{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W5MATT5FNNODZTWQUSGAA7BCBI","short_pith_number":"pith:W5MATT5F","schema_version":"1.0","canonical_sha256":"b75809cfa56b5c3cced0a48c007c220a0b6d5ffcf163517ae0ff920a7017aa4b","source":{"kind":"arxiv","id":"2603.27405","version":2},"attestation_state":"computed","paper":{"title":"DynamicLogLog: Faster, Smaller, and More Accurate Cardinality Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DynamicLogLog stores relative leading-zero counts with a shared exponent to cut memory by one-third while removing HyperLogLog's error spike and adding an early-exit mask.","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Brian Bushnell","submitted_at":"2026-03-28T20:52:33Z","abstract_excerpt":"Cardinality estimation - calculating the number of distinct elements in a stream - is a longstanding problem with applications from networking to bioinformatics. HyperLogLog (HLL), the prevailing standard, has a well-known error spike in its transition region and requires 6 bits per bucket, with data structure size scaling as B*log(log(cardinality)). We present DynamicLogLog (DLL), which uses a shared exponent across all buckets, storing only relative leading-zero counts. This yields three benefits: (1) only 4 bits per bucket (33% memory reduction), (2) an early exit mask that rejects >99.9% 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":true},"canonical_record":{"source":{"id":"2603.27405","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2026-03-28T20:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"938b2355904921a132b8933e1f24d352fdf3042ee73a5cbdbc39d69e42ce0595","abstract_canon_sha256":"e4099590fd48b779e4d13d6ae710a32829f6a9ee99fea85b3fb432f71cd0931c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:22.480426Z","signature_b64":"4uTDoE6eBMYCPuQBCaHmJY/9sgJiR9vzdXky7Y8aj0FCF0T/5COV7fxJ9mA9dyfxF6MYW8vZSguy09hIE8LLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b75809cfa56b5c3cced0a48c007c220a0b6d5ffcf163517ae0ff920a7017aa4b","last_reissued_at":"2026-05-18T03:09:22.479757Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:22.479757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynamicLogLog: Faster, Smaller, and More Accurate Cardinality Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DynamicLogLog stores relative leading-zero counts with a shared exponent to cut memory by one-third while removing HyperLogLog's error spike and adding an early-exit mask.","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Brian Bushnell","submitted_at":"2026-03-28T20:52:33Z","abstract_excerpt":"Cardinality estimation - calculating the number of distinct elements in a stream - is a longstanding problem with applications from networking to bioinformatics. HyperLogLog (HLL), the prevailing standard, has a well-known error spike in its transition region and requires 6 bits per bucket, with data structure size scaling as B*log(log(cardinality)). We present DynamicLogLog (DLL), which uses a shared exponent across all buckets, storing only relative leading-zero counts. This yields three benefits: (1) only 4 bits per bucket (33% memory reduction), (2) an early exit mask that rejects >99.9% o"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"At 2,048 buckets with 512k simulations, DLL4's hybrid estimate achieves 1.830% mean and 1.834% peak absolute error using 1,024 bytes, compared to 1.84% mean and 34.1% peak for HLL using 1,536 bytes.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the early-exit mask and hybrid blend maintain their reported accuracy and speed on real-world data distributions rather than only on the synthetic streams used in the 512k simulations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DynamicLogLog cuts memory by 33%, speeds up queries over 10x in bandwidth-limited cases, and removes HyperLogLog's transition-region error spike while matching or beating accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DynamicLogLog stores relative leading-zero counts with a shared exponent to cut memory by one-third while removing HyperLogLog's error spike and adding an early-exit mask.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0038df3c4a0ca1ac45be0659ce2bf3a15cb7e28fff02f917ac11cf59d186d085"},"source":{"id":"2603.27405","kind":"arxiv","version":2},"verdict":{"id":"33023362-5753-4f00-88d0-bfc2c726af05","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:16:30.098530Z","strongest_claim":"At 2,048 buckets with 512k simulations, DLL4's hybrid estimate achieves 1.830% mean and 1.834% peak absolute error using 1,024 bytes, compared to 1.84% mean and 34.1% peak for HLL using 1,536 bytes.","one_line_summary":"DynamicLogLog cuts memory by 33%, speeds up queries over 10x in bandwidth-limited cases, and removes HyperLogLog's transition-region error spike while matching or beating accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the early-exit mask and hybrid blend maintain their reported accuracy and speed on real-world data distributions rather than only on the synthetic streams used in the 512k simulations.","pith_extraction_headline":"DynamicLogLog stores relative leading-zero counts with a shared exponent to cut memory by one-third while removing HyperLogLog's error spike and adding an early-exit mask."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4f57b7bea4eddbe1300f4734a6c319fd9e6a6f25532cce7f361663bc9ebcbd06"},"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":"2603.27405","created_at":"2026-05-18T03:09:22.479855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.27405v2","created_at":"2026-05-18T03:09:22.479855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27405","created_at":"2026-05-18T03:09:22.479855+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5MATT5FNNOD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5MATT5FNNODZTWQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5MATT5F","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI","json":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI.json","graph_json":"https://pith.science/api/pith-number/W5MATT5FNNODZTWQUSGAA7BCBI/graph.json","events_json":"https://pith.science/api/pith-number/W5MATT5FNNODZTWQUSGAA7BCBI/events.json","paper":"https://pith.science/paper/W5MATT5F"},"agent_actions":{"view_html":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI","download_json":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI.json","view_paper":"https://pith.science/paper/W5MATT5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.27405&json=true","fetch_graph":"https://pith.science/api/pith-number/W5MATT5FNNODZTWQUSGAA7BCBI/graph.json","fetch_events":"https://pith.science/api/pith-number/W5MATT5FNNODZTWQUSGAA7BCBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI/action/storage_attestation","attest_author":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI/action/author_attestation","sign_citation":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI/action/citation_signature","submit_replication":"https://pith.science/pith/W5MATT5FNNODZTWQUSGAA7BCBI/action/replication_record"}},"created_at":"2026-05-18T03:09:22.479855+00:00","updated_at":"2026-05-18T03:09:22.479855+00:00"}