{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UANVZCO532HCHUYDIH2Q7PWYJM","short_pith_number":"pith:UANVZCO5","schema_version":"1.0","canonical_sha256":"a01b5c89ddde8e23d30341f50fbed84b2e7de5bab8c55b38884da8209c9f7b34","source":{"kind":"arxiv","id":"2606.04196","version":1},"attestation_state":"computed","paper":{"title":"Puffin-Backed Vector Indexes: Attaching Approximate Nearest Neighbor Indexes to Apache Iceberg Snapshots for Compute-Disaggregated Query Engines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Artur Borycki","submitted_at":"2026-06-02T20:27:42Z","abstract_excerpt":"We describe a design pattern and concrete implementation for embedding distributed approximate nearest neighbor indexes inside the Apache Iceberg table format, using the Puffin sidecar file as the storage container and the snapshot summary as the binding mechanism. Modern analytical query engines increasingly adopt a compute disaggregated architecture: executors are stateless, scale elastically, and read all data from object storage. Adding vector similarity search to such an engine traditionally requires a dedicated index storage layer with its own lifecycle, consistency model, and operationa"},"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":"2606.04196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-02T20:27:42Z","cross_cats_sorted":[],"title_canon_sha256":"f669fda946f4f908e1a71058b4ae3831eeb3c17583884f3da751345a1d82eeb5","abstract_canon_sha256":"ff823c3b351ef10cc18cf23804aeffeaeeb5a63400d4b44be737a17443d1b2fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:57.916109Z","signature_b64":"nUZSNvxc7Z4Qnq7zk5MdeQxoF4jQ/c7r4DBhiQTBcmVOxz54bE27C5kOuDnSxMC39YcUbhWODYTy+DBJOeM7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a01b5c89ddde8e23d30341f50fbed84b2e7de5bab8c55b38884da8209c9f7b34","last_reissued_at":"2026-06-04T01:08:57.915554Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:57.915554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Puffin-Backed Vector Indexes: Attaching Approximate Nearest Neighbor Indexes to Apache Iceberg Snapshots for Compute-Disaggregated Query Engines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Artur Borycki","submitted_at":"2026-06-02T20:27:42Z","abstract_excerpt":"We describe a design pattern and concrete implementation for embedding distributed approximate nearest neighbor indexes inside the Apache Iceberg table format, using the Puffin sidecar file as the storage container and the snapshot summary as the binding mechanism. Modern analytical query engines increasingly adopt a compute disaggregated architecture: executors are stateless, scale elastically, and read all data from object storage. Adding vector similarity search to such an engine traditionally requires a dedicated index storage layer with its own lifecycle, consistency model, and operationa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04196","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/2606.04196/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":"2606.04196","created_at":"2026-06-04T01:08:57.915619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04196v1","created_at":"2026-06-04T01:08:57.915619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04196","created_at":"2026-06-04T01:08:57.915619+00:00"},{"alias_kind":"pith_short_12","alias_value":"UANVZCO532HC","created_at":"2026-06-04T01:08:57.915619+00:00"},{"alias_kind":"pith_short_16","alias_value":"UANVZCO532HCHUYD","created_at":"2026-06-04T01:08:57.915619+00:00"},{"alias_kind":"pith_short_8","alias_value":"UANVZCO5","created_at":"2026-06-04T01:08:57.915619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05441","citing_title":"Filtered Vector Search in a Disaggregated Lakehouse: Composing Table-Format Pruning with Per-File ANN","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM","json":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM.json","graph_json":"https://pith.science/api/pith-number/UANVZCO532HCHUYDIH2Q7PWYJM/graph.json","events_json":"https://pith.science/api/pith-number/UANVZCO532HCHUYDIH2Q7PWYJM/events.json","paper":"https://pith.science/paper/UANVZCO5"},"agent_actions":{"view_html":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM","download_json":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM.json","view_paper":"https://pith.science/paper/UANVZCO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04196&json=true","fetch_graph":"https://pith.science/api/pith-number/UANVZCO532HCHUYDIH2Q7PWYJM/graph.json","fetch_events":"https://pith.science/api/pith-number/UANVZCO532HCHUYDIH2Q7PWYJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM/action/storage_attestation","attest_author":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM/action/author_attestation","sign_citation":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM/action/citation_signature","submit_replication":"https://pith.science/pith/UANVZCO532HCHUYDIH2Q7PWYJM/action/replication_record"}},"created_at":"2026-06-04T01:08:57.915619+00:00","updated_at":"2026-06-04T01:08:57.915619+00:00"}