{"as_of":"2026-08-10T23:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a43d90a379dff07f286856b95190d11e38c4e00301a96f241e0615d06b59f085","coverage":[{"denominator":105,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:47:30.100207Z","state":"measured"},{"denominator":104,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":104,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T22:42:45.302583Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T05:05:57.402476Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.03941","snapshot_observed_at":"2026-08-05T22:42:45.302583Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.06647","last_updated":"2025-08-08T18:57:23Z","snapshot_observed_at":"2026-08-05T22:42:42.411406Z","submitted_at":"2025-08-08T18:57:23Z","title":"Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T22:42:45.302583Z"},"links":{"cited_paper":"/paper/2501.03941","citing_paper":"/paper/2508.06647"},"observation_digest":"sha256:26805914865e9bb5990860076f70e8a712cf49d2bb7a5a4dab4081a76fdde517","observation_id":"840aa235-c913-4982-92ea-de5f1b66ea74","resolution":{"observed_at":"2026-08-05T22:42:45.302583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.03941","snapshot_observed_at":"2026-08-04T18:28:36.469157Z","title":"Synthetic data privacy metrics,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09960","last_updated":"2026-06-25T13:10:45Z","snapshot_observed_at":"2026-08-07T05:03:51.320604Z","submitted_at":"2025-09-12T04:34:46Z","title":"Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T18:28:36.469157Z"},"links":{"cited_paper":"/paper/2501.03941","citing_paper":"/paper/2509.09960"},"observation_digest":"sha256:add56bbd9a5b5bb53766f9bfc53fdfad806385702af6393f00a5004e0a356add","observation_id":"26040519-2d7c-4c8a-8ec8-a507ac447882","resolution":{"observed_at":"2026-08-04T18:28:36.469157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"cited_work":{"arxiv_id":"2501.03941","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.03941","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Synthetic data privacy metrics","venue":null,"work_id":"bc36ce0b-29d7-4940-b589-fd214d8f654c","year":2025},"citing_paper":{"arxiv_id":"2604.15461","last_updated":"2026-04-16T18:24:58Z","snapshot_observed_at":"2026-08-02T12:46:53.786004Z","submitted_at":"2026-04-16T18:24:58Z","title":"Evaluating LLM Simulators as Differentially Private Data Generators","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T11:57:19.397498Z"},"links":{"cited_paper":"/paper/2501.03941","citing_paper":"/paper/2604.15461"},"observation_digest":"sha256:ee9f81dd178ec5c7af813a06b8fbe61192758354e21daccc1a4f62ffc8970c2d","observation_id":"5d4c7217-6344-4de3-8978-197252499cc8","resolution":{"observed_at":"2026-05-10T12:00:22.185269Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"cited_work":{"arxiv_id":"2501.03941","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.03941","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Synthetic data privacy metrics","venue":null,"work_id":"bc36ce0b-29d7-4940-b589-fd214d8f654c","year":2025},"citing_paper":{"arxiv_id":"2605.06835","last_updated":"2026-05-07T18:42:35Z","snapshot_observed_at":"2026-07-06T23:19:15.382283Z","submitted_at":"2026-05-07T18:42:35Z","title":"On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-11T00:52:34.784185Z"},"links":{"cited_paper":"/paper/2501.03941","citing_paper":"/paper/2605.06835"},"observation_digest":"sha256:b73ca5c7ee99e3510bef389ef0de18048bed2a269890a70d2b915ab418f046c7","observation_id":"2b5dd244-c14f-4874-8f07-ddcc31a6ff03","resolution":{"observed_at":"2026-05-11T05:05:57.409563Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.03941/citation-record","integrity":"/paper/2501.03941/integrity","json":"/paper/2501.03941/citation-record.json","paper":"/paper/2501.03941"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:29.725019Z","title":"What is synthetic data? https://blogs.nvidia.com/blog/ what-is-synthetic-data/ , 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.725019Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:ab9fbf90845c595ab89a4707eca7899895da2462686511b3331bf1a27daa34cd","observation_id":"0578afac-0faf-4bfa-89a2-89049b483e7b","resolution":{"observed_at":"2026-08-10T21:47:29.725019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.08232","last_updated":"2019-07-16T17:05:32Z","snapshot_observed_at":"2026-08-06T23:45:16.145644Z","submitted_at":"2018-02-22T18:42:41Z","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.08232","snapshot_observed_at":"2026-08-10T21:47:29.729806Z","title":"The secret sharer: Measuring unintended neural network memorization & extracting secrets","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.729806Z"},"links":{"cited_paper":"/paper/1802.08232","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:804bd156b362f4e2162400ccce8683306f95ae2d547cb314daf4263cbc187653","observation_id":"53db1f9d-a4e2-4320-b733-a8d9dc66c1cb","resolution":{"observed_at":"2026-08-10T21:47:29.729806Z","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":"2026-08-10T21:47:29.734201Z","title":"Performing co-membership attacks against deep generative models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.734201Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:f84685533c26d9b0af9aee074018d78517155f8c8c0a7fed4a6cce2b23b38c41","observation_id":"ac0cd565-403d-451f-8ed2-353b6aed3102","resolution":{"observed_at":"2026-08-10T21:47:29.734201Z","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":"2026-08-10T21:47:29.738098Z","title":"Monte carlo and reconstruction membership inference attacks against generative models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.738098Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:604f7a880063ad88de14996fe52f0cab7e2e9e6c38f237b5d52187422f41ad6c","observation_id":"7b4a4278-c7b8-4545-8c49-6f3282269ba8","resolution":{"observed_at":"2026-08-10T21:47:29.738098Z","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":"2026-08-10T21:47:29.741832Z","title":"privgan: Protecting gans from membership inference attacks at low cost to utility","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.741832Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:74e0e2e1dc9a4cd826416bf9e3e3d49f468d61bb870a3a365d4294c2295c18e6","observation_id":"998ab3a3-b5ae-49f9-ae3d-bf413dc72182","resolution":{"observed_at":"2026-08-10T21:47:29.741832Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07663","last_updated":"2018-08-21T13:24:17Z","snapshot_observed_at":"2026-08-05T09:53:41.639197Z","submitted_at":"2017-05-22T11:05:06Z","title":"LOGAN: Membership Inference Attacks Against Generative Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07663","snapshot_observed_at":"2026-08-10T21:47:29.745451Z","title":"Logan: