{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UYW3Q3LRLJP7X4QMPCT234VIQL","short_pith_number":"pith:UYW3Q3LR","schema_version":"1.0","canonical_sha256":"a62db86d715a5ffbf20c78a7adf2a882e72accdf807ee724e853e8da2ef94bae","source":{"kind":"arxiv","id":"2002.06757","version":2},"attestation_state":"computed","paper":{"title":"Relational Message Passing for Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongwei Wang, Hongyu Ren, Jure Leskovec","submitted_at":"2020-02-17T03:33:41Z","abstract_excerpt":"Knowledge graph completion aims to predict missing relations between entities in a knowledge graph. In this work, we propose a relational message passing method for knowledge graph completion. Different from existing embedding-based methods, relational message passing only considers edge features (i.e., relation types) without entity IDs in the knowledge graph, and passes relational messages among edges iteratively to aggregate neighborhood information. Specifically, two kinds of neighborhood topology are modeled for a given entity pair under the relational message passing framework: (1) Relat"},"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":"2002.06757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T03:33:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a40e83c281462fcfc948ef075279e1bd6bf03c739c77673d616b7edc8b3eb5d3","abstract_canon_sha256":"2c67ff65983fbfbf9bd97d8b5db0e75bb535ec535abb354a12b6fa8334574c05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:02.119310Z","signature_b64":"HVZsxf1zIUCsslrzUkNi+5fFEPXbcc5leXKoB4h3UQtCIfTXIgEpuG1ISRL+7IyKIimI+yPDNGIjXz+7lyWrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a62db86d715a5ffbf20c78a7adf2a882e72accdf807ee724e853e8da2ef94bae","last_reissued_at":"2026-07-05T02:44:02.118771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:02.118771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relational Message Passing for Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongwei Wang, Hongyu Ren, Jure Leskovec","submitted_at":"2020-02-17T03:33:41Z","abstract_excerpt":"Knowledge graph completion aims to predict missing relations between entities in a knowledge graph. In this work, we propose a relational message passing method for knowledge graph completion. Different from existing embedding-based methods, relational message passing only considers edge features (i.e., relation types) without entity IDs in the knowledge graph, and passes relational messages among edges iteratively to aggregate neighborhood information. Specifically, two kinds of neighborhood topology are modeled for a given entity pair under the relational message passing framework: (1) Relat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06757","kind":"arxiv","version":2},"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/2002.06757/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":"2002.06757","created_at":"2026-07-05T02:44:02.118828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06757v2","created_at":"2026-07-05T02:44:02.118828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06757","created_at":"2026-07-05T02:44:02.118828+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYW3Q3LRLJP7","created_at":"2026-07-05T02:44:02.118828+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYW3Q3LRLJP7X4QM","created_at":"2026-07-05T02:44:02.118828+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYW3Q3LR","created_at":"2026-07-05T02:44:02.118828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07422","citing_title":"InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29346","citing_title":"Understanding and Reducing Metadata-Driven Host Overheads in Sampling-Based GNN Training","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL","json":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL.json","graph_json":"https://pith.science/api/pith-number/UYW3Q3LRLJP7X4QMPCT234VIQL/graph.json","events_json":"https://pith.science/api/pith-number/UYW3Q3LRLJP7X4QMPCT234VIQL/events.json","paper":"https://pith.science/paper/UYW3Q3LR"},"agent_actions":{"view_html":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL","download_json":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL.json","view_paper":"https://pith.science/paper/UYW3Q3LR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06757&json=true","fetch_graph":"https://pith.science/api/pith-number/UYW3Q3LRLJP7X4QMPCT234VIQL/graph.json","fetch_events":"https://pith.science/api/pith-number/UYW3Q3LRLJP7X4QMPCT234VIQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL/action/storage_attestation","attest_author":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL/action/author_attestation","sign_citation":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL/action/citation_signature","submit_replication":"https://pith.science/pith/UYW3Q3LRLJP7X4QMPCT234VIQL/action/replication_record"}},"created_at":"2026-07-05T02:44:02.118828+00:00","updated_at":"2026-07-05T02:44:02.118828+00:00"}