{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZZVGYJ3XMXKKYBVHJTXBCAZK4L","short_pith_number":"pith:ZZVGYJ3X","schema_version":"1.0","canonical_sha256":"ce6a6c277765d4ac06a74cee11032ae2dfa26a14c011ea9d97eea63c3723f621","source":{"kind":"arxiv","id":"2506.03437","version":2},"attestation_state":"computed","paper":{"title":"Quake: Adaptive Indexing for Vector Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Anil Pacaci, Devesh Sarda, Ihab F. Ilyas, Jason Mohoney, Mengze Tang, Shihabur Rahman Chowdhury, Shivaram Venkataraman, Theodoros Rekatsinas","submitted_at":"2025-06-03T22:37:37Z","abstract_excerpt":"Vector search, the task of finding the k-nearest neighbors of a query vector against a database of high-dimensional vectors, underpins many machine learning applications, including retrieval-augmented generation, recommendation systems, and information retrieval. However, existing approximate nearest neighbor (ANN) methods perform poorly under dynamic and skewed workloads where data distributions evolve. We introduce Quake, an adaptive indexing system that maintains low latency and high recall in such environments. Quake employs a multi-level partitioning scheme that adjusts to updates and cha"},"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":"2506.03437","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-03T22:37:37Z","cross_cats_sorted":[],"title_canon_sha256":"5b9684d5b10a856071fecb005bfb13a381c3d7dd09dc7b3662518409577bc42f","abstract_canon_sha256":"10d9c751f8e4d71098c94ac6b98f2a1b0e066f95eb0c2ee1d3ab6dfb9baa229a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:47.001330Z","signature_b64":"KYvzutFoXF/EzpGc8ZAFX0MU4wlKBGhAfev+hDyd3zynq/PsjECv4S1LbIy2QrJqstOgE0qZaI2ZTxvVAbQ6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce6a6c277765d4ac06a74cee11032ae2dfa26a14c011ea9d97eea63c3723f621","last_reissued_at":"2026-07-05T11:17:47.000859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:47.000859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quake: Adaptive Indexing for Vector Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Anil Pacaci, Devesh Sarda, Ihab F. Ilyas, Jason Mohoney, Mengze Tang, Shihabur Rahman Chowdhury, Shivaram Venkataraman, Theodoros Rekatsinas","submitted_at":"2025-06-03T22:37:37Z","abstract_excerpt":"Vector search, the task of finding the k-nearest neighbors of a query vector against a database of high-dimensional vectors, underpins many machine learning applications, including retrieval-augmented generation, recommendation systems, and information retrieval. However, existing approximate nearest neighbor (ANN) methods perform poorly under dynamic and skewed workloads where data distributions evolve. We introduce Quake, an adaptive indexing system that maintains low latency and high recall in such environments. Quake employs a multi-level partitioning scheme that adjusts to updates and cha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03437","kind":"arxiv","version":2},"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/2506.03437/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":"2506.03437","created_at":"2026-07-05T11:17:47.000916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03437v2","created_at":"2026-07-05T11:17:47.000916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03437","created_at":"2026-07-05T11:17:47.000916+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZVGYJ3XMXKK","created_at":"2026-07-05T11:17:47.000916+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZVGYJ3XMXKKYBVH","created_at":"2026-07-05T11:17:47.000916+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZVGYJ3X","created_at":"2026-07-05T11:17:47.000916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29968","citing_title":"CLIP: Lightweight Cosine-Law-Based Inverted-List Pruning for IVF-Based Vector Search","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20417","citing_title":"Semantic Recall for Vector Search","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L","json":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L.json","graph_json":"https://pith.science/api/pith-number/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/graph.json","events_json":"https://pith.science/api/pith-number/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/events.json","paper":"https://pith.science/paper/ZZVGYJ3X"},"agent_actions":{"view_html":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L","download_json":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L.json","view_paper":"https://pith.science/paper/ZZVGYJ3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03437&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/action/storage_attestation","attest_author":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/action/author_attestation","sign_citation":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/action/citation_signature","submit_replication":"https://pith.science/pith/ZZVGYJ3XMXKKYBVHJTXBCAZK4L/action/replication_record"}},"created_at":"2026-07-05T11:17:47.000916+00:00","updated_at":"2026-07-05T11:17:47.000916+00:00"}