{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:77OJZXESYV3VKE5M4GJDTHVXX4","short_pith_number":"pith:77OJZXES","schema_version":"1.0","canonical_sha256":"ffdc9cdc92c5775513ace192399eb7bf3f93cde3c822afd8982fe6ce2ae503eb","source":{"kind":"arxiv","id":"2505.19538","version":1},"attestation_state":"computed","paper":{"title":"DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.IR","cs.MA"],"primary_cat":"cs.CL","authors_text":"Gecheng Fu, Jinzhuo Wang, Sin Yee Goi, Wei Wu, Xukai Zhao, Yuxing Lu","submitted_at":"2025-05-26T05:56:23Z","abstract_excerpt":"Existing medical RAG systems mainly leverage knowledge from medical knowledge bases, neglecting the crucial role of experiential knowledge derived from similar patient cases -- a key component of human clinical reasoning. To bridge this gap, we propose DoctorRAG, a RAG framework that emulates doctor-like reasoning by integrating both explicit clinical knowledge and implicit case-based experience. DoctorRAG enhances retrieval precision by first allocating conceptual tags for queries and knowledge sources, together with a hybrid retrieval mechanism from both relevant knowledge and patient. In ad"},"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":"2505.19538","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T05:56:23Z","cross_cats_sorted":["cs.AI","cs.CE","cs.IR","cs.MA"],"title_canon_sha256":"e08aefb410632e3e51ecac266f3eba11ec495a319051db88c1cdd50ef52e4b3d","abstract_canon_sha256":"17cece4c701b81e178fe1ea5a7a6073ff72e055ca2ce921179e1d5870218b334"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:32.001060Z","signature_b64":"TAFnDE56+9k94tOxVUOMW9M90gguvFIJMRNrdBzLHI53OrLxhEWpvs/CCf6AUYh+5+8C0nysPPVKgtU0/y0GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffdc9cdc92c5775513ace192399eb7bf3f93cde3c822afd8982fe6ce2ae503eb","last_reissued_at":"2026-07-05T11:09:32.000551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:32.000551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.IR","cs.MA"],"primary_cat":"cs.CL","authors_text":"Gecheng Fu, Jinzhuo Wang, Sin Yee Goi, Wei Wu, Xukai Zhao, Yuxing Lu","submitted_at":"2025-05-26T05:56:23Z","abstract_excerpt":"Existing medical RAG systems mainly leverage knowledge from medical knowledge bases, neglecting the crucial role of experiential knowledge derived from similar patient cases -- a key component of human clinical reasoning. To bridge this gap, we propose DoctorRAG, a RAG framework that emulates doctor-like reasoning by integrating both explicit clinical knowledge and implicit case-based experience. DoctorRAG enhances retrieval precision by first allocating conceptual tags for queries and knowledge sources, together with a hybrid retrieval mechanism from both relevant knowledge and patient. In ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19538","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/2505.19538/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":"2505.19538","created_at":"2026-07-05T11:09:32.000611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19538v1","created_at":"2026-07-05T11:09:32.000611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19538","created_at":"2026-07-05T11:09:32.000611+00:00"},{"alias_kind":"pith_short_12","alias_value":"77OJZXESYV3V","created_at":"2026-07-05T11:09:32.000611+00:00"},{"alias_kind":"pith_short_16","alias_value":"77OJZXESYV3VKE5M","created_at":"2026-07-05T11:09:32.000611+00:00"},{"alias_kind":"pith_short_8","alias_value":"77OJZXES","created_at":"2026-07-05T11:09:32.000611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09584","citing_title":"CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4","json":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4.json","graph_json":"https://pith.science/api/pith-number/77OJZXESYV3VKE5M4GJDTHVXX4/graph.json","events_json":"https://pith.science/api/pith-number/77OJZXESYV3VKE5M4GJDTHVXX4/events.json","paper":"https://pith.science/paper/77OJZXES"},"agent_actions":{"view_html":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4","download_json":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4.json","view_paper":"https://pith.science/paper/77OJZXES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19538&json=true","fetch_graph":"https://pith.science/api/pith-number/77OJZXESYV3VKE5M4GJDTHVXX4/graph.json","fetch_events":"https://pith.science/api/pith-number/77OJZXESYV3VKE5M4GJDTHVXX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4/action/storage_attestation","attest_author":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4/action/author_attestation","sign_citation":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4/action/citation_signature","submit_replication":"https://pith.science/pith/77OJZXESYV3VKE5M4GJDTHVXX4/action/replication_record"}},"created_at":"2026-07-05T11:09:32.000611+00:00","updated_at":"2026-07-05T11:09:32.000611+00:00"}