{"as_of":"2026-08-15T17:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:716c2caf5a095f9301c6f5efe1334c2dd9764d6956a270dee34e2e8d20c78db7","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:06:27.033357Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.06525/citation-record","integrity":"/paper/2507.06525/integrity","json":"/paper/2507.06525/citation-record.json","paper":"/paper/2507.06525"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.345052Z","title":"Deep learning with differential privacy","venue":null,"work_id":"3b9fe05c-6ed1-4821-8f17-d133d6464614","year":2016},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.004029Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:2709a4ad8ab78801669889e5f58d1d564921c71c6ccafc2385ac1ece7a470279","observation_id":"457469f5-8dae-4659-9578-b20f4a7e2af7","resolution":{"observed_at":"2026-08-06T19:06:27.348331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.09074","last_updated":"2022-01-26T03:39:50Z","snapshot_observed_at":"2026-08-14T01:01:31.898474Z","submitted_at":"2021-10-18T07:49:52Z","title":"Towards General Deep Leakage in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.09074","snapshot_observed_at":"2026-08-06T19:06:25.717574Z","title":"Towards general deep leakage in federated learning.arXiv:2110.09074,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.717574Z"},"links":{"cited_paper":"/paper/2110.09074","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:f1de30ac53fc88970563e2c8504435aa8780fac8fe524a3ecc36ce951b11f764","observation_id":"c9a7a396-7340-4430-9ff9-5a3fdb983690","resolution":{"observed_at":"2026-08-06T19:06:25.717574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02744","last_updated":"2024-06-04T19:57:47Z","snapshot_observed_at":"2026-08-13T20:22:53.295498Z","submitted_at":"2024-06-04T19:57:47Z","title":"DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02744","snapshot_observed_at":"2026-08-06T19:06:26.125944Z","title":"DPDR: Gradient decomposition and reconstruction for differentially private deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.125944Z"},"links":{"cited_paper":"/paper/2406.02744","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:9f53f1cbce8b219bf247d86bdf7736e55a87d0c16493fa46120f1705fb2a094d","observation_id":"2f9871e2-8ac7-4892-8083-bb8a262beaeb","resolution":{"observed_at":"2026-08-06T19:06:26.125944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.11524","last_updated":"2020-07-22T16:33:14Z","snapshot_observed_at":"2026-08-04T15:18:26.501887Z","submitted_at":"2020-07-22T16:33:14Z","title":"Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.11524","snapshot_observed_at":"2026-08-06T19:06:26.279978Z","title":"Improving deep learning with differential privacy using gradient encoding and denoising.arXiv:2007.11524,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.279978Z"},"links":{"cited_paper":"/paper/2007.11524","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:da68b8947c117b3f82b5ffaa36c52c6df3f6c9f613cd86598fedfdbd350f196a","observation_id":"350f5e72-4312-48d2-a9ea-0121bf50fe7f","resolution":{"observed_at":"2026-08-06T19:06:26.279978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.261524Z","title":"Privacy- preserving deep learning: Revisited and enhanced","venue":null,"work_id":"a81d17f8-899d-49c4-af2a-a1ed3908d3b3","year":2017},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.371855Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:9ca32812b2e2b7c0da08fb347b9ec0de569b09cee846dc742583cd0ad3d097b7","observation_id":"ee57e676-084a-4fdd-98e0-09881b960196","resolution":{"observed_at":"2026-08-06T19:06:27.265174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07643","last_updated":"2019-10-23T19:02:00Z","snapshot_observed_at":"2026-08-15T11:50:16.329843Z","submitted_at":"2019-08-20T23:19:21Z","title":"AdaCliP: Adaptive Clipping for Private SGD","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07643","snapshot_observed_at":"2026-08-06T19:06:26.464885Z","title":"AdaClip: Adaptive clipping for private sgd.arXiv:1908.07643,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.464885Z"},"links":{"cited_paper":"/paper/1908.07643","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:8659dcab08998a4d7696ed00f124d5dcb3e1ce7d9fc569459bb8d47e2e53b208","observation_id":"6c751ce0-90ed-4357-9fba-8e537a34f38f","resolution":{"observed_at":"2026-08-06T19:06:26.464885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.01246","last_updated":"2018-12-14T19:39:43Z","snapshot_observed_at":"2026-08-14T19:07:42.874279Z","submitted_at":"2018-06-04T17:38:42Z","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.01246","snapshot_observed_at":"2026-08-06T19:06:26.543195Z","title":"ML-Leaks: Model and data independent membership inference attacks and de- fenses on machine learning models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.543195Z"},"links":{"cited_paper":"/paper/1806.01246","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:86a6ca74a7cd337e64f5754a5404249a071097d770f0874ad86a8ec071a7fdce","observation_id":"da1ee37f-b161-4796-9e79-f1f4f0f8de4a","resolution":{"observed_at":"2026-08-06T19:06:26.543195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.250774Z","title":"Machine learning models that remember too much","venue":null,"work_id":"21ed12fc-a18c-407f-8894-64f531ec778e","year":2017},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.764397Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:39c1271261c242515337141c16eecf29e4e36dd72ea9be6c3e23853960ebedcd","observation_id":"8d6072ef-94c8-4330-9883-8184ed2f10d7","resolution":{"observed_at":"2026-08-06T19:06:27.253985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.239746Z","title":"Subsampled rényi differ- ential privacy and analytical moments accountant","venue":null,"work_id":"308253ca-5a19-49ba-bbbd-128c751695eb","year":2019},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.849758Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:8d94cfa3c9e4b7b27370953bfd61573e3fd9e494d416dfe4438e011ec5a111a1","observation_id":"05b4a1b9-163c-41e8-8e65-ef69cadf3dd3","resolution":{"observed_at":"2026-08-06T19:06:27.243363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-06T19:06:27.018676Z","title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms.arXiv:1708.07747,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:27.018676Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:22f3cf549565fc43280986dddac1fe9c55159521added151ec1ad28819e44e08","observation_id":"5f7c4feb-cf55-49d5-9c54-3d218ca22d5c","resolution":{"observed_at":"2026-08-06T19:06:27.018676Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.12677","last_updated":"2021-10-12T09:38:48Z","snapshot_observed_at":"2026-08-13T20:08:53.934752Z","submitted_at":"2021-02-25T04:29:58Z","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.12677","snapshot_observed_at":"2026-08-06T19:06:27.022546Z","title":"Do not let privacy overbill utility: Gradient embedding perturbation for private learning.arXiv:2102.12677, 2021a","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:27.022546Z"},"links":{"cited_paper":"/paper/2102.12677","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:178dd82a75d8b5e96b24ee023ea01810591d8b27e28e3ed2e85aefd624d465c9","observation_id":"66118899-b1dd-4ad2-94e3-f6141651ead7","resolution":{"observed_at":"2026-08-06T19:06:27.022546Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.03813","last_updated":"2021-04-23T23:07:28Z","snapshot_observed_at":"2026-08-09T17:03:52.549604Z","submitted_at":"2020-07-07T22:31:01Z","title":"Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.03813","snapshot_observed_at":"2026-08-06T19:06:27.025962Z","title":"Bypassingtheambientdimension: Private SGD with gradient subspace identification.arXiv:2007.03813,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:27.025962Z"},"links":{"cited_paper":"/paper/2007.03813","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:82b84d7018772b55edb98679773dc63a6ba451228eb3933fddb8220f833cae87","observation_id":"ecbb342a-1348-42b7-9873-69e375add08b","resolution":{"observed_at":"2026-08-06T19:06:27.025962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.07733","last_updated":"2021-03-16T11:16:25Z","snapshot_observed_at":"2026-08-08T23:11:08.785736Z","submitted_at":"2020-10-15T13:22:40Z","title":"R-GAP: Recursive Gradient Attack on Privacy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.07733","snapshot_observed_at":"2026-08-06T19:06:27.029681Z","title":"R-GAP: Recursive gradient attack on privacy","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:27.029681Z"},"links":{"cited_paper":"/paper/2010.07733","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:29bd79e80c1e1213f9b6c6eb3c9f0bf544c35bbb8ac406a5315e278c3eea428b","observation_id":"b46e39da-8938-4aef-a4c0-f741e283aec4","resolution":{"observed_at":"2026-08-06T19:06:27.029681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.00845","last_updated":"2023-06-28T13:30:48Z","snapshot_observed_at":"2026-08-13T17:23:33.664787Z","submitted_at":"2021-12-01T21:43:34Z","title":"Improving