{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7ZM26ISRZMK2AJFWSG5LLV5XBB","short_pith_number":"pith:7ZM26ISR","schema_version":"1.0","canonical_sha256":"fe59af2251cb15a024b691bab5d7b7084d8fa3ffa74ac8596a43075eb070de09","source":{"kind":"arxiv","id":"2501.02727","version":1},"attestation_state":"computed","paper":{"title":"Tree-based RAG-Agent Recommendation System: A Case Study in Medical Test Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chengyue Huang, Yahe Yang","submitted_at":"2025-01-06T02:50:51Z","abstract_excerpt":"We present HiRMed (Hierarchical RAG-enhanced Medical Test Recommendation), a novel tree-structured recommendation system that leverages Retrieval-Augmented Generation (RAG) for intelligent medical test recommendations. Unlike traditional vector similarity-based approaches, our system performs medical reasoning at each tree node through a specialized RAG process. Starting from the root node with initial symptoms, the system conducts step-wise medical analysis to identify potential underlying conditions and their corresponding diagnostic requirements. At each level, instead of simple matching, o"},"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":"2501.02727","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-06T02:50:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de71db9fe6155a25cd7d91b4996243c49f0134e6bf6a8a430b1f0580b0eb0df4","abstract_canon_sha256":"c19abda43ec2de45c272b2bf983e7551b6b860e63e19b83d688cc4698dbc97ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:11.228311Z","signature_b64":"Pv+KY9Ddxl9lKHt82idheEfGgYAtSgFQxXiFGsNk8ht2z8gXeG1JZdbNijLC6Fs+WaiRlieRYNlF4D3P5j8rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe59af2251cb15a024b691bab5d7b7084d8fa3ffa74ac8596a43075eb070de09","last_reissued_at":"2026-07-05T09:57:11.227830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:11.227830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tree-based RAG-Agent Recommendation System: A Case Study in Medical Test Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chengyue Huang, Yahe Yang","submitted_at":"2025-01-06T02:50:51Z","abstract_excerpt":"We present HiRMed (Hierarchical RAG-enhanced Medical Test Recommendation), a novel tree-structured recommendation system that leverages Retrieval-Augmented Generation (RAG) for intelligent medical test recommendations. Unlike traditional vector similarity-based approaches, our system performs medical reasoning at each tree node through a specialized RAG process. Starting from the root node with initial symptoms, the system conducts step-wise medical analysis to identify potential underlying conditions and their corresponding diagnostic requirements. At each level, instead of simple matching, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02727","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/2501.02727/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":"2501.02727","created_at":"2026-07-05T09:57:11.227889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02727v1","created_at":"2026-07-05T09:57:11.227889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02727","created_at":"2026-07-05T09:57:11.227889+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZM26ISRZMK2","created_at":"2026-07-05T09:57:11.227889+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZM26ISRZMK2AJFW","created_at":"2026-07-05T09:57:11.227889+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZM26ISR","created_at":"2026-07-05T09:57:11.227889+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07761","citing_title":"Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning","ref_index":134,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24219","citing_title":"Adaptive ToR: Complexity-Aware Tree-Based Retrieval for Pareto-Optimal Multi-Intent NLU","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB","json":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB.json","graph_json":"https://pith.science/api/pith-number/7ZM26ISRZMK2AJFWSG5LLV5XBB/graph.json","events_json":"https://pith.science/api/pith-number/7ZM26ISRZMK2AJFWSG5LLV5XBB/events.json","paper":"https://pith.science/paper/7ZM26ISR"},"agent_actions":{"view_html":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB","download_json":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB.json","view_paper":"https://pith.science/paper/7ZM26ISR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02727&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZM26ISRZMK2AJFWSG5LLV5XBB/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZM26ISRZMK2AJFWSG5LLV5XBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB/action/storage_attestation","attest_author":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB/action/author_attestation","sign_citation":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB/action/citation_signature","submit_replication":"https://pith.science/pith/7ZM26ISRZMK2AJFWSG5LLV5XBB/action/replication_record"}},"created_at":"2026-07-05T09:57:11.227889+00:00","updated_at":"2026-07-05T09:57:11.227889+00:00"}