{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5J3GKVSQUYKHQI3UD35CFXANJT","short_pith_number":"pith:5J3GKVSQ","schema_version":"1.0","canonical_sha256":"ea76655650a6147823741efa22dc0d4ce218482ac07abcf529e4bafe80c420ef","source":{"kind":"arxiv","id":"2406.04369","version":1},"attestation_state":"computed","paper":{"title":"RAG Does Not Work for Enterprises","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Tilmann Bruckhaus (Strative.ai)","submitted_at":"2024-05-31T23:30:52Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) improves the accuracy and relevance of large language model outputs by incorporating knowledge retrieval. However, implementing RAG in enterprises poses challenges around data security, accuracy, scalability, and integration. This paper explores the unique requirements for enterprise RAG, surveys current approaches and limitations, and discusses potential advances in semantic search, hybrid queries, and optimized retrieval. It proposes an evaluation framework to validate enterprise RAG solutions, including quantitative testing, qualitative analysis, ablatio"},"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":"2406.04369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-05-31T23:30:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9f3b23b67cc0955ab12e973c2ce4cb4644453441d9cd59d3784fba9e300c25d","abstract_canon_sha256":"24968fda5962bdd825ae107cf6cc6a721d8d4c45a5b7710380aead7e19137421"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:43.136504Z","signature_b64":"8Ft2qzlz9F+5fb5v90Ay3rEERp/att/3ha8l5Ck47R+RULKm+rdrBJebtwITU7NFpfo5Z7IEBbjTtcmVn8n2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea76655650a6147823741efa22dc0d4ce218482ac07abcf529e4bafe80c420ef","last_reissued_at":"2026-07-05T08:28:43.136030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:43.136030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG Does Not Work for Enterprises","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Tilmann Bruckhaus (Strative.ai)","submitted_at":"2024-05-31T23:30:52Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) improves the accuracy and relevance of large language model outputs by incorporating knowledge retrieval. However, implementing RAG in enterprises poses challenges around data security, accuracy, scalability, and integration. This paper explores the unique requirements for enterprise RAG, surveys current approaches and limitations, and discusses potential advances in semantic search, hybrid queries, and optimized retrieval. It proposes an evaluation framework to validate enterprise RAG solutions, including quantitative testing, qualitative analysis, ablatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04369","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/2406.04369/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":"2406.04369","created_at":"2026-07-05T08:28:43.136088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04369v1","created_at":"2026-07-05T08:28:43.136088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04369","created_at":"2026-07-05T08:28:43.136088+00:00"},{"alias_kind":"pith_short_12","alias_value":"5J3GKVSQUYKH","created_at":"2026-07-05T08:28:43.136088+00:00"},{"alias_kind":"pith_short_16","alias_value":"5J3GKVSQUYKHQI3U","created_at":"2026-07-05T08:28:43.136088+00:00"},{"alias_kind":"pith_short_8","alias_value":"5J3GKVSQ","created_at":"2026-07-05T08:28:43.136088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21535","citing_title":"From Embedding Geometry to Spectral Search: Energy Dispersion Networks For Vector Retrieval","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19366","citing_title":"Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems","ref_index":167,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":185,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT","json":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT.json","graph_json":"https://pith.science/api/pith-number/5J3GKVSQUYKHQI3UD35CFXANJT/graph.json","events_json":"https://pith.science/api/pith-number/5J3GKVSQUYKHQI3UD35CFXANJT/events.json","paper":"https://pith.science/paper/5J3GKVSQ"},"agent_actions":{"view_html":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT","download_json":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT.json","view_paper":"https://pith.science/paper/5J3GKVSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04369&json=true","fetch_graph":"https://pith.science/api/pith-number/5J3GKVSQUYKHQI3UD35CFXANJT/graph.json","fetch_events":"https://pith.science/api/pith-number/5J3GKVSQUYKHQI3UD35CFXANJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT/action/storage_attestation","attest_author":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT/action/author_attestation","sign_citation":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT/action/citation_signature","submit_replication":"https://pith.science/pith/5J3GKVSQUYKHQI3UD35CFXANJT/action/replication_record"}},"created_at":"2026-07-05T08:28:43.136088+00:00","updated_at":"2026-07-05T08:28:43.136088+00:00"}