Membership inference attacks against generative models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.745451Z"},"links":{"cited_paper":"/paper/1705.07663","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:87a1ceb7bbf38c513d1b05bf3cfe5b99109c737056a75f3a11a6231663abc22b","observation_id":"b5e541b5-d530-427f-ab7b-044d5f32c9f9","resolution":{"observed_at":"2026-08-10T21:47:29.745451Z","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":"2026-08-10T21:47:29.749510Z","title":"Gan-leaks: A taxonomy of membership inference attacks against generative models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.749510Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:06eaf0635a4e13b742f6c4e270eb4f9e58754db9d7184013928128d331bc9037","observation_id":"8c077884-b0e3-4b55-a854-7df091422b1e","resolution":{"observed_at":"2026-08-10T21:47:29.749510Z","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":"2026-08-10T21:47:29.752762Z","title":"Synthetic tab- ular data evaluation in the health domain covering resemblance, utility, and privacy dimensions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.752762Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:b687d63a7da3d204db6573abb495d3c99052accc0eabb62462b2e175a285b2bc","observation_id":"ddee1c0c-43bb-4613-ab8e-465c4e34b82f","resolution":{"observed_at":"2026-08-10T21:47:29.752762Z","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":"2026-08-10T21:47:29.756127Z","title":"A multifaceted benchmarking of synthetic electronic health record generation models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.756127Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:25b5065c1f8b28cb7eea21c1650f2135f510dca641df927ae18217d9f8475de2","observation_id":"e9db704e-f4d6-4d45-a4df-1499201581bd","resolution":{"observed_at":"2026-08-10T21:47:29.756127Z","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":"2026-08-10T21:47:29.759316Z","title":"Generation and evaluation of synthetic patient data.BMC medical research methodology, 20:1–40, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.759316Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:9bdb331a797f65507e79b2c886e39fee24ccb4d7dca5be5f7bee2f4ab7635049","observation_id":"0587d92d-bb75-4012-a1ee-8748691b72f2","resolution":{"observed_at":"2026-08-10T21:47:29.759316Z","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":"2026-08-10T21:47:29.762698Z","title":"Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.762698Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:217fa6675a830fd948597071bde396dad09075034d007aee671aadf649dd2a6c","observation_id":"5c9eaa26-d72f-48a5-a4d1-cca99a2ac337","resolution":{"observed_at":"2026-08-10T21:47:29.762698Z","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":"2026-08-10T21:47:29.766069Z","title":"Finding a needle in a haystack","venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.766069Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:2b966f23db4604b16c0806ac0d581f8b8eb4e85157fe5a0ece6c6c2ea1d71461","observation_id":"a56c42e5-6f49-4619-80d2-f7b57e27854f","resolution":{"observed_at":"2026-08-10T21:47:29.766069Z","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":"2026-08-10T21:47:29.769916Z","title":"t-closeness: Privacy beyond k-anonymity and l-diversity","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.769916Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:54351852a2da3db79302f3eaee24adbbbf3d551cb4649e3f54d95036bfed546c","observation_id":"fde4b5d7-374c-4007-b4ca-28153444d93f","resolution":{"observed_at":"2026-08-10T21:47:29.769916Z","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":"2026-08-10T21:47:29.773677Z","title":"Revisiting the uniqueness of simple demographics in the us population","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.773677Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:52501bf023b3b0ea88913209a2867897ced69f4eab10550ce085166ba45a5340","observation_id":"85c097da-3d75-4e34-9837-044e1cb51307","resolution":{"observed_at":"2026-08-10T21:47:29.773677Z","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":"2026-08-10T21:47:29.777150Z","title":"Aggarwal","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.777150Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:49c8c5b55d71778bee747eb5b9b4096325e24fe4ffaad2dbf55170245bcb9d0f","observation_id":"196626e8-e823-4d7f-bd94-ece62cee2325","resolution":{"observed_at":"2026-08-10T21:47:29.777150Z","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":"2026-08-10T21:47:29.780865Z","title":"Analyzing leakage of personally identifiable information in language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.780865Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:b78f0182f4cc87893f85cb6e3dbbb9576a7bb66b13de7a6b73ecd0ec5b19038f","observation_id":"082f955d-d0ee-4741-8834-23faff1dce3e","resolution":{"observed_at":"2026-08-10T21:47:29.780865Z","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":"2026-08-10T21:47:29.784408Z","title":"Extracting training data from large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.784408Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:655dfd157650f6b6928a888e9c8679e8e8d218460f57dffaa9e50c2f82941621","observation_id":"1f3f1006-7833-42cc-bfb2-57c3fb7b695f","resolution":{"observed_at":"2026-08-10T21:47:29.784408Z","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":"2026-08-10T21:47:29.787881Z","title":"Madisetti","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.787881Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:2c46095c0f721159c1a60c715d5deed247908a7d6f34bf9a43fe01ffd3fa9cf7","observation_id":"3ef5c133-0983-4d29-8c91-f4be18b49d37","resolution":{"observed_at":"2026-08-10T21:47:29.787881Z","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":"2026-08-10T21:47:29.791374Z","title":"A study on extracting named entities from fine-tuned vs","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.791374Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:cf8753a7c1642a67b8dd72eed58f252e7c1ab1b5db5900eb6acc3ab494292b9d","observation_id":"595ac30e-9718-4075-a9da-018051197b20","resolution":{"observed_at":"2026-08-10T21:47:29.791374Z","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":"2026-08-10T21:47:29.795183Z","title":"Introducing gretel’s transform v2, January 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.795183Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:0cfe7e7d7f25dddf83fbc381ce4a75dea33cbc599cd9a2fcd37c32a99fc8e280","observation_id":"cd1f51c8-456a-40ff-b04a-44ba2e1394bd","resolution":{"observed_at":"2026-08-10T21:47:29.795183Z","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":"2026-08-10T21:47:29.799136Z","title":"Truly anonymous synthetic data – evolving legal definitions and technologies (part