{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HBSYJL46G5VBAJEPBR2U5KC6OU","short_pith_number":"pith:HBSYJL46","schema_version":"1.0","canonical_sha256":"386584af9e376a10248f0c754ea85e752996ba269d52d3da8f55c45d3a8d7b93","source":{"kind":"arxiv","id":"2311.17330","version":2},"attestation_state":"computed","paper":{"title":"Biomedical knowledge graph-optimized prompt generation for large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Rizk-Jackson, Braian Peetoom, Brett Smith, Catalina Villouta-Reyes, Charlotte A Nelson, Gabriel Cerono, John H Morris, Karthik Soman, Peter W Rose, Rabia E Akbas, Sergio E Baranzini, Sharat Israni, Sui Huang, Yongmei Shi","submitted_at":"2023-11-29T03:07:00Z","abstract_excerpt":"Large Language Models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains like biomedicine. Solutions such as pre-training and domain-specific fine-tuning add substantial computational overhead, requiring further domain expertise. Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) framework by leveraging a massive biomedical KG (SPOKE) with LLMs such as Llama-2-13b, GPT-3.5-Turbo and GPT-4, to generate meaningful biomedical text rooted in established knowledge. Compared to the exi"},"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":"2311.17330","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T03:07:00Z","cross_cats_sorted":[],"title_canon_sha256":"c6b6a76d72df89b505d09b9a993e1c45aa50ea6c524d2abb51843755ea204895","abstract_canon_sha256":"65beffc370b6a9eba328d8f6cf7dba877a3f491695e118654d4f175a12490d41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:46.495238Z","signature_b64":"I0+arnpLxbmrYP3d/290Ip3WfDeyagzqxiF9DSg6OYDk2fISlJbF05oyVWTA3NS6do0gA1YmxVUsdwPiIQP3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"386584af9e376a10248f0c754ea85e752996ba269d52d3da8f55c45d3a8d7b93","last_reissued_at":"2026-07-05T08:18:46.494726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:46.494726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Biomedical knowledge graph-optimized prompt generation for large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Rizk-Jackson, Braian Peetoom, Brett Smith, Catalina Villouta-Reyes, Charlotte A Nelson, Gabriel Cerono, John H Morris, Karthik Soman, Peter W Rose, Rabia E Akbas, Sergio E Baranzini, Sharat Israni, Sui Huang, Yongmei Shi","submitted_at":"2023-11-29T03:07:00Z","abstract_excerpt":"Large Language Models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains like biomedicine. Solutions such as pre-training and domain-specific fine-tuning add substantial computational overhead, requiring further domain expertise. Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) framework by leveraging a massive biomedical KG (SPOKE) with LLMs such as Llama-2-13b, GPT-3.5-Turbo and GPT-4, to generate meaningful biomedical text rooted in established knowledge. Compared to the exi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17330","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/2311.17330/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":"2311.17330","created_at":"2026-07-05T08:18:46.494791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17330v2","created_at":"2026-07-05T08:18:46.494791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17330","created_at":"2026-07-05T08:18:46.494791+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBSYJL46G5VB","created_at":"2026-07-05T08:18:46.494791+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBSYJL46G5VBAJEP","created_at":"2026-07-05T08:18:46.494791+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBSYJL46","created_at":"2026-07-05T08:18:46.494791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06003","citing_title":"Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21974","citing_title":"Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU","json":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU.json","graph_json":"https://pith.science/api/pith-number/HBSYJL46G5VBAJEPBR2U5KC6OU/graph.json","events_json":"https://pith.science/api/pith-number/HBSYJL46G5VBAJEPBR2U5KC6OU/events.json","paper":"https://pith.science/paper/HBSYJL46"},"agent_actions":{"view_html":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU","download_json":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU.json","view_paper":"https://pith.science/paper/HBSYJL46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17330&json=true","fetch_graph":"https://pith.science/api/pith-number/HBSYJL46G5VBAJEPBR2U5KC6OU/graph.json","fetch_events":"https://pith.science/api/pith-number/HBSYJL46G5VBAJEPBR2U5KC6OU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/action/storage_attestation","attest_author":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/action/author_attestation","sign_citation":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/action/citation_signature","submit_replication":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/action/replication_record"}},"created_at":"2026-07-05T08:18:46.494791+00:00","updated_at":"2026-07-05T08:18:46.494791+00:00"}