{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WL7PBAC5SSQABFCS7SMQT7N4M2","short_pith_number":"pith:WL7PBAC5","schema_version":"1.0","canonical_sha256":"b2fef0805d94a0009452fc9909fdbc66ab9a379497d0117558e6c15df6722249","source":{"kind":"arxiv","id":"2405.07437","version":2},"attestation_state":"computed","paper":{"title":"Evaluation of Retrieval-Augmented Generation: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aoran Gan, Hao Yu, Kai Zhang, Qi Liu, Shiwei Tong, Zhaofeng Liu","submitted_at":"2024-05-13T02:33:25Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has recently gained traction in natural language processing. Numerous studies and real-world applications are leveraging its ability to enhance generative models through external information retrieval. Evaluating these RAG systems, however, poses unique challenges due to their hybrid structure and reliance on dynamic knowledge sources. To better understand these challenges, we conduct A Unified Evaluation Process of RAG (Auepora) and aim to provide a comprehensive overview of the evaluation and benchmarks of RAG systems. Specifically, we examine and compare"},"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":"2405.07437","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T02:33:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"63aff626c64159e8417e1d9aadb5eacaa9f018fa940e0cf7fb13e06bf89854a4","abstract_canon_sha256":"e4232af252c6672f501ed5e4f5f57bb8dce4244ee833835d2add1ea23b608d3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:03.215368Z","signature_b64":"1wtuE6pdNhTSyqGg7MmUAVx5IBnPT63w6KGX/aGWclHPq7x96SvenXjjWusI9WbMdWbTvJ5HacyJfu5BBAzoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2fef0805d94a0009452fc9909fdbc66ab9a379497d0117558e6c15df6722249","last_reissued_at":"2026-07-05T10:14:03.214851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:03.214851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Retrieval-Augmented Generation: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aoran Gan, Hao Yu, Kai Zhang, Qi Liu, Shiwei Tong, Zhaofeng Liu","submitted_at":"2024-05-13T02:33:25Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has recently gained traction in natural language processing. Numerous studies and real-world applications are leveraging its ability to enhance generative models through external information retrieval. Evaluating these RAG systems, however, poses unique challenges due to their hybrid structure and reliance on dynamic knowledge sources. To better understand these challenges, we conduct A Unified Evaluation Process of RAG (Auepora) and aim to provide a comprehensive overview of the evaluation and benchmarks of RAG systems. Specifically, we examine and compare"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07437","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/2405.07437/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":"2405.07437","created_at":"2026-07-05T10:14:03.214910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.07437v2","created_at":"2026-07-05T10:14:03.214910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07437","created_at":"2026-07-05T10:14:03.214910+00:00"},{"alias_kind":"pith_short_12","alias_value":"WL7PBAC5SSQA","created_at":"2026-07-05T10:14:03.214910+00:00"},{"alias_kind":"pith_short_16","alias_value":"WL7PBAC5SSQABFCS","created_at":"2026-07-05T10:14:03.214910+00:00"},{"alias_kind":"pith_short_8","alias_value":"WL7PBAC5","created_at":"2026-07-05T10:14:03.214910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20505","citing_title":"RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08333","citing_title":"CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAG","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07752","citing_title":"MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05467","citing_title":"CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14222","citing_title":"Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":292,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2","json":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2.json","graph_json":"https://pith.science/api/pith-number/WL7PBAC5SSQABFCS7SMQT7N4M2/graph.json","events_json":"https://pith.science/api/pith-number/WL7PBAC5SSQABFCS7SMQT7N4M2/events.json","paper":"https://pith.science/paper/WL7PBAC5"},"agent_actions":{"view_html":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2","download_json":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2.json","view_paper":"https://pith.science/paper/WL7PBAC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.07437&json=true","fetch_graph":"https://pith.science/api/pith-number/WL7PBAC5SSQABFCS7SMQT7N4M2/graph.json","fetch_events":"https://pith.science/api/pith-number/WL7PBAC5SSQABFCS7SMQT7N4M2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2/action/storage_attestation","attest_author":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2/action/author_attestation","sign_citation":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2/action/citation_signature","submit_replication":"https://pith.science/pith/WL7PBAC5SSQABFCS7SMQT7N4M2/action/replication_record"}},"created_at":"2026-07-05T10:14:03.214910+00:00","updated_at":"2026-07-05T10:14:03.214910+00:00"}