{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XTOG3WKQLU4ORQ6SGL3WDSGTQW","short_pith_number":"pith:XTOG3WKQ","schema_version":"1.0","canonical_sha256":"bcdc6dd9505d38e8c3d232f761c8d3858c71f53b5dca0f75735cd43b505d7a94","source":{"kind":"arxiv","id":"1912.03443","version":4},"attestation_state":"computed","paper":{"title":"Joins on Samples: A Theoretical Guide for Practitioners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Barzan Mozafari, Dawei Huang, Dong Young Yoon, Seth Pettie","submitted_at":"2019-12-07T05:20:43Z","abstract_excerpt":"Despite decades of research on approximate query processing (AQP), our understanding of sample-based joins has remained limited and, to some extent, even superficial. The common belief in the community is that joining random samples is futile. This belief is largely based on an early result showing that the join of two uniform samples is not an independent sample of the original join, and that it leads to quadratically fewer output tuples. However, unfortunately, this result has little applicability to the key questions practitioners face. For example, the success metric is often the final app"},"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":"1912.03443","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-12-07T05:20:43Z","cross_cats_sorted":[],"title_canon_sha256":"a5c965ae3889b13ac377ac238fcd3d09ef4430059486ff77315077865fc82a5f","abstract_canon_sha256":"58051f03f7d606bc3f55bc2ec0d987ebb5e0889b14e25d51354da5ea95273ff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:53.950951Z","signature_b64":"gWkfKn58jlvgy3G8ByOZm7OGzyJbELBHTQGQEWSx1YVQ6cplwbIZ17aYuvJEnUKlYcm85YmP3GKAI6Gw9+ACCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcdc6dd9505d38e8c3d232f761c8d3858c71f53b5dca0f75735cd43b505d7a94","last_reissued_at":"2026-07-05T00:35:53.950468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:53.950468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joins on Samples: A Theoretical Guide for Practitioners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Barzan Mozafari, Dawei Huang, Dong Young Yoon, Seth Pettie","submitted_at":"2019-12-07T05:20:43Z","abstract_excerpt":"Despite decades of research on approximate query processing (AQP), our understanding of sample-based joins has remained limited and, to some extent, even superficial. The common belief in the community is that joining random samples is futile. This belief is largely based on an early result showing that the join of two uniform samples is not an independent sample of the original join, and that it leads to quadratically fewer output tuples. However, unfortunately, this result has little applicability to the key questions practitioners face. For example, the success metric is often the final app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03443","kind":"arxiv","version":4},"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/1912.03443/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":"1912.03443","created_at":"2026-07-05T00:35:53.950523+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03443v4","created_at":"2026-07-05T00:35:53.950523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03443","created_at":"2026-07-05T00:35:53.950523+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTOG3WKQLU4O","created_at":"2026-07-05T00:35:53.950523+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTOG3WKQLU4ORQ6S","created_at":"2026-07-05T00:35:53.950523+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTOG3WKQ","created_at":"2026-07-05T00:35:53.950523+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/XTOG3WKQLU4ORQ6SGL3WDSGTQW","json":"https://pith.science/pith/XTOG3WKQLU4ORQ6SGL3WDSGTQW.json","graph_json":"https://pith.science/api/pith-number/XTOG3WKQLU4ORQ6SGL3WDSGTQW/graph.json","events_json":"https://pith.science/api/pith-number/XTOG3WKQLU4ORQ6SGL3WDSGTQW/events.json","paper":"https://pith.science/paper/XTOG3WKQ"},"agent_actions":{"view_html":"https://pith.science/pith/XTOG3WKQLU4ORQ6SGL3WDSGTQW","download_json":"https://pith.science/pith/XTOG3WKQLU4ORQ6SGL3WDSGTQW.json","view_paper":"https://pith.science/paper/XTOG3WKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03443&json=true","fetch_graph":"https://pith.science/api/pith-number/XTOG3WKQLU4ORQ6SGL3WDSGTQW/graph.json","fetch_events":"https://pith.science/api/pith-number/XTOG3WKQLU4ORQ6SGL3WDSGTQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTOG3WKQLU4ORQ6SGL3WDSGTQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTOG3WKQLU4ORQ6SGL3WDSGTQW/action/storage_attestation","attest_author":"https://pith.science/pith/XTOG3WKQLU4ORQ6SGL3WDSGTQW/action/author_attestation","sign_citation":"https://pith.science/pith/XTOG3WKQLU4ORQ6SGL3WDSGTQW/action/citation_signature","submit_replication":"https://pith.science/pith/XTOG3WKQLU4ORQ6SGL3WDSGTQW/action/replication_record"}},"created_at":"2026-07-05T00:35:53.950523+00:00","updated_at":"2026-07-05T00:35:53.950523+00:00"}