{"as_of":"2026-08-24T03:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:677e464104512e1c9f9cc8eed3417cceaf1bc6551e422ae710dd60d891c72bbd","coverage":[{"denominator":65,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":65,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:02:17.674345Z","state":"measured"},{"denominator":65,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":65,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2504.21634/citation-record","integrity":"/paper/2504.21634/integrity","json":"/paper/2504.21634/citation-record.json","paper":"/paper/2504.21634"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2004.07740","last_updated":"2021-10-01T17:11:29Z","snapshot_observed_at":"2026-08-20T19:39:10.761024Z","submitted_at":"2020-04-16T16:24:22Z","title":"Really Useful Synthetic Data -- A Framework to Evaluate the Quality of Differentially Private Synthetic Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.07740","snapshot_observed_at":"2026-08-16T05:02:17.437629Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.437629Z"},"links":{"cited_paper":"/paper/2004.07740","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:deeda23f3ec843c73dd664e72eb1301c3b37ff245528aa1700e2640a238929eb","observation_id":"646085e9-05a0-4dd9-8130-04c1ffa3f3de","resolution":{"observed_at":"2026-08-16T05:02:17.437629Z","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":"2026-08-16T05:02:18.346604Z","title":null,"venue":null,"work_id":"9e194c42-7e49-4af1-99ba-b99d9436e911","year":2019},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.442146Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:b4915b4733aeb36fc84b8457298dd136554081b7135bafe8e2e189878ed4f372","observation_id":"2b0d095a-92f2-4ead-87a8-76c2dfa0e88e","resolution":{"observed_at":"2026-08-16T05:02:18.350217Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.334728Z","title":null,"venue":null,"work_id":"0e53bb71-16fc-4d86-8af4-4dc0470f93d4","year":2007},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.445532Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:17a5155d5844c720c608fd1b60e2b1ffe7b72283148a021395f002a5d417b55f","observation_id":"6640f947-af82-4cb9-adc0-49f7f1df0213","resolution":{"observed_at":"2026-08-16T05:02:18.338738Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.449345Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.449345Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:81691cb655b9ff417c152e3d3f8de7191e3bdf2004c0d67c72840fdb219f1e3f","observation_id":"c3d3f137-0dfe-434a-8cb8-e65012c5d449","resolution":{"observed_at":"2026-08-16T05:02:17.449345Z","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":"2026-08-16T05:02:18.315005Z","title":null,"venue":null,"work_id":"b6350b50-be55-4e8a-8061-14742b7d1846","year":2023},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.453735Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:0cd86fe3ac206a61c9e0de6b25017f0f221014c7a6f116e6fd7a466995808a31","observation_id":"3d04cd2e-486e-45c4-b20d-72708a43a116","resolution":{"observed_at":"2026-08-16T05:02:18.318958Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.457839Z","title":null,"venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.457839Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:5e2ff53d9507444994afbaa24013b9a82845429d08650f6f8c4759fa8067abc1","observation_id":"56969c8e-0114-4677-9712-5dc02212cc72","resolution":{"observed_at":"2026-08-16T05:02:17.457839Z","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":"2026-08-16T05:02:17.462267Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.462267Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:7c687e8555ead466a25c838ecc0e8f832d8a65c34b1968e537e28f4beff5b7bd","observation_id":"3b8d6dab-3c2f-453a-8d58-a8d79447b6cb","resolution":{"observed_at":"2026-08-16T05:02:17.462267Z","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":"2026-08-16T05:02:17.466281Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.466281Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:018aa9d4ec64df638a70593bb21e2c2163d689cf0de29e752d85950b9fcf24bd","observation_id":"33eea84b-2966-47ad-8c37-1ff636b55ca9","resolution":{"observed_at":"2026-08-16T05:02:17.466281Z","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":"2026-08-16T05:02:17.469801Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.469801Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:df5b782e164536ddf973aa7c6896fe43ef2375e803561f6cbc9bf7d356027a86","observation_id":"b3c48511-9edf-49d3-b020