{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:6L4G4E2MOWDESPQ7D4GFCPBHFM","short_pith_number":"pith:6L4G4E2M","schema_version":"1.0","canonical_sha256":"f2f86e134c7586493e1f1f0c513c272b2bf626e99bc58fca8932f5f2968170fc","source":{"kind":"arxiv","id":"1404.4693","version":1},"attestation_state":"computed","paper":{"title":"Consistent Subset Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Konstantin Kutzkov, Rasmus Pagh","submitted_at":"2014-04-18T06:09:42Z","abstract_excerpt":"Consistent sampling is a technique for specifying, in small space, a subset $S$ of a potentially large universe $U$ such that the elements in $S$ satisfy a suitably chosen sampling condition. Given a subset $\\mathcal{I}\\subseteq U$ it should be possible to quickly compute $\\mathcal{I}\\cap S$, i.e., the elements in $\\mathcal{I}$ satisfying the sampling condition. Consistent sampling has important applications in similarity estimation, and estimation of the number of distinct items in a data stream.\n  In this paper we generalize consistent sampling to the setting where we are interested in sampl"},"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":"1404.4693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-04-18T06:09:42Z","cross_cats_sorted":[],"title_canon_sha256":"9bdb8c6fe7780f16de8645ef42bb2f0bc40c56e9ef42ae0a0eeacf096f5b56e4","abstract_canon_sha256":"4878713086b72628e9c2089eb3ac1deb1f221d3957384dfdfa2fc73ec4b5abe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:53:55.377579Z","signature_b64":"dauRO6A6ek3xPisHrhrc5cGEyKP656ridNH+k7t2JhrxA6Ju9qqkRsDTR7rw9e1gX2DGo8+d1vykYx7rO5CWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2f86e134c7586493e1f1f0c513c272b2bf626e99bc58fca8932f5f2968170fc","last_reissued_at":"2026-05-18T02:53:55.376686Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:53:55.376686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistent Subset Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Konstantin Kutzkov, Rasmus Pagh","submitted_at":"2014-04-18T06:09:42Z","abstract_excerpt":"Consistent sampling is a technique for specifying, in small space, a subset $S$ of a potentially large universe $U$ such that the elements in $S$ satisfy a suitably chosen sampling condition. Given a subset $\\mathcal{I}\\subseteq U$ it should be possible to quickly compute $\\mathcal{I}\\cap S$, i.e., the elements in $\\mathcal{I}$ satisfying the sampling condition. Consistent sampling has important applications in similarity estimation, and estimation of the number of distinct items in a data stream.\n  In this paper we generalize consistent sampling to the setting where we are interested in sampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.4693","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":""},"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":"1404.4693","created_at":"2026-05-18T02:53:55.376825+00:00"},{"alias_kind":"arxiv_version","alias_value":"1404.4693v1","created_at":"2026-05-18T02:53:55.376825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.4693","created_at":"2026-05-18T02:53:55.376825+00:00"},{"alias_kind":"pith_short_12","alias_value":"6L4G4E2MOWDE","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"6L4G4E2MOWDESPQ7","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"6L4G4E2M","created_at":"2026-05-18T12:28:16.859392+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/6L4G4E2MOWDESPQ7D4GFCPBHFM","json":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM.json","graph_json":"https://pith.science/api/pith-number/6L4G4E2MOWDESPQ7D4GFCPBHFM/graph.json","events_json":"https://pith.science/api/pith-number/6L4G4E2MOWDESPQ7D4GFCPBHFM/events.json","paper":"https://pith.science/paper/6L4G4E2M"},"agent_actions":{"view_html":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM","download_json":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM.json","view_paper":"https://pith.science/paper/6L4G4E2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1404.4693&json=true","fetch_graph":"https://pith.science/api/pith-number/6L4G4E2MOWDESPQ7D4GFCPBHFM/graph.json","fetch_events":"https://pith.science/api/pith-number/6L4G4E2MOWDESPQ7D4GFCPBHFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/action/storage_attestation","attest_author":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/action/author_attestation","sign_citation":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/action/citation_signature","submit_replication":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/action/replication_record"}},"created_at":"2026-05-18T02:53:55.376825+00:00","updated_at":"2026-05-18T02:53:55.376825+00:00"}