{"as_of":"2026-08-22T13:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9a9e08a39adf1b6420ebe555f5e31a7a090086f3d9294984f666a50119c8d622","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":71,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":71,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":71,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":71,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:05:07.033013Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-08T10:14:52.062226Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2411.04680","last_updated":"2026-04-24T11:56:08Z","snapshot_observed_at":"2026-08-18T03:31:49.627416Z","submitted_at":"2024-11-07T13:08:06Z","title":"Privacy Leakage via Output Label Space and Differentially Private Continual Learning","version":5},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-05-23T17:18:22.300467Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2411.04680"},"observation_digest":"sha256:cfc048129babb4af00638e55ac3f0d4901a7746bfd91b227607561f5c00be0d1","observation_id":"ebc6433b-5cb6-42b6-9aea-253078c43cde","resolution":{"observed_at":"2026-05-23T17:23:15.482184Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-12T20:26:05.077545Z","title":"Yousefpour et al., ``Opacus: User-friendly differential privacy library in pytorch,'' in arXiv:2109.12298, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-19T19:48:59.794372Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":174,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:05.077545Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:fd46eb76f4aa260c2f4ac044d531ca158c83459196d7021536ee1230fc4b1694","observation_id":"27d6b13f-a2a8-4879-aa95-fbdabd7dc508","resolution":{"observed_at":"2026-08-12T20:26:05.077545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-11T20:28:27.864049Z","title":"Opacus: User-friendly differential privacy library in pytorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-18T15:22:12.437463Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.864049Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:41aad0b33cc0a0942fce3679e327d0647c6ec0fe9178ab8a88f445d41f62b398","observation_id":"de82fb05-d003-4431-b3e6-51b46b5dabea","resolution":{"observed_at":"2026-08-11T20:28:27.864049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-11T17:58:42.970651Z","title":"arXiv preprint arXiv:2109.12298 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08534","last_updated":"2025-04-17T11:38:29Z","snapshot_observed_at":"2026-08-16T05:11:04.787005Z","submitted_at":"2024-12-11T16:48:18Z","title":"Protecting Confidentiality, Privacy and Integrity in Collaborative Learning","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-11T17:58:42.970651Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2412.08534"},"observation_digest":"sha256:e7864bc0ee7db0fe129cca4f1d1eec90dbfd239bbb6ece69b55b25b1d7c873b8","observation_id":"9d8bf83a-f52b-4cd0-9428-17cb6a3a2629","resolution":{"observed_at":"2026-08-11T17:58:42.970651Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-11T16:47:59.149451Z","title":"Opacus: User-friendly differential privacy library in pytorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.149451Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:17cfa13281ddfb8cfd46224dd2e3bcf8bcf12ccd8f3fa0ad54dcc3a477c396c7","observation_id":"70466643-d72f-4f5c-bcdb-08d80930971e","resolution":{"observed_at":"2026-08-11T16:47:59.149451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-11T10:51:53.103437Z","title":"Opacus: User-friendly differential privacy library in PyTorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16083","last_updated":"2025-08-29T15:00:26Z","snapshot_observed_at":"2026-08-16T17:03:07.142317Z","submitted_at":"2024-12-20T17:30:58Z","title":"Federated Diffusion Modeling with Differential Privacy for Tabular Data Synthesis","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:53.103437Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2412.16083"},"observation_digest":"sha256:a1be0fa4969a42b159a3414b91b2804f0828c44364c434e835f5f7067395c0cb","observation_id":"95870773-418a-427a-b4ac-363901bdac2c","resolution":{"observed_at":"2026-08-11T10:51:53.103437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-11T10:22:24.207263Z","title":"Opacus: User-friendly differential privacy library in PyTorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16802","last_updated":"2025-03-31T22:49:32Z","snapshot_observed_at":"2026-08-21T03:02:34.776495Z","submitted_at":"2024-12-21T23:09:14Z","title":"Balls-and-Bins Sampling for DP-SGD","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-11T10:22:24.207263Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2412.16802"},"observation_digest":"sha256:5e8759610acde5f662e8e36d4865e9b1fb320c74385deb1da6d0077eb474836b","observation_id":"47340917-beea-467b-8ca6-5c4e493bd917","resolution":{"observed_at":"2026-08-11T10:22:24.207263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-10T23:15:09.324499Z","title":"Jianming Zhang, Sarah Adel Bargal, Zhe Lin, Jonathan Brandt, Xiaohui Shen, and Stan Sclaroff","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.20798","last_updated":"2025-05-22T14:09:00Z","snapshot_observed_at":"2026-08-21T09:44:38.133653Z","submitted_at":"2024-12-30T08:43:28Z","title":"Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T23:15:09.324499Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2412.20798"},"observation_digest":"sha256:da7398e97178d7c7b738ef13c2bb1f32f510ef7c3e447e7f8e79670a7ee5889c","observation_id":"df1406aa-efc0-4b2d-91ca-20a2d1274b4f","resolution":{"observed_at":"2026-08-10T23:15:09.324499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-10T17:41:47.722281Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.12012","last_updated":"2025-02-06T16:18:09Z","snapshot_observed_at":"2026-08-14T17:51:54.194375Z","submitted_at":"2025-01-21T10:06:19Z","title":"TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-10T17:41:47.722281Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2501.12012"},"observation_digest":"sha256:4ea260019c745eae2eccc950eee7a173bbe75ece4e55451c9581de63c3af016d","observation_id":"e334afae-3f00-45db-a1e8-5dc5a5530e93","resolution":{"observed_at":"2026-08-10T17:41:47.722281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-09T12:28:55.135176Z","title":"Wang, Q., Zhang, Y ., Lu, X., Wang, Z., Qin, Z., and Ren, K","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.135176Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:4681bca55ee6e8b0f4795c3a9d5f8a83840d80e3b23aba651799e68a44ee7356","observation_id":"8eb927d6-982f-432a-bfc1-eaa789a6e4d9","resolution":{"observed_at":"2026-08-09T12:28:55.135176Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-08T23:53:24.514234Z","title":"Opacus: User-friendly differential privacy library in pytorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.04045","last_updated":"2025-02-06T13:04:25Z","snapshot_observed_at":"2026-08-21T07:33:08.159913Z","submitted_at":"2025-02-06T13:04:25Z","title":"Comparing privacy notions for protection against reconstruction attacks in machine learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-08T23:53:24.514234Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2502.04045"},"observation_digest":"sha256:6e5c5a2122e15b6aa6ddc2538be35b7056c9c437cc57bf11599ea3298e336c7d","observation_id":"4f0c9b1b-fd62-4b3b-ae0f-2370c50b9bea","resolution":{"observed_at":"2026-08-08T23:53:24.514234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-08T15:44:00.779502Z","title":"Opacus: User-friendly Differential Privacy Library in PyTorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.06374","last_updated":"2025-02-27T05:44:37Z","snapshot_observed_at":"2026-08-10T11:03:16.827198Z","submitted_at":"2025-02-10T11:44:46Z","title":"Hyperparameters in Score-Based Membership Inference Attacks","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T15:44:00.779502Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2502.06374"},"observation_digest":"sha256:c9c1e57eab818e46f3b788cc08e36ab70ed9617610a0cb626e3ecbe946a48d8a","observation_id":"9e229d75-e37e-469b-a89c-ff86027d0e34","resolution":{"observed_at":"2026-08-08T15:44:00.779502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-08T14:00:17.764081Z","title":"Opacus: User-friendly differ- ential privacy library in pytorch.arXiv preprint arXiv:2109.12298 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07066","last_updated":"2025-06-13T08:22:39Z","snapshot_observed_at":"2026-08-19T20:45:02.766226Z","submitted_at":"2025-02-10T21:58:17Z","title":"General-Purpose $f$-DP Estimation and Auditing in a Black-Box Setting","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T14:00:17.764081Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2502.07066"},"observation_digest":"sha256:515ca9adeff868e432bef7cb61b7a29d2d33240fdeb653a05c95ab1d9df44bd6","observation_id":"51720231-639b-43d0-9084-8fc4df41e23a","resolution":{"observed_at":"2026-08-08T14:00:17.764081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-16T11:05:07.033013Z","title":"Opacus: User- friendly differential privacy library in pytorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.16557","last_updated":"2025-04-23T09:33:10Z","snapshot_observed_at":"2026-08-22T11:17:28.423110Z","submitted_at":"2025-04-23T09:33:10Z","title":"Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Tasks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-16T11:05:07.033013Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2504.16557"},"observation_digest":"sha256:47aebae135f6f98e57f00b37c5da9393048e1d96420f114a9a3db6149c922367","observation_id":"e351fc81-e4cb-4818-88f0-234af00b7a3b","resolution":{"observed_at":"2026-08-16T11:05:07.033013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-16T10:29:42.091602Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.18147","last_updated":"2025-04-25T07:56:24Z","snapshot_observed_at":"2026-08-17T12:20:48.256780Z","submitted_at":"2025-04-25T07:56:24Z","title":"NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T10:29:42.091602Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2504.18147"},"observation_digest":"sha256:9cfd1c778a54757410322e48dda1a3ca7c5749d24b2f70ec084c57527ef9a3f7","observation_id":"4e4f63dd-6dcc-4591-a06b-f2a8de502ae4","resolution":{"observed_at":"2026-08-16T10:29:42.091602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-16T04:21:00.532103Z","title":"Opacus: User-friendly differential privacy library in pytorch, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-22T12:59:58.856861Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.532103Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:63eaeb29c44c15c06e5206e25b39c2f45a7e9898938e32965117f336d48b1942","observation_id":"c27c6d70-14a4-4f42-bff6-9ab15aba4889","resolution":{"observed_at":"2026-08-16T04:21:00.532103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-15T23:05:39.843625Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.05648","last_updated":"2025-05-08T21:08:04Z","snapshot_observed_at":"2026-08-21T12:43:12.902973Z","submitted_at":"2025-05-08T21:08:04Z","title":"Privacy-Preserving Transformers: SwiftKey's Differential Privacy Implementation","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T23:05:39.843625Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2505.05648"},"observation_digest":"sha256:9a7992c1b293291767746a6c933cd2eec187c7fdd3555d147914bc25d599f565","observation_id":"0fc59f3a-57b7-4cd1-b83f-41d78a3b7644","resolution":{"observed_at":"2026-08-15T23:05:39.843625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-15T22:33:56.210979Z","title":"Opacus: User-friendly differential privacy library in pytorch.arXiv preprint