{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:77ULOZN66U2XGCDFVF24BJYUSI","short_pith_number":"pith:77ULOZN6","canonical_record":{"source":{"id":"2507.17066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T22:59:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8b82b73ba25cffe5279bc3b1a643f741d8252f0de1ef568aa81c228d4451ca86","abstract_canon_sha256":"c6d47f2898311aa78d1da088780be9d981c9a63b4219163a0ce98028341cdbe1"},"schema_version":"1.0"},"canonical_sha256":"ffe8b765bef535730865a975c0a7149212d4891bb66750c3b284f7dbbf7a72f0","source":{"kind":"arxiv","id":"2507.17066","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17066","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17066v1","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17066","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_12","alias_value":"77ULOZN66U2X","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_16","alias_value":"77ULOZN66U2XGCDF","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_8","alias_value":"77ULOZN6","created_at":"2026-07-05T11:42:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:77ULOZN66U2XGCDFVF24BJYUSI","target":"record","payload":{"canonical_record":{"source":{"id":"2507.17066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T22:59:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8b82b73ba25cffe5279bc3b1a643f741d8252f0de1ef568aa81c228d4451ca86","abstract_canon_sha256":"c6d47f2898311aa78d1da088780be9d981c9a63b4219163a0ce98028341cdbe1"},"schema_version":"1.0"},"canonical_sha256":"ffe8b765bef535730865a975c0a7149212d4891bb66750c3b284f7dbbf7a72f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:01.050556Z","signature_b64":"6MxpdZasWjY10KUwrBw46TRSre4njGMRHpNk6eCJEWlE7qgV5SbAi3GyKTQakg68hunRsVGU6lYFxXxsgD03Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffe8b765bef535730865a975c0a7149212d4891bb66750c3b284f7dbbf7a72f0","last_reissued_at":"2026-07-05T11:42:01.050130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:01.050130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.17066","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":"2026-07-05T11:42:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oqea3zMqcxXF9w+Klsv9G0RjREgrVAwu1pFOoTX62og3wrJk50Y5FRa/egXxmlkpeHhGPiVt5BYBqXf9z7VIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:46:42.750370Z"},"content_sha256":"35c04f475cb83a8a93d5f1e7ff4654989053e9c7c2e48c32741378abc1c9efb6","schema_version":"1.0","event_id":"sha256:35c04f475cb83a8a93d5f1e7ff4654989053e9c7c2e48c32741378abc1c9efb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:77ULOZN66U2XGCDFVF24BJYUSI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guang Cheng, Jessup Byun, Joshua Ward, Xiaofeng Lin","submitted_at":"2025-07-22T22:59:08Z","abstract_excerpt":"Synthetic tabular data is essential for machine learning workflows, especially for expanding small or imbalanced datasets and enabling privacy-preserving data sharing. However, state-of-the-art generative models (GANs, VAEs, diffusion models) rely on large datasets with thousands of examples. In low-data settings, often the primary motivation for synthetic data, these models can overfit, leak sensitive records, and require frequent retraining. Recent work uses large pre-trained transformers to generate rows via in-context learning (ICL), which needs only a few seed examples and no parameter up"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17066","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/2507.17066/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":"2026-07-05T11:42:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VSuNjkyVzruX1sI+UyhBFm/5iTGo7bVivyXhgMbSSeNxxMNEHBpPZ06jKSyT/SG56JwrK+mw95coMCYE/4qOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:46:42.750887Z"},"content_sha256":"733c2268ee003d4a7a4d7b5c8387dfb699e8f4259331ae5367e67138d1543d0f","schema_version":"1.0","event_id":"sha256:733c2268ee003d4a7a4d7b5c8387dfb699e8f4259331ae5367e67138d1543d0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77ULOZN66U2XGCDFVF24BJYUSI/bundle.json","state_url":"https://pith.science/pith/77ULOZN66U2XGCDFVF24BJYUSI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77ULOZN66U2XGCDFVF24BJYUSI/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":"2026-08-07T04:46:42Z","links":{"resolver":"https://pith.science/pith/77ULOZN66U2XGCDFVF24BJYUSI","bundle":"https://pith.science/pith/77ULOZN66U2XGCDFVF24BJYUSI/bundle.json","state":"https://pith.science/pith/77ULOZN66U2XGCDFVF24BJYUSI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77ULOZN66U2XGCDFVF24BJYUSI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:77ULOZN66U2XGCDFVF24BJYUSI","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":"c6d47f2898311aa78d1da088780be9d981c9a63b4219163a0ce98028341cdbe1","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T22:59:08Z","title_canon_sha256":"8b82b73ba25cffe5279bc3b1a643f741d8252f0de1ef568aa81c228d4451ca86"},"schema_version":"1.0","source":{"id":"2507.17066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17066","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17066v1","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17066","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_12","alias_value":"77ULOZN66U2X","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_16","alias_value":"77ULOZN66U2XGCDF","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_8","alias_value":"77ULOZN6","created_at":"2026-07-05T11:42:01Z"}],"graph_snapshots":[{"event_id":"sha256:733c2268ee003d4a7a4d7b5c8387dfb699e8f4259331ae5367e67138d1543d0f","target":"graph","created_at":"2026-07-05T11:42:01Z","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/2507.17066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic tabular data is essential for machine learning workflows, especially for expanding small or imbalanced datasets and enabling privacy-preserving data sharing. However, state-of-the-art generative models (GANs, VAEs, diffusion models) rely on large datasets with thousands of examples. In low-data settings, often the primary motivation for synthetic data, these models can overfit, leak sensitive records, and require frequent retraining. Recent work uses large pre-trained transformers to generate rows via in-context learning (ICL), which needs only a few seed examples and no parameter up","authors_text":"Guang Cheng, Jessup Byun, Joshua Ward, Xiaofeng Lin","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T22:59:08Z","title":"Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17066","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":"sha256:35c04f475cb83a8a93d5f1e7ff4654989053e9c7c2e48c32741378abc1c9efb6","target":"record","created_at":"2026-07-05T11:42:01Z","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":"c6d47f2898311aa78d1da088780be9d981c9a63b4219163a0ce98028341cdbe1","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T22:59:08Z","title_canon_sha256":"8b82b73ba25cffe5279bc3b1a643f741d8252f0de1ef568aa81c228d4451ca86"},"schema_version":"1.0","source":{"id":"2507.17066","kind":"arxiv","version":1}},"canonical_sha256":"ffe8b765bef535730865a975c0a7149212d4891bb66750c3b284f7dbbf7a72f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffe8b765bef535730865a975c0a7149212d4891bb66750c3b284f7dbbf7a72f0","first_computed_at":"2026-07-05T11:42:01.050130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:01.050130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6MxpdZasWjY10KUwrBw46TRSre4njGMRHpNk6eCJEWlE7qgV5SbAi3GyKTQakg68hunRsVGU6lYFxXxsgD03Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:01.050556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35c04f475cb83a8a93d5f1e7ff4654989053e9c7c2e48c32741378abc1c9efb6","sha256:733c2268ee003d4a7a4d7b5c8387dfb699e8f4259331ae5367e67138d1543d0f"],"state_sha256":"db50b223d058b0297ce0b101b62698f6fc11c3a99ee200682a0d2922d9c87a1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wh8L1BDNF5pHxy9qn7aZj+2DoP8sFvH6HKrHL4HvKNWm30IENIr3/IeyfjMhAQ8GIb0XWV0XmbPrR9c/0W8OBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:46:42.762542Z","bundle_sha256":"688abbc1539e49c9096a2e90b55fa7d306b93ae5bdd73002830032b8cc3800e5"}}