{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:6L4G4E2MOWDESPQ7D4GFCPBHFM","short_pith_number":"pith:6L4G4E2M","canonical_record":{"source":{"id":"1404.4693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-04-18T06:09:42Z","cross_cats_sorted":[],"title_canon_sha256":"9bdb8c6fe7780f16de8645ef42bb2f0bc40c56e9ef42ae0a0eeacf096f5b56e4","abstract_canon_sha256":"4878713086b72628e9c2089eb3ac1deb1f221d3957384dfdfa2fc73ec4b5abe0"},"schema_version":"1.0"},"canonical_sha256":"f2f86e134c7586493e1f1f0c513c272b2bf626e99bc58fca8932f5f2968170fc","source":{"kind":"arxiv","id":"1404.4693","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.4693","created_at":"2026-05-18T02:53:55Z"},{"alias_kind":"arxiv_version","alias_value":"1404.4693v1","created_at":"2026-05-18T02:53:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.4693","created_at":"2026-05-18T02:53:55Z"},{"alias_kind":"pith_short_12","alias_value":"6L4G4E2MOWDE","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"6L4G4E2MOWDESPQ7","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"6L4G4E2M","created_at":"2026-05-18T12:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:6L4G4E2MOWDESPQ7D4GFCPBHFM","target":"record","payload":{"canonical_record":{"source":{"id":"1404.4693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-04-18T06:09:42Z","cross_cats_sorted":[],"title_canon_sha256":"9bdb8c6fe7780f16de8645ef42bb2f0bc40c56e9ef42ae0a0eeacf096f5b56e4","abstract_canon_sha256":"4878713086b72628e9c2089eb3ac1deb1f221d3957384dfdfa2fc73ec4b5abe0"},"schema_version":"1.0"},"canonical_sha256":"f2f86e134c7586493e1f1f0c513c272b2bf626e99bc58fca8932f5f2968170fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:53:55.377579Z","signature_b64":"dauRO6A6ek3xPisHrhrc5cGEyKP656ridNH+k7t2JhrxA6Ju9qqkRsDTR7rw9e1gX2DGo8+d1vykYx7rO5CWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2f86e134c7586493e1f1f0c513c272b2bf626e99bc58fca8932f5f2968170fc","last_reissued_at":"2026-05-18T02:53:55.376686Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:53:55.376686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1404.4693","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":"2026-05-18T02:53:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/HaqrYsHmgT9oYr0rBwCNitBep3oJTj0yFDDpROPoqGr3cCoMnMgNTeVKwYVKke/DfObfGLkz10TOUqs3asAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T09:55:43.246572Z"},"content_sha256":"fc7ce63029dd45022601b530df73d5e46fcd1826e6a0d779b105411b609f41a0","schema_version":"1.0","event_id":"sha256:fc7ce63029dd45022601b530df73d5e46fcd1826e6a0d779b105411b609f41a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:6L4G4E2MOWDESPQ7D4GFCPBHFM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Consistent Subset Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Konstantin Kutzkov, Rasmus Pagh","submitted_at":"2014-04-18T06:09:42Z","abstract_excerpt":"Consistent sampling is a technique for specifying, in small space, a subset $S$ of a potentially large universe $U$ such that the elements in $S$ satisfy a suitably chosen sampling condition. Given a subset $\\mathcal{I}\\subseteq U$ it should be possible to quickly compute $\\mathcal{I}\\cap S$, i.e., the elements in $\\mathcal{I}$ satisfying the sampling condition. Consistent sampling has important applications in similarity estimation, and estimation of the number of distinct items in a data stream.\n  In this paper we generalize consistent sampling to the setting where we are interested in sampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.4693","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":"2026-05-18T02:53:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OHUaMm4OlG0qNESoYCb8g2bZWKBQk2yr1peUreDJGdx4E1mIsXBxAXDUeHfDNIVbhL2J3M9p/WG/0WpBHeveCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T09:55:43.246912Z"},"content_sha256":"628f80261a832cc4f78cfb07f07eadca341655c028d34e48e8cc2d29dd0c8e52","schema_version":"1.0","event_id":"sha256:628f80261a832cc4f78cfb07f07eadca341655c028d34e48e8cc2d29dd0c8e52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/bundle.json","state_url":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/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":"2026-06-20T09:55:43Z","links":{"resolver":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM","bundle":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/bundle.json","state":"https://pith.science/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6L4G4E2MOWDESPQ7D4GFCPBHFM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:6L4G4E2MOWDESPQ7D4GFCPBHFM","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":"4878713086b72628e9c2089eb3ac1deb1f221d3957384dfdfa2fc73ec4b5abe0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-04-18T06:09:42Z","title_canon_sha256":"9bdb8c6fe7780f16de8645ef42bb2f0bc40c56e9ef42ae0a0eeacf096f5b56e4"},"schema_version":"1.0","source":{"id":"1404.4693","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.4693","created_at":"2026-05-18T02:53:55Z"},{"alias_kind":"arxiv_version","alias_value":"1404.4693v1","created_at":"2026-05-18T02:53:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.4693","created_at":"2026-05-18T02:53:55Z"},{"alias_kind":"pith_short_12","alias_value":"6L4G4E2MOWDE","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"6L4G4E2MOWDESPQ7","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"6L4G4E2M","created_at":"2026-05-18T12:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:628f80261a832cc4f78cfb07f07eadca341655c028d34e48e8cc2d29dd0c8e52","target":"graph","created_at":"2026-05-18T02:53:55Z","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":"Consistent sampling is a technique for specifying, in small space, a subset $S$ of a potentially large universe $U$ such that the elements in $S$ satisfy a suitably chosen sampling condition. Given a subset $\\mathcal{I}\\subseteq U$ it should be possible to quickly compute $\\mathcal{I}\\cap S$, i.e., the elements in $\\mathcal{I}$ satisfying the sampling condition. Consistent sampling has important applications in similarity estimation, and estimation of the number of distinct items in a data stream.\n  In this paper we generalize consistent sampling to the setting where we are interested in sampl","authors_text":"Konstantin Kutzkov, Rasmus Pagh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-04-18T06:09:42Z","title":"Consistent Subset Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.4693","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:fc7ce63029dd45022601b530df73d5e46fcd1826e6a0d779b105411b609f41a0","target":"record","created_at":"2026-05-18T02:53:55Z","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":"4878713086b72628e9c2089eb3ac1deb1f221d3957384dfdfa2fc73ec4b5abe0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-04-18T06:09:42Z","title_canon_sha256":"9bdb8c6fe7780f16de8645ef42bb2f0bc40c56e9ef42ae0a0eeacf096f5b56e4"},"schema_version":"1.0","source":{"id":"1404.4693","kind":"arxiv","version":1}},"canonical_sha256":"f2f86e134c7586493e1f1f0c513c272b2bf626e99bc58fca8932f5f2968170fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2f86e134c7586493e1f1f0c513c272b2bf626e99bc58fca8932f5f2968170fc","first_computed_at":"2026-05-18T02:53:55.376686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:53:55.376686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dauRO6A6ek3xPisHrhrc5cGEyKP656ridNH+k7t2JhrxA6Ju9qqkRsDTR7rw9e1gX2DGo8+d1vykYx7rO5CWBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:53:55.377579Z","signed_message":"canonical_sha256_bytes"},"source_id":"1404.4693","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc7ce63029dd45022601b530df73d5e46fcd1826e6a0d779b105411b609f41a0","sha256:628f80261a832cc4f78cfb07f07eadca341655c028d34e48e8cc2d29dd0c8e52"],"state_sha256":"5d3ecc99808079c189770afbe5e0fa55af2bf416670ea21664c5414c44b9fef2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uSle2sE2W3TX0mlcB04IZC5t9Cpbp12xYCBrnrB2Hw3TnWT6bJ5rcFx/nysLpu/kNIQ/44F8iU7heeUGDSTuBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T09:55:43.248776Z","bundle_sha256":"c4568ac99fa7b5495a1c57149aa984c46d6f87f01eb3256d3d06fafc8431bae6"}}