{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S4ND7CIM7ARNPMBA5GGQBBXHST","short_pith_number":"pith:S4ND7CIM","schema_version":"1.0","canonical_sha256":"971a3f890cf822d7b020e98d0086e794e30b8a7c68c15670e15f0f58966a2e87","source":{"kind":"arxiv","id":"2607.16973","version":1},"attestation_state":"computed","paper":{"title":"TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Kamal Pandey, Navnit Shukla, Omsankar Tiwari","submitted_at":"2026-07-18T21:43:40Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems increasingly power enterprise LLM applications, yet the vector retrieval layer introduces two underexplored challenges: (1) trained codebook quantizers may expose corpus statistics during index construction, creating a leakage channel in multi-tenant deployments, and (2) post-hoc filtering for tenant isolation degrades recall on selective queries. We study TurboVec, an open-source vector index built on TurboQuant - a codebook-oblivious scalar quantizer requiring no corpus-dependent training. On the DBpedia OpenAI embeddings benchmark (d=1536, 100K-9"},"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":"2607.16973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T21:43:40Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"60968ff29d34a7379a549ce4c685e3364142b00e4581c5f161f183426c45428c","abstract_canon_sha256":"4be3bc220461be1a4684b8c665a9a4e2a60be346759d2415d16426da4050da6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:08.797899Z","signature_b64":"A0me3sTYQ1YVBDlIP+NpMruypiG4Lh8ERrOD+Dg7MFbOLkdJwxkDpmKBFN/tbDOeA8KhL66eUBgjcu8YcdeuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"971a3f890cf822d7b020e98d0086e794e30b8a7c68c15670e15f0f58966a2e87","last_reissued_at":"2026-07-21T01:21:08.797059Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:08.797059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Kamal Pandey, Navnit Shukla, Omsankar Tiwari","submitted_at":"2026-07-18T21:43:40Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems increasingly power enterprise LLM applications, yet the vector retrieval layer introduces two underexplored challenges: (1) trained codebook quantizers may expose corpus statistics during index construction, creating a leakage channel in multi-tenant deployments, and (2) post-hoc filtering for tenant isolation degrades recall on selective queries. We study TurboVec, an open-source vector index built on TurboQuant - a codebook-oblivious scalar quantizer requiring no corpus-dependent training. On the DBpedia OpenAI embeddings benchmark (d=1536, 100K-9"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16973","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/2607.16973/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":"2607.16973","created_at":"2026-07-21T01:21:08.797497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16973v1","created_at":"2026-07-21T01:21:08.797497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16973","created_at":"2026-07-21T01:21:08.797497+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4ND7CIM7ARN","created_at":"2026-07-21T01:21:08.797497+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4ND7CIM7ARNPMBA","created_at":"2026-07-21T01:21:08.797497+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4ND7CIM","created_at":"2026-07-21T01:21:08.797497+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/S4ND7CIM7ARNPMBA5GGQBBXHST","json":"https://pith.science/pith/S4ND7CIM7ARNPMBA5GGQBBXHST.json","graph_json":"https://pith.science/api/pith-number/S4ND7CIM7ARNPMBA5GGQBBXHST/graph.json","events_json":"https://pith.science/api/pith-number/S4ND7CIM7ARNPMBA5GGQBBXHST/events.json","paper":"https://pith.science/paper/S4ND7CIM"},"agent_actions":{"view_html":"https://pith.science/pith/S4ND7CIM7ARNPMBA5GGQBBXHST","download_json":"https://pith.science/pith/S4ND7CIM7ARNPMBA5GGQBBXHST.json","view_paper":"https://pith.science/paper/S4ND7CIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16973&json=true","fetch_graph":"https://pith.science/api/pith-number/S4ND7CIM7ARNPMBA5GGQBBXHST/graph.json","fetch_events":"https://pith.science/api/pith-number/S4ND7CIM7ARNPMBA5GGQBBXHST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4ND7CIM7ARNPMBA5GGQBBXHST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4ND7CIM7ARNPMBA5GGQBBXHST/action/storage_attestation","attest_author":"https://pith.science/pith/S4ND7CIM7ARNPMBA5GGQBBXHST/action/author_attestation","sign_citation":"https://pith.science/pith/S4ND7CIM7ARNPMBA5GGQBBXHST/action/citation_signature","submit_replication":"https://pith.science/pith/S4ND7CIM7ARNPMBA5GGQBBXHST/action/replication_record"}},"created_at":"2026-07-21T01:21:08.797497+00:00","updated_at":"2026-07-21T01:21:08.797497+00:00"}