{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XLHESHABEBY2IOFRT33M47MP3I","short_pith_number":"pith:XLHESHAB","canonical_record":{"source":{"id":"2303.00940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-03-02T03:27:52Z","cross_cats_sorted":[],"title_canon_sha256":"f593e4fc7483651a90c54e78e1d7db14e4da63bbc342e4e067d5224ff5dc7cb0","abstract_canon_sha256":"0a13761b47198f64f334c6dd74555b93a564fbd7e1a2fb76945f028bd6e5ceed"},"schema_version":"1.0"},"canonical_sha256":"bace491c012071a438b19ef6ce7d8fda10abc9806e5dcd65a0a457902334d153","source":{"kind":"arxiv","id":"2303.00940","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00940","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00940v2","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00940","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"XLHESHABEBY2","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"XLHESHABEBY2IOFR","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"XLHESHAB","created_at":"2026-07-05T05:49:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XLHESHABEBY2IOFRT33M47MP3I","target":"record","payload":{"canonical_record":{"source":{"id":"2303.00940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-03-02T03:27:52Z","cross_cats_sorted":[],"title_canon_sha256":"f593e4fc7483651a90c54e78e1d7db14e4da63bbc342e4e067d5224ff5dc7cb0","abstract_canon_sha256":"0a13761b47198f64f334c6dd74555b93a564fbd7e1a2fb76945f028bd6e5ceed"},"schema_version":"1.0"},"canonical_sha256":"bace491c012071a438b19ef6ce7d8fda10abc9806e5dcd65a0a457902334d153","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:33.466272Z","signature_b64":"hwnoRX6WD7TR6w1VUZ1avO0O5jNwUiA1k68HdBdOMxf+2i7WAKCRdceqCStU76ZokANsceShUhkxmEGkUNJnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bace491c012071a438b19ef6ce7d8fda10abc9806e5dcd65a0a457902334d153","last_reissued_at":"2026-07-05T05:49:33.465851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:33.465851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.00940","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":"2026-07-05T05:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66bKARO15iKZXhfxniN8Zb0rwLd3+MY9EjOJ/ShHIkkoKhahEKYbu9O8bmIS7JdoS9T+Q3RQEqRjfqgAWZj9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:23:54.589983Z"},"content_sha256":"4215ea05defb7aa0970dd1ae0d5bf9030dccb590e4413d4ff56aff9fe8022ea1","schema_version":"1.0","event_id":"sha256:4215ea05defb7aa0970dd1ae0d5bf9030dccb590e4413d4ff56aff9fe8022ea1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XLHESHABEBY2IOFRT33M47MP3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sampling over Union of Joins","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Fatemeh Nargesian, Yunlong Xu, Yurong Liu","submitted_at":"2023-03-02T03:27:52Z","abstract_excerpt":"Data scientists often draw on multiple relational data sources for analysis. A standard assumption in learning and approximate query answering is that the data is a uniform and independent sample of the underlying distribution. To avoid the cost of join and union, given a set of joins, we study the problem of obtaining a random sample from the union of joins without performing the full join and union. We present a general framework for random sampling over the set union of chain, acyclic, and cyclic joins, with sample uniformity and independence guarantees. We study the novel problem of the un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00940","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.00940/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kphzUjQJcquctSiOnAiqP7uSNscCHsCf3lmxXSK8y3dorRjznClvakEzqbrwdsXH513f7XHdFCDF+UTgHSHYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:23:54.590506Z"},"content_sha256":"45bef036638cabb6268bb73504132fa7a86909226a8eeddda1497b8339cce547","schema_version":"1.0","event_id":"sha256:45bef036638cabb6268bb73504132fa7a86909226a8eeddda1497b8339cce547"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/bundle.json","state_url":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLHESHABEBY2IOFRT33M47MP3I/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":"2026-08-23T11:23:54Z","links":{"resolver":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I","bundle":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/bundle.json","state":"https://pith.science/pith/XLHESHABEBY2IOFRT33M47MP3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLHESHABEBY2IOFRT33M47MP3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XLHESHABEBY2IOFRT33M47MP3I","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":"0a13761b47198f64f334c6dd74555b93a564fbd7e1a2fb76945f028bd6e5ceed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-03-02T03:27:52Z","title_canon_sha256":"f593e4fc7483651a90c54e78e1d7db14e4da63bbc342e4e067d5224ff5dc7cb0"},"schema_version":"1.0","source":{"id":"2303.00940","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00940","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00940v2","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00940","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"XLHESHABEBY2","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"XLHESHABEBY2IOFR","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"XLHESHAB","created_at":"2026-07-05T05:49:33Z"}],"graph_snapshots":[{"event_id":"sha256:45bef036638cabb6268bb73504132fa7a86909226a8eeddda1497b8339cce547","target":"graph","created_at":"2026-07-05T05:49:33Z","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/2303.00940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data scientists often draw on multiple relational data sources for analysis. A standard assumption in learning and approximate query answering is that the data is a uniform and independent sample of the underlying distribution. To avoid the cost of join and union, given a set of joins, we study the problem of obtaining a random sample from the union of joins without performing the full join and union. We present a general framework for random sampling over the set union of chain, acyclic, and cyclic joins, with sample uniformity and independence guarantees. We study the novel problem of the un","authors_text":"Fatemeh Nargesian, Yunlong Xu, Yurong Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-03-02T03:27:52Z","title":"Sampling over Union of Joins"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00940","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":"sha256:4215ea05defb7aa0970dd1ae0d5bf9030dccb590e4413d4ff56aff9fe8022ea1","target":"record","created_at":"2026-07-05T05:49:33Z","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":"0a13761b47198f64f334c6dd74555b93a564fbd7e1a2fb76945f028bd6e5ceed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-03-02T03:27:52Z","title_canon_sha256":"f593e4fc7483651a90c54e78e1d7db14e4da63bbc342e4e067d5224ff5dc7cb0"},"schema_version":"1.0","source":{"id":"2303.00940","kind":"arxiv","version":2}},"canonical_sha256":"bace491c012071a438b19ef6ce7d8fda10abc9806e5dcd65a0a457902334d153","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bace491c012071a438b19ef6ce7d8fda10abc9806e5dcd65a0a457902334d153","first_computed_at":"2026-07-05T05:49:33.465851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:33.465851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hwnoRX6WD7TR6w1VUZ1avO0O5jNwUiA1k68HdBdOMxf+2i7WAKCRdceqCStU76ZokANsceShUhkxmEGkUNJnDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:33.466272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00940","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4215ea05defb7aa0970dd1ae0d5bf9030dccb590e4413d4ff56aff9fe8022ea1","sha256:45bef036638cabb6268bb73504132fa7a86909226a8eeddda1497b8339cce547"],"state_sha256":"e15f84cc2a6a8338c41b0c8fef82f3c8166e067eac1e5102f6f6fc8f67ae5c35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4w7krtOLnj0YTUt6uTS6e4CLu9eUSAJihn9u4Df7RGZ5XRTxLx2BHLr9eVEEZdwS1gCpvarJaZ9mCnp11F9aAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T11:23:54.595818Z","bundle_sha256":"e0b789d5b7a67b43ee19af5e620195a79dff71ee6dcc443d1412c4aa33e9e8ea"}}