to scale to large graphs due to the quadratic complexity on the number of nodes for the self-attention computation. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constru"},"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":"2206.04910","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-10T07:23:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73148c1a928f278f3849191b9575f4e990738881e77551ae23e534fe399df889","abstract_canon_sha256":"96d9903889c0ce58d4b067767f833f37ef33a784a740d6e009015a43a97411dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:29.577776Z","signature_b64":"ToD9tTo5zHACOxRNv9NjEAy97KBVjE36SK9M51j1+XJkBunNc90YTZ+jM40M78FS3Me01rcjMAIVBzZRs7h1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88932609c3d5f321fbb46f24786c97172098fdbc8f8412a437c6ddf30695c2f4","last_reissued_at":"2026-07-05T05:45:29.577299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:29.577299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaichao Li, Jinsong Chen, Kaiyuan Gao, Kun He","submitted_at":"2022-06-10T07:23:51Z","abstract_excerpt":"The graph Transformer emerges as a new architecture and has shown superior performance on various graph mining tasks. In this work, we observe that existing graph Transformers treat nodes as independent tokens and construct a single long sequence composed of all node tokens so as to train the Transformer model, causing it hard to scale to large graphs due to the quadratic complexity on the number of nodes for the self-attention computation. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04910","kind":"arxiv","version":4},"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/2206.04910/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":"2206.04910","created_at":"2026-07-05T05:45:29.577375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04910v4","created_at":"2026-07-05T05:45:29.577375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04910","created_at":"2026-07-05T05:45:29.577375+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCJSMCOD2XZS","created_at":"2026-07-05T05:45:29.577375+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCJSMCOD2XZSD65U","created_at":"2026-07-05T05:45:29.577375+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCJSMCOD","created_at":"2026-07-05T05:45:29.577375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.12369","citing_title":"A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20248","citing_title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4","json":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4.json","graph_json":"https://pith.science/api/pith-number/RCJSMCOD2XZSD65UN4SHQ3EXC4/graph.json","events_json":"https://pith.science/api/pith-number/RCJSMCOD2XZSD65UN4SHQ3EXC4/events.json","paper":"https://pith.science/paper/RCJSMCOD"},"agent_actions":{"view_html":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4","download_json":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4.json","view_paper":"https://pith.science/paper/RCJSMCOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04910&json=true","fetch_graph":"https://pith.science/api/pith-number/RCJSMCOD2XZSD65UN4SHQ3EXC4/graph.json","fetch_events":"https://pith.science/api/pith-number/RCJSMCOD2XZSD65UN4SHQ3EXC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4/action/storage_attestation","attest_author":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4/action/author_attestation","sign_citation":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4/action/citation_signature","submit_replication":"https://pith.science/pith/RCJSMCOD2XZSD65UN4SHQ3EXC4/action/replication_record"}},"created_at":"2026-07-05T05:45:29.577375+00:00","updated_at":"2026-07-05T05:45:29.577375+00:00"}