{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:NK6DBZKVBOOBLIBU4FQR7547VR","short_pith_number":"pith:NK6DBZKV","schema_version":"1.0","canonical_sha256":"6abc30e5550b9c15a034e1611ff79fac7996b47105e580fdcb1fdbcdef46858f","source":{"kind":"arxiv","id":"1101.5805","version":3},"attestation_state":"computed","paper":{"title":"The VC-Dimension of Queries and Selectivity Estimation Through Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"cs.DB","authors_text":"Eli Upfal, Matteo Riondato, Mert Akdere, Stanley B. Zdonik, Ugur Cetintemel","submitted_at":"2011-01-30T19:13:43Z","abstract_excerpt":"We develop a novel method, based on the statistical concept of the Vapnik-Chervonenkis dimension, to evaluate the selectivity (output cardinality) of SQL queries - a crucial step in optimizing the execution of large scale database and data-mining operations. The major theoretical contribution of this work, which is of independent interest, is an explicit bound to the VC-dimension of a range space defined by all possible outcomes of a collection (class) of queries. We prove that the VC-dimension is a function of the maximum number of Boolean operations in the selection predicate and of the maxi"},"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":"1101.5805","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2011-01-30T19:13:43Z","cross_cats_sorted":["cs.DS","cs.LG"],"title_canon_sha256":"c39f51a2b0dc83482e0a1326af890c557f7257154b25ef3216d287a7a4b585c4","abstract_canon_sha256":"54ecdb01f8def3cb43e0cc1996a9e8de99a3376b13862112c564d6ec8636d044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:22:41.929226Z","signature_b64":"sn0b01TPx7ze3aCUb96UBuSF4ruXxjmq1byeL9F01SZ/+9AgGt0mOxWZgfuqAe1LF7dCbloLpPMJw9/a2Bv/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6abc30e5550b9c15a034e1611ff79fac7996b47105e580fdcb1fdbcdef46858f","last_reissued_at":"2026-05-18T02:22:41.928602Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:22:41.928602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The VC-Dimension of Queries and Selectivity Estimation Through Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"cs.DB","authors_text":"Eli Upfal, Matteo Riondato, Mert Akdere, Stanley B. Zdonik, Ugur Cetintemel","submitted_at":"2011-01-30T19:13:43Z","abstract_excerpt":"We develop a novel method, based on the statistical concept of the Vapnik-Chervonenkis dimension, to evaluate the selectivity (output cardinality) of SQL queries - a crucial step in optimizing the execution of large scale database and data-mining operations. The major theoretical contribution of this work, which is of independent interest, is an explicit bound to the VC-dimension of a range space defined by all possible outcomes of a collection (class) of queries. We prove that the VC-dimension is a function of the maximum number of Boolean operations in the selection predicate and of the maxi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1101.5805","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1101.5805","created_at":"2026-05-18T02:22:41.928694+00:00"},{"alias_kind":"arxiv_version","alias_value":"1101.5805v3","created_at":"2026-05-18T02:22:41.928694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1101.5805","created_at":"2026-05-18T02:22:41.928694+00:00"},{"alias_kind":"pith_short_12","alias_value":"NK6DBZKVBOOB","created_at":"2026-05-18T12:26:37.096874+00:00"},{"alias_kind":"pith_short_16","alias_value":"NK6DBZKVBOOBLIBU","created_at":"2026-05-18T12:26:37.096874+00:00"},{"alias_kind":"pith_short_8","alias_value":"NK6DBZKV","created_at":"2026-05-18T12:26:37.096874+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/NK6DBZKVBOOBLIBU4FQR7547VR","json":"https://pith.science/pith/NK6DBZKVBOOBLIBU4FQR7547VR.json","graph_json":"https://pith.science/api/pith-number/NK6DBZKVBOOBLIBU4FQR7547VR/graph.json","events_json":"https://pith.science/api/pith-number/NK6DBZKVBOOBLIBU4FQR7547VR/events.json","paper":"https://pith.science/paper/NK6DBZKV"},"agent_actions":{"view_html":"https://pith.science/pith/NK6DBZKVBOOBLIBU4FQR7547VR","download_json":"https://pith.science/pith/NK6DBZKVBOOBLIBU4FQR7547VR.json","view_paper":"https://pith.science/paper/NK6DBZKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1101.5805&json=true","fetch_graph":"https://pith.science/api/pith-number/NK6DBZKVBOOBLIBU4FQR7547VR/graph.json","fetch_events":"https://pith.science/api/pith-number/NK6DBZKVBOOBLIBU4FQR7547VR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NK6DBZKVBOOBLIBU4FQR7547VR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NK6DBZKVBOOBLIBU4FQR7547VR/action/storage_attestation","attest_author":"https://pith.science/pith/NK6DBZKVBOOBLIBU4FQR7547VR/action/author_attestation","sign_citation":"https://pith.science/pith/NK6DBZKVBOOBLIBU4FQR7547VR/action/citation_signature","submit_replication":"https://pith.science/pith/NK6DBZKVBOOBLIBU4FQR7547VR/action/replication_record"}},"created_at":"2026-05-18T02:22:41.928694+00:00","updated_at":"2026-05-18T02:22:41.928694+00:00"}