{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VMRBHRGMEKBZW2HBGGO4ZHP6GC","short_pith_number":"pith:VMRBHRGM","schema_version":"1.0","canonical_sha256":"ab2213c4cc22839b68e1319dcc9dfe30b691c73e2ea8acab70e0390bf63ac30d","source":{"kind":"arxiv","id":"1908.04895","version":2},"attestation_state":"computed","paper":{"title":"HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandros Kalousis, Dimitris Kiritsis, Prodromos Kolyvakis","submitted_at":"2019-08-14T00:24:54Z","abstract_excerpt":"Learning embeddings of entities and relations existing in knowledge bases allows the discovery of hidden patterns in data. In this work, we examine the geometrical space's contribution to the task of knowledge base completion. We focus on the family of translational models, whose performance has been lagging, and propose a model, dubbed HyperKG, which exploits the hyperbolic space in order to better reflect the topological properties of knowledge bases. We investigate the type of regularities that our model can capture and we show that it is a prominent candidate for effectively representing a"},"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":"1908.04895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T00:24:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53ae93bc6922e521910896f66f9d318a28900c1d0f5f2cec5215b5d62218d78e","abstract_canon_sha256":"bab1ec6e1b570e77026f64e911e4e2887fae2dbd1533f826affe4023426f36ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:11.844896Z","signature_b64":"AABhlRHv97PimXPT1JKMIa3ipjM5wqufGrts3TJc+QqckGNajdtwPkgreYGOptCERoTtuLEmtOUJ1G10Tb5wAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab2213c4cc22839b68e1319dcc9dfe30b691c73e2ea8acab70e0390bf63ac30d","last_reissued_at":"2026-07-04T23:58:11.844534Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:11.844534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandros Kalousis, Dimitris Kiritsis, Prodromos Kolyvakis","submitted_at":"2019-08-14T00:24:54Z","abstract_excerpt":"Learning embeddings of entities and relations existing in knowledge bases allows the discovery of hidden patterns in data. In this work, we examine the geometrical space's contribution to the task of knowledge base completion. We focus on the family of translational models, whose performance has been lagging, and propose a model, dubbed HyperKG, which exploits the hyperbolic space in order to better reflect the topological properties of knowledge bases. We investigate the type of regularities that our model can capture and we show that it is a prominent candidate for effectively representing a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04895","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/1908.04895/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":"1908.04895","created_at":"2026-07-04T23:58:11.844591+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04895v2","created_at":"2026-07-04T23:58:11.844591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04895","created_at":"2026-07-04T23:58:11.844591+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMRBHRGMEKBZ","created_at":"2026-07-04T23:58:11.844591+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMRBHRGMEKBZW2HB","created_at":"2026-07-04T23:58:11.844591+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMRBHRGM","created_at":"2026-07-04T23:58:11.844591+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03612","citing_title":"Multi-Hop Reasoning for Question Answering with Hyperbolic Representations","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC","json":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC.json","graph_json":"https://pith.science/api/pith-number/VMRBHRGMEKBZW2HBGGO4ZHP6GC/graph.json","events_json":"https://pith.science/api/pith-number/VMRBHRGMEKBZW2HBGGO4ZHP6GC/events.json","paper":"https://pith.science/paper/VMRBHRGM"},"agent_actions":{"view_html":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC","download_json":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC.json","view_paper":"https://pith.science/paper/VMRBHRGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04895&json=true","fetch_graph":"https://pith.science/api/pith-number/VMRBHRGMEKBZW2HBGGO4ZHP6GC/graph.json","fetch_events":"https://pith.science/api/pith-number/VMRBHRGMEKBZW2HBGGO4ZHP6GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC/action/storage_attestation","attest_author":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC/action/author_attestation","sign_citation":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC/action/citation_signature","submit_replication":"https://pith.science/pith/VMRBHRGMEKBZW2HBGGO4ZHP6GC/action/replication_record"}},"created_at":"2026-07-04T23:58:11.844591+00:00","updated_at":"2026-07-04T23:58:11.844591+00:00"}