{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MKXRDZNB6U4QJACLNH44ISKBOF","short_pith_number":"pith:MKXRDZNB","schema_version":"1.0","canonical_sha256":"62af11e5a1f53904804b69f9c44941717692fe5d6134a7dec71d1ed1f65eff0c","source":{"kind":"arxiv","id":"2012.10595","version":1},"attestation_state":"computed","paper":{"title":"T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jaehun Jung, Jinhong Jung, U Kang","submitted_at":"2020-12-19T04:45:32Z","abstract_excerpt":"Temporal knowledge graphs (TKGs) inherently reflect the transient nature of real-world knowledge, as opposed to static knowledge graphs. Naturally, automatic TKG completion has drawn much research interests for a more realistic modeling of relational reasoning. However, most of the existing mod-els for TKG completion extend static KG embeddings that donot fully exploit TKG structure, thus lacking in 1) account-ing for temporally relevant events already residing in the lo-cal neighborhood of a query, and 2) path-based inference that facilitates multi-hop reasoning and better interpretability. I"},"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":"2012.10595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-19T04:45:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8aae914e7a5896341c366fb4c37ba3b88d3efd37fe83a9ce8bc3f9fae3a8334b","abstract_canon_sha256":"0aebcdb1a17d39ef90a3d27fb30a85f0fe35f09decfe41b680bb556c71f06d04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:53.534512Z","signature_b64":"q5c9FAS9r+h/b4LuppqZ2KWrKMIoeWKi0O6HuRAmEhX1ecToIHLyPwAYlKESEGmCackEw1goq36tpq+fBSqeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62af11e5a1f53904804b69f9c44941717692fe5d6134a7dec71d1ed1f65eff0c","last_reissued_at":"2026-07-05T02:00:53.534111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:53.534111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jaehun Jung, Jinhong Jung, U Kang","submitted_at":"2020-12-19T04:45:32Z","abstract_excerpt":"Temporal knowledge graphs (TKGs) inherently reflect the transient nature of real-world knowledge, as opposed to static knowledge graphs. Naturally, automatic TKG completion has drawn much research interests for a more realistic modeling of relational reasoning. However, most of the existing mod-els for TKG completion extend static KG embeddings that donot fully exploit TKG structure, thus lacking in 1) account-ing for temporally relevant events already residing in the lo-cal neighborhood of a query, and 2) path-based inference that facilitates multi-hop reasoning and better interpretability. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10595","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/2012.10595/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":"2012.10595","created_at":"2026-07-05T02:00:53.534171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.10595v1","created_at":"2026-07-05T02:00:53.534171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10595","created_at":"2026-07-05T02:00:53.534171+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKXRDZNB6U4Q","created_at":"2026-07-05T02:00:53.534171+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKXRDZNB6U4QJACL","created_at":"2026-07-05T02:00:53.534171+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKXRDZNB","created_at":"2026-07-05T02:00:53.534171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11803","citing_title":"VITA: Versatile Time Representation Learning for Temporal Hyper-Relational Knowledge Graphs","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF","json":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF.json","graph_json":"https://pith.science/api/pith-number/MKXRDZNB6U4QJACLNH44ISKBOF/graph.json","events_json":"https://pith.science/api/pith-number/MKXRDZNB6U4QJACLNH44ISKBOF/events.json","paper":"https://pith.science/paper/MKXRDZNB"},"agent_actions":{"view_html":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF","download_json":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF.json","view_paper":"https://pith.science/paper/MKXRDZNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.10595&json=true","fetch_graph":"https://pith.science/api/pith-number/MKXRDZNB6U4QJACLNH44ISKBOF/graph.json","fetch_events":"https://pith.science/api/pith-number/MKXRDZNB6U4QJACLNH44ISKBOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF/action/storage_attestation","attest_author":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF/action/author_attestation","sign_citation":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF/action/citation_signature","submit_replication":"https://pith.science/pith/MKXRDZNB6U4QJACLNH44ISKBOF/action/replication_record"}},"created_at":"2026-07-05T02:00:53.534171+00:00","updated_at":"2026-07-05T02:00:53.534171+00:00"}