ii)., November 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.799136Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:12b91a572e84c5c7045faa33b70c89f6aa9cd637c15282f63467edf7b13aa67b","observation_id":"58635127-85d4-4ec7-8add-fd2b14fdd76c","resolution":{"observed_at":"2026-08-10T21:47:29.799136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.08658","last_updated":"2021-06-02T04:41:17Z","snapshot_observed_at":"2026-07-06T10:34:22.541296Z","submitted_at":"2021-01-18T23:01:27Z","title":"Fidelity and Privacy of Synthetic Medical Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.08658","snapshot_observed_at":"2026-08-10T21:47:29.803008Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.803008Z"},"links":{"cited_paper":"/paper/2101.08658","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:eeb1c8d6722e048233f1b44299c75daa0803a62d65f45b570ba1ebcdb692e5ee","observation_id":"d39bda7a-1f0f-4903-9cab-ccb34b814e61","resolution":{"observed_at":"2026-08-10T21:47:29.803008Z","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":"2026-08-10T21:47:29.807092Z","title":"Synthetic data quality metrics, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.807092Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:349da3e28d722b0e3e84b02565f9789aed4264d9ca73af7fde99e7e35a3a8c00","observation_id":"ce75e1a8-a785-4062-8907-da1fdec1200e","resolution":{"observed_at":"2026-08-10T21:47:29.807092Z","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":"2026-08-10T21:47:29.810775Z","title":"How to evaluate the quality of the synthetic data – measuring from the perspective of fidelity, utility, and privacy, December 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.810775Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:606032fcebe8a2e2783a038c78ae90df54b9058fd59aaf054ebebe18f6c47300","observation_id":"40c05367-c004-4f25-b6d1-0b0338c071a9","resolution":{"observed_at":"2026-08-10T21:47:29.810775Z","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":"2026-08-10T21:47:29.814678Z","title":"Outlier protection in continuous microdata masking","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.814678Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:e4e395472fbb2866e1d6d92813ba34a7cabd3ea70b0c2af207f6896e23eddcb1","observation_id":"034e53e4-79f5-4eba-afcd-8e97503a05da","resolution":{"observed_at":"2026-08-10T21:47:29.814678Z","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":"2026-08-10T21:47:29.818434Z","title":"Maintaining data relationships in structural generation output, March 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.818434Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:9cbf8ab9546b236e3b7bffd6844338f25c64dc715b24bccd5381f96345ca8423","observation_id":"1ad44701-3fc0-47a8-9f3f-2108184bb86d","resolution":{"observed_at":"2026-08-10T21:47:29.818434Z","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":"2026-08-10T21:47:29.822038Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.822038Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:6075e8ff63c395b2e5db10aa82c4582507f4e213d907053499f87399ec015b10","observation_id":"62be0c9e-4500-4a92-b3b4-1a8fa6e46134","resolution":{"observed_at":"2026-08-10T21:47:29.822038Z","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":"2026-08-10T21:47:29.825653Z","title":"The curse of recursion: Training on generated data makes models forget, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.825653Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:f2016716c4cb3ac5175650e537b8dfa024500be2755b563f50b5487978d487da","observation_id":"a9997dbf-c8c8-4cef-8f63-0f440a34db86","resolution":{"observed_at":"2026-08-10T21:47:29.825653Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:31.076538Z","title":"Hazy privacy: Distance to closest record, 2023","venue":null,"work_id":"d4cbe66d-6657-4cd3-be4e-38e25b94e10b","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.829735Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:ecb6c734c88a48dd919c7724b99ae0ca2d8e95cee9d76bcd3d6588384b7a754c","observation_id":"71586f37-c869-478a-b625-eca183089e60","resolution":{"observed_at":"2026-08-10T21:47:31.079880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:31.066361Z","title":"Tabddpm: Mod- elling tabular data with diffusion models, 2022","venue":null,"work_id":"0f64d6e3-9f51-4461-8455-88dae658333c","year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.833389Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:c788e15eb82797e044173109a58b9953dfa8e0553382867483bae217de4a2c61","observation_id":"c66dda8d-9a81-4107-9400-015b4143b9cd","resolution":{"observed_at":"2026-08-10T21:47:31.069843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:31.055780Z","title":"Mixed-type tabular data synthesis with score-based diffusion in latent space","venue":null,"work_id":"b57f390b-a14c-4b02-9e52-b9a57d624c13","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.836872Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:69d722e142cec971465d5658c562df33b9480412162a1cba40d5fa80cd141775","observation_id":"77cd3ada-740b-4e90-adac-27e7085ba231","resolution":{"observed_at":"2026-08-10T21:47:31.059231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:31.043977Z","title":"Guillaudeux, O","venue":null,"work_id":"dbc10ebb-9b9a-4e7d-b3a2-86b45c1bc3cc","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.840704Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:fc911103171284014673845556b1198e013c5f9dcc18647364af2202e9d0344a","observation_id":"20eb5bc5-db31-4d7f-8238-3d5b28c2bd5c","resolution":{"observed_at":"2026-08-10T21:47:31.048145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:31.032446Z","title":null,"venue":null,"work_id":"c1ad2d04-1004-47e2-b141-dbd366b91fe3","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.844203Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:17a9133eb3aac3b47a36217e7e2a37734e8fcc4a2012a46bf5679aa86aaa3b3f","observation_id":"9a33be52-0e55-4f5f-bfe9-8a3ba516e14d","resolution":{"observed_at":"2026-08-10T21:47:31.036409Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:31.020856Z","title":"Data synthesis based on generative adversarial