{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RSE7JJKQNXCOO5NACQL6GSOQLR","short_pith_number":"pith:RSE7JJKQ","schema_version":"1.0","canonical_sha256":"8c89f4a5506dc4e775a01417e349d05c5a4d6a70b874d281db05313af6888978","source":{"kind":"arxiv","id":"2304.04759","version":2},"attestation_state":"computed","paper":{"title":"Similarity search in the blink of an eye with compressed indices","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Cecilia Aguerrebere, Ishwar Bhati, Mariano Tepper, Mark Hildebrand, Ted Willke","submitted_at":"2023-04-07T23:10:39Z","abstract_excerpt":"Nowadays, data is represented by vectors. Retrieving those vectors, among millions and billions, that are similar to a given query is a ubiquitous problem, known as similarity search, of relevance for a wide range of applications. Graph-based indices are currently the best performing techniques for billion-scale similarity search. However, their random-access memory pattern presents challenges to realize their full potential. In this work, we present new techniques and systems for creating faster and smaller graph-based indices. To this end, we introduce a novel vector compression method, Loca"},"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":"2304.04759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-07T23:10:39Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"041d8f30c78e63dfe1b5e7c53afcb8a140d9adb86ebe1e94110dc7c81a8a0a03","abstract_canon_sha256":"fb95dfab544c5e9984cc35e0cdd875e96c075cfa6316e089d766180c696a572f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:04.988408Z","signature_b64":"daKgf2jC2X7hMtRG7vGA+7+MWxNYplO0ljh+yxwMZL6/y5cOv3H9JEIj9ujwy22WgTf8H7/jqpY6uqLrzhj/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c89f4a5506dc4e775a01417e349d05c5a4d6a70b874d281db05313af6888978","last_reissued_at":"2026-07-05T06:34:04.987859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:04.987859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Similarity search in the blink of an eye with compressed indices","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Cecilia Aguerrebere, Ishwar Bhati, Mariano Tepper, Mark Hildebrand, Ted Willke","submitted_at":"2023-04-07T23:10:39Z","abstract_excerpt":"Nowadays, data is represented by vectors. Retrieving those vectors, among millions and billions, that are similar to a given query is a ubiquitous problem, known as similarity search, of relevance for a wide range of applications. Graph-based indices are currently the best performing techniques for billion-scale similarity search. However, their random-access memory pattern presents challenges to realize their full potential. In this work, we present new techniques and systems for creating faster and smaller graph-based indices. To this end, we introduce a novel vector compression method, Loca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04759","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/2304.04759/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":"2304.04759","created_at":"2026-07-05T06:34:04.987917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04759v2","created_at":"2026-07-05T06:34:04.987917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04759","created_at":"2026-07-05T06:34:04.987917+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSE7JJKQNXCO","created_at":"2026-07-05T06:34:04.987917+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSE7JJKQNXCOO5NA","created_at":"2026-07-05T06:34:04.987917+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSE7JJKQ","created_at":"2026-07-05T06:34:04.987917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25522","citing_title":"Co-Designing Graph-based Approximate Nearest Neighbor Search at Billion Scale for Processing-in-Memory","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23342","citing_title":"AlayaLaser: Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR","json":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR.json","graph_json":"https://pith.science/api/pith-number/RSE7JJKQNXCOO5NACQL6GSOQLR/graph.json","events_json":"https://pith.science/api/pith-number/RSE7JJKQNXCOO5NACQL6GSOQLR/events.json","paper":"https://pith.science/paper/RSE7JJKQ"},"agent_actions":{"view_html":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR","download_json":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR.json","view_paper":"https://pith.science/paper/RSE7JJKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04759&json=true","fetch_graph":"https://pith.science/api/pith-number/RSE7JJKQNXCOO5NACQL6GSOQLR/graph.json","fetch_events":"https://pith.science/api/pith-number/RSE7JJKQNXCOO5NACQL6GSOQLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR/action/storage_attestation","attest_author":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR/action/author_attestation","sign_citation":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR/action/citation_signature","submit_replication":"https://pith.science/pith/RSE7JJKQNXCOO5NACQL6GSOQLR/action/replication_record"}},"created_at":"2026-07-05T06:34:04.987917+00:00","updated_at":"2026-07-05T06:34:04.987917+00:00"}