arXiv:2109.12298, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07041","last_updated":"2025-05-11T16:25:06Z","snapshot_observed_at":"2026-08-18T15:41:44.732582Z","submitted_at":"2025-05-11T16:25:06Z","title":"Empirical Analysis of Asynchronous Federated Learning on Heterogeneous Devices: Efficiency, Fairness, and Privacy Trade-offs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:33:56.210979Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2505.07041"},"observation_digest":"sha256:c118df830437ceb1e669f8082645e738ddf75ab61dda557bc1c36bbb79d90151","observation_id":"98f2395c-66de-456c-bb2f-6fe0c56d503a","resolution":{"observed_at":"2026-08-15T22:33:56.210979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-07T13:58:13.486506Z","title":"Opacus: U ser-friendly D ifferential P rivacy L ibrary in P yTorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20621","last_updated":"2025-05-27T01:59:25Z","snapshot_observed_at":"2026-08-14T04:48:58.835118Z","submitted_at":"2025-05-27T01:59:25Z","title":"Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T13:58:13.486506Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2505.20621"},"observation_digest":"sha256:8c28e3d549066fd6829b2d3e54173737a81f1e1c13d465f7f0e96c7311d67ba9","observation_id":"e3968089-bdcd-4e9b-968a-9028aae86aa0","resolution":{"observed_at":"2026-08-07T13:58:13.486506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-07T13:22:10.041647Z","title":"arXiv preprint arXiv:2109.12298 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22108","last_updated":"2026-07-14T17:52:02Z","snapshot_observed_at":"2026-08-09T23:30:10.942493Z","submitted_at":"2025-05-28T08:36:21Z","title":"Inclusive Federated Learning Through Compliance-Weighted Noise Allocation in Healthcare AI","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:22:10.041647Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2505.22108"},"observation_digest":"sha256:eca97b8efdbcfdce5702e04e5543161f7d926f33aac894561ea4b3aec96ff0d8","observation_id":"b8d97bf0-9dd6-4afa-aa7d-3390d31f67f1","resolution":{"observed_at":"2026-08-07T13:22:10.041647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-07T12:31:56.839268Z","title":"Opacus: User-friendly differential privacy library in PyTorch","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.24603","last_updated":"2025-06-04T16:02:22Z","snapshot_observed_at":"2026-08-09T23:29:40.574002Z","submitted_at":"2025-05-30T13:52:48Z","title":"The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T12:31:56.839268Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2505.24603"},"observation_digest":"sha256:9f0cdd1c959c25cae873db765f8509286d144626aa6e8085c13564d542556271","observation_id":"8a782b08-c043-4001-a549-aa508a3e5f12","resolution":{"observed_at":"2026-08-07T12:31:56.839268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-07T11:52:52.491446Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.01396","last_updated":"2026-06-10T07:57:35Z","snapshot_observed_at":"2026-08-18T14:03:50.906937Z","submitted_at":"2025-06-02T07:44:17Z","title":"Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T11:52:52.491446Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2506.01396"},"observation_digest":"sha256:52579b7cbfe9b085d34554c14063dc718dd71df6737ec37cb01e828ca33e4c6a","observation_id":"e59bdb1d-de12-4a1d-be47-036607547270","resolution":{"observed_at":"2026-08-07T11:52:52.491446Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-07T10:31:20.544798Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05447","last_updated":"2025-07-14T23:29:38Z","snapshot_observed_at":"2026-08-21T16:05:35.632679Z","submitted_at":"2025-06-05T15:18:35Z","title":"Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T10:31:20.544798Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2506.05447"},"observation_digest":"sha256:5b992c4dec5136d38ffad9637441a1b5a9788eafee2acf4b2c50ba19dccdd354","observation_id":"380618aa-20e5-4ba1-9f0c-1ad070b497d9","resolution":{"observed_at":"2026-08-07T10:31:20.544798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-07T05:03:51.144373Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09312","last_updated":"2025-06-11T00:59:52Z","snapshot_observed_at":"2026-08-20T21:12:00.838232Z","submitted_at":"2025-06-11T00:59:52Z","title":"What is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation?","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T05:03:51.144373Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2506.09312"},"observation_digest":"sha256:ae1806403d4791ed9dc70d1578c24a37e20b87ad1b931340a26d026e035115ec","observation_id":"f47e21f8-dabc-463e-ba55-dbcd91d2b39a","resolution":{"observed_at":"2026-08-07T05:03:51.144373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-06T23:04:44.624028Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20000","last_updated":"2025-06-24T20:39:49Z","snapshot_observed_at":"2026-08-16T00:35:24.479966Z","submitted_at":"2025-06-24T20:39:49Z","title":"Can One Safety Loop Guard Them All? Agentic Guard Rails for Federated Computing","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T23:04:44.624028Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2506.20000"},"observation_digest":"sha256:4f0631b0dd46dc11a42b5d234b81c3a1f8e9474b651415d3c76fb33834abeaf6","observation_id":"087ba672-32dc-4ea9-a0dd-1522d918c573","resolution":{"observed_at":"2026-08-06T23:04:44.624028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-06T21:27:05.626738Z","title":"Opacus: User-friendly differential privacy library in PyTorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.00230","last_updated":"2025-10-27T19:09:31Z","snapshot_observed_at":"2026-08-15T19:48:11.403774Z","submitted_at":"2025-06-30T19:54:34Z","title":"PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstruction","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T21:27:05.626738Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2507.00230"},"observation_digest":"sha256:7783c998a3f9929b42d521d6b27b4d4f615b79577eb2ecd0540481bbc588511d","observation_id":"338df136-f224-4ce4-9b96-bbda16078be5","resolution":{"observed_at":"2026-08-06T21:27:05.626738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-06T21:06:03.619209Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.01154","last_updated":"2025-07-01T19:28:37Z","snapshot_observed_at":"2026-08-14T20:29:38.731467Z","submitted_at":"2025-07-01T19:28:37Z","title":"FlashDP: Private Training Large Language Models with Efficient DP-SGD","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-06T21:06:03.619209Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2507.01154"},"observation_digest":"sha256:15343e6cd17291ea7938acc5b70db72c73a18ed5654bbeace36b194f9db135a6","observation_id":"aedfebe5-17e8-4b70-9137-578e5c81bb0b","resolution":{"observed_at":"2026-08-06T21:06:03.619209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-06T20:27:52.505131Z","title":"arXiv:2109.12298 (2021) Embedding-Based Federated Data Sharing via DP-CVAE 11","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.02671","last_updated":"2025-07-03T14:36:15Z","snapshot_observed_at":"2026-08-15T09:07:02.635485Z","submitted_at":"2025-07-03T14:36:15Z","title":"Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T20:27:52.505131Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2507.02671"},"observation_digest":"sha256:6c6fd71e1b16cc4e0fbca525b3d2c768e4a9b58f67cab76a1213f55d2bbad73b","observation_id":"2ff7ad96-94d3-44c7-9a1b-023e54f12e6b","resolution":{"observed_at":"2026-08-06T20:27:52.505131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-06T05:32:47.499074Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.01749","last_updated":"2025-08-03T13:15:52Z","snapshot_observed_at":"2026-08-18T00:44:56.191097Z","submitted_at":"2025-08-03T13:15:52Z","title":"Improving Noise Efficiency in Privacy-preserving Dataset Distillation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T05:32:47.499074Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2508.01749"},"observation_digest":"sha256:56288521eaeb54e26196dc42ba65ea707ea0338e943f8c79308f5237b46e1e4b","observation_id":"9521abe8-326d-46e4-ba6d-45531a6ee02c","resolution":{"observed_at":"2026-08-06T05:32:47.499074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-05T22:09:12.260255Z","title":"Opacus: U ser-friendly differential privacy library in PyTorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.07556","last_updated":"2025-09-06T12:35:53Z","snapshot_observed_at":"2026-08-20T23:44:37.908763Z","submitted_at":"2025-08-11T02:33:53Z","title":"Uncertainty-Driven Reliability: Selective Prediction and Trustworthy Deployment in Modern Machine Learning","version":2},"reference_index":174,"source":"arxiv_source","source_observed_at":"2026-08-05T22:09:12.260255Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2508.07556"},"observation_digest":"sha256:a3528e1fd6cf5812d572db32dcf85bcc2b17d4c297bfdf44e1ad4126c6098a35","observation_id":"bd885526-567d-45e3-bbed-0c821437e19a","resolution":{"observed_at":"2026-08-05T22:09:12.260255Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-05T18:18:52.465820Z","title":"Yousefpour, I","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15183","last_updated":"2025-08-21T02:42:23Z","snapshot_observed_at":"2026-08-21T20:11:06.859166Z","submitted_at":"2025-08-21T02:42:23Z","title":"Private Hyperparameter Tuning with Ex-Post Guarantee","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-05T18:18:52.465820Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2508.15183"},"observation_digest":"sha256:791add6b26418fa5dd97387e6d3c285c238e71a5a2188b32f9f17dc57819e0d6","observation_id":"8aad5a5d-0f6f-4515-b290-ac59be85ee8f","resolution":{"observed_at":"2026-08-05T18:18:52.465820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-05T13:59:46.344430Z","title":"Hengrui Zhang, Jiani Zhang, Zhengyuan Shen, Balasubramaniam Srinivasan, Xiao Qin, Christos Faloutsos, Huzefa Rangwala, and George Karypis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.21815","last_updated":"2025-08-29T17:51:42Z","snapshot_observed_at":"2026-08-17T15:36:59.651741Z","submitted_at":"2025-08-29T17:51:42Z","title":"Achieving Hilbert-Schmidt Independence Under R\\'enyi Differential Privacy for Fair and Private Data Generation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T13:59:46.344430Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2508.21815"},"observation_digest":"sha256:4fd556efef03425c538fdc31b1a9302a45dcfd5443dbb46c88ff2123c16dac77","observation_id":"9c803bdc-7e63-4a2a-8c74-17452adef764","resolution":{"observed_at":"2026-08-05T13:59:46.344430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-15T16:35:03.671430Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03341","last_updated":"2025-09-03T14:18:22Z","snapshot_observed_at":"2026-08-22T01:50:18.484266Z","submitted_at":"2025-09-03T14:18:22Z","title":"On the MIA Vulnerability Gap Between Private GANs and Diffusion Models","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T16:35:03.671430Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2509.03341"},"observation_digest":"sha256:c7873cad304643e4ff698b67748960539d96b3655bb551488d7b07f36630e8c2","observation_id":"04c0a7ec-340d-40c9-8205-668454718ef8","resolution":{"observed_at":"2026-08-15T16:35:03.671430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2509.03472","last_updated":"2026-04-15T20:18:20Z","snapshot_observed_at":"2026-08-13T01:10:37.465737Z","submitted_at":"2025-09-03T16:51:26Z","title":"DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-18T19:09:04.217591Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2509.03472"},"observation_digest":"sha256:fefe0945e1efd452fb82ffb0f0c5b790b03ba2ce6c54c3eadd883a4f4fa38cd2","observation_id":"d35c5015-eb39-4b8a-89fc-d0badfdc22ba","resolution":{"observed_at":"2026-05-18T19:11:46.563669Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-05T10:22:24.312980Z","title":"Opacus: U ser-Friendly Differential Privacy Library in PyTorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.04290","last_updated":"2025-09-04T15:02:10Z","snapshot_observed_at":"2026-08-22T01:52:52.785905Z","submitted_at":"2025-09-04T15:02:10Z","title":"An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-05T10:22:24.312980Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2509.04290"},"observation_digest":"sha256:72497295e0d817b0fbfa5cd12a6b8b278eb8b4613e23711d0b97f420af4d5501","observation_id":"c8e5d791-0473-44a4-81d8-34edc2fcbfe7","resolution":{"observed_at":"2026-08-05T10:22:24.312980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-05T06:00:19.442858Z","title":"arXiv preprint arXiv:2109.12298(2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.04710","last_updated":"2025-09-04T23:53:54Z","snapshot_observed_at":"2026-08-21T15:52:26.543728Z","submitted_at":"2025-09-04T23:53:54Z","title":"Network-Aware Differential Privacy","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-05T06:00:19.442858Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2509.04710"},"observation_digest":"sha256:74e8ed73a2ec6c85dac286de29603c8cb15503fbf24d400e3d08591bb000c3c2","observation_id":"7ff7f96e-fd24-4e74-a612-645367406a0b","resolution":{"observed_at":"2026-08-05T06:00:19.442858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-15T16:29:55.357247Z","title":"Opacus: User-friendly differential privacy library in PyTorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05265","last_updated":"2025-09-05T17:23:03Z","snapshot_observed_at":"2026-08-21T03:02:36.250049Z","submitted_at":"2025-09-05T17:23:03Z","title":"On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T16:29:55.357247Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2509.05265"},"observation_digest":"sha256:8dcb9dee73aea15d4506cb71a34f2da1eeb0cfa30832bc55a46aecfa96ac7fbf","observation_id":"f0c769f1-01bf-45c3-9513-cbd21a02f3d2","resolution":{"observed_at":"2026-08-15T16:29:55.357247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-04T19:11:57.429770Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09485","last_updated":"2025-09-12T01:27:15Z","snapshot_observed_at":"2026-08-20T01:40:18.656100Z","submitted_at":"2025-09-11T14:17:04Z","title":"Balancing Utility and Privacy: Dynamically Private SGD with Random Projection","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-04T19:11:57.429770Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2509.09485"},"observation_digest":"sha256:66e7383f3e1e34ff20ed8c1997a8bb070b4378592f29c3ddbab0574f6d351b75","observation_id":"d905cf6d-215d-4442-93a8-655192c64173","resolution":{"observed_at":"2026-08-04T19:11:57.429770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-15T15:57:48.259113Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10882","last_updated":"2025-09-13T16:26:38Z","snapshot_observed_at":"2026-08-19T09:39:38.294588Z","submitted_at":"2025-09-13T16:26:38Z","title":"Term2Note: Synthesising Differentially Private Clinical Notes from Medical Terms","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T15:57:48.259113Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2509.10882"},"observation_digest":"sha256:938e60b526e69e9722ee6d7fb2248aadf50239827d6a74ec0144acc1e8c1061a","observation_id":"d1171136-0d3e-483f-a5b5-5f2f0df81da2","resolution":{"observed_at":"2026-08-15T15:57:48.259113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-04T11:24:34.927555Z","title":"Opacus: U ser-friendly differential privacy library in PyTorch","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.05416","last_updated":"2026-07-24T00:15:07Z","snapshot_observed_at":"2026-08-19T20:00:11.208763Z","submitted_at":"2025-10-06T22:13:02Z","title":"Correlating Cross-Iteration Noise for DP-SGD using Model Curvature","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-04T11:24:34.927555Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2510.05416"},"observation_digest":"sha256:6f07383ac8d698c1e81f63ce57e0728d7ee120be34c99384d6fc2393913dc73c","observation_id":"bc60db6b-6dd5-445b-a16e-5edc69a925ef","resolution":{"observed_at":"2026-08-04T11:24:34.927555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2510.20616","last_updated":"2026-04-17T12:23:04Z","snapshot_observed_at":"2026-07-06T22:33:53.834577Z","submitted_at":"2025-10-23T14:48:03Z","title":"On Optimal Hyperparameters for Differentially Private Deep Transfer Learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-18T04:40:50.449894Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2510.20616"},"observation_digest":"sha256:45d3281994b927d407100a07fae95b73b62fed9035aa39b086a4dfc65154b50c","observation_id":"32e806b9-3789-4f1f-88b0-fa413bd81ea2","resolution":{"observed_at":"2026-05-18T04:40:52.723676Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2511.21804","last_updated":"2026-04-07T10:27:13Z","snapshot_observed_at":"2026-08-14T20:38:43.984285Z","submitted_at":"2025-11-26T18:55:13Z","title":"Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-17T04:41:22.733999Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2511.21804"},"observation_digest":"sha256:16cdad3c2bf9b94f3506e80f165b1e305ed284e900750c78cdd357c2e1027c11","observation_id":"1101091f-d5ed-40dd-a1c7-055d0b639974","resolution":{"observed_at":"2026-05-17T04:41:31.412929Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-03T18:53:10.777371Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.03238","last_updated":"2026-07-09T21:40:53Z","snapshot_observed_at":"2026-08-20T18:36:35.111387Z","submitted_at":"2025-12-02T21:14:39Z","title":"How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy","version":2},"reference_index":264,"source":"arxiv_source","source_observed_at":"2026-08-