-fa59df431720","resolution":{"observed_at":"2026-08-16T05:02:17.469801Z","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":"2026-08-16T05:02:18.282567Z","title":null,"venue":null,"work_id":"fff1c846-4ca4-4955-bcbd-f6cab8d1483b","year":2020},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.473677Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:4a96e0fa5f9a225e04ee1ebf7aa8c440070bc27c099651ce4580b37bf3248f64","observation_id":"48b4683f-4163-4b29-a66a-9702bc11bafe","resolution":{"observed_at":"2026-08-16T05:02:18.286764Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.12704","last_updated":"2020-10-12T13:38:52Z","snapshot_observed_at":"2026-08-18T11:11:07.674985Z","submitted_at":"2019-11-28T13:38:17Z","title":"Comparative Study of Differentially Private Synthetic Data Algorithms from the NIST PSCR Differential Privacy Synthetic Data Challenge","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.12704","snapshot_observed_at":"2026-08-16T05:02:17.477543Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.477543Z"},"links":{"cited_paper":"/paper/1911.12704","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:2bce7761d82476ce3090988d2f8055e5a32708463a92c9c9150bf5d987bdd839","observation_id":"e4f18cf5-4089-44e3-90de-16916ace2e7c","resolution":{"observed_at":"2026-08-16T05:02:17.477543Z","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":"2026-08-16T05:02:18.271755Z","title":null,"venue":null,"work_id":"f8ab9515-2a75-45af-9d4f-ca994c069edd","year":2017},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.481925Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:2fe69281c02e360624a0ec8f058899aebc02849147fad5e0f1c5259eeb25605c","observation_id":"4446e91b-4864-44ed-8679-c23478ff5d43","resolution":{"observed_at":"2026-08-16T05:02:18.275279Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.260749Z","title":null,"venue":null,"work_id":"a602b449-a257-4cd0-bb14-140c41b3f253","year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.485853Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:89670953f9d9197be0c772b56189c14a78856a7f666bdbca38a025c2845bb319","observation_id":"bb0862d8-11ba-450a-bc91-d153ad58f7a3","resolution":{"observed_at":"2026-08-16T05:02:18.264591Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.490147Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.490147Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:ffc2a1461d91e86a52a166e19d51c43105c4bbd69c63a006bb1ec7194a149861","observation_id":"b426ae2c-7310-41d6-aa0f-fc63d0d3a0cc","resolution":{"observed_at":"2026-08-16T05:02:17.490147Z","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":"2026-08-16T05:02:17.494022Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.494022Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:5095d6318937d32b349e1d5348460b8d656f65152644c4339bb3ab04c665e3aa","observation_id":"f186832d-5f49-4b0d-9e6e-56e1ef6d6544","resolution":{"observed_at":"2026-08-16T05:02:17.494022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.01337","last_updated":"2022-11-13T21:39:01Z","snapshot_observed_at":"2026-08-21T04:57:31.177152Z","submitted_at":"2019-06-04T10:55:01Z","title":"SoK: Differential Privacies","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.01337","snapshot_observed_at":"2026-08-16T05:02:17.498911Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.498911Z"},"links":{"cited_paper":"/paper/1906.01337","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:9cfccdc7a3e7345ec7ca51270853702971c9cafa57b0bf3a815a0677c797aeda","observation_id":"314ed5eb-358b-45d7-8f43-6cb9eca1c476","resolution":{"observed_at":"2026-08-16T05:02:17.498911Z","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":"2026-08-16T05:02:18.235248Z","title":null,"venue":null,"work_id":"431444d7-c345-4ddb-a2e6-bd4740a32347","year":2022},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.503508Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:08e60e459a0d8d41b90b2d8b42f95eb15613ec8477f7f585277b0f05ce0e4d17","observation_id":"76d16f66-5a51-4f43-a1c5-8eb28cd10694","resolution":{"observed_at":"2026-08-16T05:02:18.239001Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.223340Z","title":null,"venue":null,"work_id":"e06ce83a-95dc-4e9b-a6d5-993ca04a68cb","year":2006},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.507554Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:e01280d10cf5f2b5963127baf69d66dcfaf282c4e10d6955778606fcb0e7949b","observation_id":"7aa0ff71-97a4-4993-be18-f0f34fbeac89","resolution":{"observed_