{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XLHESHABEBY2IOFRT33M47MP3I","short_pith_number":"pith:XLHESHAB","schema_version":"1.0","canonical_sha256":"bace491c012071a438b19ef6ce7d8fda10abc9806e5dcd65a0a457902334d153","source":{"kind":"arxiv","id":"2303.00940","version":2},"attestation_state":"computed","paper":{"title":"Sampling over Union of Joins","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Fatemeh Nargesian, Yunlong Xu, Yurong Liu","submitted_at":"2023-03-02T03:27:52Z","abstract_excerpt":"Data scientists often draw on multiple relational data sources for analysis. A standard assumption in learning and approximate query answering is that the data is a uniform and independent sample of the underlying distribution. To avoid the cost of join and union, given a set of joins, we study the problem of obtaining a random sample from the union of joins without performing the full join and union. We present a general framework for random sampling over the set union of chain, acyclic, and cyclic joins, with sample uniformity and independence guarantees. We study the novel problem of the un"},"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":"2303.00940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-03-02T03:27:52Z","cross_cats_sorted":[],"title_canon_sha256":"f593e4fc7483651a90c54e78e1d7db14e4da63bbc342e4e067d5224ff5dc7cb0","abstract_canon_sha256":"0a13761b47198f64f334c6dd74555b93a564fbd7e1a2fb76945f028bd6e5ceed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:33.466272Z","signature_b64":"hwnoRX6WD7TR6w1VUZ1avO0O5jNwUiA1k68HdBdOMxf+2i7WAKCRdceqCStU76ZokANsceShUhkxmEGkUNJnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bace491c012071a438b19ef6ce7d8fda10abc9806e5dcd65a0a457902334d153","last_reissued_at":"2026-07-05T05:49:33.465851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:33.465851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling over Union of Joins","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Fatemeh Nargesian, Yunlong Xu, Yurong Liu","submitted_at":"2023-03-02T03:27:52Z","abstract_excerpt":"Data scientists often draw on multiple relational data sources for analysis. A standard assumption in learning and approximate query answering is that the data is a uniform and independent sample of the underlying distribution. To avoid the cost of join and union, given a set of joins, we study the problem of obtaining a random sample from the union of joins without performing the full join and union. We present a general framework for random sampling over the set union of chain, acyclic, and cyclic joins, with sample uniformity and independence guarantees. We study the novel problem of the un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00940","kind":"arxiv","version":2},"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/2303.00940/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":"2303.00940","created_at":"2026-07-05T05:49:33.465919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00940v2","created_at":"2026-07-05T05:49:33.465919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00940","created_at":"2026-07-05T05:49:33.465919+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLHESHABEBY2","created_at":"2026-07-05T05:49:33.465919+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLHESHABEBY2IOFR","created_at":"2026-07-05T05:49:33.465919+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLHESHAB","created_at":"2026-07-05T05:49:33.465919+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/XLHESHABEBY2IOFRT33M47MP3I","json":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I.json","graph_json":"https://pith.science/api/pith-number/XLHESHABEBY2IOFRT33M47MP3I/graph.json","events_json":"https://pith.science/api/pith-number/XLHESHABEBY2IOFRT33M47MP3I/events.json","paper":"https://pith.science/paper/XLHESHAB"},"agent_actions":{"view_html":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I","download_json":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I.json","view_paper":"https://pith.science/paper/XLHESHAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00940&json=true","fetch_graph":"https://pith.science/api/pith-number/XLHESHABEBY2IOFRT33M47MP3I/graph.json","fetch_events":"https://pith.science/api/pith-number/XLHESHABEBY2IOFRT33M47MP3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/action/storage_attestation","attest_author":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/action/author_attestation","sign_citation":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/action/citation_signature","submit_replication":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/action/replication_record"}},"created_at":"2026-07-05T05:49:33.465919+00:00","updated_at":"2026-07-05T05:49:33.465919+00:00"}