03T18:53:10.777371Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2512.03238"},"observation_digest":"sha256:7ffdb290306cd157166ec465d109251537aecebd2e0618913bd239ee4b51a115","observation_id":"f79e3bd8-5544-4aec-a033-a809d7b884e2","resolution":{"observed_at":"2026-08-03T18:53:10.777371Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2512.18809","last_updated":"2026-04-03T11:51:07Z","snapshot_observed_at":"2026-08-13T23:52:35.105425Z","submitted_at":"2025-12-21T17:01:44Z","title":"FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-16T20:36:16.561576Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2512.18809"},"observation_digest":"sha256:34f6fef70a3ef86ab709126e58cd33ce4fd7f3b26c560c0eefb0b782398b5e82","observation_id":"fa1ea77f-bdad-4128-af95-67b93fc1d251","resolution":{"observed_at":"2026-05-16T20:38:24.735067Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2601.10237","last_updated":"2026-08-09T17:52:48Z","snapshot_observed_at":"2026-08-13T23:26:39.797921Z","submitted_at":"2026-01-15T09:50:36Z","title":"Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-16T13:37:50.765735Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2601.10237"},"observation_digest":"sha256:ac032e295228a077badc5446918c64f71bd995299823d40881398cee09462f14","observation_id":"6859cfc2-5142-4119-91c5-dbfd3278a174","resolution":{"observed_at":"2026-05-16T13:37:56.477863Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-03T05:24:31.232893Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.02718","last_updated":"2026-06-07T17:20:24Z","snapshot_observed_at":"2026-08-03T05:24:23.728917Z","submitted_at":"2026-02-02T19:36:44Z","title":"Composition for Pufferfish Privacy","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T05:24:31.232893Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2602.02718"},"observation_digest":"sha256:d0705e7252522628f45b2e555799291295c5c9db2084489e484c73658259d775","observation_id":"acbb4db8-e5d1-4460-82df-8f873ab9ee41","resolution":{"observed_at":"2026-08-03T05:24:31.232893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-02T21:51:50.371690Z","title":"Opacus: User-friendly differential privacy library in pytorch.arXiv preprint arXiv:2109.12298, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.18900","last_updated":"2026-06-24T23:50:52Z","snapshot_observed_at":"2026-08-16T18:26:08.851405Z","submitted_at":"2026-02-21T16:45:56Z","title":"PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-02T21:51:50.371690Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2602.18900"},"observation_digest":"sha256:019e9f34fa0c8487abf29365fbaaac2c7465b7b02e2421f72de2d6caf3e7d576","observation_id":"87057a70-3025-4f0d-bcd8-895ea34c133b","resolution":{"observed_at":"2026-08-02T21:51:50.371690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-02T19:59:26.310972Z","title":"Yousefpour, I","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.13293","last_updated":"2026-06-20T09:46:39Z","snapshot_observed_at":"2026-08-14T12:20:33.774725Z","submitted_at":"2026-02-28T09:36:38Z","title":"A Robust Framework for Secure Cardiovascular Risk Prediction: An Architectural Case Study of Differentially Private Federated Learning","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-02T19:59:26.310972Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2603.13293"},"observation_digest":"sha256:05741fc30947607f67c5da640a0e64bdcb05e8a1612407449dfa0ca0dbad3b98","observation_id":"d9fdaad6-36d6-4633-8801-1d35654c66f4","resolution":{"observed_at":"2026-08-02T19:59:26.310972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2604.07493","last_updated":"2026-04-08T18:34:20Z","snapshot_observed_at":"2026-08-17T00:37:02.604538Z","submitted_at":"2026-04-08T18:34:20Z","title":"Differentially Private Modeling of Disease Transmission within Human Contact Networks","version":1},"reference_index":104,"source":"pdf_text","source_observed_at":"2026-05-10T17:23:12.073248Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2604.07493"},"observation_digest":"sha256:13f286a254e9c9aa05194fa40037a7870de74d77d843d5715877cbadfcbcb631","observation_id":"7c1afa2e-b222-41c9-a999-029a85ce690d","resolution":{"observed_at":"2026-05-11T06:56:00.865908Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2604.13474","last_updated":"2026-04-15T04:55:40Z","snapshot_observed_at":"2026-08-15T14:42:33.602578Z","submitted_at":"2026-04-15T04:55:40Z","title":"Secure and Privacy-Preserving Vertical Federated Learning","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-05-10T13:44:02.024816Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2604.13474"},"observation_digest":"sha256:4d285554775fcc0231199657ab542ddd8fedf234c00f4fe11a384ee6a6840b76","observation_id":"bc6a516e-1726-4045-9a7a-d7c81abd91f0","resolution":{"observed_at":"2026-05-10T13:45:27.749919Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2604.15851","last_updated":"2026-05-18T02:43:59Z","snapshot_observed_at":"2026-08-22T08:20:41.925966Z","submitted_at":"2026-04-17T09:03:11Z","title":"DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T08:53:13.427364Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2604.15851"},"observation_digest":"sha256:576bbd7160c6a2db4d4cd8c1aa67648f4d6e2c9c87a0b0f454b68b189702b8f9","observation_id":"b99c5807-6bcd-4b20-9849-fdd928a6217a","resolution":{"observed_at":"2026-05-10T08:58:13.014235Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2604.15851","last_updated":"2026-05-18T02:43:59Z","snapshot_observed_at":"2026-08-22T08:20:41.925966Z","submitted_at":"2026-04-17T09:03:11Z","title":"DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-21T00:50:11.410735Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2604.15851"},"observation_digest":"sha256:4cc74c7f5128501d60adc6236b7eaaf9ebff6148ed9db4cb41b6cba49d8a6fa7","observation_id":"672fc446-bdef-4b52-b2ff-8fd5710fb60d","resolution":{"observed_at":"2026-05-21T00:53:53.616825Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2604.20985","last_updated":"2026-05-20T07:13:13Z","snapshot_observed_at":"2026-08-11T13:15:24.283355Z","submitted_at":"2026-04-22T18:13:37Z","title":"Differentially