{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:HAHIOJKPXRSOF744HRKG6ZT4MU","short_pith_number":"pith:HAHIOJKP","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"},"canonical_sha256":"380e87254fbc64e2ff9c3c546f667c650fbad14f1e934c01c879862574008371","source":{"kind":"arxiv","id":"1611.01853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01853","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01853v1","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01853","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"pith_short_12","alias_value":"HAHIOJKPXRSO","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HAHIOJKPXRSOF744","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HAHIOJKP","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:HAHIOJKPXRSOF744HRKG6ZT4MU","target":"record","payload":{"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"},"canonical_sha256":"380e87254fbc64e2ff9c3c546f667c650fbad14f1e934c01c879862574008371","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"},"source_kind":"arxiv","source_id":"1611.01853","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:00:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EIVw6J2F3UA8Fb0ILmL3JPgHyKJsUBm8p287Q89TwQEtg0y6DwgRgZLWXWIzoQG+BUFmRrvfEbYZMd/5VkNgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T06:58:24.654237Z"},"content_sha256":"9f8f92306be9c3f9d116f995e8c5cb927e7dcf7345f756aac97b5e4a352f2cb7","schema_version":"1.0","event_id":"sha256:9f8f92306be9c3f9d116f995e8c5cb927e7dcf7345f756aac97b5e4a352f2cb7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:HAHIOJKPXRSOF744HRKG6ZT4MU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:00:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UCtNI86fatQR2saXE6u43j1xMLZtXHX0VKvcblnQZuTsifbR2XDWTISfyhQnio7pktnakz5juUByWGcBTaPmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T06:58:24.654595Z"},"content_sha256":"37bed83f60f103367b0127cea0e0f4e30e9c5ace40064de36bb2166cc6e1e20d","schema_version":"1.0","event_id":"sha256:37bed83f60f103367b0127cea0e0f4e30e9c5ace40064de36bb2166cc6e1e20d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/bundle.json","state_url":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T06:58:24Z","links":{"resolver":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU","bundle":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/bundle.json","state":"https://pith.science/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HAHIOJKPXRSOF744HRKG6ZT4MU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:HAHIOJKPXRSOF744HRKG6ZT4MU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bd0c4d3c61e116c1f976c97442780b968addb22106349d5c359756635db5a61e","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-11-06T22:22:40Z","title_canon_sha256":"b1b839ea7933da1882ed45e0804f8d37998953ccb09ad4c2807ea4eb11b6813f"},"schema_version":"1.0","source":{"id":"1611.01853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01853","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01853v1","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01853","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"pith_short_12","alias_value":"HAHIOJKPXRSO","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HAHIOJKPXRSOF744","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HAHIOJKP","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:37bed83f60f103367b0127cea0e0f4e30e9c5ace40064de36bb2166cc6e1e20d","target":"graph","created_at":"2026-05-18T01:00:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Aviv Yehezkel, Liran Katzir, Reuven Cohen","cross_cats":["cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-11-06T22:22:40Z","title":"MTS Sketch for Accurate Estimation of Set-Expression Cardinalities from Small Samples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01853","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9f8f92306be9c3f9d116f995e8c5cb927e7dcf7345f756aac97b5e4a352f2cb7","target":"record","created_at":"2026-05-18T01:00:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bd0c4d3c61e116c1f976c97442780b968addb22106349d5c359756635db5a61e","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-11-06T22:22:40Z","title_canon_sha256":"b1b839ea7933da1882ed45e0804f8d37998953ccb09ad4c2807ea4eb11b6813f"},"schema_version":"1.0","source":{"id":"1611.01853","kind":"arxiv","version":1}},"canonical_sha256":"380e87254fbc64e2ff9c3c546f667c650fbad14f1e934c01c879862574008371","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"380e87254fbc64e2ff9c3c546f667c650fbad14f1e934c01c879862574008371","first_computed_at":"2026-05-18T01:00:04.335276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:04.335276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CTflIPwwKILT4xJA143XZ0VZcIUL6d8sNUDzPc5NHVPAXbYDmy21sz6BSWlTl/5t3KZpY1+D1Q3UyazHe3NVBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:04.335995Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f8f92306be9c3f9d116f995e8c5cb927e7dcf7345f756aac97b5e4a352f2cb7","sha256:37bed83f60f103367b0127cea0e0f4e30e9c5ace40064de36bb2166cc6e1e20d"],"state_sha256":"7d1d13a7b82cd0f9d902ed8acade21a4a0e83a5be1ca0d89312fde0bc7183fc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fr+Cc6BE6mvEgFzi6O6q5byvVUmP5DMV0YDOfVFb4FrYFs22MQ507RqESv5Zsww5HI4hztJQtEOEG+yVmWv6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T06:58:24.656468Z","bundle_sha256":"3f3141ad5e8d18ca066a4ba90bd65b03d3346fd417f6593e04c1f9dfc84f5111"}}