{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2008:B4UFZWIXQITSBBJNNI3H2MLKJO","short_pith_number":"pith:B4UFZWIX","schema_version":"1.0","canonical_sha256":"0f285cd917822720852d6a367d316a4b89a352c9950066a256bae42fd7fffc46","source":{"kind":"arxiv","id":"0803.0473","version":2},"attestation_state":"computed","paper":{"title":"Stream sampling for variance-optimal estimation of subset sums","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Carsten Lund, Edith Cohen, Haim Kaplan, Mikkel Thorup, Nick Duffield","submitted_at":"2008-03-04T15:12:24Z","abstract_excerpt":"From a high volume stream of weighted items, we want to maintain a generic sample of a certain limited size $k$ that we can later use to estimate the total weight of arbitrary subsets. This is the classic context of on-line reservoir sampling, thinking of the generic sample as a reservoir. We present an efficient reservoir sampling scheme, $\\varoptk$, that dominates all previous schemes in terms of estimation quality.\n  $\\varoptk$ provides {\\em variance optimal unbiased estimation of subset sums}. More precisely, if we have seen $n$ items of the stream, then for {\\em any} subset size $m$, our "},"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":"0803.0473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2008-03-04T15:12:24Z","cross_cats_sorted":[],"title_canon_sha256":"8c323efbf6f23d06b9d5c2b254912be36af2a56c50a9dae4aa7ed2a4189b81a5","abstract_canon_sha256":"1ac194437da8228d07de6b79ca92e0b5509bbc91e8c5d720414bd6a46a6b1cbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:35:57.506342Z","signature_b64":"0ve8lqp8ifdyDMPfQnHUjKX9yBSFYQOl4RC0B/5MI1ebCwxB4EMwbAqB1d+L6Agz1htxBkhjl2dhxv0Mof2TDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f285cd917822720852d6a367d316a4b89a352c9950066a256bae42fd7fffc46","last_reissued_at":"2026-05-18T04:35:57.505487Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:35:57.505487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stream sampling for variance-optimal estimation of subset sums","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Carsten Lund, Edith Cohen, Haim Kaplan, Mikkel Thorup, Nick Duffield","submitted_at":"2008-03-04T15:12:24Z","abstract_excerpt":"From a high volume stream of weighted items, we want to maintain a generic sample of a certain limited size $k$ that we can later use to estimate the total weight of arbitrary subsets. This is the classic context of on-line reservoir sampling, thinking of the generic sample as a reservoir. We present an efficient reservoir sampling scheme, $\\varoptk$, that dominates all previous schemes in terms of estimation quality.\n  $\\varoptk$ provides {\\em variance optimal unbiased estimation of subset sums}. More precisely, if we have seen $n$ items of the stream, then for {\\em any} subset size $m$, our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0803.0473","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":"0803.0473","created_at":"2026-05-18T04:35:57.505618+00:00"},{"alias_kind":"arxiv_version","alias_value":"0803.0473v2","created_at":"2026-05-18T04:35:57.505618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0803.0473","created_at":"2026-05-18T04:35:57.505618+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4UFZWIXQITS","created_at":"2026-05-18T12:25:56.245647+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4UFZWIXQITSBBJN","created_at":"2026-05-18T12:25:56.245647+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4UFZWIX","created_at":"2026-05-18T12:25:56.245647+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/B4UFZWIXQITSBBJNNI3H2MLKJO","json":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO.json","graph_json":"https://pith.science/api/pith-number/B4UFZWIXQITSBBJNNI3H2MLKJO/graph.json","events_json":"https://pith.science/api/pith-number/B4UFZWIXQITSBBJNNI3H2MLKJO/events.json","paper":"https://pith.science/paper/B4UFZWIX"},"agent_actions":{"view_html":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO","download_json":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO.json","view_paper":"https://pith.science/paper/B4UFZWIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0803.0473&json=true","fetch_graph":"https://pith.science/api/pith-number/B4UFZWIXQITSBBJNNI3H2MLKJO/graph.json","fetch_events":"https://pith.science/api/pith-number/B4UFZWIXQITSBBJNNI3H2MLKJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/action/storage_attestation","attest_author":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/action/author_attestation","sign_citation":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/action/citation_signature","submit_replication":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/action/replication_record"}},"created_at":"2026-05-18T04:35:57.505618+00:00","updated_at":"2026-05-18T04:35:57.505618+00:00"}