{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GJQ67D37R7YW6BFOCRBU6264ZB","short_pith_number":"pith:GJQ67D37","schema_version":"1.0","canonical_sha256":"3261ef8f7f8ff16f04ae14434f6bdcc85e3897b9d7c41dc13950d99d9dbfc148","source":{"kind":"arxiv","id":"2608.05441","version":1},"attestation_state":"computed","paper":{"title":"Filtered Vector Search in a Disaggregated Lakehouse: Composing Table-Format Pruning with Per-File ANN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.ET","cs.IR"],"primary_cat":"cs.DB","authors_text":"Rakesh Jain, Syed Zawad (IBM Research), Thomas Griffin","submitted_at":"2026-08-05T22:20:01Z","abstract_excerpt":"Approximate nearest-neighbor (ANN) search increasingly runs alongside structured data - \"find the 10 nearest documents where tenant='acme' AND lang='en'\" - yet similarity and filtering are usually bolted together: a specialized vector index for one, a separate filter step for the other. We ask what happens when both live inside an open lakehouse table (Apache Iceberg over Parquet on object storage), where the engine already owns a mature file-pruning stack (partition pruning, zone-maps, a bitmap index). We embed an IVF index in place in each Parquet file's footer and make filtered vector queri"},"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":"2608.05441","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-05T22:20:01Z","cross_cats_sorted":["cs.DC","cs.ET","cs.IR"],"title_canon_sha256":"71344a41474d3ea28d76ee76fe4dc6128c15d16abfdf64dee47587d6682d4cd2","abstract_canon_sha256":"a28f8856840fb921a39cdd0e0865f696975881b9f5342e2c204b6967ca31852e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:47:52.051945Z","signature_b64":"YopcZ3YFNC/6FKvm4imX68Hkxs4ByKVVJOwTPx8mMosOHguiK3Exg0/QucHgAfad5mHL/hhfus2Eqq2lEr7mCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3261ef8f7f8ff16f04ae14434f6bdcc85e3897b9d7c41dc13950d99d9dbfc148","last_reissued_at":"2026-08-07T00:47:52.050342Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:47:52.050342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Filtered Vector Search in a Disaggregated Lakehouse: Composing Table-Format Pruning with Per-File ANN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.ET","cs.IR"],"primary_cat":"cs.DB","authors_text":"Rakesh Jain, Syed Zawad (IBM Research), Thomas Griffin","submitted_at":"2026-08-05T22:20:01Z","abstract_excerpt":"Approximate nearest-neighbor (ANN) search increasingly runs alongside structured data - \"find the 10 nearest documents where tenant='acme' AND lang='en'\" - yet similarity and filtering are usually bolted together: a specialized vector index for one, a separate filter step for the other. We ask what happens when both live inside an open lakehouse table (Apache Iceberg over Parquet on object storage), where the engine already owns a mature file-pruning stack (partition pruning, zone-maps, a bitmap index). We embed an IVF index in place in each Parquet file's footer and make filtered vector queri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05441","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/2608.05441/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":"2608.05441","created_at":"2026-08-07T00:47:52.051808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05441v1","created_at":"2026-08-07T00:47:52.051808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05441","created_at":"2026-08-07T00:47:52.051808+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJQ67D37R7YW","created_at":"2026-08-07T00:47:52.051808+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJQ67D37R7YW6BFO","created_at":"2026-08-07T00:47:52.051808+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJQ67D37","created_at":"2026-08-07T00:47:52.051808+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/GJQ67D37R7YW6BFOCRBU6264ZB","json":"https://pith.science/pith/GJQ67D37R7YW6BFOCRBU6264ZB.json","graph_json":"https://pith.science/api/pith-number/GJQ67D37R7YW6BFOCRBU6264ZB/graph.json","events_json":"https://pith.science/api/pith-number/GJQ67D37R7YW6BFOCRBU6264ZB/events.json","paper":"https://pith.science/paper/GJQ67D37"},"agent_actions":{"view_html":"https://pith.science/pith/GJQ67D37R7YW6BFOCRBU6264ZB","download_json":"https://pith.science/pith/GJQ67D37R7YW6BFOCRBU6264ZB.json","view_paper":"https://pith.science/paper/GJQ67D37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05441&json=true","fetch_graph":"https://pith.science/api/pith-number/GJQ67D37R7YW6BFOCRBU6264ZB/graph.json","fetch_events":"https://pith.science/api/pith-number/GJQ67D37R7YW6BFOCRBU6264ZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJQ67D37R7YW6BFOCRBU6264ZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJQ67D37R7YW6BFOCRBU6264ZB/action/storage_attestation","attest_author":"https://pith.science/pith/GJQ67D37R7YW6BFOCRBU6264ZB/action/author_attestation","sign_citation":"https://pith.science/pith/GJQ67D37R7YW6BFOCRBU6264ZB/action/citation_signature","submit_replication":"https://pith.science/pith/GJQ67D37R7YW6BFOCRBU6264ZB/action/replication_record"}},"created_at":"2026-08-07T00:47:52.051808+00:00","updated_at":"2026-08-07T00:47:52.051808+00:00"}