{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TREJVLMQICHPAEYLTX2N4KCTQH","short_pith_number":"pith:TREJVLMQ","schema_version":"1.0","canonical_sha256":"9c489aad90408ef0130b9df4de285381ef6d309bcc6db3fd9628a3e91f76e230","source":{"kind":"arxiv","id":"2411.03538","version":1},"attestation_state":"computed","paper":{"title":"Long Context RAG Performance of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jacob Portes, Matei Zaharia, Michael Carbin, Quinn Leng, Sam Havens","submitted_at":"2024-11-05T22:37:43Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context lengths, there is a growing interest in understanding how these models perform in RAG scenarios. Can these new long context models improve RAG performance? This paper presents a comprehensive study of the impact of increased context length on RAG performance across 20 popular open source and commercial LLMs. We ran RAG workflows while varying the total context le"},"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":"2411.03538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T22:37:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"91ba1ef20f14159a874c9c50d86cd53485e1e5755b2e595703e287764de98c84","abstract_canon_sha256":"80de1616dfc1b9edc9cd540f5eb82f60ed7a684d16a875da9839cb3919ff941f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:34.100519Z","signature_b64":"63q6pX2p3m1PMwL9E4dp9pKc+Zjgmwgu3Q8NrrP2oBiUZosIHV4/ZZTt56RvwIHRt3WyE5E0Ab5zRpjc50nMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c489aad90408ef0130b9df4de285381ef6d309bcc6db3fd9628a3e91f76e230","last_reissued_at":"2026-07-05T09:31:34.100000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:34.100000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long Context RAG Performance of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jacob Portes, Matei Zaharia, Michael Carbin, Quinn Leng, Sam Havens","submitted_at":"2024-11-05T22:37:43Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context lengths, there is a growing interest in understanding how these models perform in RAG scenarios. Can these new long context models improve RAG performance? This paper presents a comprehensive study of the impact of increased context length on RAG performance across 20 popular open source and commercial LLMs. We ran RAG workflows while varying the total context le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03538","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/2411.03538/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":"2411.03538","created_at":"2026-07-05T09:31:34.100058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03538v1","created_at":"2026-07-05T09:31:34.100058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03538","created_at":"2026-07-05T09:31:34.100058+00:00"},{"alias_kind":"pith_short_12","alias_value":"TREJVLMQICHP","created_at":"2026-07-05T09:31:34.100058+00:00"},{"alias_kind":"pith_short_16","alias_value":"TREJVLMQICHPAEYL","created_at":"2026-07-05T09:31:34.100058+00:00"},{"alias_kind":"pith_short_8","alias_value":"TREJVLMQ","created_at":"2026-07-05T09:31:34.100058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25030","citing_title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11759","citing_title":"Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19265","citing_title":"MuMuTestUp: Mutation-based Multi-Agent Test Case Update","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11759","citing_title":"Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH","json":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH.json","graph_json":"https://pith.science/api/pith-number/TREJVLMQICHPAEYLTX2N4KCTQH/graph.json","events_json":"https://pith.science/api/pith-number/TREJVLMQICHPAEYLTX2N4KCTQH/events.json","paper":"https://pith.science/paper/TREJVLMQ"},"agent_actions":{"view_html":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH","download_json":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH.json","view_paper":"https://pith.science/paper/TREJVLMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03538&json=true","fetch_graph":"https://pith.science/api/pith-number/TREJVLMQICHPAEYLTX2N4KCTQH/graph.json","fetch_events":"https://pith.science/api/pith-number/TREJVLMQICHPAEYLTX2N4KCTQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH/action/storage_attestation","attest_author":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH/action/author_attestation","sign_citation":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH/action/citation_signature","submit_replication":"https://pith.science/pith/TREJVLMQICHPAEYLTX2N4KCTQH/action/replication_record"}},"created_at":"2026-07-05T09:31:34.100058+00:00","updated_at":"2026-07-05T09:31:34.100058+00:00"}