{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ET6JAOFON2PIS3QQLKE34ACWHQ","short_pith_number":"pith:ET6JAOFO","schema_version":"1.0","canonical_sha256":"24fc9038ae6e9e896e105a89be00563c1c1a41f3fa7d03f96e2f8ea2e9e86670","source":{"kind":"arxiv","id":"2310.04562","version":2},"attestation_state":"computed","paper":{"title":"Towards Foundation Models for Knowledge Graph Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hesham Mostafa, Jian Tang, Mikhail Galkin, Xinyu Yuan, Zhaocheng Zhu","submitted_at":"2023-10-06T20:00:07Z","abstract_excerpt":"Foundation models in language and vision have the ability to run inference on any textual and visual inputs thanks to the transferable representations such as a vocabulary of tokens in language. Knowledge graphs (KGs) have different entity and relation vocabularies that generally do not overlap. The key challenge of designing foundation models on KGs is to learn such transferable representations that enable inference on any graph with arbitrary entity and relation vocabularies. In this work, we make a step towards such foundation models and present ULTRA, an approach for learning universal 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":"2310.04562","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-06T20:00:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"348dbe95002008027e2248bce0f178a04f32d33a0fddbe1c876e8fd3dc65bd26","abstract_canon_sha256":"0841b90d6f4ca02f81e714502c70a6330bcff46563a3ab5dac567fb96ee451dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:11.512151Z","signature_b64":"yLPKL04hYe/xJRV34pltOm6Q+tSRAtZfL7fS6p4CXcKILQt376JpjjkEz0+VaqEPdO0qqK3GOKyHVQRuoXdXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24fc9038ae6e9e896e105a89be00563c1c1a41f3fa7d03f96e2f8ea2e9e86670","last_reissued_at":"2026-07-05T08:06:11.511694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:11.511694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Foundation Models for Knowledge Graph Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hesham Mostafa, Jian Tang, Mikhail Galkin, Xinyu Yuan, Zhaocheng Zhu","submitted_at":"2023-10-06T20:00:07Z","abstract_excerpt":"Foundation models in language and vision have the ability to run inference on any textual and visual inputs thanks to the transferable representations such as a vocabulary of tokens in language. Knowledge graphs (KGs) have different entity and relation vocabularies that generally do not overlap. The key challenge of designing foundation models on KGs is to learn such transferable representations that enable inference on any graph with arbitrary entity and relation vocabularies. In this work, we make a step towards such foundation models and present ULTRA, an approach for learning universal and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04562","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/2310.04562/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":"2310.04562","created_at":"2026-07-05T08:06:11.511751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04562v2","created_at":"2026-07-05T08:06:11.511751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04562","created_at":"2026-07-05T08:06:11.511751+00:00"},{"alias_kind":"pith_short_12","alias_value":"ET6JAOFON2PI","created_at":"2026-07-05T08:06:11.511751+00:00"},{"alias_kind":"pith_short_16","alias_value":"ET6JAOFON2PIS3QQ","created_at":"2026-07-05T08:06:11.511751+00:00"},{"alias_kind":"pith_short_8","alias_value":"ET6JAOFO","created_at":"2026-07-05T08:06:11.511751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07422","citing_title":"InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14907","citing_title":"KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04244","citing_title":"GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06154","citing_title":"Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ","json":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ.json","graph_json":"https://pith.science/api/pith-number/ET6JAOFON2PIS3QQLKE34ACWHQ/graph.json","events_json":"https://pith.science/api/pith-number/ET6JAOFON2PIS3QQLKE34ACWHQ/events.json","paper":"https://pith.science/paper/ET6JAOFO"},"agent_actions":{"view_html":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ","download_json":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ.json","view_paper":"https://pith.science/paper/ET6JAOFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04562&json=true","fetch_graph":"https://pith.science/api/pith-number/ET6JAOFON2PIS3QQLKE34ACWHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ET6JAOFON2PIS3QQLKE34ACWHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ/action/storage_attestation","attest_author":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ/action/author_attestation","sign_citation":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ/action/citation_signature","submit_replication":"https://pith.science/pith/ET6JAOFON2PIS3QQLKE34ACWHQ/action/replication_record"}},"created_at":"2026-07-05T08:06:11.511751+00:00","updated_at":"2026-07-05T08:06:11.511751+00:00"}