{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4DRB2JMQ532TAYKSTWRAVX5JFE","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":"974d85cd3340c54b91988c2d3390236a06bfdc3b55aab674ea99739f1bf3ad75","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T17:44:06Z","title_canon_sha256":"d7dbbb83b1d982eb6bd94f93c8bcb5c6c719f987db61f95a7ddc8b21c87eec84"},"schema_version":"1.0","source":{"id":"2402.13178","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13178","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13178v2","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13178","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"4DRB2JMQ532T","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"pith_short_16","alias_value":"4DRB2JMQ532TAYKS","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"pith_short_8","alias_value":"4DRB2JMQ","created_at":"2026-07-05T07:48:35Z"}],"graph_snapshots":[{"event_id":"sha256:704d1e72c82fe0c6d4bc5b28d54d4863a995121a49e2e3beb0036c48d87dfd64","target":"graph","created_at":"2026-07-05T07:48:35Z","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/2402.13178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aidong Zhang, Guangzhi Xiong, Qiao Jin, Zhiyong Lu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T17:44:06Z","title":"Benchmarking Retrieval-Augmented Generation for Medicine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13178","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":"sha256:117b0cad924641429caada8f142d32fcb176234e70d5c6b4bec95657950f3d96","target":"record","created_at":"2026-07-05T07:48:35Z","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":"974d85cd3340c54b91988c2d3390236a06bfdc3b55aab674ea99739f1bf3ad75","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T17:44:06Z","title_canon_sha256":"d7dbbb83b1d982eb6bd94f93c8bcb5c6c719f987db61f95a7ddc8b21c87eec84"},"schema_version":"1.0","source":{"id":"2402.13178","kind":"arxiv","version":2}},"canonical_sha256":"e0e21d2590eef53061529da20adfa9290195eb1cc96e87557e9701cac19e5d24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0e21d2590eef53061529da20adfa9290195eb1cc96e87557e9701cac19e5d24","first_computed_at":"2026-07-05T07:48:35.095909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:35.095909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m7YNJqHeil+QDa64mNI/ImYcacPyw+2tXijopN9663mE2XuZis7Hs+PQxfQTHPq2WddFozar1zpsyQe6Yup3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:35.096351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13178","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:117b0cad924641429caada8f142d32fcb176234e70d5c6b4bec95657950f3d96","sha256:704d1e72c82fe0c6d4bc5b28d54d4863a995121a49e2e3beb0036c48d87dfd64"],"state_sha256":"08fcb167614d9c15809e586665defea3fa12e7900dfc67922866404d32eb654d"}