{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HYQKNFC2MBD3KKPEFRMHIAWDNB","short_pith_number":"pith:HYQKNFC2","schema_version":"1.0","canonical_sha256":"3e20a6945a6047b529e42c587402c36849a5c6ed689869ec0d34605cfa2fd8c2","source":{"kind":"arxiv","id":"2407.01219","version":1},"attestation_state":"computed","paper":{"title":"Searching for Best Practices in Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changze Lv, Feiran Zhang, Qi Qian, Ruicheng Yin, Shizheng Li, Tianyuan Shi, Xiaohua Wang, Xiaoqing Zheng, Xuan Gao, Xuanjing Huang, Yixin Wu, Zhenghua Wang, Zhengyuan Wang, Zhibo Xu","submitted_at":"2024-07-01T12:06:34Z","abstract_excerpt":"Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While many RAG approaches have been proposed to enhance large language models through query-dependent retrievals, these approaches still suffer from their complex implementation and prolonged response times. Typically, a RAG workflow involves multiple processing steps, each of which can be executed in various ways. Here, we investigate existing RAG approaches and their potential combina"},"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":"2407.01219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T12:06:34Z","cross_cats_sorted":[],"title_canon_sha256":"3127b9f45f321a52f2e4cd6ba8b56892f6265a4e619249cefffbdcdf10aba7b4","abstract_canon_sha256":"71d133daf9f221f26c2da8b368c7aeef198aab28148ba5070cde1a4bc6665d8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:44.759859Z","signature_b64":"DZSIovNR2sNP3hJyqPSnm9xjn7EJuXJ69SsL470JOLPeH8i4i8ek/gwfa21OOuXqD0Ioi116AEbU+WeZ8fuHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e20a6945a6047b529e42c587402c36849a5c6ed689869ec0d34605cfa2fd8c2","last_reissued_at":"2026-07-05T08:38:44.759383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:44.759383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Searching for Best Practices in Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changze Lv, Feiran Zhang, Qi Qian, Ruicheng Yin, Shizheng Li, Tianyuan Shi, Xiaohua Wang, Xiaoqing Zheng, Xuan Gao, Xuanjing Huang, Yixin Wu, Zhenghua Wang, Zhengyuan Wang, Zhibo Xu","submitted_at":"2024-07-01T12:06:34Z","abstract_excerpt":"Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While many RAG approaches have been proposed to enhance large language models through query-dependent retrievals, these approaches still suffer from their complex implementation and prolonged response times. Typically, a RAG workflow involves multiple processing steps, each of which can be executed in various ways. Here, we investigate existing RAG approaches and their potential combina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01219","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/2407.01219/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":"2407.01219","created_at":"2026-07-05T08:38:44.759443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01219v1","created_at":"2026-07-05T08:38:44.759443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01219","created_at":"2026-07-05T08:38:44.759443+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYQKNFC2MBD3","created_at":"2026-07-05T08:38:44.759443+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYQKNFC2MBD3KKPE","created_at":"2026-07-05T08:38:44.759443+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYQKNFC2","created_at":"2026-07-05T08:38:44.759443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27705","citing_title":"Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02643","citing_title":"Inference Cost Attacks for Retrieval-Augmented Large Language Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20173","citing_title":"Qiskit Code Migration with LLMs","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":144,"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":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15184","citing_title":"Is Grep All You Need? How Agent Harnesses Reshape Agentic Search","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14503","citing_title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB","json":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB.json","graph_json":"https://pith.science/api/pith-number/HYQKNFC2MBD3KKPEFRMHIAWDNB/graph.json","events_json":"https://pith.science/api/pith-number/HYQKNFC2MBD3KKPEFRMHIAWDNB/events.json","paper":"https://pith.science/paper/HYQKNFC2"},"agent_actions":{"view_html":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB","download_json":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB.json","view_paper":"https://pith.science/paper/HYQKNFC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01219&json=true","fetch_graph":"https://pith.science/api/pith-number/HYQKNFC2MBD3KKPEFRMHIAWDNB/graph.json","fetch_events":"https://pith.science/api/pith-number/HYQKNFC2MBD3KKPEFRMHIAWDNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB/action/storage_attestation","attest_author":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB/action/author_attestation","sign_citation":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB/action/citation_signature","submit_replication":"https://pith.science/pith/HYQKNFC2MBD3KKPEFRMHIAWDNB/action/replication_record"}},"created_at":"2026-07-05T08:38:44.759443+00:00","updated_at":"2026-07-05T08:38:44.759443+00:00"}