{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2277BSCJEQLXOYTD7QZMY63ZYK","short_pith_number":"pith:2277BSCJ","schema_version":"1.0","canonical_sha256":"d6bff0c8492417776263fc32cc7b79c2bf3d47fae3efaae6cfb811bd02867091","source":{"kind":"arxiv","id":"2507.10391","version":1},"attestation_state":"computed","paper":{"title":"Instance-Optimized String Fingerprints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alexander van Renen, Andreas Kipf, Andreas Zimmerer, Johannes Th\\\"urauf, Mihail Stoian","submitted_at":"2025-07-14T15:30:36Z","abstract_excerpt":"Recent research found that cloud data warehouses are text-heavy. However, their capabilities for efficiently processing string columns remain limited, relying primarily on techniques like dictionary encoding and prefix-based partition pruning. In recent work, we introduced string fingerprints - a lightweight secondary index structure designed to approximate LIKE predicates, albeit with false positives. This approach is particularly compelling for columnar query engines, where fingerprints can help reduce both compute and I/O overhead. We show that string fingerprints can be optimized for speci"},"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":"2507.10391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-07-14T15:30:36Z","cross_cats_sorted":[],"title_canon_sha256":"72581f9ca62eca6e2fb5d039161239ca15c4fc3b81f0525db8948ba6346a7edf","abstract_canon_sha256":"5653780bb3cc455bfe5c4a6318f40fa35d46d166d22965ca0708ce0545c8b396"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:50.620397Z","signature_b64":"rjS3qCYEM+oRV6pS9cWqPbTWN/drK6P47fAdR9rSaAwnUkDFzM+kyxfaLbXAaseGGn9WAWObdyfCu2uy1daIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6bff0c8492417776263fc32cc7b79c2bf3d47fae3efaae6cfb811bd02867091","last_reissued_at":"2026-07-05T11:36:50.619860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:50.619860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-Optimized String Fingerprints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alexander van Renen, Andreas Kipf, Andreas Zimmerer, Johannes Th\\\"urauf, Mihail Stoian","submitted_at":"2025-07-14T15:30:36Z","abstract_excerpt":"Recent research found that cloud data warehouses are text-heavy. However, their capabilities for efficiently processing string columns remain limited, relying primarily on techniques like dictionary encoding and prefix-based partition pruning. In recent work, we introduced string fingerprints - a lightweight secondary index structure designed to approximate LIKE predicates, albeit with false positives. This approach is particularly compelling for columnar query engines, where fingerprints can help reduce both compute and I/O overhead. We show that string fingerprints can be optimized for speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10391","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/2507.10391/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":"2507.10391","created_at":"2026-07-05T11:36:50.619922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10391v1","created_at":"2026-07-05T11:36:50.619922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10391","created_at":"2026-07-05T11:36:50.619922+00:00"},{"alias_kind":"pith_short_12","alias_value":"2277BSCJEQLX","created_at":"2026-07-05T11:36:50.619922+00:00"},{"alias_kind":"pith_short_16","alias_value":"2277BSCJEQLXOYTD","created_at":"2026-07-05T11:36:50.619922+00:00"},{"alias_kind":"pith_short_8","alias_value":"2277BSCJ","created_at":"2026-07-05T11:36:50.619922+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/2277BSCJEQLXOYTD7QZMY63ZYK","json":"https://pith.science/pith/2277BSCJEQLXOYTD7QZMY63ZYK.json","graph_json":"https://pith.science/api/pith-number/2277BSCJEQLXOYTD7QZMY63ZYK/graph.json","events_json":"https://pith.science/api/pith-number/2277BSCJEQLXOYTD7QZMY63ZYK/events.json","paper":"https://pith.science/paper/2277BSCJ"},"agent_actions":{"view_html":"https://pith.science/pith/2277BSCJEQLXOYTD7QZMY63ZYK","download_json":"https://pith.science/pith/2277BSCJEQLXOYTD7QZMY63ZYK.json","view_paper":"https://pith.science/paper/2277BSCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10391&json=true","fetch_graph":"https://pith.science/api/pith-number/2277BSCJEQLXOYTD7QZMY63ZYK/graph.json","fetch_events":"https://pith.science/api/pith-number/2277BSCJEQLXOYTD7QZMY63ZYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2277BSCJEQLXOYTD7QZMY63ZYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2277BSCJEQLXOYTD7QZMY63ZYK/action/storage_attestation","attest_author":"https://pith.science/pith/2277BSCJEQLXOYTD7QZMY63ZYK/action/author_attestation","sign_citation":"https://pith.science/pith/2277BSCJEQLXOYTD7QZMY63ZYK/action/citation_signature","submit_replication":"https://pith.science/pith/2277BSCJEQLXOYTD7QZMY63ZYK/action/replication_record"}},"created_at":"2026-07-05T11:36:50.619922+00:00","updated_at":"2026-07-05T11:36:50.619922+00:00"}