at":"2026-08-16T05:02:18.227414Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.511226Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.511226Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:ff107218acfeec9f8cdd6845fa54fd15b47d2676161203204ab62b6df0500d2f","observation_id":"7dca468e-54d9-4334-b089-a84004fe230b","resolution":{"observed_at":"2026-08-16T05:02:17.511226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.12763","last_updated":"2020-08-28T17:41:11Z","snapshot_observed_at":"2026-08-21T04:57:35.984668Z","submitted_at":"2020-08-28T17:41:11Z","title":"Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.12763","snapshot_observed_at":"2026-08-16T05:02:17.514910Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.514910Z"},"links":{"cited_paper":"/paper/2008.12763","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:b78a946271a743c7c2ef4ad478f8591f83055b31a280db4f5266ded113cb018c","observation_id":"acd80137-8ab6-4307-9957-7b492d0a24e7","resolution":{"observed_at":"2026-08-16T05:02:17.514910Z","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":"2026-08-16T05:02:18.204071Z","title":null,"venue":null,"work_id":"94b1dc31-68b7-4041-a9a1-7f0fb464fc2f","year":2018},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.519451Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:eb4611acc07e60d1787844a96b3b0d3b0360d905459d825e313a107ce449f88c","observation_id":"81c1ebb6-fb2e-4ad3-b3e7-5e2292192aa8","resolution":{"observed_at":"2026-08-16T05:02:18.208201Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.192680Z","title":null,"venue":null,"work_id":"4cfd0754-c7c9-4658-93a0-765b6b65dc1c","year":2023},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.523951Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:689584070bb1d0b69f2a2b4651118943cc63239fe50776878d88dd46521dc063","observation_id":"c072ab52-2069-43c8-beb5-a21cfc813700","resolution":{"observed_at":"2026-08-16T05:02:18.196730Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.527660Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.527660Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:6cc4e8c2d2a5e2935d63c0e75d81d94bc86d2a4b77cc005f85e5cdd37998ff29","observation_id":"924b38cf-13df-4bfb-8988-c550d2e50d1e","resolution":{"observed_at":"2026-08-16T05:02:17.527660Z","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":"2026-08-16T05:02:17.531350Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.531350Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:0ce9cf55c93099c62dc96b94e60bb2dceafe8a313a047482dfc3f943c6cc6834","observation_id":"c7f0df55-2362-4a88-bb76-e4a66af55907","resolution":{"observed_at":"2026-08-16T05:02:17.531350Z","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":"2026-08-16T05:02:18.168874Z","title":null,"venue":null,"work_id":"da1ce8e0-50cd-46c6-a1f2-3cf8b2564bb9","year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.534869Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:6562e1e266d7d351731232e54f80ace8d927cabfbb6860759f5493e5ddcc012f","observation_id":"8db86902-0917-4cb5-9234-3b0003cb8c48","resolution":{"observed_at":"2026-08-16T05:02:18.171844Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.159525Z","title":null,"venue":null,"work_id":"f34303f1-3b0f-4366-8bd9-9ae8408dbb85","year":2024},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.538498Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:5d7e7cd7216a4eb16af05ff7abce7d9da85d2fc4b1addc034a1f7c22ed0ba28e","observation_id":"bb33c9ac-9701-4231-8abf-3a5bd6eb152b","resolution":{"observed_at":"2026-08-16T05:02:18.162571Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.542295Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.542295Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:79e2095336dea3ea58b3544770a1a3339bed94b1f611eadc493e7adae441982d","observation_id":"f1d1aa1e-dc51-4187-99b3-f8d331932ab8","resolution":{"observed_at":"2026-08-16T05:02:17.542295Z","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":"2026-08-16T05:02:18.150329Z","title":null,"venue":null,"work_id":"a68ecf6f-3564-4949-9995-b0dba423f640","year":2012},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.545745Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:2150aebce30f1f22e181401542b6bc36635f5a2aa73f80fce52216eb62fb312b","observation_id":"fbb174ce-5a21-411f-8546-eb83071f918f","resolution":{"observed_at":"2026-08-16T05:02:18.153283Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.05807","last_updated":"2016-11-17T16:41:21Z","snapshot_observed_at":