{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:L653Y5GMATWSVDADX2YPPVDFWK","short_pith_number":"pith:L653Y5GM","schema_version":"1.0","canonical_sha256":"5fbbbc74cc04ed2a8c03beb0f7d465b2a0ada87f12ccca2df902806293bb0972","source":{"kind":"arxiv","id":"1611.00532","version":1},"attestation_state":"computed","paper":{"title":"An asymptotically optimal, online algorithm for weighted random sampling with replacement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Micha{\\l} Startek","submitted_at":"2016-11-02T10:20:21Z","abstract_excerpt":"This paper presents a novel algorithm solving the classic problem of generating a random sample of size s from population of size n with non-uniform probabilities. The sampling is done with replacement. The algorithm requires constant additional memory, and works in O(n) time (even when s >> n, in which case the algorithm produces a list containing, for every population member, the number of times it has been selected for sample). The algorithm works online, and as such is well-suited to processing streams. In addition, a novel method of mass-sampling from any discrete distribution using the a"},"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":"1611.00532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2016-11-02T10:20:21Z","cross_cats_sorted":[],"title_canon_sha256":"7b298cb88f6d46070f2d8a050cab7fc05fe0260908ab5b5aa7581c4df2a7fb3e","abstract_canon_sha256":"27f5354d89f366ef7bdaa0c3a51d8b0371e34bd8c3945ac9b79efbaa82b23dd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:32.518033Z","signature_b64":"7H0JeCgDR9D8CPSS6r/m4y8K8h6z4J1Mewn2kvNBuNC68QdjoArV7Ze30BeCo3X4lNO+k0mfyXV7RtV2J7/FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fbbbc74cc04ed2a8c03beb0f7d465b2a0ada87f12ccca2df902806293bb0972","last_reissued_at":"2026-05-18T01:00:32.517480Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:32.517480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An asymptotically optimal, online algorithm for weighted random sampling with replacement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Micha{\\l} Startek","submitted_at":"2016-11-02T10:20:21Z","abstract_excerpt":"This paper presents a novel algorithm solving the classic problem of generating a random sample of size s from population of size n with non-uniform probabilities. The sampling is done with replacement. The algorithm requires constant additional memory, and works in O(n) time (even when s >> n, in which case the algorithm produces a list containing, for every population member, the number of times it has been selected for sample). The algorithm works online, and as such is well-suited to processing streams. In addition, a novel method of mass-sampling from any discrete distribution using the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00532","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":"1611.00532","created_at":"2026-05-18T01:00:32.517565+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.00532v1","created_at":"2026-05-18T01:00:32.517565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00532","created_at":"2026-05-18T01:00:32.517565+00:00"},{"alias_kind":"pith_short_12","alias_value":"L653Y5GMATWS","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"L653Y5GMATWSVDAD","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"L653Y5GM","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.21996","citing_title":"StreamSampling.jl: Efficient Sampling from Data Streams in Julia","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK","json":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK.json","graph_json":"https://pith.science/api/pith-number/L653Y5GMATWSVDADX2YPPVDFWK/graph.json","events_json":"https://pith.science/api/pith-number/L653Y5GMATWSVDADX2YPPVDFWK/events.json","paper":"https://pith.science/paper/L653Y5GM"},"agent_actions":{"view_html":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK","download_json":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK.json","view_paper":"https://pith.science/paper/L653Y5GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.00532&json=true","fetch_graph":"https://pith.science/api/pith-number/L653Y5GMATWSVDADX2YPPVDFWK/graph.json","fetch_events":"https://pith.science/api/pith-number/L653Y5GMATWSVDADX2YPPVDFWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK/action/storage_attestation","attest_author":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK/action/author_attestation","sign_citation":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK/action/citation_signature","submit_replication":"https://pith.science/pith/L653Y5GMATWSVDADX2YPPVDFWK/action/replication_record"}},"created_at":"2026-05-18T01:00:32.517565+00:00","updated_at":"2026-05-18T01:00:32.517565+00:00"}