{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y4H43MTS4EWUMDYJEGBB74GU5X","short_pith_number":"pith:Y4H43MTS","schema_version":"1.0","canonical_sha256":"c70fcdb272e12d460f0921821ff0d4edf2eea2f71672d1b09a1fed94ea893bca","source":{"kind":"arxiv","id":"2507.20059","version":1},"attestation_state":"computed","paper":{"title":"RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Haoyu Wang, Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu","submitted_at":"2025-07-26T20:57:24Z","abstract_excerpt":"Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved at inference time. While RAG demonstrates strong performance on benchmarks largely derived from general-domain corpora like Wikipedia, its effectiveness under realistic, diverse retrieval scenarios remains underexplored. We evaluated RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge, and identified critical limitations: retrieval mainly benefits smaller models, rerankers add minimal value, and no single retrieval source consistently excels. Moreove"},"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":"2507.20059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T20:57:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1695fb4b8fff0ed5c5f6333ee8fc156a12be287199fe41bbe5df7a8f3a9dca2e","abstract_canon_sha256":"44b6f8c93db4c6225b16a1fb3bf8bfdf0e310e8105512fee4f019b651af0665a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:12.668682Z","signature_b64":"bP7pUfAj1htB/A5/KgGM8mvYJmQXCk7Mp6tJ918ytke3qZ/Q/EJQLIRM93StO50LLttWVJw3LuocZH1500pSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c70fcdb272e12d460f0921821ff0d4edf2eea2f71672d1b09a1fed94ea893bca","last_reissued_at":"2026-07-05T11:44:12.668190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:12.668190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Haoyu Wang, Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu","submitted_at":"2025-07-26T20:57:24Z","abstract_excerpt":"Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved at inference time. While RAG demonstrates strong performance on benchmarks largely derived from general-domain corpora like Wikipedia, its effectiveness under realistic, diverse retrieval scenarios remains underexplored. We evaluated RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge, and identified critical limitations: retrieval mainly benefits smaller models, rerankers add minimal value, and no single retrieval source consistently excels. Moreove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20059","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/2507.20059/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":"2507.20059","created_at":"2026-07-05T11:44:12.668250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20059v1","created_at":"2026-07-05T11:44:12.668250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20059","created_at":"2026-07-05T11:44:12.668250+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4H43MTS4EWU","created_at":"2026-07-05T11:44:12.668250+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4H43MTS4EWUMDYJ","created_at":"2026-07-05T11:44:12.668250+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4H43MTS","created_at":"2026-07-05T11:44:12.668250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X","json":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X.json","graph_json":"https://pith.science/api/pith-number/Y4H43MTS4EWUMDYJEGBB74GU5X/graph.json","events_json":"https://pith.science/api/pith-number/Y4H43MTS4EWUMDYJEGBB74GU5X/events.json","paper":"https://pith.science/paper/Y4H43MTS"},"agent_actions":{"view_html":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X","download_json":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X.json","view_paper":"https://pith.science/paper/Y4H43MTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20059&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4H43MTS4EWUMDYJEGBB74GU5X/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4H43MTS4EWUMDYJEGBB74GU5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/action/storage_attestation","attest_author":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/action/author_attestation","sign_citation":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/action/citation_signature","submit_replication":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/action/replication_record"}},"created_at":"2026-07-05T11:44:12.668250+00:00","updated_at":"2026-07-05T11:44:12.668250+00:00"}