{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2PTWVGSM5OMFCQQORQCIKPCWZW","short_pith_number":"pith:2PTWVGSM","schema_version":"1.0","canonical_sha256":"d3e76a9a4ceb9851420e8c04853c56cd917dc460cc835a751ba230c180341b85","source":{"kind":"arxiv","id":"2104.08167","version":1},"attestation_state":"computed","paper":{"title":"Improving Hyper-Relational Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donghan Yu, Yiming Yang","submitted_at":"2021-04-16T15:26:41Z","abstract_excerpt":"Different from traditional knowledge graphs (KGs) where facts are represented as entity-relation-entity triplets, hyper-relational KGs (HKGs) allow triplets to be associated with additional relation-entity pairs (a.k.a qualifiers) to convey more complex information. How to effectively and efficiently model the triplet-qualifier relationship for prediction tasks such as HKG completion is an open challenge for research. This paper proposes to improve the best-performing method in HKG completion, namely STARE, by introducing two novel revisions: (1) Replacing the computation-heavy graph neural ne"},"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":"2104.08167","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-16T15:26:41Z","cross_cats_sorted":[],"title_canon_sha256":"8b5dc8b29d0fc50f9921ad285b6869995dc166aba4db1ebe5334f1062d378e7d","abstract_canon_sha256":"6597d28e46a9aa8991e007605ac6bbe0d9eb72f3a5c6ea2a7308e66e9896d1a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:41.620298Z","signature_b64":"whkJBP9GwFRFP9kiUM8UB45MHgsfeRicQvGbazr4hFWE8qTky096Waz7PJybK4Ntc3l8i9/tTJGy3QFAU+8CAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3e76a9a4ceb9851420e8c04853c56cd917dc460cc835a751ba230c180341b85","last_reissued_at":"2026-07-05T02:32:41.619891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:41.619891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Hyper-Relational Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donghan Yu, Yiming Yang","submitted_at":"2021-04-16T15:26:41Z","abstract_excerpt":"Different from traditional knowledge graphs (KGs) where facts are represented as entity-relation-entity triplets, hyper-relational KGs (HKGs) allow triplets to be associated with additional relation-entity pairs (a.k.a qualifiers) to convey more complex information. How to effectively and efficiently model the triplet-qualifier relationship for prediction tasks such as HKG completion is an open challenge for research. This paper proposes to improve the best-performing method in HKG completion, namely STARE, by introducing two novel revisions: (1) Replacing the computation-heavy graph neural ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08167","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/2104.08167/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":"2104.08167","created_at":"2026-07-05T02:32:41.619953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08167v1","created_at":"2026-07-05T02:32:41.619953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08167","created_at":"2026-07-05T02:32:41.619953+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PTWVGSM5OMF","created_at":"2026-07-05T02:32:41.619953+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PTWVGSM5OMFCQQO","created_at":"2026-07-05T02:32:41.619953+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PTWVGSM","created_at":"2026-07-05T02:32:41.619953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08970","citing_title":"A Survey of Link Prediction in N-ary Knowledge Graphs","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW","json":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW.json","graph_json":"https://pith.science/api/pith-number/2PTWVGSM5OMFCQQORQCIKPCWZW/graph.json","events_json":"https://pith.science/api/pith-number/2PTWVGSM5OMFCQQORQCIKPCWZW/events.json","paper":"https://pith.science/paper/2PTWVGSM"},"agent_actions":{"view_html":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW","download_json":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW.json","view_paper":"https://pith.science/paper/2PTWVGSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08167&json=true","fetch_graph":"https://pith.science/api/pith-number/2PTWVGSM5OMFCQQORQCIKPCWZW/graph.json","fetch_events":"https://pith.science/api/pith-number/2PTWVGSM5OMFCQQORQCIKPCWZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW/action/storage_attestation","attest_author":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW/action/author_attestation","sign_citation":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW/action/citation_signature","submit_replication":"https://pith.science/pith/2PTWVGSM5OMFCQQORQCIKPCWZW/action/replication_record"}},"created_at":"2026-07-05T02:32:41.619953+00:00","updated_at":"2026-07-05T02:32:41.619953+00:00"}