{"as_of":"2026-08-13T18:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:99cb09dd238b84e9e78e272622f67cbcbb25975bbee6cc43c00c6ac02c8373dd","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T11:15:51.779883Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.16952/citation-record","integrity":"/paper/2606.16952/integrity","json":"/paper/2606.16952/citation-record.json","paper":"/paper/2606.16952"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:47.423428Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:47.423428Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:f76366e49fb061b61ab7ad7bbf2d77e6c606645dece1b694b3db402cb32ef6f6","observation_id":"1492e760-9254-47e8-8b11-2a791aa73014","resolution":{"observed_at":"2026-08-02T11:15:47.423428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:47.605633Z","title":"The us census bureau adopts differential privacy","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:47.605633Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:a19a9c32f4a7779802dece44a680ec0038806f974b6bea458ca57e9c6e59e05c","observation_id":"7e3e8805-6e13-4546-a043-5cbbdf4fe761","resolution":{"observed_at":"2026-08-02T11:15:47.605633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:47.719059Z","title":"Anonymous-by-construction: An llm-driven framework for privacy-preserving text.arXiv preprint arXiv:2603.17217, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:47.719059Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:ad0e86c9d3db8475c642a3069eb57310290ef288dd7ac06a40e540e2b93d0086","observation_id":"150f3762-6517-4377-adf2-6415f8a94960","resolution":{"observed_at":"2026-08-02T11:15:47.719059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:47.856981Z","title":"Private prediction for large-scale synthetic text gener- ation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:47.856981Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:024112ddeccb803a950f4cd3ab163fbf929f133b4e90d7317cd59d2ff24d7be7","observation_id":"4842e1dd-98ae-4288-8cc3-6b300f14daa5","resolution":{"observed_at":"2026-08-02T11:15:47.856981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:47.962117Z","title":"Reconstructing training data with informed adversaries","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:47.962117Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:ceda021a7b84799faf003b2ce8abbe9844bb2d3fb5cfb025f44172fbf2b86242","observation_id":"acc44fc6-45fc-461f-be2e-cc8dc18b37dd","resolution":{"observed_at":"2026-08-02T11:15:47.962117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.15836","last_updated":"2025-07-21T17:47:33Z","snapshot_observed_at":"2026-08-10T22:39:07.863214Z","submitted_at":"2025-07-21T17:47:33Z","title":"Optimizing Canaries for Privacy Auditing with Metagradient Descent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.15836","snapshot_observed_at":"2026-08-02T11:15:48.105239Z","title":"Optimizing canaries for privacy auditing with metagradient descent.arXiv preprint arXiv:2507.15836, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:48.105239Z"},"links":{"cited_paper":"/paper/2507.15836","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:96d3f1b6e8b1022d541305fa145619d3ea7950cbba12344b792391576ff6fb87","observation_id":"e9cf0070-7f81-46f4-843c-fe04624f8457","resolution":{"observed_at":"2026-08-02T11:15:48.105239Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:48.270033Z","title":"Membership inference attacks from first principles","venue":null,"work_id":null,"year":1914},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:48.270033Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:02be86daae23283c3ff0459a900f06e7b164be236583302d84c29c124b4d9428","observation_id":"e7e763c2-8e7d-4b41-a2ff-114ea2080fd0","resolution":{"observed_at":"2026-08-02T11:15:48.270033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07646","last_updated":"2023-03-06T06:28:18Z","snapshot_observed_at":"2026-08-03T19:51:05.627063Z","submitted_at":"2022-02-15T18:48:31Z","title":"Quantifying Memorization Across Neural Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07646","snapshot_observed_at":"2026-08-02T11:15:48.430953Z","title":"Quantifying memorization across neural language models, 2023.URL https://arxiv","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:48.430953Z"},"links":{"cited_paper":"/paper/2202.07646","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:a7f7a5cc11c5ca1319e049fea949cffcf50da2681232ac2f4e3a956f0e329d5a","observation_id":"3bac4668-4c25-49f1-813d-dcc2f61c2ca6","resolution":{"observed_at":"2026-08-02T11:15:48.430953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:48.519120Z","title":"The