"2026-08-15T21:21:58.666896Z","submitted_at":"2016-09-19T16:08:51Z","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.05807","snapshot_observed_at":"2026-08-16T05:02:17.549247Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.549247Z"},"links":{"cited_paper":"/paper/1609.05807","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:5f3a9315a686ed94feec94c1669176c9e2168aa4763f6cb9f5f2ee3e8aaacabb","observation_id":"af528c72-c95a-4bab-8b46-a14f506fe01c","resolution":{"observed_at":"2026-08-16T05:02:17.549247Z","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":"2026-08-16T05:02:18.140396Z","title":null,"venue":null,"work_id":"9e9e0cea-a204-4501-a97c-d6f97e6073e1","year":2009},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.553190Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:c748ed8b77fec2a8a57625f204f1ab4daf597ff09db4e92b88bdc326e975f2f4","observation_id":"bbdc8817-cc28-4fd3-901b-79a28fadfe63","resolution":{"observed_at":"2026-08-16T05:02:18.143795Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.129458Z","title":null,"venue":null,"work_id":"1cb623b9-0ca0-49c5-acb4-7ff312032afa","year":2020},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.556540Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:c48088ddf1b5525276182ce4c85afec14a4b7b66655960ab4b349aaab9ecde29","observation_id":"2abc8cb4-f383-4b3b-8602-f42461f0268e","resolution":{"observed_at":"2026-08-16T05:02:18.133423Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.118921Z","title":null,"venue":null,"work_id":"62abdcbc-408a-45b8-884f-b26af3567b9e","year":2016},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.559639Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:8bec71bd7404240dd72dbab6e7c46fb2cef880a425532f295d0778ec68adeac5","observation_id":"f01a8223-06d0-40db-8476-cee34f2ce561","resolution":{"observed_at":"2026-08-16T05:02:18.122547Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.107910Z","title":null,"venue":null,"work_id":"191afbf0-907d-4f18-870e-6d23f1f1cc85","year":2016},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.562245Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:2a3bc9defa6bb54ebdb1b679290f705cf01d75602f9c7e3714dc7548ea269ad8","observation_id":"140ea3a6-a9e7-4747-b09e-b771bc917ebf","resolution":{"observed_at":"2026-08-16T05:02:18.111773Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.04062","last_updated":"2025-04-04T09:34:37Z","snapshot_observed_at":"2026-08-18T16:42:16.821528Z","submitted_at":"2023-02-08T13:59:31Z","title":"Machine Learning for Synthetic Data Generation: A Review","version":10},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.04062","snapshot_observed_at":"2026-08-16T05:02:17.565517Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.565517Z"},"links":{"cited_paper":"/paper/2302.04062","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:32e006721b08a00b24c7f6d6c67e817ed3cc45464b2bdcb1e834e1e6631b265c","observation_id":"92fa56aa-9211-4e3c-b3fc-8baf7735ec34","resolution":{"observed_at":"2026-08-16T05:02:17.565517Z","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":"2026-08-16T05:02:18.097521Z","title":null,"venue":null,"work_id":"90bb0110-02e3-4fdf-87e1-b3d3710a9f8d","year":2018},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.568757Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:3585dc02aaa64d531853d1da56a8266c22a0e223ec521df086f3b6a483231ff2","observation_id":"ee5e1076-445f-4a8a-b275-721dc43dc0ba","resolution":{"observed_at":"2026-08-16T05:02:18.101081Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.086575Z","title":null,"venue":null,"work_id":"40769173-e284-4c8a-856b-26e0715c8b77","year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.571746Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:13bb1f82bb438a4cd362cfd85f980e02c86645e600835c18b250d6fc49e56503","observation_id":"aae71df7-534e-4c1e-9433-c824fec475eb","resolution":{"observed_at":"2026-08-16T05:02:18.090229Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.076278Z","title":null,"venue":null,"work_id":"fbc2730a-45c8-4261-aa75-e2617f0a64a1","year":2022},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.574517Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:2b2e18d3e6ef06fa1cee2b3719533d013a7e0c4d8e872e354a965f98cca77cf9","observation_id":"9189b28d-2896-4e0d-acd6-359f13fd8aaf","resolution":{"observed_at":"2026-08-16T05:02:18.079805Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.065513Z","title":null,"venue":null,"work_id":"c4af2d64-f26e-43be-b687-85fbd5637b39","year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.577732Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:9e831aadbbeff960d1bfaf8e41f97454eb94211022cd7ee0ade1922423d28971","observation_id":"85770bff-cca5-470a-b307-f4e36eacce21","resolution":{"observed_at":"2026-08-16T05:02:18.068976Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04978","last_updated":"2021-08-11T00:49:48Z","snapshot_observed_at":"2026-08-19T22:35:00.300034Z","submitted_at":"2021-08-11T00:49:48Z","title":"Winning