{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:HAHIOJKPXRSOF744HRKG6ZT4MU","short_pith_number":"pith:HAHIOJKP","schema_version":"1.0","canonical_sha256":"380e87254fbc64e2ff9c3c546f667c650fbad14f1e934c01c879862574008371","source":{"kind":"arxiv","id":"1611.01853","version":1},"attestation_state":"computed","paper":{"title":"MTS Sketch for Accurate Estimation of Set-Expression Cardinalities from Small Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DB","authors_text":"Aviv Yehezkel, Liran Katzir, Reuven Cohen","submitted_at":"2016-11-06T22:22:40Z","abstract_excerpt":"Sketch-based streaming algorithms allow efficient processing of big data. These algorithms use small fixed-size storage to store a summary (\"sketch\") of the input data, and use probabilistic algorithms to estimate the desired quantity. However, in many real-world applications it is impractical to collect and process the entire data stream, the common practice is thus to sample and process only a small part of it. While sampling is crucial for handling massive data sets, it may reduce accuracy. In this paper we present a new framework that can accurately estimate the cardinality of any set expr"},"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":"1611.01853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-11-06T22:22:40Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"b1b839ea7933da1882ed45e0804f8d37998953ccb09ad4c2807ea4eb11b6813f","abstract_canon_sha256":"bd0c4d3c61e116c1f976c97442780b968addb22106349d5c359756635db5a61e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:04.335995Z","signature_b64":"CTflIPwwKILT4xJA143XZ0VZcIUL6d8sNUDzPc5NHVPAXbYDmy21sz6BSWlTl/5t3KZpY1+D1Q3UyazHe3NVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"380e87254fbc64e2ff9c3c546f667c650fbad14f1e934c01c879862574008371","last_reissued_at":"2026-05-18T01:00:04.335276Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:04.335276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTS Sketch for Accurate Estimation of Set-Expression Cardinalities from Small Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DB","authors_text":"Aviv Yehezkel, Liran Katzir, Reuven Cohen","submitted_at":"2016-11-06T22:22:40Z","abstract_excerpt":"Sketch-based streaming algorithms allow efficient processing of big data. These algorithms use small fixed-size storage to store a summary (\"sketch\") of the input data, and use probabilistic algorithms to estimate the desired quantity. However, in many real-world applications it is impractical to collect and process the entire data stream, the common practice is thus to sample and process only a small part of it. While sampling is crucial for handling massive data sets, it may reduce accuracy. In this paper we present a new framework that can accurately estimate the cardinality of any set expr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01853","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":"1611.01853","created_at":"2026-05-18T01:00:04.335426+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.01853v1","created_at":"2026-05-18T01:00:04.335426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01853","created_at":"2026-05-18T01:00:04.335426+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAHIOJKPXRSO","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAHIOJKPXRSOF744","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAHIOJKP","created_at":"2026-05-18T12:30:19.053100+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/HAHIOJKPXRSOF744HRKG6ZT4MU","json":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU.json","graph_json":"https://pith.science/api/pith-number/HAHIOJKPXRSOF744HRKG6ZT4MU/graph.json","events_json":"https://pith.science/api/pith-number/HAHIOJKPXRSOF744HRKG6ZT4MU/events.json","paper":"https://pith.science/paper/HAHIOJKP"},"agent_actions":{"view_html":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU","download_json":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU.json","view_paper":"https://pith.science/paper/HAHIOJKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.01853&json=true","fetch_graph":"https://pith.science/api/pith-number/HAHIOJKPXRSOF744HRKG6ZT4MU/graph.json","fetch_events":"https://pith.science/api/pith-number/HAHIOJKPXRSOF744HRKG6ZT4MU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/action/storage_attestation","attest_author":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/action/author_attestation","sign_citation":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/action/citation_signature","submit_replication":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/action/replication_record"}},"created_at":"2026-05-18T01:00:04.335426+00:00","updated_at":"2026-05-18T01:00:04.335426+00:00"}