Private Model Merging","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-10T01:14:32.116028Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2604.20985"},"observation_digest":"sha256:adb5db7599dec44d02ee31f025fe4589fe96d2e423a5076c0be1f04840cfd67f","observation_id":"acf8d866-923e-4750-884f-db22d489ca5d","resolution":{"observed_at":"2026-05-11T13:41:05.239870Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2604.26467","last_updated":"2026-04-29T09:25:06Z","snapshot_observed_at":"2026-08-13T00:28:13.937946Z","submitted_at":"2026-04-29T09:25:06Z","title":"Differentially Private Contrastive Learning via Bounding Group-level Contribution","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-07T13:07:53.564066Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2604.26467"},"observation_digest":"sha256:55fbad654482630245ef110b62e71ef25c3517ac412f62ee44432e51dca163ed","observation_id":"91b10ef9-5c03-4950-84e8-8a9cc0bbfd55","resolution":{"observed_at":"2026-05-12T09:06:25.014380Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.01679","last_updated":"2026-05-03T02:34:54Z","snapshot_observed_at":"2026-08-11T14:09:19.375616Z","submitted_at":"2026-05-03T02:34:54Z","title":"Class-Aware Adaptive Differential Privacy in Deep Learning for Sensor-Based Fall Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-10T16:25:50.762664Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.01679"},"observation_digest":"sha256:448674792e047bfbcc402d004b3f002f649bc0e3a76117e56a8104e37fb07417","observation_id":"898409bc-d5c9-4834-aace-466b02a884ee","resolution":{"observed_at":"2026-05-11T08:56:00.123335Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.02718","last_updated":"2026-05-04T15:19:02Z","snapshot_observed_at":"2026-08-11T12:22:20.830987Z","submitted_at":"2026-05-04T15:19:02Z","title":"Private Speech Classification without Collapse: Stabilized DP Training and Offline Distillation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-08T02:47:47.383940Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.02718"},"observation_digest":"sha256:12d95de0497f0d5257b29713ae0be01c257928690947c0e8262aaf474abe09f1","observation_id":"cafbc604-3b07-4900-aead-9c8586204e1b","resolution":{"observed_at":"2026-05-11T22:26:13.762807Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.03425","last_updated":"2026-05-05T07:02:32Z","snapshot_observed_at":"2026-08-13T17:05:24.666207Z","submitted_at":"2026-05-05T07:02:32Z","title":"FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-05-07T04:14:15.586233Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.03425"},"observation_digest":"sha256:2af07c5983461f6ac59d999485d308915ee9eb3a9dc307cc82f784bf81d27e8b","observation_id":"ff565336-9975-495c-be32-023ae1f36694","resolution":{"observed_at":"2026-05-12T10:41:30.499803Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.05769","last_updated":"2026-05-07T07:01:00Z","snapshot_observed_at":"2026-08-13T17:36:01.464751Z","submitted_at":"2026-05-07T07:01:00Z","title":"Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-08T14:50:12.857642Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.05769"},"observation_digest":"sha256:82cf08ddc1d18199df1d8bfb4bf69f6d0e573e77599d2051fa6974002af4694f","observation_id":"c4bc710e-7062-4738-a619-26b8377d91ad","resolution":{"observed_at":"2026-05-11T18:41:09.230745Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.06505","last_updated":"2026-05-24T15:32:48Z","snapshot_observed_at":"2026-08-10T22:10:50.405459Z","submitted_at":"2026-05-07T16:20:20Z","title":"PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-08T12:33:11.872532Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.06505"},"observation_digest":"sha256:c7fd492ea14523bc422241c8983cd8d5536683b6f3960319cfddda9db29b7732","observation_id":"7cc8288f-1c82-4099-ac2d-2e4bd6d42d8b","resolution":{"observed_at":"2026-05-11T19:06:12.174878Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.06505","last_updated":"2026-05-24T15:32:48Z","snapshot_observed_at":"2026-08-10T22:10:50.405459Z","submitted_at":"2026-05-07T16:20:20Z","title":"PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-30T23:17:50.401236Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.06505"},"observation_digest":"sha256:e3cab0b1c3dd71eb039818b3fb92ebfc5e09cebbffa7aeefbb9175a9bdbd97c2","observation_id":"f917f902-a8ce-404c-878b-cb5b51619ae7","resolution":{"observed_at":"2026-07-01T13:25:45.405882Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.17373","last_updated":"2026-05-29T04:24:32Z","snapshot_observed_at":"2026-08-15T09:26:02.151681Z","submitted_at":"2026-05-17T10:30:38Z","title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-20T14:25:15.565386Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.17373"},"observation_digest":"sha256:57fde099e48d1cdd26c149dd4b7c73f1330bf7e640783de6aa3ecdb7428158fa","observation_id":"791e950c-6ec7-42b6-9011-517cfed5e2de","resolution":{"observed_at":"2026-05-20T14:28:21.410756Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.17373","last_updated":"2026-05-29T04:24:32Z","snapshot_observed_at":"2026-08-15T09:26:02.151681Z","submitted_at":"2026-05-17T10:30:38Z","title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-06-30T19:00:30.961402Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.17373"},"observation_digest":"sha256:f3420d2823e2659c87061d1f98345a9f4d88e0c3b76ee60456f2590d62b3a690","observation_id":"de73cf17-4079-4fdd-837e-08bc4d518526","resolution":{"observed_at":"2026-06-30T19:05:00.933597Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.20521","last_updated":"2026-05-19T21:43:22Z","snapshot_observed_at":"2026-08-15T00:37:57.239