{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BFLQJTYNOQ6D5YEMROMLFXWNFE","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":"fc13728a8f07a1aba9c151908f4aa0336e97b3a3be323795f6e701bc3c237bb9","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-01-07T20:41:57Z","title_canon_sha256":"df388311eeeec87c8bd9418d9efb9d7788282c58a82d589894935234b1ac0f68"},"schema_version":"1.0","source":{"id":"2201.02670","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02670","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02670v1","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02670","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"BFLQJTYNOQ6D","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"BFLQJTYNOQ6D5YEM","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"BFLQJTYN","created_at":"2026-07-05T03:46:46Z"}],"graph_snapshots":[{"event_id":"sha256:f265e54f37e732ecc76ea142f109b2b4d17234863235d6fe04e63d6bcbf1eb91","target":"graph","created_at":"2026-07-05T03:46:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.02670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joining records with all other records that meet a linkage condition can result in an astronomically large number of combinations due to many-to-many relationships. For such challenging (acyclic) joins, a random sample over the join result is a practical alternative to working with the oversized join result. Whereas prior works are limited to uniform join sampling where each join row is assigned the same probability, the scope is extended in this work to weighted sampling to support emerging applications such as scientific discovery in observational data and privacy-preserving query answering.","authors_text":"Ali Shanghooshabad, Graham Cormode, Michael Shekelyan, Peter Triantafillou, Qingzhi Ma","cross_cats":["cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-01-07T20:41:57Z","title":"Weighted Random Sampling over Joins"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02670","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:cf517aa0ae97d25e4105a7d3e64193fcc95172a967bc791a93ad95575e90c692","target":"record","created_at":"2026-07-05T03:46:46Z","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":"fc13728a8f07a1aba9c151908f4aa0336e97b3a3be323795f6e701bc3c237bb9","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-01-07T20:41:57Z","title_canon_sha256":"df388311eeeec87c8bd9418d9efb9d7788282c58a82d589894935234b1ac0f68"},"schema_version":"1.0","source":{"id":"2201.02670","kind":"arxiv","version":1}},"canonical_sha256":"095704cf0d743c3ee08c8b98b2decd2919134faf49e3917fc19a56728368c8cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"095704cf0d743c3ee08c8b98b2decd2919134faf49e3917fc19a56728368c8cf","first_computed_at":"2026-07-05T03:46:46.947303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:46.947303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EXQYF+MYZsk/0spiVGsNMPkfvcFGhVPhjsaBTmgptkpS4MqwMqDuyIRzXidVghICfiFmVxuD2tdLHyHV20DlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:46.947684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.02670","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf517aa0ae97d25e4105a7d3e64193fcc95172a967bc791a93ad95575e90c692","sha256:f265e54f37e732ecc76ea142f109b2b4d17234863235d6fe04e63d6bcbf1eb91"],"state_sha256":"fd229f089355c84fc5fd544459482b5cc65955a66d30f1e36319aa3908a9454b"}