{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R32M5TEC5NYPL3SLJIPPDTQZQ2","short_pith_number":"pith:R32M5TEC","schema_version":"1.0","canonical_sha256":"8ef4cecc82eb70f5ee4b4a1ef1ce198688903ee20e220345b6ae49cc6ce5597d","source":{"kind":"arxiv","id":"2410.12288","version":1},"attestation_state":"computed","paper":{"title":"A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Wei Hu, Yuanning Cui, Zequn Sun","submitted_at":"2024-10-16T06:47:18Z","abstract_excerpt":"Extensive knowledge graphs (KGs) have been constructed to facilitate knowledge-driven tasks across various scenarios. However, existing work usually develops separate reasoning models for different KGs, lacking the ability to generalize and transfer knowledge across diverse KGs and reasoning settings. In this paper, we propose a prompt-based KG foundation model via in-context learning, namely KG-ICL, to achieve a universal reasoning ability. Specifically, we introduce a prompt graph centered with a query-related example fact as context to understand the query relation. To encode prompt graphs "},"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":"2410.12288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T06:47:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dc22d332c591f5c1b2fcc5dcac9c0a3f02d848e38635fd14053ea27662198614","abstract_canon_sha256":"781b6d8d1ed1635779e7cfc11be217b773a6502a2b3a3600599ecc003f82391d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:17.183125Z","signature_b64":"2JRshe6LxijRrNYt20IuwbXmLOdNxHV4msbIvEbO1IrAjZOX8Uc4T5qyzBYrZC7J2fyTNPtsxUnQ73zL7tuhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ef4cecc82eb70f5ee4b4a1ef1ce198688903ee20e220345b6ae49cc6ce5597d","last_reissued_at":"2026-07-05T09:21:17.182655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:17.182655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Wei Hu, Yuanning Cui, Zequn Sun","submitted_at":"2024-10-16T06:47:18Z","abstract_excerpt":"Extensive knowledge graphs (KGs) have been constructed to facilitate knowledge-driven tasks across various scenarios. However, existing work usually develops separate reasoning models for different KGs, lacking the ability to generalize and transfer knowledge across diverse KGs and reasoning settings. In this paper, we propose a prompt-based KG foundation model via in-context learning, namely KG-ICL, to achieve a universal reasoning ability. Specifically, we introduce a prompt graph centered with a query-related example fact as context to understand the query relation. To encode prompt graphs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12288","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/2410.12288/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":"2410.12288","created_at":"2026-07-05T09:21:17.182709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12288v1","created_at":"2026-07-05T09:21:17.182709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12288","created_at":"2026-07-05T09:21:17.182709+00:00"},{"alias_kind":"pith_short_12","alias_value":"R32M5TEC5NYP","created_at":"2026-07-05T09:21:17.182709+00:00"},{"alias_kind":"pith_short_16","alias_value":"R32M5TEC5NYPL3SL","created_at":"2026-07-05T09:21:17.182709+00:00"},{"alias_kind":"pith_short_8","alias_value":"R32M5TEC","created_at":"2026-07-05T09:21:17.182709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15755","citing_title":"GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2","json":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2.json","graph_json":"https://pith.science/api/pith-number/R32M5TEC5NYPL3SLJIPPDTQZQ2/graph.json","events_json":"https://pith.science/api/pith-number/R32M5TEC5NYPL3SLJIPPDTQZQ2/events.json","paper":"https://pith.science/paper/R32M5TEC"},"agent_actions":{"view_html":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2","download_json":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2.json","view_paper":"https://pith.science/paper/R32M5TEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12288&json=true","fetch_graph":"https://pith.science/api/pith-number/R32M5TEC5NYPL3SLJIPPDTQZQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/R32M5TEC5NYPL3SLJIPPDTQZQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2/action/storage_attestation","attest_author":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2/action/author_attestation","sign_citation":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2/action/citation_signature","submit_replication":"https://pith.science/pith/R32M5TEC5NYPL3SLJIPPDTQZQ2/action/replication_record"}},"created_at":"2026-07-05T09:21:17.182709+00:00","updated_at":"2026-07-05T09:21:17.182709+00:00"}