the NIST Contest: A scalable and general approach to differentially private synthetic data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04978","snapshot_observed_at":"2026-08-16T05:02:17.580592Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.580592Z"},"links":{"cited_paper":"/paper/2108.04978","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:864889adab95641af927500ad94732074a0830042de93a6b5ee416c43604350b","observation_id":"5f6be024-a234-4eec-af2a-19c92f11616c","resolution":{"observed_at":"2026-08-16T05:02:17.580592Z","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":"2026-08-16T05:02:18.054752Z","title":null,"venue":null,"work_id":"f09fe754-b280-4ffb-a654-869efaed6f11","year":2019},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.583775Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:50613b63da0bdca148bb1562c735a4e833145484af25952a3c11785753382490","observation_id":"ec794c5c-9bd4-4a69-a6ef-47d63530be46","resolution":{"observed_at":"2026-08-16T05:02:18.058476Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.043763Z","title":null,"venue":null,"work_id":"69300250-42c2-42e8-a0e1-bbb934afa494","year":2017},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.586666Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:503b9db5ef428db31df4aae5a0a3cca60f168b783ca3358ac0947de0856b5eb5","observation_id":"5d189df6-6cb7-499b-a053-e0f7f8c57a23","resolution":{"observed_at":"2026-08-16T05:02:18.047744Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.032557Z","title":null,"venue":null,"work_id":"ea3a3466-4df1-4a9b-bf79-48aeb7fdb14b","year":2023},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.589715Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:a0a4b62f73be3fef2fac7a389fc150a3d6828ee7b315ea052f9098d21d776a86","observation_id":"d205a6d4-714f-4101-a855-6a525c6e36e6","resolution":{"observed_at":"2026-08-16T05:02:18.036007Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.022207Z","title":null,"venue":null,"work_id":"8ff27d71-6cb2-4b7a-b8f8-90fde0c797d2","year":2022},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.593046Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:fc42cf65c90cae072c9102e317bca7352e3425017c3ba2f3c1b1d13989b53744","observation_id":"e5aa31e9-f1d1-4156-8c36-7feeb1f5a56f","resolution":{"observed_at":"2026-08-16T05:02:18.025674Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.011360Z","title":null,"venue":null,"work_id":"52b4c14a-855e-4772-840b-a59c517d7524","year":2018},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.597396Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:260c21de2116641cc15e3f3ff1b429dd592f3116f1b4e0dbc9327ff57f9a106b","observation_id":"06b17af8-5f41-4734-8dbc-49c043807395","resolution":{"observed_at":"2026-08-16T05:02:18.014868Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:18.000269Z","title":null,"venue":null,"work_id":"b166956f-ed74-4814-a676-b2cd1870c016","year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.601045Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:f688a2b39637f9642c4708f6677ec7eeb3b09e6d0d301f4e88fc220bccd796a9","observation_id":"e36afb4e-ee92-4d6d-b276-bf6f82df10e4","resolution":{"observed_at":"2026-08-16T05:02:18.003971Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.989327Z","title":null,"venue":null,"work_id":"071a4a57-df59-48e4-9a5b-caeb4c43e2a6","year":2017},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.604947Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:9217ce97952c9d1830b8d70e27698c88ab57539a6e1c9f3c28c2e55601302e97","observation_id":"915f972f-ecad-40b4-9f58-e7d95b1b91da","resolution":{"observed_at":"2026-08-16T05:02:17.992860Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.608367Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.608367Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:b347c4dd73e39f192e01c11cbbc447e5d0d1b2f3ebd480b7d49f9b367b73a50c","observation_id":"8846cf05-3e9a-4f4c-af11-8b0f57acb9e9","resolution":{"observed_at":"2026-08-16T05:02:17.608367