{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KUX3ZOEFD7BSTJF5YYADBSKTTE","short_pith_number":"pith:KUX3ZOEF","schema_version":"1.0","canonical_sha256":"552fbcb8851fc329a4bdc60030c95399040df482f6250fbb54186bbbdfbdb463","source":{"kind":"arxiv","id":"2205.10852","version":6},"attestation_state":"computed","paper":{"title":"Relphormer: Relational Graph Transformer for Knowledge Graph Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Feiyu Xiong, Jing Chen, Ningyu Zhang, Siyuan Cheng, Xiaozhuan Liang, Zhen Bi","submitted_at":"2022-05-22T15:30:18Z","abstract_excerpt":"Transformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer architectures have not yielded promising improvements in the Knowledge Graph (KG) representations, where the translational distance paradigm dominates this area. Note that vanilla Transformer architectures struggle to capture the intrinsically heterogeneous structural and semantic information of knowledge graphs. To this end, we propose a new variant of Transformer for knowledge graph representations dubbed Relphormer. Spe"},"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":"2205.10852","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-22T15:30:18Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"c9377c1c41ac6920076d104a211f7077dc2470f250ac4ad5076dc26a62840f0c","abstract_canon_sha256":"d4d4bb525dfd6c63f9db461bfa5ddd16d2132381d3126c9c4e576e956d0ee340"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:50.257497Z","signature_b64":"/BTz2J0AZebpjNHit1jA0KzAylj2Kelk61mrbClbQ18bWxYnoFMsmtkx5nm3ADedzrESaCOR6ZaXf+87GMmXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"552fbcb8851fc329a4bdc60030c95399040df482f6250fbb54186bbbdfbdb463","last_reissued_at":"2026-07-05T07:14:50.257021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:50.257021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relphormer: Relational Graph Transformer for Knowledge Graph Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Feiyu Xiong, Jing Chen, Ningyu Zhang, Siyuan Cheng, Xiaozhuan Liang, Zhen Bi","submitted_at":"2022-05-22T15:30:18Z","abstract_excerpt":"Transformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer architectures have not yielded promising improvements in the Knowledge Graph (KG) representations, where the translational distance paradigm dominates this area. Note that vanilla Transformer architectures struggle to capture the intrinsically heterogeneous structural and semantic information of knowledge graphs. To this end, we propose a new variant of Transformer for knowledge graph representations dubbed Relphormer. Spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10852","kind":"arxiv","version":6},"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/2205.10852/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":"2205.10852","created_at":"2026-07-05T07:14:50.257079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10852v6","created_at":"2026-07-05T07:14:50.257079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10852","created_at":"2026-07-05T07:14:50.257079+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUX3ZOEFD7BS","created_at":"2026-07-05T07:14:50.257079+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUX3ZOEFD7BSTJF5","created_at":"2026-07-05T07:14:50.257079+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUX3ZOEF","created_at":"2026-07-05T07:14:50.257079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08278","citing_title":"Knowledge Bases in Support of Large Language Models for Processing Web News","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE","json":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE.json","graph_json":"https://pith.science/api/pith-number/KUX3ZOEFD7BSTJF5YYADBSKTTE/graph.json","events_json":"https://pith.science/api/pith-number/KUX3ZOEFD7BSTJF5YYADBSKTTE/events.json","paper":"https://pith.science/paper/KUX3ZOEF"},"agent_actions":{"view_html":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE","download_json":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE.json","view_paper":"https://pith.science/paper/KUX3ZOEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10852&json=true","fetch_graph":"https://pith.science/api/pith-number/KUX3ZOEFD7BSTJF5YYADBSKTTE/graph.json","fetch_events":"https://pith.science/api/pith-number/KUX3ZOEFD7BSTJF5YYADBSKTTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE/action/storage_attestation","attest_author":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE/action/author_attestation","sign_citation":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE/action/citation_signature","submit_replication":"https://pith.science/pith/KUX3ZOEFD7BSTJF5YYADBSKTTE/action/replication_record"}},"created_at":"2026-07-05T07:14:50.257079+00:00","updated_at":"2026-07-05T07:14:50.257079+00:00"}