{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5PXA74RUT5JZNNY3IS5FWTIHXU","short_pith_number":"pith:5PXA74RU","canonical_record":{"source":{"id":"2411.00879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-31T13:02:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e3addd029223a13933a280991a5301037e193c47e23de144eaa4a7d7dbe88f1e","abstract_canon_sha256":"4c0e994123095c2bdba636b20fec615c867f225085da17fbd4dba747cef7a421"},"schema_version":"1.0"},"canonical_sha256":"ebee0ff2349f5396b71b44ba5b4d07bd3a88b82d0c934bb3ecfed4fead124975","source":{"kind":"arxiv","id":"2411.00879","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00879","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00879v1","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00879","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"pith_short_12","alias_value":"5PXA74RUT5JZ","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"pith_short_16","alias_value":"5PXA74RUT5JZNNY3","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"pith_short_8","alias_value":"5PXA74RU","created_at":"2026-07-05T09:29:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5PXA74RUT5JZNNY3IS5FWTIHXU","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-31T13:02:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e3addd029223a13933a280991a5301037e193c47e23de144eaa4a7d7dbe88f1e","abstract_canon_sha256":"4c0e994123095c2bdba636b20fec615c867f225085da17fbd4dba747cef7a421"},"schema_version":"1.0"},"canonical_sha256":"ebee0ff2349f5396b71b44ba5b4d07bd3a88b82d0c934bb3ecfed4fead124975","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:51.871768Z","signature_b64":"xFbGyMhOWyvvED8KJHKjhQA/56GzQjPxsSuRKEX1b+TjCtw88v5Tql7FJPXEk7ug0m14bZZSU2GakXovh8OBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebee0ff2349f5396b71b44ba5b4d07bd3a88b82d0c934bb3ecfed4fead124975","last_reissued_at":"2026-07-05T09:29:51.871387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:51.871387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00879","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":"2026-07-05T09:29:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GsLTSDuyhGzO5zjQUBehh3qb5n7ybf0Uh2SyKCJAj4mfLBi/0Ae1h1+LAjKmBfS8hDcWxHvQGacCKXDFKAvKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:20:51.210020Z"},"content_sha256":"8a7323d0433519070edcae22725f5d6f980f7c9e7e70991ffbbc0b58f81d49dd","schema_version":"1.0","event_id":"sha256:8a7323d0433519070edcae22725f5d6f980f7c9e7e70991ffbbc0b58f81d49dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5PXA74RUT5JZNNY3IS5FWTIHXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Chi-Hua Wang, Guang Cheng, Tung Sum Thomas Kwok","submitted_at":"2024-10-31T13:02:55Z","abstract_excerpt":"Data collaboration via Data Clean Room offers value but raises privacy concerns, which can be addressed through synthetic data and multi-table synthesizers. Common multi-table synthesizers fail to perform when subjects occur repeatedly in both tables. This is an urgent yet unresolved problem, since having both tables with repeating subjects is common. To improve performance in this scenario, we present the DEREC 3-step pre-processing pipeline to generalize adaptability of multi-table synthesizers. We also introduce the SIMPRO 3-aspect evaluation metrics, which leverage conditional distribution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00879","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.00879/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":"2026-07-05T09:29:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ii9b1gcRHIEW4KfDeoh17JoQ7jCegKRG/DyMZQi1SM+P5jYDCtXbGf2vxz1CpLegQBSh0VRkIiLBZW2Xrbg5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:20:51.210951Z"},"content_sha256":"814126236c3628906908a3368c3c6c80e8fb4e6c04d27f19bff8ff953a9d221a","schema_version":"1.0","event_id":"sha256:814126236c3628906908a3368c3c6c80e8fb4e6c04d27f19bff8ff953a9d221a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5PXA74RUT5JZNNY3IS5FWTIHXU/bundle.json","state_url":"https://pith.science/pith/5PXA74RUT5JZNNY3IS5FWTIHXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5PXA74RUT5JZNNY3IS5FWTIHXU/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":"2026-08-04T13:20:51Z","links":{"resolver":"https://pith.science/pith/5PXA74RUT5JZNNY3IS5FWTIHXU","bundle":"https://pith.science/pith/5PXA74RUT5JZNNY3IS5FWTIHXU/bundle.json","state":"https://pith.science/pith/5PXA74RUT5JZNNY3IS5FWTIHXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5PXA74RUT5JZNNY3IS5FWTIHXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5PXA74RUT5JZNNY3IS5FWTIHXU","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":"4c0e994123095c2bdba636b20fec615c867f225085da17fbd4dba747cef7a421","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-31T13:02:55Z","title_canon_sha256":"e3addd029223a13933a280991a5301037e193c47e23de144eaa4a7d7dbe88f1e"},"schema_version":"1.0","source":{"id":"2411.00879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00879","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00879v1","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00879","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"pith_short_12","alias_value":"5PXA74RUT5JZ","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"pith_short_16","alias_value":"5PXA74RUT5JZNNY3","created_at":"2026-07-05T09:29:51Z"},{"alias_kind":"pith_short_8","alias_value":"5PXA74RU","created_at":"2026-07-05T09:29:51Z"}],"graph_snapshots":[{"event_id":"sha256:814126236c3628906908a3368c3c6c80e8fb4e6c04d27f19bff8ff953a9d221a","target":"graph","created_at":"2026-07-05T09:29:51Z","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/2411.00879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data collaboration via Data Clean Room offers value but raises privacy concerns, which can be addressed through synthetic data and multi-table synthesizers. Common multi-table synthesizers fail to perform when subjects occur repeatedly in both tables. This is an urgent yet unresolved problem, since having both tables with repeating subjects is common. To improve performance in this scenario, we present the DEREC 3-step pre-processing pipeline to generalize adaptability of multi-table synthesizers. We also introduce the SIMPRO 3-aspect evaluation metrics, which leverage conditional distribution","authors_text":"Chi-Hua Wang, Guang Cheng, Tung Sum Thomas Kwok","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-31T13:02:55Z","title":"DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00879","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":"sha256:8a7323d0433519070edcae22725f5d6f980f7c9e7e70991ffbbc0b58f81d49dd","target":"record","created_at":"2026-07-05T09:29:51Z","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":"4c0e994123095c2bdba636b20fec615c867f225085da17fbd4dba747cef7a421","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-31T13:02:55Z","title_canon_sha256":"e3addd029223a13933a280991a5301037e193c47e23de144eaa4a7d7dbe88f1e"},"schema_version":"1.0","source":{"id":"2411.00879","kind":"arxiv","version":1}},"canonical_sha256":"ebee0ff2349f5396b71b44ba5b4d07bd3a88b82d0c934bb3ecfed4fead124975","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebee0ff2349f5396b71b44ba5b4d07bd3a88b82d0c934bb3ecfed4fead124975","first_computed_at":"2026-07-05T09:29:51.871387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:51.871387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xFbGyMhOWyvvED8KJHKjhQA/56GzQjPxsSuRKEX1b+TjCtw88v5Tql7FJPXEk7ug0m14bZZSU2GakXovh8OBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:51.871768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a7323d0433519070edcae22725f5d6f980f7c9e7e70991ffbbc0b58f81d49dd","sha256:814126236c3628906908a3368c3c6c80e8fb4e6c04d27f19bff8ff953a9d221a"],"state_sha256":"2811ca860795a54a1d8eb7241599ed5aca0ab1539bf0e13f1c1ac34690ae12a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"asLZFPS9Q7wVYovN2PdFYqTNwZXituSS6VWHf806YSLnebLw0AJYLoyF4Zrz1AAC8GdsXOD0Qd6okyWyjE9gDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:20:51.216514Z","bundle_sha256":"5d9d598d875cb417624bf0214f151204896471b1ef603a617fbf3deda0c2e19a"}}