{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KGSJSKMQ2U4F23ZTNORAOE6555","short_pith_number":"pith:KGSJSKMQ","schema_version":"1.0","canonical_sha256":"51a4992990d5385d6f336ba20713ddef63ab0ec56515848c81a0ab6af8979e36","source":{"kind":"arxiv","id":"2312.01025","version":1},"attestation_state":"computed","paper":{"title":"Adding Domain Knowledge to Query-Driven Learned Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Peizhi Wu, Ryan Marcus, Zachary G. Ives","submitted_at":"2023-12-02T04:21:29Z","abstract_excerpt":"In recent years, \\emph{learned cardinality estimation} has emerged as an alternative to traditional query optimization methods: by training machine learning models over observed query performance, learned cardinality estimation techniques can accurately predict query cardinalities and costs -- accounting for skew, correlated predicates, and many other factors that traditional methods struggle to capture. However, query-driven learned cardinality estimators are dependent on sample workloads, requiring vast amounts of labeled queries. Further, we show that state-of-the-art query-driven technique"},"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":"2312.01025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-12-02T04:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"682221550aedeb98cbcde60083b1f6d21e8cb596e64b4ece30b8e649d536c64e","abstract_canon_sha256":"405a02e608c0cdff3b5b64f19672d2a700dde48bd22e0ad34204d149f800f375"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:28.111469Z","signature_b64":"KirTkdPmcKNpatcZYFqF3lA4Mz/n4Mc6Y//CoJcsUyAmKhkdtzcySU79K+sxhqFG2oZGas5QQjg0NT4kS6PyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51a4992990d5385d6f336ba20713ddef63ab0ec56515848c81a0ab6af8979e36","last_reissued_at":"2026-07-05T07:19:28.111025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:28.111025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adding Domain Knowledge to Query-Driven Learned Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Peizhi Wu, Ryan Marcus, Zachary G. Ives","submitted_at":"2023-12-02T04:21:29Z","abstract_excerpt":"In recent years, \\emph{learned cardinality estimation} has emerged as an alternative to traditional query optimization methods: by training machine learning models over observed query performance, learned cardinality estimation techniques can accurately predict query cardinalities and costs -- accounting for skew, correlated predicates, and many other factors that traditional methods struggle to capture. However, query-driven learned cardinality estimators are dependent on sample workloads, requiring vast amounts of labeled queries. Further, we show that state-of-the-art query-driven technique"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01025","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/2312.01025/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":"2312.01025","created_at":"2026-07-05T07:19:28.111081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01025v1","created_at":"2026-07-05T07:19:28.111081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01025","created_at":"2026-07-05T07:19:28.111081+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGSJSKMQ2U4F","created_at":"2026-07-05T07:19:28.111081+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGSJSKMQ2U4F23ZT","created_at":"2026-07-05T07:19:28.111081+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGSJSKMQ","created_at":"2026-07-05T07:19:28.111081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.02284","citing_title":"Conformal Prediction for Verifiable Learned Query Optimization","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555","json":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555.json","graph_json":"https://pith.science/api/pith-number/KGSJSKMQ2U4F23ZTNORAOE6555/graph.json","events_json":"https://pith.science/api/pith-number/KGSJSKMQ2U4F23ZTNORAOE6555/events.json","paper":"https://pith.science/paper/KGSJSKMQ"},"agent_actions":{"view_html":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555","download_json":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555.json","view_paper":"https://pith.science/paper/KGSJSKMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01025&json=true","fetch_graph":"https://pith.science/api/pith-number/KGSJSKMQ2U4F23ZTNORAOE6555/graph.json","fetch_events":"https://pith.science/api/pith-number/KGSJSKMQ2U4F23ZTNORAOE6555/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555/action/storage_attestation","attest_author":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555/action/author_attestation","sign_citation":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555/action/citation_signature","submit_replication":"https://pith.science/pith/KGSJSKMQ2U4F23ZTNORAOE6555/action/replication_record"}},"created_at":"2026-07-05T07:19:28.111081+00:00","updated_at":"2026-07-05T07:19:28.111081+00:00"}