{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJR6QBHASCBGMZFRO3ZWY6U7HS","short_pith_number":"pith:BJR6QBHA","schema_version":"1.0","canonical_sha256":"0a63e804e090826664b176f36c7a9f3cb5b2cf0ad18bfcf8e2b3c896938f0394","source":{"kind":"arxiv","id":"2402.02464","version":3},"attestation_state":"computed","paper":{"title":"A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Bozhen Hu, Cheng Tan, Daize Dong, Jun Xia, Stan Z. Li, Zhangyang Gao","submitted_at":"2024-02-04T12:29:40Z","abstract_excerpt":"Can we model Non-Euclidean graphs as pure language or even Euclidean vectors while retaining their inherent information? The Non-Euclidean property have posed a long term challenge in graph modeling. Despite recent graph neural networks and graph transformers efforts encoding graphs as Euclidean vectors, recovering the original graph from vectors remains a challenge. In this paper, we introduce GraphsGPT, featuring an Graph2Seq encoder that transforms Non-Euclidean graphs into learnable Graph Words in the Euclidean space, along with a GraphGPT decoder that reconstructs the original graph from "},"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":"2402.02464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T12:29:40Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"0dc18f1d012decd9f13e252919698c8bc46e24d29c6c487d304d5644fa8e729a","abstract_canon_sha256":"ccfaf8df478d29a2716b083067860e1a4231b359eee3c181b1c6945fb2b87e1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:23.877304Z","signature_b64":"fjXueZmmb0013nNVE50dkAcSWCYmi2lCmmgCn3MjAO6x4K5lfHfDE4p2Whp4P/LIhlPy+Sm2wXpFtJtABIxMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a63e804e090826664b176f36c7a9f3cb5b2cf0ad18bfcf8e2b3c896938f0394","last_reissued_at":"2026-07-05T08:24:23.876853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:23.876853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Bozhen Hu, Cheng Tan, Daize Dong, Jun Xia, Stan Z. Li, Zhangyang Gao","submitted_at":"2024-02-04T12:29:40Z","abstract_excerpt":"Can we model Non-Euclidean graphs as pure language or even Euclidean vectors while retaining their inherent information? The Non-Euclidean property have posed a long term challenge in graph modeling. Despite recent graph neural networks and graph transformers efforts encoding graphs as Euclidean vectors, recovering the original graph from vectors remains a challenge. In this paper, we introduce GraphsGPT, featuring an Graph2Seq encoder that transforms Non-Euclidean graphs into learnable Graph Words in the Euclidean space, along with a GraphGPT decoder that reconstructs the original graph from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02464","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/2402.02464/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":"2402.02464","created_at":"2026-07-05T08:24:23.876909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02464v3","created_at":"2026-07-05T08:24:23.876909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02464","created_at":"2026-07-05T08:24:23.876909+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJR6QBHASCBG","created_at":"2026-07-05T08:24:23.876909+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJR6QBHASCBGMZFR","created_at":"2026-07-05T08:24:23.876909+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJR6QBHA","created_at":"2026-07-05T08:24:23.876909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01073","citing_title":"Graph Generative Pre-trained Transformer","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS","json":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS.json","graph_json":"https://pith.science/api/pith-number/BJR6QBHASCBGMZFRO3ZWY6U7HS/graph.json","events_json":"https://pith.science/api/pith-number/BJR6QBHASCBGMZFRO3ZWY6U7HS/events.json","paper":"https://pith.science/paper/BJR6QBHA"},"agent_actions":{"view_html":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS","download_json":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS.json","view_paper":"https://pith.science/paper/BJR6QBHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02464&json=true","fetch_graph":"https://pith.science/api/pith-number/BJR6QBHASCBGMZFRO3ZWY6U7HS/graph.json","fetch_events":"https://pith.science/api/pith-number/BJR6QBHASCBGMZFRO3ZWY6U7HS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS/action/storage_attestation","attest_author":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS/action/author_attestation","sign_citation":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS/action/citation_signature","submit_replication":"https://pith.science/pith/BJR6QBHASCBGMZFRO3ZWY6U7HS/action/replication_record"}},"created_at":"2026-07-05T08:24:23.876909+00:00","updated_at":"2026-07-05T08:24:23.876909+00:00"}