networks.Proc","venue":null,"work_id":"ae11ae7a-f5e2-4250-a546-c42442ffc085","year":2018},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.848054Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:2ca9c079376f30cf9987b221720693ac511c3c4b684750b49c09c6befc822409","observation_id":"f38a7c40-397b-41e7-9113-42e74ada7d24","resolution":{"observed_at":"2026-08-10T21:47:31.024778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:31.009696Z","title":null,"venue":null,"work_id":"90eba8a8-4a3a-427f-a6db-d036d245c005","year":2019},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.851823Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:aaafc1246fadfab0b729bc328800ea1dfc5a5aaade929cd3ec268ae9e07cb044","observation_id":"723c1ece-6352-44c7-b04c-c7dcda66496e","resolution":{"observed_at":"2026-08-10T21:47:31.013481Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.997778Z","title":null,"venue":null,"work_id":"4d6d042a-db91-4203-a703-c95a5588ebf6","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.855271Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:02cb66a422e3a1dbfe2d03cd439dae60dc2ee2f3f18bb9a6b81437bfdb6f9dc7","observation_id":"0fa46cdd-42b2-42ff-944e-9c495d423873","resolution":{"observed_at":"2026-08-10T21:47:31.001505Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.986337Z","title":"Gunter, and Kai Chen","venue":null,"work_id":"5c7f1690-1d47-4535-9335-8be096bb2b34","year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.859022Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:228c1283460112a9d346ccddaf2327a5d9fb7f5acf1627aae595942172d0b0ed","observation_id":"39e17d5a-7e0b-45ca-bd18-1e500e756806","resolution":{"observed_at":"2026-08-10T21:47:30.990168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.974816Z","title":"Achilles’ Heels: Vulnerable Record Identification in Synthetic Data Publishing, page 380–399","venue":null,"work_id":"ef2e3b7d-4fed-4d8c-b332-cbdeda9e31a9","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.862489Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:83ac57bb8558bb634ab86ca59662b820db69b03bfb4662452ad5954192ebfa89","observation_id":"cba448cc-8d9d-435a-a828-eae7e5c8b600","resolution":{"observed_at":"2026-08-10T21:47:30.978917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.963884Z","title":"The privacy onion effect: Memorization is relative","venue":null,"work_id":"20c1c1d6-b623-4aca-8186-9aaa9699484e","year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.866114Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:91d2628a14a81cda2b5a1f2a251d04bdd9f8b2759f7cb2fa578c2603d4cd7136","observation_id":"f485fe10-630e-428b-b7ea-043c5a917c03","resolution":{"observed_at":"2026-08-10T21:47:30.967853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.952710Z","title":"Patient- centric synthetic data generation, no reason to risk re-identification in biomedical data analysis","venue":null,"work_id":"b102fedc-936c-49eb-b925-e00fcddb19a2","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.869664Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:ccb3faf0d74875b1b11fe81c5a454ddacf26428017ffab7e17bb32b2fcda9930","observation_id":"c3105d05-bc02-443f-8774-bcd466ef28ae","resolution":{"observed_at":"2026-08-10T21:47:30.956786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.941107Z","title":"Scaling while privacy preserving: A comprehensive synthetic tabular data generation and evaluation in learning analytics","venue":null,"work_id":"2e62c864-7879-41ee-857e-5d000cb180b8","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.873213Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:0764bba75b5a626d49e42ff210d68ea38ac5f95ae50644d1071729b48034ae01","observation_id":"6d07589d-6bc2-4147-a109-41278518ae59","resolution":{"observed_at":"2026-08-10T21:47:30.945363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.930307Z","title":"Virtualdatalab: A python library for measuring the quality of your synthetic sequential dataset","venue":null,"work_id":"e97ffa91-f4ae-401b-9b7d-9137273d91bd","year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.876827Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:a44ca39a634c9f776b36561174baf4346f27f5f6bc528c390b1b2d37975231de","observation_id":"25110d66-05dd-473a-a60d-e1531c96fa89","resolution":{"observed_at":"2026-08-10T21:47:30.934069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.919698Z","title":null,"venue":null,"work_id":"2c9f4ca7-fd6a-4529-b3d7-84376bf0bd6d","year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.880470Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:51e0c8fa217f50b0aac80797ade0c1c938ba84bebe93b4129403fbf631eab618","observation_id":"df276675-8a30-4cc1-84ee-a79405664e6a","resolution":{"observed_at":"2026-08-10T21:47:30.922758Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.909441Z","title":null,"venue":null,"work_id":"9362a4a2-2aaf-4abf-ac4a-3b77ae070bd0","year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.884089Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:143424b480ba56cf87ed67e5c6e97be91ff0b7a10f229abc281367e2ae57abd7","observation_id":"5ecb5f38-720a-493a-8314-5c5c4266e5a4","resolution":{"observed_at":"2026-08-10T21:47:30.912695Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.899326Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"422bc65e-2d61-4846-9583-48d84dcc7962","year":2017},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.888035Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:8baa138268b2d585f84f4370fb9824da0172b42551149fba65a8d9e19edc474f","observation_id":"d6bca0d6-0ad8-4242-ad39-d8741f4e2794","resolution":{"observed_at":"2026-08-10T21:47:30.903096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.888646Z","title":"Privacy risk in machine learning: Analyzing the connection to overfitting","venue":null,"work_id":"f28c86a9-f508-41c8-a35e-269b62df66a6","year":2018},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.891713Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:acfd64e3cf5b87b2b47405f489e1827efbb0dbdc4db62dc178f7170e26ff3f2e","observation_id":"1b518e88-cc8d-402c-9038-08f56f9187b0","resolution":{"observed_at":"2026-08-10T21:47:30.892465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.877263Z","title":"Marshall, Severin Elvatun, Helga M.B","venue":null,"work_id":"e87c3dd3-f244-46ec-8c48-eca808ff7781","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.895407Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:5fe02174afe5491de9769d44c3131d1a776f0dc56e2d13e837e9b920860a96bd","observation_id":"f266e46b-e491-4746-8222-0018042e4c3e","resolution":{"observed_at":"2026-08-10T21:47:30.881218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.866075Z","title":"Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models","venue":null,"work_id":"cee67a56-39dc-474b-a788-c91f51155bad","year":2019},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.899245Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:80c4d1a0d414de38dac9bc389c53ad7cd142d41ab0d9aa52898188491cedd9b0","observation_id":"0937b966-0be7-4412-90c9-246b0829ffce","resolution":{"observed_at":"2026-08-10T21:47:30.870097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.854901Z","title":"Choquette-Choo, Florian Tramer, Nicholas Carlini, and Nicolas