{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y3AD556WCQXCRU6JBAJYRETBYW","short_pith_number":"pith:Y3AD556W","schema_version":"1.0","canonical_sha256":"c6c03ef7d6142e28d3c90813889261c5b6545b79b0d53685c6bc227d730282ea","source":{"kind":"arxiv","id":"2411.19463","version":3},"attestation_state":"computed","paper":{"title":"Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chengcheng Wan, Jiayang Song, Lei Ma, Shengming Zhao, Yuchen Shao, Yuheng Huang, Zhijie Wang","submitted_at":"2024-11-29T04:25:31Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a critical technique for enhancing large language model (LLM) capabilities. However, practitioners face significant challenges when making RAG deployment decisions. While existing research prioritizes algorithmic innovations, a systematic gap persists in understanding fundamental engineering trade-offs that determine RAG success. We present the first comprehensive study of three universal RAG deployment decisions: whether to deploy RAG, how much information to retrieve, and how to integrate retrieved knowledge effectively. Through systematic "},"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":"2411.19463","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-11-29T04:25:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"290559289f1b558b8e536d21bb0ebc9ea8474f7c720f20e52942d1e2a03d1e48","abstract_canon_sha256":"20bdc3311bb11b7297ccab7850930e76bdcbdfc5cc8a7be9c3045aff559147fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:13.599509Z","signature_b64":"rIQvfs+A4sZp5VMtLs7gU5HJn1bSaYbFdR2cKdKXjhUXzh4T+L25mD2GW8Gwq8i4GqtqREWmp/pAK2mnbHBACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6c03ef7d6142e28d3c90813889261c5b6545b79b0d53685c6bc227d730282ea","last_reissued_at":"2026-06-01T01:02:13.598484Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:13.598484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chengcheng Wan, Jiayang Song, Lei Ma, Shengming Zhao, Yuchen Shao, Yuheng Huang, Zhijie Wang","submitted_at":"2024-11-29T04:25:31Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a critical technique for enhancing large language model (LLM) capabilities. However, practitioners face significant challenges when making RAG deployment decisions. While existing research prioritizes algorithmic innovations, a systematic gap persists in understanding fundamental engineering trade-offs that determine RAG success. We present the first comprehensive study of three universal RAG deployment decisions: whether to deploy RAG, how much information to retrieve, and how to integrate retrieved knowledge effectively. Through systematic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19463","kind":"arxiv","version":3},"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/2411.19463/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":"2411.19463","created_at":"2026-06-01T01:02:13.598627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19463v3","created_at":"2026-06-01T01:02:13.598627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19463","created_at":"2026-06-01T01:02:13.598627+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3AD556WCQXC","created_at":"2026-06-01T01:02:13.598627+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3AD556WCQXCRU6J","created_at":"2026-06-01T01:02:13.598627+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3AD556W","created_at":"2026-06-01T01:02:13.598627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.03826","citing_title":"Context Matters: Evaluating Context Strategies for Automated ADR Generation Using LLMs","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11092","citing_title":"ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense Retrieval","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW","json":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW.json","graph_json":"https://pith.science/api/pith-number/Y3AD556WCQXCRU6JBAJYRETBYW/graph.json","events_json":"https://pith.science/api/pith-number/Y3AD556WCQXCRU6JBAJYRETBYW/events.json","paper":"https://pith.science/paper/Y3AD556W"},"agent_actions":{"view_html":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW","download_json":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW.json","view_paper":"https://pith.science/paper/Y3AD556W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19463&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3AD556WCQXCRU6JBAJYRETBYW/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3AD556WCQXCRU6JBAJYRETBYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW/action/storage_attestation","attest_author":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW/action/author_attestation","sign_citation":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW/action/citation_signature","submit_replication":"https://pith.science/pith/Y3AD556WCQXCRU6JBAJYRETBYW/action/replication_record"}},"created_at":"2026-06-01T01:02:13.598627+00:00","updated_at":"2026-06-01T01:02:13.598627+00:00"}