{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KEQ3DAKCPVOXOG2ZAJXUMXH3T4","short_pith_number":"pith:KEQ3DAKC","schema_version":"1.0","canonical_sha256":"5121b181427d5d771b59026f465cfb9f32bb6bd2e348bcd6e35a02f2d0d57604","source":{"kind":"arxiv","id":"2406.19249","version":1},"attestation_state":"computed","paper":{"title":"NTFormer: A Composite Node Tokenized Graph Transformer for Node Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinsong Chen, Kun He, Siyu Jiang","submitted_at":"2024-06-27T15:16:00Z","abstract_excerpt":"Recently, the emerging graph Transformers have made significant advancements for node classification on graphs. In most graph Transformers, a crucial step involves transforming the input graph into token sequences as the model input, enabling Transformer to effectively learn the node representations. However, we observe that existing methods only express partial graph information of nodes through single-type token generation. Consequently, they require tailored strategies to encode additional graph-specific features into the Transformer to ensure the quality of node representation learning, li"},"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":"2406.19249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-27T15:16:00Z","cross_cats_sorted":[],"title_canon_sha256":"c8b36a06097062bbbd9ec1e18026d9fead050112e4da4684b66cdbd830a20ec4","abstract_canon_sha256":"1f4f3847e0c629cf94b5a2ae41e629fb630ab761f26d335f1eb7eac62d3e5a70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:32.329881Z","signature_b64":"BDB6xtDii3eh66kA/9ky2cdVX43kaRerJpuT1Q6Q/V2tJW7+qjIfR0XluLWa483+B47KPz/5KIYAPHMJ0SrqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5121b181427d5d771b59026f465cfb9f32bb6bd2e348bcd6e35a02f2d0d57604","last_reissued_at":"2026-07-05T08:37:32.329496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:32.329496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NTFormer: A Composite Node Tokenized Graph Transformer for Node Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinsong Chen, Kun He, Siyu Jiang","submitted_at":"2024-06-27T15:16:00Z","abstract_excerpt":"Recently, the emerging graph Transformers have made significant advancements for node classification on graphs. In most graph Transformers, a crucial step involves transforming the input graph into token sequences as the model input, enabling Transformer to effectively learn the node representations. However, we observe that existing methods only express partial graph information of nodes through single-type token generation. Consequently, they require tailored strategies to encode additional graph-specific features into the Transformer to ensure the quality of node representation learning, li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19249","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/2406.19249/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":"2406.19249","created_at":"2026-07-05T08:37:32.329550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19249v1","created_at":"2026-07-05T08:37:32.329550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19249","created_at":"2026-07-05T08:37:32.329550+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEQ3DAKCPVOX","created_at":"2026-07-05T08:37:32.329550+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEQ3DAKCPVOXOG2Z","created_at":"2026-07-05T08:37:32.329550+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEQ3DAKC","created_at":"2026-07-05T08:37:32.329550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.17071","citing_title":"AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4","json":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4.json","graph_json":"https://pith.science/api/pith-number/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/graph.json","events_json":"https://pith.science/api/pith-number/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/events.json","paper":"https://pith.science/paper/KEQ3DAKC"},"agent_actions":{"view_html":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4","download_json":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4.json","view_paper":"https://pith.science/paper/KEQ3DAKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19249&json=true","fetch_graph":"https://pith.science/api/pith-number/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/graph.json","fetch_events":"https://pith.science/api/pith-number/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/action/storage_attestation","attest_author":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/action/author_attestation","sign_citation":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/action/citation_signature","submit_replication":"https://pith.science/pith/KEQ3DAKCPVOXOG2ZAJXUMXH3T4/action/replication_record"}},"created_at":"2026-07-05T08:37:32.329550+00:00","updated_at":"2026-07-05T08:37:32.329550+00:00"}