{"as_of":"2026-08-08T11:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b29e5575ef887518b4dd925ab6954008b77db79ba9c64252276e6e4bcaa5fb3a","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":8,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":8,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":8,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":8,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:21:07.622647Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-23T17:23:15.442913Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":"2201.12328","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Toward training at imagenet scale with differential privacy","venue":null,"work_id":"636f2a9e-3b4b-471f-839d-0cf0c57c52ab","year":2022},"citing_paper":{"arxiv_id":"2411.04680","last_updated":"2026-04-24T11:56:08Z","snapshot_observed_at":"2026-07-06T19:46:41.798193Z","submitted_at":"2024-11-07T13:08:06Z","title":"Privacy Leakage via Output Label Space and Differentially Private Continual Learning","version":5},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-23T17:18:22.300467Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2411.04680"},"observation_digest":"sha256:1e1a73669e7c8647f790fba4d7318adce01dbfa61fe4244c1e6ee8d5e6c0604a","observation_id":"375a1069-d6c2-4c12-8bd2-eb892b9f78e7","resolution":{"observed_at":"2026-05-23T17:23:15.446378Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":"2201.12328","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Toward training at imagenet scale with differential privacy","venue":null,"work_id":"636f2a9e-3b4b-471f-839d-0cf0c57c52ab","year":2022},"citing_paper":{"arxiv_id":"2505.16329","last_updated":"2026-04-26T14:33:57Z","snapshot_observed_at":"2026-08-02T23:19:18.105404Z","submitted_at":"2025-05-22T07:34:27Z","title":"High-Dimensional Private Linear Regression with Optimal Rates","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-22T02:50:09.196457Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2505.16329"},"observation_digest":"sha256:a2b5a295057a9f1b6b7cb637dbc3b0cf013a17a4f172b7b492e5f207b91f8025","observation_id":"f6c4a4ce-299a-4ae2-adc1-1d748e326c40","resolution":{"observed_at":"2026-05-22T02:50:58.314431Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-08-07T05:21:07.622647Z","title":"Toward training at imagenet scale with differential pri- vacy.CoRR, abs/2201.12328, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-07T05:08:52.862153Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.622647Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:52dd8238b106c969c63f36edab456e82cca26a2cead085fc4c83a7a6c2cd46ee","observation_id":"2bf75c8c-3793-49f2-b04a-e818d50d5c92","resolution":{"observed_at":"2026-08-07T05:21:07.622647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-08-06T14:56:03.972461Z","title":"Toward training at imagenet scale with differential privacy","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-07T08:09:24.648949Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.972461Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:c1c27db087883807b0ffe0edbeb32fa27f0ffbdc6681e9866281cc9a353b52c4","observation_id":"c25713c9-bbf6-4dce-97ae-7a818bd0007a","resolution":{"observed_at":"2026-08-06T14:56:03.972461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-08-04T11:24:33.364120Z","title":"Toward training at imagenet scale with differential privacy","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.05416","last_updated":"2026-07-24T00:15:07Z","snapshot_observed_at":"2026-08-06T04:43:01.911516Z","submitted_at":"2025-10-06T22:13:02Z","title":"Correlating Cross-Iteration Noise for DP-SGD using Model Curvature","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T11:24:33.364120Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2510.05416"},"observation_digest":"sha256:62f8ae89f30eb8dcff7a90bf84bc58e98f549e70dedab05bd1812ecdc265b68b","observation_id":"87dfe996-15d5-4851-b1a6-c04e1fc5fa2f","resolution":{"observed_at":"2026-08-04T11:24:33.364120Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":"2201.12328","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Toward training at imagenet scale with differential privacy","venue":null,"work_id":"636f2a9e-3b4b-471f-839d-0cf0c57c52ab","year":2022},"citing_paper":{"arxiv_id":"2601.10237","last_updated":"2026-04-16T13:16:57Z","snapshot_observed_at":"2026-07-30T08:45:45.642515Z","submitted_at":"2026-01-15T09:50:36Z","title":"Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-16T13:37:50.765735Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2601.10237"},"observation_digest":"sha256:5878376e65b5e03e41fc0b6d983c071fcc5f9a840f3af7a777a01b9c1e46cbbb","observation_id":"82594f9d-07d7-4fdd-9745-09b27be53181","resolution":{"observed_at":"2026-05-16T13:37:56.500209Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-08-03T07:37:44.575083Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.19618","last_updated":"2026-07-22T19:51:14Z","snapshot_observed_at":"2026-08-06T10:09:03.324643Z","submitted_at":"2026-01-27T13:50:43Z","title":"The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T07:37:44.575083Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2601.19618"},"observation_digest":"sha256:8c9bb7ccd46e4a00a1de923d153cc22ba8893a5b0f1514a13c8c7727747ca094","observation_id":"5022a9b7-e608-4f6c-99fe-bd5752449bc2","resolution":{"observed_at":"2026-08-03T07:37:44.575083Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":"2201.12328","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Toward training at imagenet scale with differential privacy","venue":null,"work_id":"636f2a9e-3b4b-471f-839d-0cf0c57c52ab","year":2022},"citing_paper":{"arxiv_id":"2604.26467","last_updated":"2026-04-29T09:25:06Z","snapshot_observed_at":"2026-07-06T23:12:06.349884Z","submitted_at":"2026-04-29T09:25:06Z","title":"Differentially Private Contrastive Learning via Bounding Group-level Contribution","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-07T13:07:53.564066Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2604.26467"},"observation_digest":"sha256:3bce6651f8aa0f551c0b58a024b51deb274b874ae6712e061611e78b003c50fa","observation_id":"1fb6ccd2-daa6-4982-b14b-1f30f0cf525e","resolution":{"observed_at":"2026-05-12T09:06:25.027864Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2201.12328/citation-record","integrity":"/paper/2201.12328/integrity","json":"/paper/2201.12328/citation-record.json","paper":"/paper/2201.12328"},"outbound":[],"paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 8 inbound Pith citation observations for arXiv:2201.12328."}