{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6ZDNEEC7GWF64XRRUDFJHEXSQO","short_pith_number":"pith:6ZDNEEC7","schema_version":"1.0","canonical_sha256":"f646d2105f358bee5e31a0ca9392f283b464b2454cea1bf5912aa5d2b640e2b2","source":{"kind":"arxiv","id":"2506.06367","version":1},"attestation_state":"computed","paper":{"title":"Towards Foundation Model on Temporal Knowledge Graph Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng cheng, Daniel Hernandez, Jiaxin Pan, Mojtaba Nayyeri, Osama Mohammed, Rongchuan Zhang, Steffen Staab","submitted_at":"2025-06-04T09:19:49Z","abstract_excerpt":"Temporal Knowledge Graphs (TKGs) store temporal facts with quadruple formats (s, p, o, t). Existing Temporal Knowledge Graph Embedding (TKGE) models perform link prediction tasks in transductive or semi-inductive settings, which means the entities, relations, and temporal information in the test graph are fully or partially observed during training. Such reliance on seen elements during inference limits the models' ability to transfer to new domains and generalize to real-world scenarios. A central limitation is the difficulty in learning representations for entities, relations, and timestamps"},"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":"2506.06367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-04T09:19:49Z","cross_cats_sorted":[],"title_canon_sha256":"0fe8a1eef2753e684c04d8acf7a18bf590921835010692821aed540a15db56a3","abstract_canon_sha256":"7367f49ca58507beafa2135d84534f27d61d3619fb84da2c59366b741e1df301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:49.020974Z","signature_b64":"cVA9F3matni9xgBCjWH0ODNS9bX84gWMVgrOzJgOiqMSh5sIitgkzAe/qyaUO1EXaZaXIBeGM54H3JNMP0K6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f646d2105f358bee5e31a0ca9392f283b464b2454cea1bf5912aa5d2b640e2b2","last_reissued_at":"2026-07-05T11:17:49.020490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:49.020490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Foundation Model on Temporal Knowledge Graph Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng cheng, Daniel Hernandez, Jiaxin Pan, Mojtaba Nayyeri, Osama Mohammed, Rongchuan Zhang, Steffen Staab","submitted_at":"2025-06-04T09:19:49Z","abstract_excerpt":"Temporal Knowledge Graphs (TKGs) store temporal facts with quadruple formats (s, p, o, t). Existing Temporal Knowledge Graph Embedding (TKGE) models perform link prediction tasks in transductive or semi-inductive settings, which means the entities, relations, and temporal information in the test graph are fully or partially observed during training. Such reliance on seen elements during inference limits the models' ability to transfer to new domains and generalize to real-world scenarios. A central limitation is the difficulty in learning representations for entities, relations, and timestamps"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06367","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/2506.06367/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":"2506.06367","created_at":"2026-07-05T11:17:49.020548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06367v1","created_at":"2026-07-05T11:17:49.020548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06367","created_at":"2026-07-05T11:17:49.020548+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZDNEEC7GWF6","created_at":"2026-07-05T11:17:49.020548+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZDNEEC7GWF64XRR","created_at":"2026-07-05T11:17:49.020548+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZDNEEC7","created_at":"2026-07-05T11:17:49.020548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10164","citing_title":"Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07121","citing_title":"AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO","json":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO.json","graph_json":"https://pith.science/api/pith-number/6ZDNEEC7GWF64XRRUDFJHEXSQO/graph.json","events_json":"https://pith.science/api/pith-number/6ZDNEEC7GWF64XRRUDFJHEXSQO/events.json","paper":"https://pith.science/paper/6ZDNEEC7"},"agent_actions":{"view_html":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO","download_json":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO.json","view_paper":"https://pith.science/paper/6ZDNEEC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06367&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZDNEEC7GWF64XRRUDFJHEXSQO/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZDNEEC7GWF64XRRUDFJHEXSQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO/action/storage_attestation","attest_author":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO/action/author_attestation","sign_citation":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO/action/citation_signature","submit_replication":"https://pith.science/pith/6ZDNEEC7GWF64XRRUDFJHEXSQO/action/replication_record"}},"created_at":"2026-07-05T11:17:49.020548+00:00","updated_at":"2026-07-05T11:17:49.020548+00:00"}