{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ECHK722QPIQ4V4Z5AZOGZR2VER","short_pith_number":"pith:ECHK722Q","schema_version":"1.0","canonical_sha256":"208eafeb507a21caf33d065c6cc755246f79c5650b7641bbee79424fcdf7b0b9","source":{"kind":"arxiv","id":"2504.08893","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Graph-extended Retrieval Augmented Generation for Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jakub M. Tomczak, Jasper Linders","submitted_at":"2025-04-11T18:03:02Z","abstract_excerpt":"Large Language Models (LLMs) and Knowledge Graphs (KGs) offer a promising approach to robust and explainable Question Answering (QA). While LLMs excel at natural language understanding, they suffer from knowledge gaps and hallucinations. KGs provide structured knowledge but lack natural language interaction. Ideally, an AI system should be both robust to missing facts as well as easy to communicate with. This paper proposes such a system that integrates LLMs and KGs without requiring training, ensuring adaptability across different KGs with minimal human effort. The resulting approach can be c"},"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":"2504.08893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-11T18:03:02Z","cross_cats_sorted":[],"title_canon_sha256":"118dc59b4c24eed7bc4c514fcfc2a04685185385f423b573a06172b9ef21dda6","abstract_canon_sha256":"26b466ba9aaf7c6340189d9cc28b22fbd7aea7546d3e78956e658f9b5b4f8569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:01.130479Z","signature_b64":"OLRgs+zX7NAMlKQDEEgKl3zFDjuFSgNVu+9YBNKAsWda3rSRxVoKv4k+2SkXbcNslwom1KJY/Zn8IC9FVqaNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"208eafeb507a21caf33d065c6cc755246f79c5650b7641bbee79424fcdf7b0b9","last_reissued_at":"2026-07-05T10:48:01.130001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:01.130001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graph-extended Retrieval Augmented Generation for Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jakub M. Tomczak, Jasper Linders","submitted_at":"2025-04-11T18:03:02Z","abstract_excerpt":"Large Language Models (LLMs) and Knowledge Graphs (KGs) offer a promising approach to robust and explainable Question Answering (QA). While LLMs excel at natural language understanding, they suffer from knowledge gaps and hallucinations. KGs provide structured knowledge but lack natural language interaction. Ideally, an AI system should be both robust to missing facts as well as easy to communicate with. This paper proposes such a system that integrates LLMs and KGs without requiring training, ensuring adaptability across different KGs with minimal human effort. The resulting approach can be c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08893","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/2504.08893/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":"2504.08893","created_at":"2026-07-05T10:48:01.130052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08893v1","created_at":"2026-07-05T10:48:01.130052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08893","created_at":"2026-07-05T10:48:01.130052+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECHK722QPIQ4","created_at":"2026-07-05T10:48:01.130052+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECHK722QPIQ4V4Z5","created_at":"2026-07-05T10:48:01.130052+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECHK722Q","created_at":"2026-07-05T10:48:01.130052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22138","citing_title":"Efficient Agentic Reasoning Through Self-Regulated Simulative Planning","ref_index":107,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER","json":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER.json","graph_json":"https://pith.science/api/pith-number/ECHK722QPIQ4V4Z5AZOGZR2VER/graph.json","events_json":"https://pith.science/api/pith-number/ECHK722QPIQ4V4Z5AZOGZR2VER/events.json","paper":"https://pith.science/paper/ECHK722Q"},"agent_actions":{"view_html":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER","download_json":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER.json","view_paper":"https://pith.science/paper/ECHK722Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08893&json=true","fetch_graph":"https://pith.science/api/pith-number/ECHK722QPIQ4V4Z5AZOGZR2VER/graph.json","fetch_events":"https://pith.science/api/pith-number/ECHK722QPIQ4V4Z5AZOGZR2VER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER/action/storage_attestation","attest_author":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER/action/author_attestation","sign_citation":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER/action/citation_signature","submit_replication":"https://pith.science/pith/ECHK722QPIQ4V4Z5AZOGZR2VER/action/replication_record"}},"created_at":"2026-07-05T10:48:01.130052+00:00","updated_at":"2026-07-05T10:48:01.130052+00:00"}