secret sharer: Evaluating and testing unintended memorization in neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:48.519120Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:bf227422b2c087f3d80f734a4d0a7bb05be6ac8a5b4271395a3f4c15a0f0dac8","observation_id":"40f8e5c9-d85a-46f9-9162-75e0d32ec93f","resolution":{"observed_at":"2026-08-02T11:15:48.519120Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:48.658689Z","title":"Gan-leaks: A taxonomy of membership inference attacks against generative models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:48.658689Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:e7d74c5ab53364557b4a9a08abdf8db94a70725868feb3388e3c228e5e71f3d6","observation_id":"a413e642-3959-4775-94e3-f321ad2ebc5b","resolution":{"observed_at":"2026-08-02T11:15:48.658689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:48.810330Z","title":"Calibrating noise to sensi- tivity in private data analysis","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:48.810330Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:7bd4677299e276caf1a4aa129dcb2c8af45bd77d96d81c08cb20b3fff47865ae","observation_id":"35c362da-7251-4159-a739-9e7c8d39ef32","resolution":{"observed_at":"2026-08-02T11:15:48.810330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:48.907596Z","title":"Calibrating noise to sen- sitivity in private data analysis","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:48.907596Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:d090455b33607b1cdae5c6c56ebefb4dc9db6eebb33ac81ffbf469a81eb8e9fd","observation_id":"ec25e618-f304-4fd8-857c-f3271c8a99e6","resolution":{"observed_at":"2026-08-02T11:15:48.907596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.002200Z","title":"Differ- entially private optimization with sparse gradients.Advances in Neural Information Processing Systems, 37:63406–63440, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.002200Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:e40b182b6645c0910cac32fb7616444e96352e36ab67388ca511a7664ad58d32","observation_id":"755ad7f0-178a-48c1-83e4-fd66f6d8d88e","resolution":{"observed_at":"2026-08-02T11:15:49.002200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.116892Z","title":"Property testing for differential privacy, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.116892Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:7bfadc5a358daa39ae32f1136c3ba0cb2d1719cbfa6a51e7ac69789dc9cc0f9c","observation_id":"2de19083-07b6-4ae6-85d7-7fdad0db6e31","resolution":{"observed_at":"2026-08-02T11:15:49.116892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.273936Z","title":"Cloud Data Loss Prevention (Cloud DLP) api.https://docs.cloud.google.com/ sensitive-data-protection/docs/infotypes-reference, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.273936Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:daca8a41026461c62696b6d916852a717f1fa3e48ae3089f676c96f1fbe06292","observation_id":"1f894f1d-372e-423d-938c-2d9d41add35a","resolution":{"observed_at":"2026-08-02T11:15:49.273936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.378561Z","title":"Bounding train- ing data reconstruction in private (deep) learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.378561Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:475bd944901882413531c79ca5f9594a099244d01b32e5dd621818e625c546c3","observation_id":"3ad301fa-7373-4b2d-8ce6-9693aebad2f5","resolution":{"observed_at":"2026-08-02T11:15:49.378561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.09603","last_updated":"2026-04-26T09:26:18Z","snapshot_observed_at":"2026-08-06T15:46:00.528049Z","submitted_at":"2025-08-13T08:35:16Z","title":"The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.09603","snapshot_observed_at":"2026-08-02T11:15:49.505084Z","title":"The surprising effectiveness of membership inference with simple n-gram coverage.arXiv preprint arXiv:2508.09603, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.505084Z"},"links":{"cited_paper":"/paper/2508.09603","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:cf5fc37ef2fca9a2e090c22b1bf3653a62c65654f68629395bc2c07f689c1fbf","observation_id":"d812ca25-b717-479a-80c4-40f660bd6960","resolution":{"observed_at":"2026-08-02T11:15:49.505084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.03006","last_updated":"2019-06-07T10:52:15Z","snapshot_observed_at":"2026-07-06T07:58:42.317554Z","submitted_at":"2019-06-07T10:52:15Z","title":"Reconstruction