Papernot","venue":null,"work_id":"9df92943-fd5f-45cf-8423-4e845c80d217","year":1964},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.902829Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:68edc74b00d094b7d142c708f250cb5bf3075f00b2c60e7f5878dc46f33114c0","observation_id":"de5b806c-487e-4b7d-9c63-9ff7922beaf2","resolution":{"observed_at":"2026-08-10T21:47:30.859013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.843693Z","title":"Segmentations-leak: Membership inference attacks and defenses in semantic image segmentation","venue":null,"work_id":"2d75e341-1d57-45e7-94dc-c70126a0def7","year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.906782Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:e573108206ec907a972d97ac4a04792c4efdde2bc3379c7082b9b27eda428dd7","observation_id":"d0301173-5ca8-46d0-9151-7d4c9bb0d410","resolution":{"observed_at":"2026-08-10T21:47:30.847700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.831885Z","title":"Evaluating differentially private machine learning in practice","venue":null,"work_id":"554baf1e-7eaf-4964-b1de-2cdef69987e3","year":1912},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.910336Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:9bb5c18dc1b4253ac831d98bed1c1d2ae5711b0a7da127e2584f3a5ad5567107","observation_id":"fe96fa4e-6c93-4d58-8595-03f88fe4537f","resolution":{"observed_at":"2026-08-10T21:47:30.836206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.817823Z","title":"Membership leakage in label-only exposures","venue":null,"work_id":"49f34e5c-be1c-4376-a83b-686e035bde1b","year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.914391Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:3e90392216838710ec94ff363547490e9bcfe31652b26e69c814730cb0f30b7e","observation_id":"8ef9df8d-d562-4437-85cc-664f5bad4377","resolution":{"observed_at":"2026-08-10T21:47:30.822021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.805389Z","title":"Towards reverse-engineering black-box neural networks","venue":null,"work_id":"d41bc8e3-933e-4074-ae0e-cfc9dbbf004c","year":2018},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.918175Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:eade2a7a5e2baab595c676bc53d830d868ded8ee2ed0ae9feabd14ea8306cb0b","observation_id":"cfa3ab25-2d60-492e-b83b-3522e8865ec9","resolution":{"observed_at":"2026-08-10T21:47:30.809524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.793140Z","title":"Membership inference attack against differentially private deep learning model.Trans","venue":null,"work_id":"224caf41-f137-4d6f-bfd3-25d970ab3f41","year":2018},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.921756Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:817b25b28f36fa424d94f5c36c7757b4738dd6030d4fadaf88e66d540b81325a","observation_id":"c75ea0ce-7748-458b-9757-10b0f0f17f87","resolution":{"observed_at":"2026-08-10T21:47:30.797115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.780745Z","title":"White-box vs black-box: Bayes optimal strategies for membership inference","venue":null,"work_id":"1652158c-b1f1-4816-b58a-20f694cbf115","year":2019},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.925353Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:fcc78252c857d1ae0346241b99e3cc774221aaad1dc67e2427c2447b7091c548","observation_id":"e70fd0c6-6d9e-446e-a652-484f545f22df","resolution":{"observed_at":"2026-08-10T21:47:30.785263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.769266Z","title":"Demystifying membership inference attacks in machine learning as a service","venue":null,"work_id":"3b8ba839-6e3c-44b9-bc86-375341996c0a","year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.929049Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:944fd570a16519ec784825a06ac0e5495933b311823962351e2eb81b7846d7ca","observation_id":"bcfcda0c-31a4-42d7-95b7-b1902d3b0850","resolution":{"observed_at":"2026-08-10T21:47:30.772470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.759436Z","title":"Synthetic data–anonymisation groundhog day","venue":null,"work_id":"d64ce0d7-550e-4571-bca4-bcbf5ed13a02","year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.932814Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:b22dcfb602252685e26f460f35598afeab17b6492d937821afad44fa89fd6de1","observation_id":"5c1bcede-ba4b-44ec-93fd-8043af92a4b7","resolution":{"observed_at":"2026-08-10T21:47:30.763185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.749372Z","title":"Membership inference attacks from first principles","venue":null,"work_id":"78159214-ec2e-4c19-9f89-92bdad43a519","year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.936714Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:375af4eec8396d256ecc673ab7b080e25cabaee4217d679e557d4df77e6f36aa","observation_id":"9d7df4c4-fd07-4ecb-963f-2eb6a658181e","resolution":{"observed_at":"2026-08-10T21:47:30.752686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.739383Z","title":"Mattern, F","venue":null,"work_id":"772a2fe6-f6b0-4bcc-9809-1b99be3d64a6","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.940418Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:887a8a323012a93d9eed0ec4d1513653bcc32dafc59ac45aa9af16e4a2292e5e","observation_id":"58b7bd58-2873-46aa-a055-ccd0136aa748","resolution":{"observed_at":"2026-08-10T21:47:30.742606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.727368Z","title":"Evans, and Quanquan Gu","venue":null,"work_id":"e11f7db7-2217-49be-9f61-78a456d8a593","year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.944515Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:edc709e7c1362bd9bbaba74d1662216ea04be28f266e898f93bf79b194de4d63","observation_id":"5e184011-9d21-4107-ab91-d101a9829d55","resolution":{"observed_at":"2026-08-10T21:47:30.731384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.715765Z","title":"On the importance of difficulty calibration in membership inference attacks","venue":null,"work_id":"1ca6d25b-d1b4-4834-bc13-c3f6cfe228dc","year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.948451Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:f20426332d8f1d9d1b0d264a51d7b5826478259e4015433decc1a46e0f2cfccd","observation_id":"d1e9e7e1-0324-4348-bdba-a66c50c807e4","resolution":{"observed_at":"2026-08-10T21:47:30.719853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.703581Z","title":"Validating a membership disclosure metric for synthetic health data","venue":null,"work_id":"7871a86f-17df-40ef-bf51-36fe01fe1f27","year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.952158Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:f710a6b869196725c851ee3e6d6936b8c383307b457b7f28f818f681946a5892","observation_id":"255085ff-f9c1-414e-b7b8-8834de741fca","resolution":{"observed_at":"2026-08-10T21:47:30.707616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.690815Z","title":"Generating synthetic mixed- type longitudinal electronic health records for artificial intelligent