{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GBPZQ3LKFFBWPDRBQBR25DJ5GC","short_pith_number":"pith:GBPZQ3LK","schema_version":"1.0","canonical_sha256":"305f986d6a2943678e218063ae8d3d30a61739b9969258f9947399a540742761","source":{"kind":"arxiv","id":"1601.05118","version":2},"attestation_state":"computed","paper":{"title":"Perfect and Maximum Randomness in Stratified Sampling over Joins","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arnab Nandi, Niranjan Kamat","submitted_at":"2016-01-19T22:18:56Z","abstract_excerpt":"Supporting sampling in the presence of joins is an important problem in data analysis, but is inherently challenging due to the need to avoid correlation between output tuples. Current solutions provide either correlated or non-correlated samples. Sampling might not always be feasible in the non-correlated sampling-based approaches -- the sample size or intermediate data size might be exceedingly large. On the other hand, a correlated sample may not be representative of the join. This paper presents a \\emph{unified} strategy towards join sampling, while considering sample correlation every ste"},"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":"1601.05118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-01-19T22:18:56Z","cross_cats_sorted":[],"title_canon_sha256":"66f6dc886b52800c55acde859c99c81c39b507a3ca9a97d4fb17777f113d0a26","abstract_canon_sha256":"f65f7580b82a42b9bcb7f2cd5c2a2849a881672516f66f46d63070de30af5f31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:47.972992Z","signature_b64":"X8r3/KrardDA6UsFaOzDNqZ2KKkdpsqS0gtChbbgqqS6oPjV6nMPq8FNpBpN5OFdA3qxsY/zyhGxYL1mmyB1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"305f986d6a2943678e218063ae8d3d30a61739b9969258f9947399a540742761","last_reissued_at":"2026-05-18T00:50:47.972285Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:47.972285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perfect and Maximum Randomness in Stratified Sampling over Joins","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arnab Nandi, Niranjan Kamat","submitted_at":"2016-01-19T22:18:56Z","abstract_excerpt":"Supporting sampling in the presence of joins is an important problem in data analysis, but is inherently challenging due to the need to avoid correlation between output tuples. Current solutions provide either correlated or non-correlated samples. Sampling might not always be feasible in the non-correlated sampling-based approaches -- the sample size or intermediate data size might be exceedingly large. On the other hand, a correlated sample may not be representative of the join. This paper presents a \\emph{unified} strategy towards join sampling, while considering sample correlation every ste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.05118","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":""},"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":"1601.05118","created_at":"2026-05-18T00:50:47.972414+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.05118v2","created_at":"2026-05-18T00:50:47.972414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.05118","created_at":"2026-05-18T00:50:47.972414+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBPZQ3LKFFBW","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBPZQ3LKFFBWPDRB","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBPZQ3LK","created_at":"2026-05-18T12:30:15.759754+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/GBPZQ3LKFFBWPDRBQBR25DJ5GC","json":"https://pith.science/pith/GBPZQ3LKFFBWPDRBQBR25DJ5GC.json","graph_json":"https://pith.science/api/pith-number/GBPZQ3LKFFBWPDRBQBR25DJ5GC/graph.json","events_json":"https://pith.science/api/pith-number/GBPZQ3LKFFBWPDRBQBR25DJ5GC/events.json","paper":"https://pith.science/paper/GBPZQ3LK"},"agent_actions":{"view_html":"https://pith.science/pith/GBPZQ3LKFFBWPDRBQBR25DJ5GC","download_json":"https://pith.science/pith/GBPZQ3LKFFBWPDRBQBR25DJ5GC.json","view_paper":"https://pith.science/paper/GBPZQ3LK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.05118&json=true","fetch_graph":"https://pith.science/api/pith-number/GBPZQ3LKFFBWPDRBQBR25DJ5GC/graph.json","fetch_events":"https://pith.science/api/pith-number/GBPZQ3LKFFBWPDRBQBR25DJ5GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBPZQ3LKFFBWPDRBQBR25DJ5GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBPZQ3LKFFBWPDRBQBR25DJ5GC/action/storage_attestation","attest_author":"https://pith.science/pith/GBPZQ3LKFFBWPDRBQBR25DJ5GC/action/author_attestation","sign_citation":"https://pith.science/pith/GBPZQ3LKFFBWPDRBQBR25DJ5GC/action/citation_signature","submit_replication":"https://pith.science/pith/GBPZQ3LKFFBWPDRBQBR25DJ5GC/action/replication_record"}},"created_at":"2026-05-18T00:50:47.972414+00:00","updated_at":"2026-05-18T00:50:47.972414+00:00"}