191Z","submitted_at":"2026-05-19T21:43:22Z","title":"An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-21T07:06:34.274842Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.20521"},"observation_digest":"sha256:890788561d5d67d197e64231fbf33e8107355f8b7820f79a34f76688c44f908f","observation_id":"23578c6f-a480-477f-8674-e1536ec32baa","resolution":{"observed_at":"2026-05-21T07:09:46.326541Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.21780","last_updated":"2026-05-20T22:17:29Z","snapshot_observed_at":"2026-08-18T13:06:01.327843Z","submitted_at":"2026-05-20T22:17:29Z","title":"Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-05-22T09:10:05.320094Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.21780"},"observation_digest":"sha256:32a37b8dff9d72d65302a0ce15b39cb76da7b20fa51c16a716add736a715076a","observation_id":"e3aa8bac-fb44-49df-8ea2-37c277a277f5","resolution":{"observed_at":"2026-05-22T09:11:21.075174Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.24879","last_updated":"2026-05-24T05:44:20Z","snapshot_observed_at":"2026-08-22T03:44:37.736500Z","submitted_at":"2026-05-24T05:44:20Z","title":"Efficient DP-SGD for LLMs with Randomized Clipping","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-06-30T12:24:58.673876Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.24879"},"observation_digest":"sha256:e4dca8b9ae9a7b76fb87d98c5011943a84bf5e19c1c5254d42c5e9e549f70a98","observation_id":"362f84be-6d7a-4fc0-9028-0d7deab001e9","resolution":{"observed_at":"2026-06-30T12:34:39.074871Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2605.26243","last_updated":"2026-05-25T18:10:20Z","snapshot_observed_at":"2026-08-12T11:01:20.564268Z","submitted_at":"2026-05-25T18:10:20Z","title":"Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-06-29T23:04:43.841278Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2605.26243"},"observation_digest":"sha256:a379159e1f1e1f799f8f43de4c060608865288b91e76a4e6e537da8755dcdca7","observation_id":"74a6729d-2ee0-42ea-9de4-bf5c86d1e0a9","resolution":{"observed_at":"2026-06-29T23:14:02.133488Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2606.01719","last_updated":"2026-06-01T05:34:19Z","snapshot_observed_at":"2026-08-12T13:51:21.468285Z","submitted_at":"2026-06-01T05:34:19Z","title":"Fair Finetuning Mitigates Distribution Inference Attacks","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-06-28T16:05:53.398690Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2606.01719"},"observation_digest":"sha256:db2c0010b67f20d074fb399b3de91b690c76455870715d4f5dbccbe1ce1ab9a1","observation_id":"c8cf524e-42ec-432d-b1f6-02423638fef3","resolution":{"observed_at":"2026-07-01T21:56:15.472547Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2606.11556","last_updated":"2026-06-10T01:33:20Z","snapshot_observed_at":"2026-08-14T05:44:26.926135Z","submitted_at":"2026-06-10T01:33:20Z","title":"Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-27T09:42:59.022080Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2606.11556"},"observation_digest":"sha256:33dd64ae6cfaa00c0c7624dfa20c0008a2320b9c9ed8c8f8f22bab33362751dc","observation_id":"1a8f48ec-924a-4e19-8bf5-1958200e1070","resolution":{"observed_at":"2026-07-03T11:08:02.964719Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":"2109.12298","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-07-08T10:14:52.062226Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":"cs.LG","work_id":"a7658d3e-1dfe-4593-a474-56151c484a58","year":2021},"citing_paper":{"arxiv_id":"2607.06320","last_updated":"2026-07-07T14:20:00Z","snapshot_observed_at":"2026-08-12T12:25:17.463938Z","submitted_at":"2026-07-07T14:20:00Z","title":"Dithered Gaussian Mechanism for Randomness-Efficient Differential Privacy","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-08T10:08:39.983029Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2607.06320"},"observation_digest":"sha256:dca0bf29da075e11fe6fb003bcf41c9426e9b32c72ea830363d8838524149ac2","observation_id":"40aba182-18f9-4d4f-a0bf-43d3fc5a4674","resolution":{"observed_at":"2026-07-08T10:14:52.065335Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-02T09:44:40.753808Z","title":"arXiv preprint arXiv:2109.12298 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.16261","last_updated":"2026-08-12T16:10:46Z","snapshot_observed_at":"2026-08-16T19:01:35.598692Z","submitted_at":"2026-06-28T18:01:27Z","title":"Reducing Per-Sample Interference in Stochastic Optimization","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-02T09:44:40.753808Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2607.16261"},"observation_digest":"sha256:3247a2d550f1c8b37d366b1ebc97133f1d787820ce93aa8902af5d949366e6f3","observation_id":"888a603f-4ad9-4b54-810d-5944ba3bdbf7","resolution":{"observed_at":"2026-08-02T09:44:40.753808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-01T12:29:21.244346Z","title":"Yousefpour, I","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19580","last_updated":"2026-07-21T21:15:55Z","snapshot_observed_at":"2026-08-16T20:53:00.374424Z","submitted_at":"2026-07-21T21:15:55Z","title":"End-to-End Differential Privacy in Training Deep Neural Network Classifiers","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-01T12:29:21.244346Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2607.19580"},"observation_digest":"sha256:1769f452ea7aa3aab6b64f9711ba47445cfcb7a9c52aada707b30432c2413ced","observation_id":"a34267c1-6f2d-469c-980c-eb164a627db0","resolution":{"observed_at":"2026-08-01T12:29:21.244346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2109.12298/citation-record","integrity":"/paper/2109.12298/integrity","json":"/paper/2109.12298/citation-record.json","paper":"/paper/2109.12298"},"outbound":[],"paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 71 inbound Pith citation observations for arXiv:2109.12298."}