{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5QTTARYPJKOMIPN7PW55M3SDS3","short_pith_number":"pith:5QTTARYP","schema_version":"1.0","canonical_sha256":"ec2730470f4a9cc43dbf7dbbd66e4396cc8ec6e44c7530053aeb749fc150d7c2","source":{"kind":"arxiv","id":"2605.14907","version":1},"attestation_state":"computed","paper":{"title":"KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haoyu Huang, Hong Ting Tsang, Jiaxin Bai, Sirui Han, Yangqiu Song, Yisen Gao, Yufei Li, Zhongwei Xie","submitted_at":"2026-05-14T14:41:19Z","abstract_excerpt":"Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure. However, most existing methods primarily emphasize relation-level universality, while in-context learning, the other pillar of foundation models remains under-explored for KG reasoning. In KGs, context is inherently structured and heterogeneous: effective prediction requires conditioning on the local context around the query entities as well as the global context that summarizes how a relation behaves across many instances. We propose KGPFN, a"},"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":"2605.14907","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T14:41:19Z","cross_cats_sorted":[],"title_canon_sha256":"b6b62a2eb5cf8c23222ac7d7c2489e1ef023743db9d41f807e4757ac6f72eafc","abstract_canon_sha256":"d76399b0f379d40713dc1a320f823be502644081dbe1cfc4f3a01a018e5d8355"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:55.804339Z","signature_b64":"l/G+MoxH5GgnxxsbU8Ja/+xnk9zAz4H97k9VdEsO/PzkdO9OMjZilknoYq+c8nk4OHZmaHjydqnfRGSTs59YCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2730470f4a9cc43dbf7dbbd66e4396cc8ec6e44c7530053aeb749fc150d7c2","last_reissued_at":"2026-05-17T23:38:55.803745Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:55.803745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haoyu Huang, Hong Ting Tsang, Jiaxin Bai, Sirui Han, Yangqiu Song, Yisen Gao, Yufei Li, Zhongwei Xie","submitted_at":"2026-05-14T14:41:19Z","abstract_excerpt":"Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure. However, most existing methods primarily emphasize relation-level universality, while in-context learning, the other pillar of foundation models remains under-explored for KG reasoning. In KGs, context is inherently structured and heterogeneous: effective prediction requires conditioning on the local context around the query entities as well as the global context that summarizes how a relation behaves across many instances. We propose KGPFN, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14907","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":""},"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":"2605.14907","created_at":"2026-05-17T23:38:55.803856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14907v1","created_at":"2026-05-17T23:38:55.803856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14907","created_at":"2026-05-17T23:38:55.803856+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QTTARYPJKOM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QTTARYPJKOMIPN7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QTTARYP","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3","json":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3.json","graph_json":"https://pith.science/api/pith-number/5QTTARYPJKOMIPN7PW55M3SDS3/graph.json","events_json":"https://pith.science/api/pith-number/5QTTARYPJKOMIPN7PW55M3SDS3/events.json","paper":"https://pith.science/paper/5QTTARYP"},"agent_actions":{"view_html":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3","download_json":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3.json","view_paper":"https://pith.science/paper/5QTTARYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14907&json=true","fetch_graph":"https://pith.science/api/pith-number/5QTTARYPJKOMIPN7PW55M3SDS3/graph.json","fetch_events":"https://pith.science/api/pith-number/5QTTARYPJKOMIPN7PW55M3SDS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3/action/storage_attestation","attest_author":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3/action/author_attestation","sign_citation":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3/action/citation_signature","submit_replication":"https://pith.science/pith/5QTTARYPJKOMIPN7PW55M3SDS3/action/replication_record"}},"created_at":"2026-05-17T23:38:55.803856+00:00","updated_at":"2026-05-17T23:38:55.803856+00:00"}