{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZBLULL6STRVLEWFPEKYVUC4EUB","short_pith_number":"pith:ZBLULL6S","schema_version":"1.0","canonical_sha256":"c85745afd29c6ab258af22b15a0b84a06b3658a6ac41fe125a9d49d88bcc1820","source":{"kind":"arxiv","id":"1706.01172","version":1},"attestation_state":"computed","paper":{"title":"Improved Consistent Weighted Sampling Revisited","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Bin Li, Chengqi Zhang, Ling Chen, Philip S. Yu, Wei Wu","submitted_at":"2017-06-05T01:17:13Z","abstract_excerpt":"Min-Hash is a popular technique for efficiently estimating the Jaccard similarity of binary sets. Consistent Weighted Sampling (CWS) generalizes the Min-Hash scheme to sketch weighted sets and has drawn increasing interest from the community. Due to its constant-time complexity independent of the values of the weights, Improved CWS (ICWS) is considered as the state-of-the-art CWS algorithm. In this paper, we revisit ICWS and analyze its underlying mechanism to show that there actually exists dependence between the two components of the hash-code produced by ICWS, which violates the condition o"},"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":"1706.01172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-06-05T01:17:13Z","cross_cats_sorted":[],"title_canon_sha256":"2ecbe1b5a3292def92654600bb19fcb551ce97995ca7205200e20e3a0931376b","abstract_canon_sha256":"c1f048619ef946494f5ecb41473fa5c36c6f375e18ba83e773a82139e567a4d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:04.284822Z","signature_b64":"by41Sq+CSzisf5J84xMAuFbmyrtDT2xk35lS4959RkABgEUaC5q943Rw3oQTbeAmcOZYefS0/WrxPRW2ADHwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c85745afd29c6ab258af22b15a0b84a06b3658a6ac41fe125a9d49d88bcc1820","last_reissued_at":"2026-05-18T00:43:04.284056Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:04.284056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Consistent Weighted Sampling Revisited","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Bin Li, Chengqi Zhang, Ling Chen, Philip S. Yu, Wei Wu","submitted_at":"2017-06-05T01:17:13Z","abstract_excerpt":"Min-Hash is a popular technique for efficiently estimating the Jaccard similarity of binary sets. Consistent Weighted Sampling (CWS) generalizes the Min-Hash scheme to sketch weighted sets and has drawn increasing interest from the community. Due to its constant-time complexity independent of the values of the weights, Improved CWS (ICWS) is considered as the state-of-the-art CWS algorithm. In this paper, we revisit ICWS and analyze its underlying mechanism to show that there actually exists dependence between the two components of the hash-code produced by ICWS, which violates the condition o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01172","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":"1706.01172","created_at":"2026-05-18T00:43:04.284185+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01172v1","created_at":"2026-05-18T00:43:04.284185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01172","created_at":"2026-05-18T00:43:04.284185+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBLULL6STRVL","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBLULL6STRVLEWFP","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBLULL6S","created_at":"2026-05-18T12:31:59.375834+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/ZBLULL6STRVLEWFPEKYVUC4EUB","json":"https://pith.science/pith/ZBLULL6STRVLEWFPEKYVUC4EUB.json","graph_json":"https://pith.science/api/pith-number/ZBLULL6STRVLEWFPEKYVUC4EUB/graph.json","events_json":"https://pith.science/api/pith-number/ZBLULL6STRVLEWFPEKYVUC4EUB/events.json","paper":"https://pith.science/paper/ZBLULL6S"},"agent_actions":{"view_html":"https://pith.science/pith/ZBLULL6STRVLEWFPEKYVUC4EUB","download_json":"https://pith.science/pith/ZBLULL6STRVLEWFPEKYVUC4EUB.json","view_paper":"https://pith.science/paper/ZBLULL6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01172&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBLULL6STRVLEWFPEKYVUC4EUB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBLULL6STRVLEWFPEKYVUC4EUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBLULL6STRVLEWFPEKYVUC4EUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBLULL6STRVLEWFPEKYVUC4EUB/action/storage_attestation","attest_author":"https://pith.science/pith/ZBLULL6STRVLEWFPEKYVUC4EUB/action/author_attestation","sign_citation":"https://pith.science/pith/ZBLULL6STRVLEWFPEKYVUC4EUB/action/citation_signature","submit_replication":"https://pith.science/pith/ZBLULL6STRVLEWFPEKYVUC4EUB/action/replication_record"}},"created_at":"2026-05-18T00:43:04.284185+00:00","updated_at":"2026-05-18T00:43:04.284185+00:00"}