Differentially Private SGD via Randomly Sparsified Gradients","version":3},"cited_work":{"arxiv_id":"2112.00845","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.00845","snapshot_observed_at":"2026-08-06T19:06:27.063134Z","title":"Improving Differentially Private SGD via Randomly Sparsified Gradients","venue":"cs.LG","work_id":"f5da5077-25d9-436e-929c-2d12d70440b3","year":2021},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:27.033357Z"},"links":{"cited_paper":"/paper/2112.00845","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:8a78764250a5b279bc5e329661fa1917176fb894379ec7bc064bc327d0f6a217","observation_id":"40617e3f-58ff-45d0-b2b7-21f937a1c405","resolution":{"observed_at":"2026-08-06T19:06:27.068944Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.293993Z","title":"Deepleakagefromgradientsinmultiple-label medical image classification","venue":null,"work_id":"50f3991a-86b0-4394-b555-154748f718a6","year":2021},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.954511Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:d783893db4277ac57fd802fabca66201a3918dec05ece504b216e333ab515139","observation_id":"2de95ee1-eef8-46cd-8ec2-11caae514e1a","resolution":{"observed_at":"2026-08-06T19:06:27.297742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.283782Z","title":"FedSel: Federated SGD under local differential privacy with top-k dimension selection","venue":null,"work_id":"f13ff332-a776-45b1-a8f6-8433e40e9fb0","year":2020},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2005,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.045664Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:d5304a6e37e14ae9f48f280ee64c93211bcc91172ade10c84f567e6f7574c78c","observation_id":"b2ccfc71-2d5e-4c83-8086-3d429fbda7b1","resolution":{"observed_at":"2026-08-06T19:06:27.287410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.315207Z","title":"Bagging classifiers for fighting poisoning attacks in adversarial classification tasks","venue":null,"work_id":"ff926d5b-644e-4e7e-97d1-75413dc51b69","year":2011},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.424095Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:eee5d0c4b2cc3b0bda9e7120c5e86524a124785ea9f657be9e1d2bef9bf09b4b","observation_id":"1ac48b0e-05f9-42aa-91de-e43646b6116a","resolution":{"observed_at":"2026-08-06T19:06:27.318415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.14056","last_updated":"2023-11-29T08:43:45Z","snapshot_observed_at":"2026-08-14T15:26:55.569519Z","submitted_at":"2023-11-23T15:19:30Z","title":"DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.14056","snapshot_observed_at":"2026-08-06T19:06:25.624583Z","title":"DP- SUR: accelerating differentially private stochastic gradient descent using selective update and release","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.624583Z"},"links":{"cited_paper":"/paper/2311.14056","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:914a1c1e94f531719526723e6f75fdee5320cd4f7a50a98a8a3b74aaba2c58ae","observation_id":"b77625df-8a98-4e59-b284-ad2deb6e0249","resolution":{"observed_at":"2026-08-06T19:06:25.624583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.04612","last_updated":"2023-03-08T14:27:35Z","snapshot_observed_at":"2026-08-15T03:49:50.980252Z","submitted_at":"2023-03-08T14:27:35Z","title":"Differential Privacy Meets Neural Network Pruning","version":1},"cited_work":{"arxiv_id":"2303.04612","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.04612","snapshot_observed_at":"2026-08-06T19:06:27.216607Z","title":"Differential Privacy Meets Neural Network Pruning","venue":"cs.LG","work_id":"0002cc40-8926-4b40-99ae-d88a7da4b4d1","year":2023},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.076820Z"},"links":{"cited_paper":"/paper/2303.04612","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:9f1373ae94d71dcb274ddf0941cedf50d7bc4b4c27a4eb625ddeee0e7dc5ca5d","observation_id":"93d1d366-1ab1-4594-8f5d-3ad38bcf588b","resolution":{"observed_at":"2026-08-06T19:06:27.220633Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.272301Z","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","venue":null,"work_id":"d7c88a54-f3a0-4ed3-9838-b6579f204165","year":2019},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.183883Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:6d670a2113d1f270b41fd55b4e43c99116b2712aebb1cb20b73c85403820b4e5","observation_id":"d1db8e4f-697d-434b-8220-c5dc7f01de0c","resolution":{"observed_at":"2026-08-06T19:06:27.276413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03792","last_updated":"2025-04-12T13:38:42Z","snapshot_observed_at":"2026-07-06T16:57:55.137830Z","submitted_at":"2023-12-06T13:34:15Z","title":"PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance","version":2},"cited_work":{"arxiv_id":"2312.03792","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.03792","snapshot_observed_at":"2026-08-06T19:06:27.124633Z","title":"PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance","venue":"cs.CR","work_id":"73a73738-c380-4a4f-b500-cbe9f92107f6","year":2023},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.672794Z"},"links":{"cited_paper":"/paper/2312.03792","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:2e8fe2b70ed86f1f92c43c89cc343138740bb8871c31f6968cc4de0257da327f","observation_id":"0e0dc86d-5a34-4254-adb7-65cde4b4b827","resolution":{"observed_at":"2026-08-06T19:06:27.128664Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01876","last_updated":"2020-03-04T03:42:54Z","snapshot_observed_at":"2026-08-09T14:59:32.125310Z","submitted_at":"2020-03-04T03:42:54Z","title":"Privacy-preserving Learning via Deep Net Pruning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.01876","snapshot_observed_at":"2026-08-06T19:06:25.820295Z","title":"Privacy- preserving learning via deep net pruning.arXiv:2003.01876,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.820295Z"},"links":{"cited_paper":"/paper/2003.01876","citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:4f5b1e920d61188b63da91c47919a9d9748ac81b66af65faecd21844254e9162","observation_id":"ef1dd743-873a-41ef-b270-edd163578ee7","resolution":{"observed_at":"2026-08-06T19:06:25.820295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.304664Z","title":"Secure multi-party computation problems and their applications: a review and open problems","venue":null,"work_id":"c4656482-a6c4-45dd-8138-07e64e31adbc","year":2001},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.536602Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:7b08cdf02d627afdf0a645ea234581d5cc546bd65d9875ad37f84812a8a767b8","observation_id":"51314688-92bf-46f6-be46-44e4a04b5cd7","resolution":{"observed_at":"2026-08-06T19:06:27.307902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.334334Z","title":"Can machine learning be secure? InProceedings of the 2006 ACM Symposium on Information, computer and communications security, pages 16–25,","venue":null,"work_id":"37b85eab-5fb0-4a55-bc9c-3c497ac723d1","year":2006},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.192925Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:1033919a1f089a7accde9c2ef390c4f32bd94facfed9f60aafc48eccdb771ca3","observation_id":"9dc4be5a-27df-41f4-9240-431d591dc4fb","resolution":{"observed_at":"2026-08-06T19:06:27.338170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.227915Z","title":"Bolt-on differential privacy for scalable stochastic gradient descent-based analytics","venue":null,"work_id":"6197c6a3-7d05-479f-a972-98f7554a49ec","year":2017},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:26.952739Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:0a5cf490954501bc65a540edd815015d8852ac026b1b0b37ba17fad5e15df6df","observation_id":"ff2e485f-f443-4456-a983-cda518eeec6e","resolution":{"observed_at":"2026-08-06T19:06:27.231994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:06:27.324661Z","title":"Multiple classifier systems for adversarial classification tasks","venue":null,"work_id":"a5320157-cc11-414c-9de7-2acf383b0c88","year":2009},"citing_paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:25.314877Z"},"links":{"citing_paper":"/paper/2507.06525"},"observation_digest":"sha256:6862744dc0d3b6658620afbf3e5521ff4bf077e9450d2fe4265812ceeb143b1b","observation_id":"5e5c86d0-be36-4376-8bfd-a89eba0bb6db","resolution":{"observed_at":"2026-08-06T19:06:27.327710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.06525","last_updated":"2025-07-09T03:53:03Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T02:57:37.171103Z","submitted_at":"2025-07-09T03:53:03Z","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":3,"verified_fuzzy":12},"total_outbound_references":26},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2507.06525."}