{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2008:B4UFZWIXQITSBBJNNI3H2MLKJO","short_pith_number":"pith:B4UFZWIX","canonical_record":{"source":{"id":"0803.0473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2008-03-04T15:12:24Z","cross_cats_sorted":[],"title_canon_sha256":"8c323efbf6f23d06b9d5c2b254912be36af2a56c50a9dae4aa7ed2a4189b81a5","abstract_canon_sha256":"1ac194437da8228d07de6b79ca92e0b5509bbc91e8c5d720414bd6a46a6b1cbc"},"schema_version":"1.0"},"canonical_sha256":"0f285cd917822720852d6a367d316a4b89a352c9950066a256bae42fd7fffc46","source":{"kind":"arxiv","id":"0803.0473","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0803.0473","created_at":"2026-05-18T04:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"0803.0473v2","created_at":"2026-05-18T04:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0803.0473","created_at":"2026-05-18T04:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"B4UFZWIXQITS","created_at":"2026-05-18T12:25:56Z"},{"alias_kind":"pith_short_16","alias_value":"B4UFZWIXQITSBBJN","created_at":"2026-05-18T12:25:56Z"},{"alias_kind":"pith_short_8","alias_value":"B4UFZWIX","created_at":"2026-05-18T12:25:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2008:B4UFZWIXQITSBBJNNI3H2MLKJO","target":"record","payload":{"canonical_record":{"source":{"id":"0803.0473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2008-03-04T15:12:24Z","cross_cats_sorted":[],"title_canon_sha256":"8c323efbf6f23d06b9d5c2b254912be36af2a56c50a9dae4aa7ed2a4189b81a5","abstract_canon_sha256":"1ac194437da8228d07de6b79ca92e0b5509bbc91e8c5d720414bd6a46a6b1cbc"},"schema_version":"1.0"},"canonical_sha256":"0f285cd917822720852d6a367d316a4b89a352c9950066a256bae42fd7fffc46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:35:57.506342Z","signature_b64":"0ve8lqp8ifdyDMPfQnHUjKX9yBSFYQOl4RC0B/5MI1ebCwxB4EMwbAqB1d+L6Agz1htxBkhjl2dhxv0Mof2TDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f285cd917822720852d6a367d316a4b89a352c9950066a256bae42fd7fffc46","last_reissued_at":"2026-05-18T04:35:57.505487Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:35:57.505487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"0803.0473","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iiYv6SzrSLwhRYsj1iHLGdRG3TnF2K+yZ0zZ0ya853Vi0+3AHWDI9xFagoBoua4vJw+4VfLkosupMVs9S6c9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T00:28:34.510605Z"},"content_sha256":"8286ca7f4b84e2ffa2504fac5cfa5f8fa2507e82e8f6492f189da666c9a4cb2a","schema_version":"1.0","event_id":"sha256:8286ca7f4b84e2ffa2504fac5cfa5f8fa2507e82e8f6492f189da666c9a4cb2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2008:B4UFZWIXQITSBBJNNI3H2MLKJO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stream sampling for variance-optimal estimation of subset sums","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Carsten Lund, Edith Cohen, Haim Kaplan, Mikkel Thorup, Nick Duffield","submitted_at":"2008-03-04T15:12:24Z","abstract_excerpt":"From a high volume stream of weighted items, we want to maintain a generic sample of a certain limited size $k$ that we can later use to estimate the total weight of arbitrary subsets. This is the classic context of on-line reservoir sampling, thinking of the generic sample as a reservoir. We present an efficient reservoir sampling scheme, $\\varoptk$, that dominates all previous schemes in terms of estimation quality.\n  $\\varoptk$ provides {\\em variance optimal unbiased estimation of subset sums}. More precisely, if we have seen $n$ items of the stream, then for {\\em any} subset size $m$, our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0803.0473","kind":"arxiv","version":2},"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":"2026-05-18T04:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28zMlt8lFjapAZJeJbA4hbci0Ga1NVu9nm+KBob8s2ODBdgnvt+ygUc0LAbhd6vyC4n/QtR0IdEtArxgQGX+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T00:28:34.510945Z"},"content_sha256":"16d0231042899b77760f4e239e962631a05747877bf7f2e525f446163e5201c1","schema_version":"1.0","event_id":"sha256:16d0231042899b77760f4e239e962631a05747877bf7f2e525f446163e5201c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/bundle.json","state_url":