{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:5ORUJSF4ZMSHSHXYTCLH2CM6S4","short_pith_number":"pith:5ORUJSF4","schema_version":"1.0","canonical_sha256":"eba344c8bccb24791ef898967d099e971aa4ae2631ca63741c206bdd47b4f5ea","source":{"kind":"arxiv","id":"1411.7191","version":3},"attestation_state":"computed","paper":{"title":"Hashing for statistics over k-partitions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Eva Rotenberg, Mathias B{\\ae}k Tejs Knudsen, Mikkel Thorup, S{\\o}ren Dahlgaard","submitted_at":"2014-11-26T11:36:15Z","abstract_excerpt":"In this paper we analyze a hash function for $k$-partitioning a set into bins, obtaining strong concentration bounds for standard algorithms combining statistics from each bin.\n  This generic method was originally introduced by Flajolet and Martin~[FOCS'83] in order to save a factor $\\Omega(k)$ of time per element over $k$ independent samples when estimating the number of distinct elements in a data stream. It was also used in the widely used HyperLogLog algorithm of Flajolet et al.~[AOFA'97] and in large-scale machine learning by Li et al.~[NIPS'12] for minwise estimation of set similarity.\n "},"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":"1411.7191","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-11-26T11:36:15Z","cross_cats_sorted":[],"title_canon_sha256":"7f71698fa1ea4d1cef1358b29f177a90a8f937c02dd89f7790a42fcaee274a7d","abstract_canon_sha256":"cc72e2ee251540299d45b73b2c57aa745f8715369c350615bd83611788235e4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:50.622359Z","signature_b64":"32KQbtZO+8LCH9JoGgHpa0rMFjV3D3gQOKcZFusOVBYiLr9Qr7XnOweTfGOW9JS2XaLUeWhWeIfYm/L589nkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eba344c8bccb24791ef898967d099e971aa4ae2631ca63741c206bdd47b4f5ea","last_reissued_at":"2026-05-18T01:20:50.621755Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:50.621755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hashing for statistics over k-partitions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Eva Rotenberg, Mathias B{\\ae}k Tejs Knudsen, Mikkel Thorup, S{\\o}ren Dahlgaard","submitted_at":"2014-11-26T11:36:15Z","abstract_excerpt":"In this paper we analyze a hash function for $k$-partitioning a set into bins, obtaining strong concentration bounds for standard algorithms combining statistics from each bin.\n  This generic method was originally introduced by Flajolet and Martin~[FOCS'83] in order to save a factor $\\Omega(k)$ of time per element over $k$ independent samples when estimating the number of distinct elements in a data stream. It was also used in the widely used HyperLogLog algorithm of Flajolet et al.~[AOFA'97] and in large-scale machine learning by Li et al.~[NIPS'12] for minwise estimation of set similarity.\n "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.7191","kind":"arxiv","version":3},"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":"1411.7191","created_at":"2026-05-18T01:20:50.621848+00:00"},{"alias_kind":"arxiv_version","alias_value":"1411.7191v3","created_at":"2026-05-18T01:20:50.621848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.7191","created_at":"2026-05-18T01:20:50.621848+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ORUJSF4ZMSH","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ORUJSF4ZMSHSHXY","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ORUJSF4","created_at":"2026-05-18T12:28:14.216126+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/5ORUJSF4ZMSHSHXYTCLH2CM6S4","json":"https://pith.science/pith/5ORUJSF4ZMSHSHXYTCLH2CM6S4.json","graph_json":"https://pith.science/api/pith-number/5ORUJSF4ZMSHSHXYTCLH2CM6S4/graph.json","events_json":"https://pith.science/api/pith-number/5ORUJSF4ZMSHSHXYTCLH2CM6S4/events.json","paper":"https://pith.science/paper/5ORUJSF4"},"agent_actions":{"view_html":"https://pith.science/pith/5ORUJSF4ZMSHSHXYTCLH2CM6S4","download_json":"https://pith.science/pith/5ORUJSF4ZMSHSHXYTCLH2CM6S4.json","view_paper":"https://pith.science/paper/5ORUJSF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1411.7191&json=true","fetch_graph":"https://pith.science/api/pith-number/5ORUJSF4ZMSHSHXYTCLH2CM6S4/graph.json","fetch_events":"https://pith.science/api/pith-number/5ORUJSF4ZMSHSHXYTCLH2CM6S4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ORUJSF4ZMSHSHXYTCLH2CM6S4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ORUJSF4ZMSHSHXYTCLH2CM6S4/action/storage_attestation","attest_author":"https://pith.science/pith/5ORUJSF4ZMSHSHXYTCLH2CM6S4/action/author_attestation","sign_citation":"https://pith.science/pith/5ORUJSF4ZMSHSHXYTCLH2CM6S4/action/citation_signature","submit_replication":"https://pith.science/pith/5ORUJSF4ZMSHSHXYTCLH2CM6S4/action/replication_record"}},"created_at":"2026-05-18T01:20:50.621848+00:00","updated_at":"2026-05-18T01:20:50.621848+00:00"}