{"as_of":"2026-08-18T21:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:25f4b6ba3ebf4305d4a4b693ea0ff944645f7c4cd272341187598e479a50709e","coverage":[{"denominator":8,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":8,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:27:53.745453Z","state":"measured"},{"denominator":8,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":8,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.16661/citation-record","integrity":"/paper/2506.16661/integrity","json":"/paper/2506.16661/citation-record.json","paper":"/paper/2506.16661"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.04566","last_updated":"2025-06-05T02:34:50Z","snapshot_observed_at":"2026-08-17T22:34:03.756063Z","submitted_at":"2025-06-05T02:34:50Z","title":"Clustering and Median Aggregation Improve Differentially Private Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.04566","snapshot_observed_at":"2026-08-15T19:27:53.717070Z","title":"Clustering and Median Aggregation Improve Differentially Private Inference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T19:27:53.717070Z"},"links":{"cited_paper":"/paper/2506.04566","citing_paper":"/paper/2506.16661"},"observation_digest":"sha256:76ecfa83dda8d5dd497a04e25cf5e246650c21c92b39cd7b2162739a02e08f3c","observation_id":"d08654af-31e7-46f5-896b-cee63b7e333c","resolution":{"observed_at":"2026-08-15T19:27:53.717070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1411.7923","last_updated":"2014-11-28T16:05:18Z","snapshot_observed_at":"2026-08-14T23:09:48.219510Z","submitted_at":"2014-11-28T16:05:18Z","title":"Learning Face Representation from Scratch","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1411.7923","snapshot_observed_at":"2026-08-15T19:27:53.745453Z","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T19:27:53.745453Z"},"links":{"cited_paper":"/paper/1411.7923","citing_paper":"/paper/2506.16661"},"observation_digest":"sha256:533dde579ea4dde4901f995e47e244f67f5e9b86b71e2ba74d1e6e65421dcb0f","observation_id":"5cb2d4f1-4953-4e69-9dc4-3c222b13577d","resolution":{"observed_at":"2026-08-15T19:27:53.745453Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-15T19:27:53.721753Z","title":"Scalable Differentially Private Clustering via Hierarchically Separated Trees","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T19:27:53.721753Z"},"links":{"citing_paper":"/paper/2506.16661"},"observation_digest":"sha256:6babbd691a9b5dbe0b70ec2fee7aec9a89e13b38de7beb405f5a50a7e8bcffd1","observation_id":"02e63e8c-9e08-45bb-be33-666801c901ac","resolution":{"observed_at":"2026-08-15T19:27:53.721753Z","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":"2026-08-15T19:27:54.015872Z","title":"Unsupervised Deep Embedding for Clustering Analysis","venue":null,"work_id":"a7a6fe0a-fbfd-4de3-880d-20b458ba6e26","year":2019},"citing_paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T19:27:53.741916Z"},"links":{"citing_paper":"/paper/2506.16661"},"observation_digest":"sha256:ce7d5f9822226df3b09853a1c2bf3982abff5b54c12e979ea2111d384cc06351","observation_id":"7750ee89-46d6-43e1-a129-c2cc8add19a1","resolution":{"observed_at":"2026-08-15T19:27:54.021798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13861","last_updated":"2023-02-27T15:02:04Z","snapshot_observed_at":"2026-08-18T00:43:39.442285Z","submitted_at":"2023-02-27T15:02:04Z","title":"Differentially Private Diffusion Models Generate Useful Synthetic Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13861","snapshot_observed_at":"2026-08-15T19:27:53.726119Z","title":"NIMA: Neural Image Assessment","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings","version":1},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-15T19:27:53.726119Z"},"links":{"cited_paper":"/paper/2302.13861","citing_paper":"/paper/2506.16661"},"observation_digest":"sha256:ce85b2cdb07718705311b06d0a70fa0606659df2127d54344e5a8b7e43efcd2d","observation_id":"8bef36e3-93f7-4155-8bc2-01799387f42b","resolution":{"observed_at":"2026-08-15T19:27:53.726119Z","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":"2026-08-15T19:27:53.733618Z","title":"Harnessing large-language models to generate private synthetic text","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings","version":1},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-15T19:27:53.733618Z"},"links":{"citing_paper":"/paper/2506.16661"},"observation_digest":"sha256:c989cb28bd50ef52583bf68697a4eabd5698fd6961f8129b648c465e1698045d","observation_id":"0d45edfc-18a9-42cd-9ff6-c20266c4798e","resolution":{"observed_at":"2026-08-15T19:27:53.733618Z","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":"2026-08-15T19:27:54.029728Z","title":"Pre-trained Perceptual Features Improve Differentially Private Image Generation","venue":null,"work_id":"7a811366-d6c9-4fd0-bad9-fd38a0a09e8c","year":2023},"citing_paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-15T19:27:53.730145Z"},"links":{"citing_paper":"/paper/2506.16661"},"observation_digest":"sha256:92b3ea7a345267e6242fa06ea654aed6cd48b6b84c91a5b7ed9fca9cebb19adf","observation_id":"4fac54ed-b504-4479-9478-b58f1bb0640d","resolution":{"observed_at":"2026-08-15T19:27:54.034105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.05537","last_updated":"2020-11-11T04:03:08Z","snapshot_observed_at":"2026-08-16T19:06:41.859160Z","submitted_at":"2020-11-11T04:03:08Z","title":"Differentially Private Synthetic Data: Applied Evaluations and Enhancements","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.05537","snapshot_observed_at":"2026-08-15T19:27:53.737716Z","title":"Gaussian mixture models","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T19:27:53.737716Z"},"links":{"cited_paper":"/paper/2011.05537","citing_paper":"/paper/2506.16661"},"observation_digest":"sha256:53d81d1741bea14100effb126e500ea73d9bb30fa84810188cd272bbad282546","observation_id":"ce711b51-63ec-481a-bd91-839f063e8d4b","resolution":{"observed_at":"2026-08-15T19:27:53.737716Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.16661","last_updated":"2025-06-20T00:17:14Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T21:05:53.340262Z","submitted_at":"2025-06-20T00:17:14Z","title":"Private Training & Data Generation by Clustering Embeddings"},"reference_resolution":{"displayed":8,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":2},"total_outbound_references":8},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 0 inbound Pith citation observations for arXiv:2506.16661."}