{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KMDTPJCIZLOT2FTM3NAA6V6B7W","short_pith_number":"pith:KMDTPJCI","schema_version":"1.0","canonical_sha256":"530737a448cadd3d166cdb400f57c1fd83eb5869ff3237cba910745619179f12","source":{"kind":"arxiv","id":"2409.01666","version":1},"attestation_state":"computed","paper":{"title":"In Defense of RAG in the Era of Long-Context Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anbang Xu, Rama Akkiraju, Tan Yu","submitted_at":"2024-09-03T07:17:41Z","abstract_excerpt":"Overcoming the limited context limitations in early-generation LLMs, retrieval-augmented generation (RAG) has been a reliable solution for context-based answer generation in the past. Recently, the emergence of long-context LLMs allows the models to incorporate much longer text sequences, making RAG less attractive. Recent studies show that long-context LLMs significantly outperform RAG in long-context applications. Unlike the existing works favoring the long-context LLM over RAG, we argue that the extremely long context in LLMs suffers from a diminished focus on relevant information and leads"},"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":"2409.01666","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T07:17:41Z","cross_cats_sorted":[],"title_canon_sha256":"932bc13bd52ea1fc24107c084f76c86da5f8a509712e7964b5aa56e437b08fe6","abstract_canon_sha256":"9957007e16d66622eb619f54f601cf685e6cabe5a0f3ee74a20fa613941c0372"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:32.470186Z","signature_b64":"MEv6IebY+aZnAqaQ90th8RG+3cbNAiHgGKabUA5XmlAAUs1tei4PhGy9yjX78Eqy9ag+WOHgYzSqNWNq0n1bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"530737a448cadd3d166cdb400f57c1fd83eb5869ff3237cba910745619179f12","last_reissued_at":"2026-07-05T09:02:32.469677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:32.469677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In Defense of RAG in the Era of Long-Context Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anbang Xu, Rama Akkiraju, Tan Yu","submitted_at":"2024-09-03T07:17:41Z","abstract_excerpt":"Overcoming the limited context limitations in early-generation LLMs, retrieval-augmented generation (RAG) has been a reliable solution for context-based answer generation in the past. Recently, the emergence of long-context LLMs allows the models to incorporate much longer text sequences, making RAG less attractive. Recent studies show that long-context LLMs significantly outperform RAG in long-context applications. Unlike the existing works favoring the long-context LLM over RAG, we argue that the extremely long context in LLMs suffers from a diminished focus on relevant information and leads"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01666","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/2409.01666/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":"2409.01666","created_at":"2026-07-05T09:02:32.469733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01666v1","created_at":"2026-07-05T09:02:32.469733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01666","created_at":"2026-07-05T09:02:32.469733+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMDTPJCIZLOT","created_at":"2026-07-05T09:02:32.469733+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMDTPJCIZLOT2FTM","created_at":"2026-07-05T09:02:32.469733+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMDTPJCI","created_at":"2026-07-05T09:02:32.469733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07740","citing_title":"Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20898","citing_title":"The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30093","citing_title":"Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27105","citing_title":"Lost in the Evidence? Reproducing Document Position and Context Size Effects in RAG","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07328","citing_title":"Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26525","citing_title":"PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":212,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15583","citing_title":"SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W","json":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W.json","graph_json":"https://pith.science/api/pith-number/KMDTPJCIZLOT2FTM3NAA6V6B7W/graph.json","events_json":"https://pith.science/api/pith-number/KMDTPJCIZLOT2FTM3NAA6V6B7W/events.json","paper":"https://pith.science/paper/KMDTPJCI"},"agent_actions":{"view_html":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W","download_json":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W.json","view_paper":"https://pith.science/paper/KMDTPJCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01666&json=true","fetch_graph":"https://pith.science/api/pith-number/KMDTPJCIZLOT2FTM3NAA6V6B7W/graph.json","fetch_events":"https://pith.science/api/pith-number/KMDTPJCIZLOT2FTM3NAA6V6B7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W/action/storage_attestation","attest_author":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W/action/author_attestation","sign_citation":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W/action/citation_signature","submit_replication":"https://pith.science/pith/KMDTPJCIZLOT2FTM3NAA6V6B7W/action/replication_record"}},"created_at":"2026-07-05T09:02:32.469733+00:00","updated_at":"2026-07-05T09:02:32.469733+00:00"}