Z","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":"2026-08-16T05:02:17.971498Z","title":null,"venue":null,"work_id":"13e3200a-6393-44f4-9d25-b7b63d815d57","year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.611740Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:1dbf7485a51ee8f9ae73ef7248ef87f8fcb3ef98b9b8b597816c876c64d70dfc","observation_id":"9b19e75c-cecf-49bb-ac2a-1f62d39e4847","resolution":{"observed_at":"2026-08-16T05:02:17.974936Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.960165Z","title":null,"venue":null,"work_id":"09ffb431-c756-4098-8911-77bd2912f2c0","year":2016},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.615292Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:6b5d0572a22f4056715de1250e9ee15ead3ae0f1035dca086a916282937998e8","observation_id":"4a67584d-547b-4f81-a230-3d25615b3c65","resolution":{"observed_at":"2026-08-16T05:02:17.964431Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.618702Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.618702Z"},"links":{"cited_paper":"/paper/2011.05537","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:525f45b4d9338b3a3efa54e8595df22f5678b5418d71be70dbd610c748057d2f","observation_id":"0f6769a3-51e1-438c-afb5-8a887b851965","resolution":{"observed_at":"2026-08-16T05:02:17.618702Z","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":"2026-08-16T05:02:17.949087Z","title":null,"venue":null,"work_id":"50d55877-ea2b-4c24-bd68-3ef9358bd96e","year":2023},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.622808Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:66bd59a9b3d5f5a0836e9a593448dd065e0f5f3b372b68290e419f02e5ceefed","observation_id":"98189f9a-da4c-4d1a-91f2-b3acba3f557f","resolution":{"observed_at":"2026-08-16T05:02:17.952772Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05577","last_updated":"2019-04-29T16:28:23Z","snapshot_observed_at":"2026-08-15T22:26:04.309671Z","submitted_at":"2018-11-14T00:34:01Z","title":"Aequitas: A Bias and Fairness Audit Toolkit","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.05577","snapshot_observed_at":"2026-08-16T05:02:17.626171Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.626171Z"},"links":{"cited_paper":"/paper/1811.05577","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:1cbdf8dd5f067489e47350d1704cc07d995dc3c60cbf5762abe711003b8b2921","observation_id":"a46454e3-0079-4034-a1e2-53a6b75f4f84","resolution":{"observed_at":"2026-08-16T05:02:17.626171Z","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":"2026-08-16T05:02:17.937983Z","title":null,"venue":null,"work_id":"2d634ebc-402a-430a-b8ab-5aa24c475e64","year":2024},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.630176Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:3db479e16408b5e846a9d5ef55749d73369460e9634d9dd7eae5671367c1b350","observation_id":"af7e61c2-c918-4d6d-9a54-0b57fe359eda","resolution":{"observed_at":"2026-08-16T05:02:17.941253Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.927767Z","title":null,"venue":null,"work_id":"c9854975-6018-4a82-bbe3-ce5b0a788d0a","year":2022},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.634012Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:38981a2934bda2d94abde9ef84950c648f5282d8252647ca4c9d7699742a158e","observation_id":"9b7fc75b-79a4-4315-aaad-9b67a3accf32","resolution":{"observed_at":"2026-08-16T05:02:17.930965Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.09238","last_updated":"2022-02-15T16:08:22Z","snapshot_observed_at":"2026-08-16T17:33:55.283937Z","submitted_at":"2021-12-16T22:49:53Z","title":"Benchmarking Differentially Private Synthetic Data Generation Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.09238","snapshot_observed_at":"2026-08-16T05:02:17.638106Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.638106Z"},"links":{"cited_paper":"/paper/2112.09238","citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:2ebf9f443359375f74d9cd1e1ade556db513f3a31a143fe5a43a37f5321fcb14","observation_id":"c8b83194-b64d-4b78-b0af-482c96372274","resolution":{"observed_at":"2026-08-16T05:02:17.638106Z","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":"2026-08-16T05:02:17.916625Z","title":null,"venue":null,"work_id":"1ef6360d-8143-4780-910b-80f60667c9ad","year":2020},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.641636Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:230cf226f76639d2c7b143e7c50ca126d2691b3340224472b2632f97b32d0877","observation_id":"1996506b-84a0-4126-be24-c7e1e6e0dc48","resolution":