applications","venue":null,"work_id":"ca6ae6bd-62a3-4dbe-a010-352bef4f5b5c","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.955681Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:5311302f7c940f0704470491793aecdb1c60f75fb088dc7be55d45193d9e5506","observation_id":"a3cc98df-646a-4322-a178-008f9389e75e","resolution":{"observed_at":"2026-08-10T21:47:30.695151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.674341Z","title":"Ehr-safe: generating high-fidelity and privacy-preserving synthetic electronic health records","venue":null,"work_id":"b439303d-d512-45ab-bb60-a4248c515458","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.958869Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:eebfabd0751d8ad0e642450b7d14af2ea0e1440c638db388d18cbcfece1e5a91","observation_id":"86527b1e-b52b-4c68-ab94-eb51da9be43b","resolution":{"observed_at":"2026-08-10T21:47:30.678296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.661345Z","title":"Gretel’s new data privacy score","venue":null,"work_id":"567cb82f-84b1-4a67-a9e6-d75ba8e28131","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.962135Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:89c9b184076e7b5327c25678ef17651ec023cdbfb1c1e64eac0ed6887d9ceffc","observation_id":"bced3e16-89f9-4910-acdf-85f7a586ad44","resolution":{"observed_at":"2026-08-10T21:47:30.665873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-10T21:47:29.965306Z","title":"Detecting pretraining data from large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.965306Z"},"links":{"cited_paper":"/paper/2310.16789","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:ef100ef796e1eef89c4689425924a37a1f9d5f5eec7aad32a389f16b786f65e5","observation_id":"0f2ee19f-f896-4119-b94b-12bfc5be3ade","resolution":{"observed_at":"2026-08-10T21:47:29.965306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02936","last_updated":"2025-02-12T04:41:34Z","snapshot_observed_at":"2026-08-06T22:02:50.460833Z","submitted_at":"2024-04-03T04:25:01Z","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.02936","snapshot_observed_at":"2026-08-10T21:47:29.968777Z","title":"Min-k%++: Improved baseline for detecting pre-training data from large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.968777Z"},"links":{"cited_paper":"/paper/2404.02936","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:d44813ab6512fe4420bcd00a5ee2b75fee7225267e37c398e470addbf7ebe771","observation_id":"4db44aa3-ff94-4d44-902b-ac848d71fa4e","resolution":{"observed_at":"2026-08-10T21:47:29.968777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.03929","last_updated":"2022-11-04T02:47:37Z","snapshot_observed_at":"2026-08-10T22:04:02.030232Z","submitted_at":"2022-03-08T08:50:34Z","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.03929","snapshot_observed_at":"2026-08-10T21:47:29.972326Z","title":"Quantifying privacy risks of masked language models using membership inference attacks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.972326Z"},"links":{"cited_paper":"/paper/2203.03929","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:9998f909f4cc229608a6c0429a7c45d842903276fec79b5b73e687ff7be3d3c2","observation_id":"022aeb95-bd65-4a1b-afd2-1e324709ad8a","resolution":{"observed_at":"2026-08-10T21:47:29.972326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.09266","last_updated":"2024-02-23T20:25:17Z","snapshot_observed_at":"2026-08-04T19:58:53.523613Z","submitted_at":"2023-10-13T17:24:52Z","title":"User Inference Attacks on Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.09266","snapshot_observed_at":"2026-08-10T21:47:29.976387Z","title":"User inference attacks on large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.976387Z"},"links":{"cited_paper":"/paper/2310.09266","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:a5b62bdfb3df53c2a36d3b4b013453a2027adad7444de656042231809d188eb3","observation_id":"ccbb3a25-3287-4493-acd0-088bf81cea27","resolution":{"observed_at":"2026-08-10T21:47:29.976387Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.648998Z","title":"On the privacy risk of in-context learning","venue":null,"work_id":"ecc9a43e-0dce-4303-b8a0-a4198b80237b","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.980393Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:4a3ff919bdd67ce7dc2d2a15910c939f466e4fc05653dbb44576097a31a25c9f","observation_id":"0f615069-7971-42bd-a83f-ccbb2c772383","resolution":{"observed_at":"2026-08-10T21:47:30.652965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.637401Z","title":"Ensuring electronic medical record simulation through better training, modeling, and evaluation","venue":null,"work_id":"523dfa24-63a0-4dd2-982b-69f653cd3c2e","year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.983960Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:e89e5946754ccaf70b32e3a27e9072f5f537cbfbbf9b0976854124530028f037","observation_id":"191a7384-4aef-4b4b-8eac-8805e7af73c7","resolution":{"observed_at":"2026-08-10T21:47:30.641437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.625267Z","title":"Generating electronic health records with multiple data types and constraints","venue":null,"work_id":"1721de0f-eb77-4046-a0e3-91fa2fe6a8b8","year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.987635Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:a1bfa1d9315b16804e79a43951eb5a7cdad273f8b6bde05f180a95b16694bd5b","observation_id":"d410221a-5106-4795-976f-51bb3e013237","resolution":{"observed_at":"2026-08-10T21:47:30.629409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.06550","last_updated":"2022-11-12T02:26:54Z","snapshot_observed_at":"2026-08-09T11:01:15.414531Z","submitted_at":"2022-11-12T02:26:54Z","title":"TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.06550","snapshot_observed_at":"2026-08-10T21:47:29.991422Z","title":"Tapas: a toolbox for adversarial privacy auditing of synthetic data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.991422Z"},"links":{"cited_paper":"/paper/2211.06550","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:7ebc78fad30c6311db1e6319916fe722a843cacab6eb29ee4eb0ff418f1e32e8","observation_id":"5d0d579b-c086-4e18-9c39-07762a116357","resolution":{"observed_at":"2026-08-10T21:47:29.991422Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.613614Z","title":"Membership inference attacks against synthetic health data","venue":null,"work_id":"abd5cea1-c00e-4af5-a02a-c73f25aff1b0","year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:29.996038Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:e9effae96638d4d504bca55a51efe4b1a351ac7b8c474f2d349545ace77e74fc","observation_id":"05b954a9-8452-4483-97e6-5b763379aa6e","resolution":{"observed_at":"2026-08-10T21:47:30.617732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.600860Z","title":"Application of bayesian networks to