{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4WXHO35T5EVFP4AKRAERAUFPRA","short_pith_number":"pith:4WXHO35T","schema_version":"1.0","canonical_sha256":"e5ae776fb3e92a57f00a88091050af8834acd43b99cb7c4de601a0cf9b097fa8","source":{"kind":"arxiv","id":"2312.15883","version":2},"attestation_state":"computed","paper":{"title":"HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongxin Ding, Jinyi Tang, Junfeng Zhao, Rihong Qiu, Ruizhe Zhang, Xinke Jiang, Xu Chu, Yasha Wang, Yongxin Xu, Yue Fang, Zhiyuan Wang","submitted_at":"2023-12-26T04:49:56Z","abstract_excerpt":"In this paper, we investigate the retrieval-augmented generation (RAG) based on Knowledge Graphs (KGs) to improve the accuracy and reliability of Large Language Models (LLMs). Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization. To this end, we develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework, which leverages LLMs' powerful reasoning capacity to compensate for the incompleteness of user queries, optimizes the interaction process with LLMs, and provides diverse retrieved know"},"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":"2312.15883","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-26T04:49:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e775995d75db56e42663ad6a91003f155d4cacd09884cc89636631f701b9f058","abstract_canon_sha256":"8c005689068a95e4a2b914dab9a1b1891f27c0fa12f01fe3bbd7d05506543bfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:47.050990Z","signature_b64":"YeqBtnNglBYcncSSVTFTSzn+2nIzDqcgM6EBYoVGTkvgwAg9xejoxjxrc6+rK1NH2USG957SytZAHc7UhQLBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5ae776fb3e92a57f00a88091050af8834acd43b99cb7c4de601a0cf9b097fa8","last_reissued_at":"2026-07-05T08:09:47.050473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:47.050473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongxin Ding, Jinyi Tang, Junfeng Zhao, Rihong Qiu, Ruizhe Zhang, Xinke Jiang, Xu Chu, Yasha Wang, Yongxin Xu, Yue Fang, Zhiyuan Wang","submitted_at":"2023-12-26T04:49:56Z","abstract_excerpt":"In this paper, we investigate the retrieval-augmented generation (RAG) based on Knowledge Graphs (KGs) to improve the accuracy and reliability of Large Language Models (LLMs). Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization. To this end, we develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework, which leverages LLMs' powerful reasoning capacity to compensate for the incompleteness of user queries, optimizes the interaction process with LLMs, and provides diverse retrieved know"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15883","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/2312.15883/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":"2312.15883","created_at":"2026-07-05T08:09:47.050532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15883v2","created_at":"2026-07-05T08:09:47.050532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15883","created_at":"2026-07-05T08:09:47.050532+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WXHO35T5EVF","created_at":"2026-07-05T08:09:47.050532+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WXHO35T5EVFP4AK","created_at":"2026-07-05T08:09:47.050532+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WXHO35T","created_at":"2026-07-05T08:09:47.050532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09492","citing_title":"APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation","ref_index":62,"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":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA","json":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA.json","graph_json":"https://pith.science/api/pith-number/4WXHO35T5EVFP4AKRAERAUFPRA/graph.json","events_json":"https://pith.science/api/pith-number/4WXHO35T5EVFP4AKRAERAUFPRA/events.json","paper":"https://pith.science/paper/4WXHO35T"},"agent_actions":{"view_html":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA","download_json":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA.json","view_paper":"https://pith.science/paper/4WXHO35T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15883&json=true","fetch_graph":"https://pith.science/api/pith-number/4WXHO35T5EVFP4AKRAERAUFPRA/graph.json","fetch_events":"https://pith.science/api/pith-number/4WXHO35T5EVFP4AKRAERAUFPRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA/action/storage_attestation","attest_author":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA/action/author_attestation","sign_citation":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA/action/citation_signature","submit_replication":"https://pith.science/pith/4WXHO35T5EVFP4AKRAERAUFPRA/action/replication_record"}},"created_at":"2026-07-05T08:09:47.050532+00:00","updated_at":"2026-07-05T08:09:47.050532+00:00"}