{"observed_at":"2026-08-16T05:02:17.920757Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.905821Z","title":null,"venue":null,"work_id":"68779c8c-b38a-40a1-965d-464f1cd7ccdb","year":2022},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.644953Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:4f8464394308cbb4b33f7592e1cf4bb4cc694e1c70b89e4aa20e61c50911f424","observation_id":"8714854e-a85e-4304-b398-bfb61137dee5","resolution":{"observed_at":"2026-08-16T05:02:17.909514Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.894903Z","title":null,"venue":null,"work_id":"e891a065-bd16-44a2-b264-f5cb997c7ea4","year":2010},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.648448Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:513998662a313cb02b4358dec26e37eadde5020d6297fa12c2cfc0b38db8d772","observation_id":"976ecf12-4db6-4d25-877d-d5d183030ad3","resolution":{"observed_at":"2026-08-16T05:02:17.898378Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.651865Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.651865Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:d2d5958f9e293f6500be38937d6bf9e713a04ab896484e2a82512c315f3bca7d","observation_id":"77f6885d-132f-4c6d-b471-6f7e77c0d155","resolution":{"observed_at":"2026-08-16T05:02:17.651865Z","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":"2026-08-16T05:02:17.876990Z","title":null,"venue":null,"work_id":"83c0787c-7121-4745-ae6d-4863843c89d4","year":2024},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.655409Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:9b39b4ca72093bf35d9aa5e8b9544b56e38be6781dc20c2d94143ed981ad5658","observation_id":"6e3d99ea-8706-463b-ae0e-0666efe47281","resolution":{"observed_at":"2026-08-16T05:02:17.881070Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.867230Z","title":null,"venue":null,"work_id":"aa013f0e-26fe-4bf7-b16e-6a32d90b0f29","year":2024},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.659367Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:4916925a167500b8eb8d550f794633968eba11b2bde603f9abe19bc75b43e467","observation_id":"3cd69e42-b12d-4433-af95-5e22762b3e3b","resolution":{"observed_at":"2026-08-16T05:02:17.870565Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.663607Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.663607Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:c4674da99a1b7f272bc4fefc6dba951d268904d09253c3e735ea81099b884303","observation_id":"60c7d0eb-caeb-4441-83c9-d3264046eeff","resolution":{"observed_at":"2026-08-16T05:02:17.663607Z","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":"2026-08-16T05:02:17.849663Z","title":null,"venue":null,"work_id":"b54b2613-c001-4dc3-a75f-07f5f96be829","year":2024},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.667158Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:6052e5213ba14cd74abed0642414d9ac2b273ad9c0a10eedde0ae8ee77230ce8","observation_id":"affcc64a-f0f4-4d39-9544-b11f7744fb34","resolution":{"observed_at":"2026-08-16T05:02:17.853179Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.839067Z","title":null,"venue":null,"work_id":"3b5696a1-1a86-4e78-947d-610927f350a9","year":2024},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.670771Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:275dfc4535956122627630841c7dd7211bb3aed6969c1578167f46e6cc304a4f","observation_id":"27fd9445-8412-43cc-b2ce-846bdf99ecb3","resolution":{"observed_at":"2026-08-16T05:02:17.842788Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T05:02:17.826773Z","title":null,"venue":null,"work_id":"9c6877c1-2537-4a32-bfe8-9659564cf6e9","year":2017},"citing_paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-16T05:02:17.674345Z"},"links":{"citing_paper":"/paper/2504.21634"},"observation_digest":"sha256:47cfa05cbd52db28b6d57abd93e698c49ae42b43f17697f904e8ce26dd118479","observation_id":"97e8119c-10a9-43ca-9d8b-e277044c9e91","resolution":{"observed_at":"2026-08-16T05:02:17.831377Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.21634","last_updated":"2025-04-30T13:36:27Z","latest_version":1,"primary_category":"cs.CY","snapshot_observed_at":"2026-08-19T08:31:04.793239Z","submitted_at":"2025-04-30T13:36:27Z","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data"},"reference_resolution":{"displayed":65,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":65,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":65},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 0 inbound Pith citation observations for arXiv:2504.21634."}