and Membership Inference Attacks against Generative Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.03006","snapshot_observed_at":"2026-08-02T11:15:49.572533Z","title":"Reconstruction and membership inference attacks against generative models.arXiv preprint arXiv:1906.03006, 2019","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.572533Z"},"links":{"cited_paper":"/paper/1906.03006","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:1792f3695069b150ee47afe9bd2ed36ceb9955b0119313d0f689c4121e5183d2","observation_id":"51052b2a-b978-44f5-affe-a29569ff9379","resolution":{"observed_at":"2026-08-02T11:15:49.572533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.632050Z","title":"Statistics and causal inference.Journal of the American Statistical Associa- tion, 81(396):945–960, 1986","venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.632050Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:f5530bab3a6b0c95343754101e4b2e40f4c4cc09202575c44cd9165905d68b2b","observation_id":"d53205d1-890b-48ed-a193-390d3f6f2ad1","resolution":{"observed_at":"2026-08-02T11:15:49.632050Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.718125Z","title":"Auditing differentially private machine learning: How private is private SGD?Advances in Neural Information Processing Systems, 33:22205–22216, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.718125Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:90c6b07b9a89a9369fdd530b68ad36ee1f57bd170dda7b5ed5acf050ba46dd56","observation_id":"f551d260-970d-4319-b0e9-809c0a69198f","resolution":{"observed_at":"2026-08-02T11:15:49.718125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.797851Z","title":"Evaluating differentially private machine learning in practice","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.797851Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:f3dd79fc5da07e7b8fe5675660a388ab04a6a885284b2b1169461284dfbf1446","observation_id":"329f3565-70dc-4f51-8214-2a1cadd5899e","resolution":{"observed_at":"2026-08-02T11:15:49.797851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.03257","last_updated":"2022-05-06T14:27:45Z","snapshot_observed_at":"2026-08-13T15:48:55.754140Z","submitted_at":"2022-05-06T14:27:45Z","title":"Synthetic Data -- what, why and how?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.03257","snapshot_observed_at":"2026-08-02T11:15:49.868216Z","title":"Synthetic data–what, why and how? arXiv preprint arXiv:2205.03257, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.868216Z"},"links":{"cited_paper":"/paper/2205.03257","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:fa37c7d0448398903359c8014f760377987c63327751a5035b7f87e32e605117","observation_id":"6426826b-302c-4915-ace8-470f9334f7b9","resolution":{"observed_at":"2026-08-02T11:15:49.868216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.910384Z","title":"The enron corpus: A new dataset for email classification research","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.910384Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:5cd065f8af375de6ad8d785df9a77e8df8ef88bc75d47dd3fbf4f4db30b29eb4","observation_id":"f3086436-2a48-404f-8d08-41d4d39cecd5","resolution":{"observed_at":"2026-08-02T11:15:49.910384Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:49.963194Z","title":"Linkedin job postings (2023 - 2024), 2024","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:49.963194Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:a79a1fd425642598ac0f6d613d2d2e3a81d71d5fd6ffe294972427106596e67d","observation_id":"e9e47ef3-9cd3-43ba-8d5b-b50c9ce32a80","resolution":{"observed_at":"2026-08-02T11:15:49.963194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.01684","last_updated":"2024-01-11T00:17:43Z","snapshot_observed_at":"2026-08-13T11:25:33.533785Z","submitted_at":"2023-06-02T16:59:36Z","title":"Harnessing large-language models to generate private synthetic text","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.01684","snapshot_observed_at":"2026-08-02T11:15:50.068311Z","title":"Harnessing large-language models to generate private synthetic text.arXiv preprint arXiv:2306.01684, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.068311Z"},"links":{"cited_paper":"/paper/2306.01684","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:59e278169507ffe91cc3d39392a715072d1de70ed21891716dc73870167e88bd","observation_id":"88157295-aba4-449a-829f-e8b4d9a7e390","resolution":{"observed_at":"2026-08-02T11:15:50.068311Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05505","last_updated":"2025-05-20T04:05:24Z","snapshot_observed_at":"2026-08-11T17:51:50.289133Z","submitted_at":"2025-02-08T09:50:30Z","title":"Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05505","snapshot_observed_at":"2026-08-02T11:15:50.140301Z","title":"Differentially