{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6D7DCUTFDH3LEDPFQ7BR37VE6Z","short_pith_number":"pith:6D7DCUTF","schema_version":"1.0","canonical_sha256":"f0fe31526519f6b20de587c31dfea4f663227f3709006594ba9c3d8af9703cc0","source":{"kind":"arxiv","id":"2607.22063","version":1},"attestation_state":"computed","paper":{"title":"HyperLogLog for probabilists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.DS","authors_text":"Lucas Gerin (MODAL'X)","submitted_at":"2026-07-24T07:58:29Z","abstract_excerpt":"HyperLogLog is a now classic probabilistic algorithm that provides an approximation of the number of distinct elements in a massive dataset, using only one pass over the data. In the original article, Flajolet, Fusy, Gandouet, Meunier (2007) provided a sharp analysis of the expectation and variance of the output, using explicit formulas analyzed using poissonization and Mellin transform. In this short article, we revisit the analysis of HyperLogLog with a more probabilistic viewpoint. This allows us to establish exponential deviation inequalities for the HyperLogLog estimator. The methods are "},"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":"2607.22063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2026-07-24T07:58:29Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"1a702a36b0e8f5f6ff34b38636dfdc5c9e2dfb29b576f050b8035a1c665a0c8c","abstract_canon_sha256":"95fb7838b9276ed84dfd795b48e01f1f09c1c7541ca2166e6754a148530e2260"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:46.040184Z","signature_b64":"2CbdBhV7DtLEh8ynvG97tEiVcNNWi9EuFBtNI5xMdDO28gCeyglfxhpW1FL+cA8+MmXiAZGL11/2d6W3dGRhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0fe31526519f6b20de587c31dfea4f663227f3709006594ba9c3d8af9703cc0","last_reissued_at":"2026-07-27T01:20:46.039301Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:46.039301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperLogLog for probabilists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.DS","authors_text":"Lucas Gerin (MODAL'X)","submitted_at":"2026-07-24T07:58:29Z","abstract_excerpt":"HyperLogLog is a now classic probabilistic algorithm that provides an approximation of the number of distinct elements in a massive dataset, using only one pass over the data. In the original article, Flajolet, Fusy, Gandouet, Meunier (2007) provided a sharp analysis of the expectation and variance of the output, using explicit formulas analyzed using poissonization and Mellin transform. In this short article, we revisit the analysis of HyperLogLog with a more probabilistic viewpoint. This allows us to establish exponential deviation inequalities for the HyperLogLog estimator. The methods are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22063","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.22063/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2607.22063","created_at":"2026-07-27T01:20:46.039757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22063v1","created_at":"2026-07-27T01:20:46.039757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22063","created_at":"2026-07-27T01:20:46.039757+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D7DCUTFDH3L","created_at":"2026-07-27T01:20:46.039757+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D7DCUTFDH3LEDPF","created_at":"2026-07-27T01:20:46.039757+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D7DCUTF","created_at":"2026-07-27T01:20:46.039757+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/6D7DCUTFDH3LEDPFQ7BR37VE6Z","json":"https://pith.science/pith/6D7DCUTFDH3LEDPFQ7BR37VE6Z.json","graph_json":"https://pith.science/api/pith-number/6D7DCUTFDH3LEDPFQ7BR37VE6Z/graph.json","events_json":"https://pith.science/api/pith-number/6D7DCUTFDH3LEDPFQ7BR37VE6Z/events.json","paper":"https://pith.science/paper/6D7DCUTF"},"agent_actions":{"view_html":"https://pith.science/pith/6D7DCUTFDH3LEDPFQ7BR37VE6Z","download_json":"https://pith.science/pith/6D7DCUTFDH3LEDPFQ7BR37VE6Z.json","view_paper":"https://pith.science/paper/6D7DCUTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22063&json=true","fetch_graph":"https://pith.science/api/pith-number/6D7DCUTFDH3LEDPFQ7BR37VE6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/6D7DCUTFDH3LEDPFQ7BR37VE6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D7DCUTFDH3LEDPFQ7BR37VE6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D7DCUTFDH3LEDPFQ7BR37VE6Z/action/storage_attestation","attest_author":"https://pith.science/pith/6D7DCUTFDH3LEDPFQ7BR37VE6Z/action/author_attestation","sign_citation":"https://pith.science/pith/6D7DCUTFDH3LEDPFQ7BR37VE6Z/action/citation_signature","submit_replication":"https://pith.science/pith/6D7DCUTFDH3LEDPFQ7BR37VE6Z/action/replication_record"}},"created_at":"2026-07-27T01:20:46.039757+00:00","updated_at":"2026-07-27T01:20:46.039757+00:00"}