generate synthetic health data","venue":null,"work_id":"113dd9ab-a466-4fbd-9737-b9242a675ebf","year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.000156Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:5738adee7d282e5b79a441c0d6b99f24144797e618505712f324636951579c55","observation_id":"7da028a0-7323-4f2b-a2fe-d5d7eddb9525","resolution":{"observed_at":"2026-08-10T21:47:30.604769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.004495Z","title":"Generating multi-label discrete patient records using generative adversarial networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.004495Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:01c1870bb09960586e435407b373a92c772e20b225a9f5b011d62f4b93d9e853","observation_id":"7f7e8baf-fd56-43c9-a56d-455eaea573a9","resolution":{"observed_at":"2026-08-10T21:47:30.004495Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.582391Z","title":"Ghosheh, Jin Li, and Tingting Zhu","venue":null,"work_id":"0faf293b-ce8e-4e8f-a140-51c9f9f10368","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.008523Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:27b2835f5739226605ad2a68dc5b64b40f1627cb436785b5acdad8f6d4a92dde","observation_id":"d0a48190-668f-4f26-b103-3c5a908f1640","resolution":{"observed_at":"2026-08-10T21:47:30.585838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.570684Z","title":"A linear reconstruction approach for attribute inference attacks against synthetic data","venue":null,"work_id":"5434a2d9-af4c-485d-b386-f7bf78e7da99","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.012512Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:1e4e865d36576aa8c0dd468614720829588aeeab33594034b4f54563346df344","observation_id":"e6ec931a-6681-4a88-933a-4f9dd22b57ab","resolution":{"observed_at":"2026-08-10T21:47:30.574591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.559234Z","title":"Evaluating identity disclosure risk in fully synthetic health data: Model development and validation","venue":null,"work_id":"1f2dc33c-c0af-4baf-a4b1-63005f84f4e2","year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.016687Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:d99011b4176a329cf275c1348f343589008ed597271fa08ef8d8418fed1fa0ad","observation_id":"35387088-344c-4cac-a1ec-8b5421ec82ed","resolution":{"observed_at":"2026-08-10T21:47:30.563046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.547769Z","title":"Pérez, Marten van Dijk, and Lydia Y","venue":null,"work_id":"ace14008-f428-4248-8278-fcbb68c7acf7","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.022002Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:32dcfb03e0d2dd4d2d09914eb801113b00b98ef951621df277a0303d98f780f0","observation_id":"6dcfc50c-1e65-45b3-b655-4741d7d29c86","resolution":{"observed_at":"2026-08-10T21:47:30.551600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.535567Z","title":null,"venue":null,"work_id":"aca2e86c-2255-45da-ad24-a3bc3e8a34b9","year":null},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.026202Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:cf29ef8c5404f7dd4a4d41ab856d7e4ad0939204c15f3a6be9ed02dd40c50a44","observation_id":"5c8efbe5-4ae2-41f0-a8a2-8a8481ba163a","resolution":{"observed_at":"2026-08-10T21:47:30.540026Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.522798Z","title":"Pate-gan: Generating synthetic data with differential privacy guarantees","venue":null,"work_id":"8775bc5a-0e7f-43ea-83f3-eb57ed1a5366","year":2018},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.030508Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:29dfafed29b67273149a5cb98a3722429ba5f58d2b63122c48354fbd97a0649b","observation_id":"926c628b-0a69-4b5b-939f-076c4eb2b88e","resolution":{"observed_at":"2026-08-10T21:47:30.527092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.510112Z","title":"A simple recipe for private synthetic data generation","venue":null,"work_id":"c84e013a-7fb2-43d5-9335-648ac5fd38cb","year":null},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.034331Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:170a955784f55210f374ab689c4c5b5a240e56ecae31b1d58ee5d5e33425ce51","observation_id":"dd7c1f55-b35d-4e4c-93a2-a443d9981241","resolution":{"observed_at":"2026-08-10T21:47:30.514743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.038247Z","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":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.038247Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:2e2f91c521858806c7e486c94e04f1adfeb2935786fc5f25aa53c043e3d41feb","observation_id":"baf544b6-4dc2-437c-b340-9f186b93574e","resolution":{"observed_at":"2026-08-10T21:47:30.038247Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.490253Z","title":"Adversary instantiation: Lower bounds for differentially private machine learning","venue":null,"work_id":"ed3efcae-e4fa-461d-8c0d-fccdaad38137","year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.042984Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:7657b9de7d965bee3f07d345e345a813631e411a23738f8761cf9a5c5cda688f","observation_id":"c1ff6ee7-c423-4547-9e1c-385ece880b41","resolution":{"observed_at":"2026-08-10T21:47:30.494813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14397","last_updated":"2024-02-22T09:26:16Z","snapshot_observed_at":"2026-07-06T17:33:50.525062Z","submitted_at":"2024-02-22T09:26:16Z","title":"Closed-Form Bounds for DP-SGD against Record-level Inference","version":1},"cited_work":{"arxiv_id":"2402.14397","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.14397","snapshot_observed_at":"2026-08-10T21:47:30.197131Z","title":"Closed-Form Bounds for DP-SGD against Record-level Inference","venue":"cs.CR","work_id":"5e9c92e8-5075-4122-8091-0886d5b16a06","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.046780Z"},"links":{"cited_paper":"/paper/2402.14397","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:176709ad7f5b98999bf01726fb0111c9afe2be572f2f87e5e1791e855df13e72","observation_id":"6c4b8979-312b-46d6-b35e-82b6f6afd24c","resolution":{"observed_at":"2026-08-10T21:47:30.201690Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.051172Z","title":"Privacy auditing with one (1) training run","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.051172Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:9c2bfbf90bf6be71dac360af7c75cd7a1867e2ce3f57e89f994a0182d25412e9","observation_id":"5e8a20b5-cc08-4d59-9afa-9f445d1aaa87","resolution":{"observed_at":"2026-08-10T21:47:30.051172Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.470205Z","title":"Investigating membership inference attacks under data