private synthetic data via apis 3: Using simulators instead of foundation model.arXiv preprint arXiv:2502.05505, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.140301Z"},"links":{"cited_paper":"/paper/2502.05505","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:1a25290305374a74273efa05004194cfada9d2270b5ecded1ebdcd71778d4dba","observation_id":"4034cf1c-1193-4292-b784-c097a09ef73d","resolution":{"observed_at":"2026-08-02T11:15:50.140301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15560","last_updated":"2025-05-17T15:12:18Z","snapshot_observed_at":"2026-08-13T11:33:57.935143Z","submitted_at":"2023-05-24T23:47:26Z","title":"Differentially Private Synthetic Data via Foundation Model APIs 1: Images","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15560","snapshot_observed_at":"2026-08-02T11:15:50.220869Z","title":"Dif- ferentially private synthetic data via foundation model apis 1: Images.arXiv preprint arXiv:2305.15560, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.220869Z"},"links":{"cited_paper":"/paper/2305.15560","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:8b44cd856908e6567759b647eea21626d5ad6d140e819dd2bfdabc19e7ad5f68","observation_id":"340961fc-3fd2-4e5d-b866-3feef06a813f","resolution":{"observed_at":"2026-08-02T11:15:50.220869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:50.308477Z","title":"Differentially private language models for secure data sharing","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.308477Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:90b2be2d188a2a2ef7135ce87729f7818b78a0b4e69913873dfbfe9fdb10d146","observation_id":"676897a0-47d3-4cb4-8693-dfc149788708","resolution":{"observed_at":"2026-08-02T11:15:50.308477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:50.368771Z","title":"Mann-whitney u test.The Corsini encyclopedia of psychology, pages 1–1, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.368771Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:698064439d0a6ddb55f1d982f9bd1e2953c5203d070de19ff2c4a3b874bc3422","observation_id":"fe3f52b9-56df-4b06-823c-d63776b72040","resolution":{"observed_at":"2026-08-02T11:15:50.368771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:50.428566Z","title":"Achilles’ heels: vulnerable record identification in synthetic data publishing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.428566Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:244289b725dabc85633f4ddeac8a9394c81a465dbb2cc4a93f094d31f49a9589","observation_id":"1ffee2b9-4cb1-4b50-a5d0-974c85e3c508","resolution":{"observed_at":"2026-08-02T11:15:50.428566Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09363","last_updated":"2024-06-04T21:07:11Z","snapshot_observed_at":"2026-08-13T04:18:54.194241Z","submitted_at":"2024-02-14T18:09:53Z","title":"Copyright Traps for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09363","snapshot_observed_at":"2026-08-02T11:15:50.473111Z","title":"Copyright traps for large language models.arXiv preprint arXiv:2402.09363, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.473111Z"},"links":{"cited_paper":"/paper/2402.09363","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:5fcd4d560581b5f911901c7241d322318d235b7f25035c9c66027d6cbace15ac","observation_id":"9288e6ad-f692-4934-badb-c17dd25bcdac","resolution":{"observed_at":"2026-08-02T11:15:50.473111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:50.523343Z","title":"The canary’s echo: Auditing privacy risks of llm-generated synthetic text.arXiv preprint arXiv:2502.14921, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.523343Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:181a6440de1f05513c5f5fe0a3287fdde530283e83bf1d0d54919ac7f61e453c","observation_id":"5ccd5ce4-d555-4fcd-9f37-de7e9b353788","resolution":{"observed_at":"2026-08-02T11:15:50.523343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:50.602503Z","title":"Tight auditing of differentially private machine learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.602503Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:77b364feac3024a30a8d1ed6f1cd3dea704d9ab3fa17e55d87107acce62056ea","observation_id":"d207183f-2e7c-472a-95fe-c3a1c8523e11","resolution":{"observed_at":"2026-08-02T11:15:50.602503Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.03238","last_updated":"2026-07-09T21:40:53Z","snapshot_observed_at":"2026-08-13T15:56:44.700477Z","submitted_at":"2025-12-02T21:14:39Z","title":"How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.03238","snapshot_observed_at":"2026-08-02T11:15:50.687522Z","title":"How to dp-fy your data: A practical guide to generating synthetic data with differential privacy","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.687522Z"},"links":{"cited_paper":"/paper/2512.03238","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:5c5551c2c37946535f56c1d5c3ad5acb5b4b797bc2c3f7df32b4f32f94a986f0","observation_id":"df7ac9e8-5092-41b7-8066-8af6c4fe3efb","resolution":{"observed_at":"2026-08-02T11:15:50.687522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.17746","last_updated":"2025-05-07T18:36:12Z","snapshot_observed_at":"2026-08-12T23:35:04.610152Z","submitted_at":"2024-06-25T17:32:16Z","title":"Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.17746","snapshot_observed_at":"2026-08-02T11:15:50.773067Z","title":"Recite, reconstruct, recollect: Memorization in lms as a multifaceted phenomenon.arXiv preprint arXiv:2406.17746, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.773067Z"},"links":{"cited_paper":"/paper/2406.17746","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:9c82d8eb4889262d1dc3de94864bd9d672b22c7eea4866c6aa73968e4226f216","observation_id":"e8e8c485-08ee-4f4c-a19f-c7345a71ba5f","resolution":{"observed_at":"2026-08-02T11:15:50.773067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:50.845377Z","title":"Differential privacy defenses and sampling attacks for membership inference","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.845377Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:9daa145ca6236c04e2999ecf3ea5bebb59722cc3f5d217dbbe7a539eb041b563","observation_id":"9bf6eb65-2130-44ae-9f02-8563a3ebb3de","resolution":{"observed_at":"2026-08-02T11:15:50.845377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.12238","last_updated":"2025-05-18T05:27:35Z","snapshot_observed_at":"2026-08-12T19:01:17.810016Z","submitted_at":"2025-05-18T05:27:35Z","title":"PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.12238","snapshot_observed_at":"2026-08-02T11:15:50.898244Z","title":"Panorama: A synthetic pii-laced dataset for studying sensitive data memorization in llms.arXiv preprint arXiv:2505.12238, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.898244Z"},"links":{"cited_paper":"/paper/2505.12238","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:e35fb234ab742eb2856e1f78549ed8cf9004ee4bb94dde26b3cb9b2dbafeb73d","observation_id":"e1989c92-1121-458a-9a37-8406e84d9dab","resolution":{"observed_at":"2026-08-02T11:15:50.898244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16789","last_updated":"2024-03-09T22:26:06Z","snapshot_observed_at":"2026-08-08T18:07:29.632928Z","submitted_at":"2023-10-25T17:21:23Z","title":"Detecting Pretraining Data from Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16789","snapshot_observed_at":"2026-08-02T11:15:50.956012Z","title":"Detecting pretraining data from large language models.arXiv preprint arXiv:2310.16789, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:50.956012Z"},"links":{"cited_paper":"/paper/2310.16789","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:163137a322e48486b5b455cf4e60a63cc904ac356ea729f219fe1aecb0562efd","observation_id":"fc54bca3-287b-441b-8bfa-5f310000a015","resolution":{"observed_at":"2026-08-02T11:15:50.956012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:51.037822Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.037822Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:2006d31b19a6873f866389588687fb0accabc4f166aa91f181563bb4f05ae9f1","observation_id":"3f5fe208-0653-438b-bbf5-9b0707f563f3","resolution":{"observed_at":"2026-08-02T11:15:51.037822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:51.161859Z","title":"Privacy auditing with one (1) training run.Advances in Neural Information Processing Systems, 36:49268–49280, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.161859Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:61e4c1576bf072f19a9a64b9aef54c414975b100ad09d2e9d47fc6c0538ef089","observation_id":"cf5ea022-72dc-4bc9-88dc-83776e5fb5b0","resolution":{"observed_at":"2026-08-02T11:15:51.161859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:51.253748Z","title":"Privacy-preserving in-context learning with differentially private few-shot generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.253748Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:18006d62d95dba83799a3ba879d88a528dac1b79e62458931cbd635e2d5f770c","observation_id":"49deb2bc-3911-4d15-a927-c9a4401aeeaf","resolution":{"observed_at":"2026-08-02T11:15:51.253748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08295","last_updated":"2024-04-16T12:52:47Z","snapshot_observed_at":"2026-08-03T03:29:01.959523Z","submitted_at":"2024-03-13T06:59:16Z","title":"Gemma: Open Models Based on Gemini Research and Technology","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08295","snapshot_observed_at":"2026-08-02T11:15:51.338272Z","title":"Gemma: Open models based on gemini research and technology.arXiv preprint arXiv:2403.08295, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.338272Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:33edc190d84ff4a293881df10f95164f09e94aa6b094239a6f3b13b103c4594f","observation_id":"0cd76521-b598-43ae-827c-92ef85617de4","resolution":{"observed_at":"2026-08-02T11:15:51.338272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:51.421185Z","title":"Proving membership in llm pretraining data via data watermarks.arXiv e-prints, pages arXiv–2402, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.421185Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:d782f4b431e637fe135d26184b11b14018be1bcd5569b269a83c4758d28a71fa","observation_id":"f7dac700-ab63-4daf-9593-4cf44d0761af","resolution":{"observed_at":"2026-08-02T11:15:51.421185Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:51.494470Z","title":"Synthetic-PII-Financial-Documents-North-America: A synthetic dataset for training language models to label and detect pii in domain specific formats, June 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.494470Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:f05a8c28761aa0caafb1523d52d28a597d1d2c60724a3273e46608532c29e164","observation_id":"13860fe2-c197-4c98-9208-2ac0b4eda4d6","resolution":{"observed_at":"2026-08-02T11:15:51.494470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:51.587255Z","title":"Differentially pri- vate synthetic data via foundation model apis 2: Text","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.587255Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:14760357b7f77f64e2613033306a3cbd5daea5e711f872bbc1cf8104bc30d27e","observation_id":"82ef001c-dcc9-419e-8b43-3755c7ab3008","resolution":{"observed_at":"2026-08-02T11:15:51.587255Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:51.658726Z","title":"Enhanced membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.658726Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:f59419a97a7a6389993dd262073f1611293ff5f1c55b6e72e40bdb3389ee6382","observation_id":"d55466b4-f716-459d-ba97-07b728ff68ec","resolution":{"observed_at":"2026-08-02T11:15:51.658726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:15:51.727318Z","title":"Synthetic text generation with differential privacy: A simple and practical recipe","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.727318Z"},"links":{"citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:243aff86b4bb9a0fae45e516ee7ae43e0c68c4991b5040e37c986e0b8b38361b","observation_id":"c6fb5db8-b98d-4d8d-82cb-cc95a1c2055d","resolution":{"observed_at":"2026-08-02T11:15:51.727318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03262","last_updated":"2024-06-12T09:02:47Z","snapshot_observed_at":"2026-08-13T05:09:03.239932Z","submitted_at":"2023-12-06T03:18:49Z","title":"Low-Cost High-Power Membership Inference Attacks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03262","snapshot_observed_at":"2026-08-02T11:15:51.779883Z","title":"A form capturing personal, financial, and employment details of a loan applicant, including loan amount, purpose, and supporting documents","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T11:15:51.779883Z"},"links":{"cited_paper":"/paper/2312.03262","citing_paper":"/paper/2606.16952"},"observation_digest":"sha256:5226a5a399893de702464cdd6a84314283545db0751d81c398efa037b7ffbd65","observation_id":"86c57d32-0c4f-497d-9c16-f45b35428cb1","resolution":{"observed_at":"2026-08-02T11:15:51.779883Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.16952","last_updated":"2026-07-20T23:44:56Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T15:50:07.505351Z","submitted_at":"2026-06-15T16:54:02Z","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":48,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":48},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2606.16952."}