{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GK3H2RXSDCAKA3OV7TKTDIPNTG","short_pith_number":"pith:GK3H2RXS","schema_version":"1.0","canonical_sha256":"32b67d46f21880a06dd5fcd531a1ed99a62b3441fd452573bcb981a7ad0b73f3","source":{"kind":"arxiv","id":"2205.06456","version":1},"attestation_state":"computed","paper":{"title":"Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dianhai Yu, Huijuan Wang, Hui Zhong, Shikun Feng, Siming Dai, Weiyue Su, Yu Sun, Zeyang Fang, Zeyu Chen, Zhengjie Huang","submitted_at":"2022-05-13T06:02:13Z","abstract_excerpt":"Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs, how to efficiently and effectively utilize graph context for large KGs remains an open problem. To this end, we propose the Relation-based Embedding Propagation (REP) method. It is a post-processing technique to adapt pre-trained KG embeddings with graph context. As relations in KGs are directional, we model the incoming head context and the outgoing tail context separately. Accordingly, we design relational context "},"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":"2205.06456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-13T06:02:13Z","cross_cats_sorted":[],"title_canon_sha256":"2e76c0faed6a15a7a97da4540863dbe59316dfe981ef59939bc360138ce5b222","abstract_canon_sha256":"87b2fb22d30392c2dfcdaca0d9949a21acdfe4964c50bbfd4b69f48589c60abe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:58.120941Z","signature_b64":"pxo9f+X28+x4v2KheomYvyjkjUCIMODJbiBS26l77L7obKR9oEo+VXpFDi4WYIfxtr4ZRkIpGtUc4V9DASM9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32b67d46f21880a06dd5fcd531a1ed99a62b3441fd452573bcb981a7ad0b73f3","last_reissued_at":"2026-07-05T04:22:58.120545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:58.120545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dianhai Yu, Huijuan Wang, Hui Zhong, Shikun Feng, Siming Dai, Weiyue Su, Yu Sun, Zeyang Fang, Zeyu Chen, Zhengjie Huang","submitted_at":"2022-05-13T06:02:13Z","abstract_excerpt":"Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs, how to efficiently and effectively utilize graph context for large KGs remains an open problem. To this end, we propose the Relation-based Embedding Propagation (REP) method. It is a post-processing technique to adapt pre-trained KG embeddings with graph context. As relations in KGs are directional, we model the incoming head context and the outgoing tail context separately. Accordingly, we design relational context "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06456","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/2205.06456/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":"2205.06456","created_at":"2026-07-05T04:22:58.120602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.06456v1","created_at":"2026-07-05T04:22:58.120602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06456","created_at":"2026-07-05T04:22:58.120602+00:00"},{"alias_kind":"pith_short_12","alias_value":"GK3H2RXSDCAK","created_at":"2026-07-05T04:22:58.120602+00:00"},{"alias_kind":"pith_short_16","alias_value":"GK3H2RXSDCAKA3OV","created_at":"2026-07-05T04:22:58.120602+00:00"},{"alias_kind":"pith_short_8","alias_value":"GK3H2RXS","created_at":"2026-07-05T04:22:58.120602+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/GK3H2RXSDCAKA3OV7TKTDIPNTG","json":"https://pith.science/pith/GK3H2RXSDCAKA3OV7TKTDIPNTG.json","graph_json":"https://pith.science/api/pith-number/GK3H2RXSDCAKA3OV7TKTDIPNTG/graph.json","events_json":"https://pith.science/api/pith-number/GK3H2RXSDCAKA3OV7TKTDIPNTG/events.json","paper":"https://pith.science/paper/GK3H2RXS"},"agent_actions":{"view_html":"https://pith.science/pith/GK3H2RXSDCAKA3OV7TKTDIPNTG","download_json":"https://pith.science/pith/GK3H2RXSDCAKA3OV7TKTDIPNTG.json","view_paper":"https://pith.science/paper/GK3H2RXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.06456&json=true","fetch_graph":"https://pith.science/api/pith-number/GK3H2RXSDCAKA3OV7TKTDIPNTG/graph.json","fetch_events":"https://pith.science/api/pith-number/GK3H2RXSDCAKA3OV7TKTDIPNTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GK3H2RXSDCAKA3OV7TKTDIPNTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GK3H2RXSDCAKA3OV7TKTDIPNTG/action/storage_attestation","attest_author":"https://pith.science/pith/GK3H2RXSDCAKA3OV7TKTDIPNTG/action/author_attestation","sign_citation":"https://pith.science/pith/GK3H2RXSDCAKA3OV7TKTDIPNTG/action/citation_signature","submit_replication":"https://pith.science/pith/GK3H2RXSDCAKA3OV7TKTDIPNTG/action/replication_record"}},"created_at":"2026-07-05T04:22:58.120602+00:00","updated_at":"2026-07-05T04:22:58.120602+00:00"}