{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FUZSDMGCB3CXCNDGUG6NRIR43P","short_pith_number":"pith:FUZSDMGC","schema_version":"1.0","canonical_sha256":"2d3321b0c20ec5713466a1bcd8a23cdbca2e150ab336fea0338d92bc016468e8","source":{"kind":"arxiv","id":"2408.00727","version":3},"attestation_state":"computed","paper":{"title":"Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aidong Zhang, Guangzhi Xiong, Minjia Zhang, Qiao Jin, Xiao Wang, Zhiyong Lu","submitted_at":"2024-08-01T17:18:17Z","abstract_excerpt":"The emergent abilities of large language models (LLMs) have demonstrated great potential in solving medical questions. They can possess considerable medical knowledge, but may still hallucinate and are inflexible in the knowledge updates. While Retrieval-Augmented Generation (RAG) has been proposed to enhance the medical question-answering capabilities of LLMs with external knowledge bases, it may still fail in complex cases where multiple rounds of information-seeking are required. To address such an issue, we propose iterative RAG for medicine (i-MedRAG), where LLMs can iteratively ask follo"},"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":"2408.00727","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-01T17:18:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac541152285ab260aa42c1f79895c45ecdb1ae150ba18c58708f10f7a67fc138","abstract_canon_sha256":"1e20a7baf2caeffa91b44c96d3572ef48ed606875168e8dd2f34fe8ae95843d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:53.571870Z","signature_b64":"R6NHsx/Pv5P0WEWA5kr6o7fuHjeHUNvmkDidtH4IVptauB93pYL1S0SG+O63x2p1bzZb3Bd4bpIGEiz0uujZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3321b0c20ec5713466a1bcd8a23cdbca2e150ab336fea0338d92bc016468e8","last_reissued_at":"2026-07-05T09:18:53.571401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:53.571401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aidong Zhang, Guangzhi Xiong, Minjia Zhang, Qiao Jin, Xiao Wang, Zhiyong Lu","submitted_at":"2024-08-01T17:18:17Z","abstract_excerpt":"The emergent abilities of large language models (LLMs) have demonstrated great potential in solving medical questions. They can possess considerable medical knowledge, but may still hallucinate and are inflexible in the knowledge updates. While Retrieval-Augmented Generation (RAG) has been proposed to enhance the medical question-answering capabilities of LLMs with external knowledge bases, it may still fail in complex cases where multiple rounds of information-seeking are required. To address such an issue, we propose iterative RAG for medicine (i-MedRAG), where LLMs can iteratively ask follo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00727","kind":"arxiv","version":3},"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/2408.00727/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":"2408.00727","created_at":"2026-07-05T09:18:53.571457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00727v3","created_at":"2026-07-05T09:18:53.571457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00727","created_at":"2026-07-05T09:18:53.571457+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUZSDMGCB3CX","created_at":"2026-07-05T09:18:53.571457+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUZSDMGCB3CXCNDG","created_at":"2026-07-05T09:18:53.571457+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUZSDMGC","created_at":"2026-07-05T09:18:53.571457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P","json":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P.json","graph_json":"https://pith.science/api/pith-number/FUZSDMGCB3CXCNDGUG6NRIR43P/graph.json","events_json":"https://pith.science/api/pith-number/FUZSDMGCB3CXCNDGUG6NRIR43P/events.json","paper":"https://pith.science/paper/FUZSDMGC"},"agent_actions":{"view_html":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P","download_json":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P.json","view_paper":"https://pith.science/paper/FUZSDMGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00727&json=true","fetch_graph":"https://pith.science/api/pith-number/FUZSDMGCB3CXCNDGUG6NRIR43P/graph.json","fetch_events":"https://pith.science/api/pith-number/FUZSDMGCB3CXCNDGUG6NRIR43P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P/action/storage_attestation","attest_author":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P/action/author_attestation","sign_citation":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P/action/citation_signature","submit_replication":"https://pith.science/pith/FUZSDMGCB3CXCNDGUG6NRIR43P/action/replication_record"}},"created_at":"2026-07-05T09:18:53.571457+00:00","updated_at":"2026-07-05T09:18:53.571457+00:00"}