{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HBSYJL46G5VBAJEPBR2U5KC6OU","short_pith_number":"pith:HBSYJL46","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"},"canonical_sha256":"386584af9e376a10248f0c754ea85e752996ba269d52d3da8f55c45d3a8d7b93","source":{"kind":"arxiv","id":"2311.17330","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17330","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17330v2","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17330","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"HBSYJL46G5VB","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"HBSYJL46G5VBAJEP","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"HBSYJL46","created_at":"2026-07-05T08:18:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HBSYJL46G5VBAJEPBR2U5KC6OU","target":"record","payload":{"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"},"canonical_sha256":"386584af9e376a10248f0c754ea85e752996ba269d52d3da8f55c45d3a8d7b93","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"},"source_kind":"arxiv","source_id":"2311.17330","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FmEAqQCzVNkMkO0Knlb/IKuSgoUqt34gR1rL4aDGYMviLxrbRHj+6PiM7npDh4s7CJhFm/to8Y5I6GTGBFYCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:34:25.836495Z"},"content_sha256":"e0789e7e6ac7150da1c160ed9969d52fc17745edd7280eb452f5449087f4a5ab","schema_version":"1.0","event_id":"sha256:e0789e7e6ac7150da1c160ed9969d52fc17745edd7280eb452f5449087f4a5ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HBSYJL46G5VBAJEPBR2U5KC6OU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XM74emEA8jzF3FYtT82mwqJrhhLttQQwHfJ/EDATFqvsN2sKjL7a5S1Yh01iWElAv0dW1jV8H9z8rA8VmQbbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:34:25.837013Z"},"content_sha256":"cc1477d7a58229f17698d198b5194c8ff3a9031aa4c7409de245dc54d1af77c5","schema_version":"1.0","event_id":"sha256:cc1477d7a58229f17698d198b5194c8ff3a9031aa4c7409de245dc54d1af77c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/bundle.json","state_url":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T01:34:25Z","links":{"resolver":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU","bundle":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/bundle.json","state":"https://pith.science/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HBSYJL46G5VBAJEPBR2U5KC6OU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HBSYJL46G5VBAJEPBR2U5KC6OU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"65beffc370b6a9eba328d8f6cf7dba877a3f491695e118654d4f175a12490d41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T03:07:00Z","title_canon_sha256":"c6b6a76d72df89b505d09b9a993e1c45aa50ea6c524d2abb51843755ea204895"},"schema_version":"1.0","source":{"id":"2311.17330","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17330","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17330v2","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17330","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"HBSYJL46G5VB","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"HBSYJL46G5VBAJEP","created_at":"2026-07-05T08:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"HBSYJL46","created_at":"2026-07-05T08:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:cc1477d7a58229f17698d198b5194c8ff3a9031aa4c7409de245dc54d1af77c5","target":"graph","created_at":"2026-07-05T08:18:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.17330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T03:07:00Z","title":"Biomedical knowledge graph-optimized prompt generation for large language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17330","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e0789e7e6ac7150da1c160ed9969d52fc17745edd7280eb452f5449087f4a5ab","target":"record","created_at":"2026-07-05T08:18:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"65beffc370b6a9eba328d8f6cf7dba877a3f491695e118654d4f175a12490d41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T03:07:00Z","title_canon_sha256":"c6b6a76d72df89b505d09b9a993e1c45aa50ea6c524d2abb51843755ea204895"},"schema_version":"1.0","source":{"id":"2311.17330","kind":"arxiv","version":2}},"canonical_sha256":"386584af9e376a10248f0c754ea85e752996ba269d52d3da8f55c45d3a8d7b93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"386584af9e376a10248f0c754ea85e752996ba269d52d3da8f55c45d3a8d7b93","first_computed_at":"2026-07-05T08:18:46.494726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:46.494726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I0+arnpLxbmrYP3d/290Ip3WfDeyagzqxiF9DSg6OYDk2fISlJbF05oyVWTA3NS6do0gA1YmxVUsdwPiIQP3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:46.495238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17330","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0789e7e6ac7150da1c160ed9969d52fc17745edd7280eb452f5449087f4a5ab","sha256:cc1477d7a58229f17698d198b5194c8ff3a9031aa4c7409de245dc54d1af77c5"],"state_sha256":"f15f65aa243405e8e255abe765488af7d80bb159339c3de28edca7e6440b100b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JzN0TTFFe3EvQAXBnIuz88lO2viCWvsbEb422msV1H/L2hDChMmcLoahMWDYPWsLMnQ7n69iIUiZ2A/daYAZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:34:25.844241Z","bundle_sha256":"4030d652b1fb1f4838618c72297682f4b95320d8ddabd124722bc1ae4e816565"}}