{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UV6RNGDWKC6OP3BUSQMGRGNHJ2","short_pith_number":"pith:UV6RNGDW","schema_version":"1.0","canonical_sha256":"a57d16987650bce7ec3494186899a74ebcae5a55f14d4ec69f058316180422d5","source":{"kind":"arxiv","id":"2404.13781","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Alireza Salemi, Hamed Zamani","submitted_at":"2024-04-21T21:22:28Z","abstract_excerpt":"Evaluating retrieval-augmented generation (RAG) presents challenges, particularly for retrieval models within these systems. Traditional end-to-end evaluation methods are computationally expensive. Furthermore, evaluation of the retrieval model's performance based on query-document relevance labels shows a small correlation with the RAG system's downstream performance. We propose a novel evaluation approach, eRAG, where each document in the retrieval list is individually utilized by the large language model within the RAG system. The output generated for each document is then evaluated based 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":"2404.13781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-21T21:22:28Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"8b582dd48419357264904c9b137dbdb269951426214773ff6451b46778ec241b","abstract_canon_sha256":"a8f603f6caf98b37cf20eae42ebb7f63b11397fd880de119ce625d556b97f107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:37.175166Z","signature_b64":"D1NS8EHHWW2+IvOTj40BFwZZmzjiB8BBAufbiywT+F1o8wlU9pqHcf7CxkCty61ssYzKNHqjkL7Mt1nJtPqnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a57d16987650bce7ec3494186899a74ebcae5a55f14d4ec69f058316180422d5","last_reissued_at":"2026-07-05T08:10:37.174715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:37.174715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Alireza Salemi, Hamed Zamani","submitted_at":"2024-04-21T21:22:28Z","abstract_excerpt":"Evaluating retrieval-augmented generation (RAG) presents challenges, particularly for retrieval models within these systems. Traditional end-to-end evaluation methods are computationally expensive. Furthermore, evaluation of the retrieval model's performance based on query-document relevance labels shows a small correlation with the RAG system's downstream performance. We propose a novel evaluation approach, eRAG, where each document in the retrieval list is individually utilized by the large language model within the RAG system. The output generated for each document is then evaluated based o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13781","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/2404.13781/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":"2404.13781","created_at":"2026-07-05T08:10:37.174768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13781v1","created_at":"2026-07-05T08:10:37.174768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13781","created_at":"2026-07-05T08:10:37.174768+00:00"},{"alias_kind":"pith_short_12","alias_value":"UV6RNGDWKC6O","created_at":"2026-07-05T08:10:37.174768+00:00"},{"alias_kind":"pith_short_16","alias_value":"UV6RNGDWKC6OP3BU","created_at":"2026-07-05T08:10:37.174768+00:00"},{"alias_kind":"pith_short_8","alias_value":"UV6RNGDW","created_at":"2026-07-05T08:10:37.174768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10177","citing_title":"VArify: A Visual Analytics System for Verifying Knowledge Enhanced Large Language Model Responses in Food Science","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20821","citing_title":"MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11954","citing_title":"VizCopilot: Fostering Appropriate Reliance on Enterprise Chatbots with Context Visualization","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16310","citing_title":"RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18234","citing_title":"Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2","json":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2.json","graph_json":"https://pith.science/api/pith-number/UV6RNGDWKC6OP3BUSQMGRGNHJ2/graph.json","events_json":"https://pith.science/api/pith-number/UV6RNGDWKC6OP3BUSQMGRGNHJ2/events.json","paper":"https://pith.science/paper/UV6RNGDW"},"agent_actions":{"view_html":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2","download_json":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2.json","view_paper":"https://pith.science/paper/UV6RNGDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13781&json=true","fetch_graph":"https://pith.science/api/pith-number/UV6RNGDWKC6OP3BUSQMGRGNHJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/UV6RNGDWKC6OP3BUSQMGRGNHJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2/action/storage_attestation","attest_author":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2/action/author_attestation","sign_citation":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2/action/citation_signature","submit_replication":"https://pith.science/pith/UV6RNGDWKC6OP3BUSQMGRGNHJ2/action/replication_record"}},"created_at":"2026-07-05T08:10:37.174768+00:00","updated_at":"2026-07-05T08:10:37.174768+00:00"}