{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UXVSPXOD6CGR4B3ANXNXJ5WMMA","short_pith_number":"pith:UXVSPXOD","schema_version":"1.0","canonical_sha256":"a5eb27ddc3f08d1e07606ddb74f6cc60374511b02f11aadcbd5473019bd5fbd4","source":{"kind":"arxiv","id":"2101.05151","version":3},"attestation_state":"computed","paper":{"title":"Temporal Knowledge Graph Forecasting with Neural ODE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Volker Tresp, Yujia Gu, Yunpu Ma, Zhen Han, Zifeng Ding","submitted_at":"2021-01-13T15:49:48Z","abstract_excerpt":"There has been an increasing interest in inferring future links on temporal knowledge graphs (KG). While links on temporal KGs vary continuously over time, the existing approaches model the temporal KGs in discrete state spaces. To this end, we propose a novel continuum model by extending the idea of neural ordinary differential equations (ODEs) to multi-relational graph convolutional networks. The proposed model preserves the continuous nature of dynamic multi-relational graph data and encodes both temporal and structural information into continuous-time dynamic embeddings. In addition, a nov"},"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":"2101.05151","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T15:49:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f4f2628bbb7dea6c372213c285da46603b8af458cb7e6a0dc78bae72bc77b27a","abstract_canon_sha256":"442ebafe70d8250a68e9b2ffa3d83e53f0c9b54c19378f922813f602b0ad0350"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:25.990362Z","signature_b64":"NYTD9+6PTVXph4VVLfPF3TH7/dPCGvEhBraqFkQctQTykDKjRGZKaN6gNQlcHVDlztVlw9bWeS2OIdM3mNOhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5eb27ddc3f08d1e07606ddb74f6cc60374511b02f11aadcbd5473019bd5fbd4","last_reissued_at":"2026-07-05T04:28:25.989944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:25.989944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Knowledge Graph Forecasting with Neural ODE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Volker Tresp, Yujia Gu, Yunpu Ma, Zhen Han, Zifeng Ding","submitted_at":"2021-01-13T15:49:48Z","abstract_excerpt":"There has been an increasing interest in inferring future links on temporal knowledge graphs (KG). While links on temporal KGs vary continuously over time, the existing approaches model the temporal KGs in discrete state spaces. To this end, we propose a novel continuum model by extending the idea of neural ordinary differential equations (ODEs) to multi-relational graph convolutional networks. The proposed model preserves the continuous nature of dynamic multi-relational graph data and encodes both temporal and structural information into continuous-time dynamic embeddings. In addition, a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05151","kind":"arxiv","version":3},"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/2101.05151/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":"2101.05151","created_at":"2026-07-05T04:28:25.989996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.05151v3","created_at":"2026-07-05T04:28:25.989996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05151","created_at":"2026-07-05T04:28:25.989996+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXVSPXOD6CGR","created_at":"2026-07-05T04:28:25.989996+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXVSPXOD6CGR4B3A","created_at":"2026-07-05T04:28:25.989996+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXVSPXOD","created_at":"2026-07-05T04:28:25.989996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07208","citing_title":"FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA","json":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA.json","graph_json":"https://pith.science/api/pith-number/UXVSPXOD6CGR4B3ANXNXJ5WMMA/graph.json","events_json":"https://pith.science/api/pith-number/UXVSPXOD6CGR4B3ANXNXJ5WMMA/events.json","paper":"https://pith.science/paper/UXVSPXOD"},"agent_actions":{"view_html":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA","download_json":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA.json","view_paper":"https://pith.science/paper/UXVSPXOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.05151&json=true","fetch_graph":"https://pith.science/api/pith-number/UXVSPXOD6CGR4B3ANXNXJ5WMMA/graph.json","fetch_events":"https://pith.science/api/pith-number/UXVSPXOD6CGR4B3ANXNXJ5WMMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA/action/storage_attestation","attest_author":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA/action/author_attestation","sign_citation":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA/action/citation_signature","submit_replication":"https://pith.science/pith/UXVSPXOD6CGR4B3ANXNXJ5WMMA/action/replication_record"}},"created_at":"2026-07-05T04:28:25.989996+00:00","updated_at":"2026-07-05T04:28:25.989996+00:00"}