{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4DRB2JMQ532TAYKSTWRAVX5JFE","short_pith_number":"pith:4DRB2JMQ","schema_version":"1.0","canonical_sha256":"e0e21d2590eef53061529da20adfa9290195eb1cc96e87557e9701cac19e5d24","source":{"kind":"arxiv","id":"2402.13178","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Retrieval-Augmented Generation for Medicine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aidong Zhang, Guangzhi Xiong, Qiao Jin, Zhiyong Lu","submitted_at":"2024-02-20T17:44:06Z","abstract_excerpt":"While large language models (LLMs) have achieved state-of-the-art performance on a wide range of medical question answering (QA) tasks, they still face challenges with hallucinations and outdated knowledge. Retrieval-augmented generation (RAG) is a promising solution and has been widely adopted. However, a RAG system can involve multiple flexible components, and there is a lack of best practices regarding the optimal RAG setting for various medical purposes. To systematically evaluate such systems, we propose the Medical Information Retrieval-Augmented Generation Evaluation (MIRAGE), a first-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":"2402.13178","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T17:44:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7dbbb83b1d982eb6bd94f93c8bcb5c6c719f987db61f95a7ddc8b21c87eec84","abstract_canon_sha256":"974d85cd3340c54b91988c2d3390236a06bfdc3b55aab674ea99739f1bf3ad75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:35.096351Z","signature_b64":"m7YNJqHeil+QDa64mNI/ImYcacPyw+2tXijopN9663mE2XuZis7Hs+PQxfQTHPq2WddFozar1zpsyQe6Yup3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0e21d2590eef53061529da20adfa9290195eb1cc96e87557e9701cac19e5d24","last_reissued_at":"2026-07-05T07:48:35.095909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:35.095909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Retrieval-Augmented Generation for Medicine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aidong Zhang, Guangzhi Xiong, Qiao Jin, Zhiyong Lu","submitted_at":"2024-02-20T17:44:06Z","abstract_excerpt":"While large language models (LLMs) have achieved state-of-the-art performance on a wide range of medical question answering (QA) tasks, they still face challenges with hallucinations and outdated knowledge. Retrieval-augmented generation (RAG) is a promising solution and has been widely adopted. However, a RAG system can involve multiple flexible components, and there is a lack of best practices regarding the optimal RAG setting for various medical purposes. To systematically evaluate such systems, we propose the Medical Information Retrieval-Augmented Generation Evaluation (MIRAGE), a first-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13178","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/2402.13178/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":"2402.13178","created_at":"2026-07-05T07:48:35.095968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13178v2","created_at":"2026-07-05T07:48:35.095968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13178","created_at":"2026-07-05T07:48:35.095968+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DRB2JMQ532T","created_at":"2026-07-05T07:48:35.095968+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DRB2JMQ532TAYKS","created_at":"2026-07-05T07:48:35.095968+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DRB2JMQ","created_at":"2026-07-05T07:48:35.095968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20164","citing_title":"MedRLM: Recursive Multimodal Health Intelligence for Long-Context Clinical Reasoning, Sensor-Guided Screening, Evidence-Grounded Decision Support, and Community-to-Tertiary Referral Optimization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12916","citing_title":"SHM-Agents: A Generalist-Specialist Integrated Agent System for Structural Health Monitoring","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2405.07960","citing_title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16679","citing_title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14488","citing_title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03476","citing_title":"CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23801","citing_title":"Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE","json":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE.json","graph_json":"https://pith.science/api/pith-number/4DRB2JMQ532TAYKSTWRAVX5JFE/graph.json","events_json":"https://pith.science/api/pith-number/4DRB2JMQ532TAYKSTWRAVX5JFE/events.json","paper":"https://pith.science/paper/4DRB2JMQ"},"agent_actions":{"view_html":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE","download_json":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE.json","view_paper":"https://pith.science/paper/4DRB2JMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13178&json=true","fetch_graph":"https://pith.science/api/pith-number/4DRB2JMQ532TAYKSTWRAVX5JFE/graph.json","fetch_events":"https://pith.science/api/pith-number/4DRB2JMQ532TAYKSTWRAVX5JFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE/action/storage_attestation","attest_author":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE/action/author_attestation","sign_citation":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE/action/citation_signature","submit_replication":"https://pith.science/pith/4DRB2JMQ532TAYKSTWRAVX5JFE/action/replication_record"}},"created_at":"2026-07-05T07:48:35.095968+00:00","updated_at":"2026-07-05T07:48:35.095968+00:00"}