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/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":"2026-06-04T00:28:34Z","links":{"resolver":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO","bundle":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/bundle.json","state":"https://pith.science/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B4UFZWIXQITSBBJNNI3H2MLKJO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2008:B4UFZWIXQITSBBJNNI3H2MLKJO","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":"1ac194437da8228d07de6b79ca92e0b5509bbc91e8c5d720414bd6a46a6b1cbc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2008-03-04T15:12:24Z","title_canon_sha256":"8c323efbf6f23d06b9d5c2b254912be36af2a56c50a9dae4aa7ed2a4189b81a5"},"schema_version":"1.0","source":{"id":"0803.0473","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0803.0473","created_at":"2026-05-18T04:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"0803.0473v2","created_at":"2026-05-18T04:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0803.0473","created_at":"2026-05-18T04:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"B4UFZWIXQITS","created_at":"2026-05-18T12:25:56Z"},{"alias_kind":"pith_short_16","alias_value":"B4UFZWIXQITSBBJN","created_at":"2026-05-18T12:25:56Z"},{"alias_kind":"pith_short_8","alias_value":"B4UFZWIX","created_at":"2026-05-18T12:25:56Z"}],"graph_snapshots":[{"event_id":"sha256:16d0231042899b77760f4e239e962631a05747877bf7f2e525f446163e5201c1","target":"graph","created_at":"2026-05-18T04:35:57Z","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":"From a high volume stream of weighted items, we want to maintain a generic sample of a certain limited size $k$ that we can later use to estimate the total weight of arbitrary subsets. This is the classic context of on-line reservoir sampling, thinking of the generic sample as a reservoir. We present an efficient reservoir sampling scheme, $\\varoptk$, that dominates all previous schemes in terms of estimation quality.\n  $\\varoptk$ provides {\\em variance optimal unbiased estimation of subset sums}. More precisely, if we have seen $n$ items of the stream, then for {\\em any} subset size $m$, our ","authors_text":"Carsten Lund, Edith Cohen, Haim Kaplan, Mikkel Thorup, Nick Duffield","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2008-03-04T15:12:24Z","title":"Stream sampling for variance-optimal estimation of subset sums"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0803.0473","kind":"arxiv","version":2},"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":"sha256:8286ca7f4b84e2ffa2504fac5cfa5f8fa2507e82e8f6492f189da666c9a4cb2a","target":"record","created_at":"2026-05-18T04:35:57Z","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":"1ac194437da8228d07de6b79ca92e0b5509bbc91e8c5d720414bd6a46a6b1cbc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2008-03-04T15:12:24Z","title_canon_sha256":"8c323efbf6f23d06b9d5c2b254912be36af2a56c50a9dae4aa7ed2a4189b81a5"},"schema_version":"1.0","source":{"id":"0803.0473","kind":"arxiv","version":2}},"canonical_sha256":"0f285cd917822720852d6a367d316a4b89a352c9950066a256bae42fd7fffc46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f285cd917822720852d6a367d316a4b89a352c9950066a256bae42fd7fffc46","first_computed_at":"2026-05-18T04:35:57.505487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:35:57.505487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ve8lqp8ifdyDMPfQnHUjKX9yBSFYQOl4RC0B/5MI1ebCwxB4EMwbAqB1d+L6Agz1htxBkhjl2dhxv0Mof2TDw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:35:57.506342Z","signed_message":"canonical_sha256_bytes"},"source_id":"0803.0473","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8286ca7f4b84e2ffa2504fac5cfa5f8fa2507e82e8f6492f189da666c9a4cb2a","sha256:16d0231042899b77760f4e239e962631a05747877bf7f2e525f446163e5201c1"],"state_sha256":"f3d7379b19cf95ac88bd6275402983c1c90caea3c2767be6b7b69a806e3ccb44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCsZbvk9pk630YrEgNsTW2QfZ3TPXENhzNjJDQa4oNDBbt87sD8GLDtYnq//Jt+6kJvEHSid7XFEyhJZU5/yBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T00:28:34.512946Z","bundle_sha256":"c117167b9bc18b831a526f8fdb5dc754e85d3346632760731a9b3318478fbe85"}}