{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:44LJN5EITTOL5S7HD6E3Q5LGKY","short_pith_number":"pith:44LJN5EI","schema_version":"1.0","canonical_sha256":"e71696f4889cdcbecbe71f89b87566562085a13c904db85faa90d8f933cc3f6e","source":{"kind":"arxiv","id":"2506.00528","version":1},"attestation_state":"computed","paper":{"title":"Ultra-Quantisation: Efficient Embedding Search via 1.58-bit Encodings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Alan Dearle, Ben Claydon, Richard Connor","submitted_at":"2025-05-31T12:22:24Z","abstract_excerpt":"Many modern search domains comprise high-dimensional vectors of floating point numbers derived from neural networks, in the form of embeddings. Typical embeddings range in size from hundreds to thousands of dimensions, making the size of the embeddings, and the speed of comparison, a significant issue.\n  Quantisation is a class of mechanism which replaces the floating point values with a smaller representation, for example a short integer. This gives an approximation of the embedding space in return for a smaller data representation and a faster comparison function.\n  Here we take this idea al"},"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":"2506.00528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T12:22:24Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"13a1498133421f758fe76d25be159e5eed3a8606a334090e0d3f74d4c2b5bd58","abstract_canon_sha256":"af3a51b7958f4e8b02fee0466ee8117614d452d82a3c398d8d6b8372aafe57a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:36.521525Z","signature_b64":"6q8q3VOJUtAyp+5gfbRHueM2WP35OHKB58cGH59oVLiBG4kPw/R9KfTUL1OPDgGOb7uX0SUtrNmIE0aglV3oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e71696f4889cdcbecbe71f89b87566562085a13c904db85faa90d8f933cc3f6e","last_reissued_at":"2026-07-05T11:13:36.521100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:36.521100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ultra-Quantisation: Efficient Embedding Search via 1.58-bit Encodings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Alan Dearle, Ben Claydon, Richard Connor","submitted_at":"2025-05-31T12:22:24Z","abstract_excerpt":"Many modern search domains comprise high-dimensional vectors of floating point numbers derived from neural networks, in the form of embeddings. Typical embeddings range in size from hundreds to thousands of dimensions, making the size of the embeddings, and the speed of comparison, a significant issue.\n  Quantisation is a class of mechanism which replaces the floating point values with a smaller representation, for example a short integer. This gives an approximation of the embedding space in return for a smaller data representation and a faster comparison function.\n  Here we take this idea al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00528","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/2506.00528/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":"2506.00528","created_at":"2026-07-05T11:13:36.521169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00528v1","created_at":"2026-07-05T11:13:36.521169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00528","created_at":"2026-07-05T11:13:36.521169+00:00"},{"alias_kind":"pith_short_12","alias_value":"44LJN5EITTOL","created_at":"2026-07-05T11:13:36.521169+00:00"},{"alias_kind":"pith_short_16","alias_value":"44LJN5EITTOL5S7H","created_at":"2026-07-05T11:13:36.521169+00:00"},{"alias_kind":"pith_short_8","alias_value":"44LJN5EI","created_at":"2026-07-05T11:13:36.521169+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/44LJN5EITTOL5S7HD6E3Q5LGKY","json":"https://pith.science/pith/44LJN5EITTOL5S7HD6E3Q5LGKY.json","graph_json":"https://pith.science/api/pith-number/44LJN5EITTOL5S7HD6E3Q5LGKY/graph.json","events_json":"https://pith.science/api/pith-number/44LJN5EITTOL5S7HD6E3Q5LGKY/events.json","paper":"https://pith.science/paper/44LJN5EI"},"agent_actions":{"view_html":"https://pith.science/pith/44LJN5EITTOL5S7HD6E3Q5LGKY","download_json":"https://pith.science/pith/44LJN5EITTOL5S7HD6E3Q5LGKY.json","view_paper":"https://pith.science/paper/44LJN5EI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00528&json=true","fetch_graph":"https://pith.science/api/pith-number/44LJN5EITTOL5S7HD6E3Q5LGKY/graph.json","fetch_events":"https://pith.science/api/pith-number/44LJN5EITTOL5S7HD6E3Q5LGKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44LJN5EITTOL5S7HD6E3Q5LGKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44LJN5EITTOL5S7HD6E3Q5LGKY/action/storage_attestation","attest_author":"https://pith.science/pith/44LJN5EITTOL5S7HD6E3Q5LGKY/action/author_attestation","sign_citation":"https://pith.science/pith/44LJN5EITTOL5S7HD6E3Q5LGKY/action/citation_signature","submit_replication":"https://pith.science/pith/44LJN5EITTOL5S7HD6E3Q5LGKY/action/replication_record"}},"created_at":"2026-07-05T11:13:36.521169+00:00","updated_at":"2026-07-05T11:13:36.521169+00:00"}