{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5PEJ5ZZXHXBDGEXWSKPDLUMQTG","short_pith_number":"pith:5PEJ5ZZX","schema_version":"1.0","canonical_sha256":"ebc89ee7373dc23312f6929e35d190999f37711ed79008e5c3e8c37fa31f9088","source":{"kind":"arxiv","id":"1808.07018","version":5},"attestation_state":"computed","paper":{"title":"Hypernetwork Knowledge Graph Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carl Allen, Ivana Bala\\v{z}evi\\'c, Timothy M. Hospedales","submitted_at":"2018-08-21T17:05:28Z","abstract_excerpt":"Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness. Inferring missing relations (links) between entities (nodes) is the task of link prediction. A recent state-of-the-art approach to link prediction, ConvE, implements a convolutional neural network to extract features from concatenated subject and relation vectors. Whilst results are impressive, the method is unintuitive and poorly understood. We propose a hypernetwork architecture that generates simplified relation-specific convolutional filters that (i) outperforms ConvE and"},"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":"1808.07018","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-21T17:05:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"59598e49901d8fa684eeda2da155062b0f9c86824da7e4e853505ca7609d1c89","abstract_canon_sha256":"cc3b9543914da376b6f3082e851e974b1fc8ad4dd70600e5c7c247c521ecb948"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:54.071391Z","signature_b64":"8sldH6sJfMlWjiBEwbJz6WnXqDEqoLEe37lUtas2S4vIUU7KeWAYxg0f2E2MeFI7+O4s/9mwu4uVZsKMXCw8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebc89ee7373dc23312f6929e35d190999f37711ed79008e5c3e8c37fa31f9088","last_reissued_at":"2026-07-05T00:03:54.070849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:54.070849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypernetwork Knowledge Graph Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carl Allen, Ivana Bala\\v{z}evi\\'c, Timothy M. Hospedales","submitted_at":"2018-08-21T17:05:28Z","abstract_excerpt":"Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness. Inferring missing relations (links) between entities (nodes) is the task of link prediction. A recent state-of-the-art approach to link prediction, ConvE, implements a convolutional neural network to extract features from concatenated subject and relation vectors. Whilst results are impressive, the method is unintuitive and poorly understood. We propose a hypernetwork architecture that generates simplified relation-specific convolutional filters that (i) outperforms ConvE and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07018","kind":"arxiv","version":5},"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/1808.07018/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":"1808.07018","created_at":"2026-07-05T00:03:54.070903+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.07018v5","created_at":"2026-07-05T00:03:54.070903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07018","created_at":"2026-07-05T00:03:54.070903+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PEJ5ZZXHXBD","created_at":"2026-07-05T00:03:54.070903+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PEJ5ZZXHXBDGEXW","created_at":"2026-07-05T00:03:54.070903+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PEJ5ZZX","created_at":"2026-07-05T00:03:54.070903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.03143","citing_title":"Diachronic Embedding for Temporal Knowledge Graph Completion","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG","json":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG.json","graph_json":"https://pith.science/api/pith-number/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/graph.json","events_json":"https://pith.science/api/pith-number/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/events.json","paper":"https://pith.science/paper/5PEJ5ZZX"},"agent_actions":{"view_html":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG","download_json":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG.json","view_paper":"https://pith.science/paper/5PEJ5ZZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.07018&json=true","fetch_graph":"https://pith.science/api/pith-number/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/graph.json","fetch_events":"https://pith.science/api/pith-number/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/action/storage_attestation","attest_author":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/action/author_attestation","sign_citation":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/action/citation_signature","submit_replication":"https://pith.science/pith/5PEJ5ZZXHXBDGEXWSKPDLUMQTG/action/replication_record"}},"created_at":"2026-07-05T00:03:54.070903+00:00","updated_at":"2026-07-05T00:03:54.070903+00:00"}