dependencies","venue":null,"work_id":"95d0e0c1-d3a2-4aa7-8bb2-9442b5c4035d","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.055135Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:a48dee0145ad1c3ad729bc57d4292567b657ba16416c6fa8b16f91b35ada613e","observation_id":"da89a8d2-5bd3-4bdf-ba26-b3ceef645b64","resolution":{"observed_at":"2026-08-10T21:47:30.474637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.457290Z","title":null,"venue":null,"work_id":"858473a8-f69a-474a-8dc9-56b4fd1df2cd","year":null},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.058884Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:622eeebd884dc364b77b38ca08da50a5b485e26d1d61ab6df98c2ab012c4e7f6","observation_id":"ea96d86a-30a8-45d1-883a-523bf27b42c7","resolution":{"observed_at":"2026-08-10T21:47:30.461294Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.443102Z","title":"Detect and redact pii in free text with ner in transform v2.https://gretel.ai/ blog/detect-and-redact-pii-in-free-text-with-ner-in-transform-v2 , 2024","venue":null,"work_id":"3dc8f415-faeb-4893-a411-f50f5908305e","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.063317Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:1f4dc1db031a67726da5ab9d5f0bf3fc9b62d838d3693d745e7f0e6fe24dbe0f","observation_id":"16d498a1-ae0a-40d3-8807-448c1a55399b","resolution":{"observed_at":"2026-08-10T21:47:30.447984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.432300Z","title":"Introducing gretel’s transform v2","venue":null,"work_id":"1a90b3db-8655-42f3-aafa-6f257e204d92","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.067847Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:e4306a5b5a015f449dabdeaf1f2b89dad9a94e201ec28028a015688c95daaa5b","observation_id":"edad4e26-8261-4899-9023-846734b6c6b6","resolution":{"observed_at":"2026-08-10T21:47:30.436043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.420189Z","title":"Introducing gretel’s privacy filters","venue":null,"work_id":"b0baee8b-a6e3-4c3b-88e1-0bb72b1bdc03","year":2021},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.071421Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:30246fb56f199bd15bda1ef4bf7e67801faba7ea3cc5d5ebb4b6b596db514148","observation_id":"067befa4-7e8a-4621-ac69-d6ac0b98344a","resolution":{"observed_at":"2026-08-10T21:47:30.424165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.406948Z","title":"Practical synthetic data generation: balancing privacy and the broad availability of data","venue":null,"work_id":"cc3a702e-92ac-479f-81be-08bbbcd620c9","year":2020},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.075436Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:bfc7e7edae44fa99e13545d247984c4c551b2a2bfecb377307f51dc9bd7fac87","observation_id":"e74316f8-30ad-4457-a771-117d3cef6852","resolution":{"observed_at":"2026-08-10T21:47:30.411318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.393724Z","title":"Strict synthesis","venue":null,"work_id":"5d944174-5b22-45be-aecd-22970f2c5f15","year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.079215Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:b5c1fc5637b7b6a94f2ed5a1d64129e02ebb0a3ecdba1d404f26b7b9de21d3db","observation_id":"24a5980c-3998-452b-a4df-497dfdaa18af","resolution":{"observed_at":"2026-08-10T21:47:30.397652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.083006Z","title":"Deduplicating training data mitigates privacy risks in language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.083006Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:d5d97d165f6169fa8a3037bbc85eb71a25d69b5545e0cf8a084d5ed0498826ca","observation_id":"9c5dd5d7-1657-409d-a35b-f8cc67713288","resolution":{"observed_at":"2026-08-10T21:47:30.083006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07841","last_updated":"2024-09-16T13:18:23Z","snapshot_observed_at":"2026-08-07T03:58:21.441544Z","submitted_at":"2024-02-12T17:52:05Z","title":"Do Membership Inference Attacks Work on Large Language Models?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07841","snapshot_observed_at":"2026-08-10T21:47:30.086668Z","title":"Do membership inference attacks work on large language models? arXiv preprint arXiv:2402.07841, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.086668Z"},"links":{"cited_paper":"/paper/2402.07841","citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:a933f45a8309f6793d2b433aa476f817dccdeb59cdd154ebc3177ff10e5791cd","observation_id":"4d21b3e2-2e99-4460-8ffd-282b8f3db0b2","resolution":{"observed_at":"2026-08-10T21:47:30.086668Z","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":"2026-08-10T21:47:30.090132Z","title":"Extracting training data from diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.090132Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:7bffe1671d3f0e6fe2c8c3c63330670660b329b2e82b85d21f08972c931232fd","observation_id":"f0ab9426-77f0-400a-bd38-6fefeae4ffae","resolution":{"observed_at":"2026-08-10T21:47:30.090132Z","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":"2026-08-10T21:47:30.093382Z","title":"Quantifying memorization across neural language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.093382Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:162eaee5038371bcbbc73939e55beec4cf7df5bd6b6ba7db2e83f2f6ae586896","observation_id":"cde56d93-1048-47b1-8e5f-f48c2e70305b","resolution":{"observed_at":"2026-08-10T21:47:30.093382Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.357915Z","title":"Deduplicating training data makes language models better","venue":null,"work_id":"c8e29551-fb01-4c48-89bf-37fcaf3cbc3b","year":2022},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.096819Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:7694d29eebf739e8b261394c8c21a05c2a70b909b36cb2b5efa4138e25974fcc","observation_id":"dd71d81c-364a-4a33-871e-94651e5b397f","resolution":{"observed_at":"2026-08-10T21:47:30.362057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:47:30.342150Z","title":"Privacy side channels in machine learning systems","venue":null,"work_id":"5fe6fbc9-98bc-48d6-bf6f-aacfc14cd715","year":2024},"citing_paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-10T21:47:30.100207Z"},"links":{"citing_paper":"/paper/2501.03941"},"observation_digest":"sha256:a539e14084a3f7f1065512ae0ef9069850f0069529c46d8539f12b36c8ca6e2e","observation_id":"1d5fb112-d7dc-4c0a-a798-78326d7c7b66","resolution":{"observed_at":"2026-08-10T21:47:30.348038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.03941","last_updated":"2025-01-07T17:02:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T22:04:56.823775Z","submitted_at":"2025-01-07T17:02:33Z","title":"Synthetic Data Privacy Metrics"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":47,"verified_exact":1,"verified_fuzzy":52},"total_outbound_references":105},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 100 of 105 outbound references and 4 inbound Pith citation observations for arXiv:2501.03941."}