{"as_of":"2026-08-13T14:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:84259000964e7a2863e25cccee2724f4f37debc7077d9071ded525de2702bfc7","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:44:14.990803Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2412.05529/citation-record","integrity":"/paper/2412.05529/integrity","json":"/paper/2412.05529/citation-record.json","paper":"/paper/2412.05529"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.768654Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.768654Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:d51b4e0aae5d95716f27def7963eb1f6eeb355f7fca085959914836bb71918ec","observation_id":"ca365848-f232-4643-8249-6897d7ee00f9","resolution":{"observed_at":"2026-08-11T20:44:14.768654Z","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":"2026-08-11T20:44:15.692839Z","title":"Inverting gradients-how easy is it to break privacy in federated learning?","venue":null,"work_id":"fcbd1329-a78a-4e98-a3ff-4b0b8a66bfbe","year":2020},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.774617Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:463cc0513cd128c977ecd267417c901c14b9be8da73d7c001b164fb686e1d1df","observation_id":"1b071f57-d5c8-4a37-b403-d74ff90e048c","resolution":{"observed_at":"2026-08-11T20:44:15.698419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T20:44:15.674141Z","title":"Feature inference attack on model predictions in vertical federated learning,","venue":null,"work_id":"c559e28a-c8a8-4150-a6f8-773b656b712c","year":2021},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.780044Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:aa6b6d85031110c1c0dbd0a5a92d24703c4fbbcd152e16ad158afaf890bc4f4d","observation_id":"fa082aa5-b40a-4ed7-b1e5-adfa4e7dd0f3","resolution":{"observed_at":"2026-08-11T20:44:15.679686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.786798Z","title":"Auditing privacy defenses in federated learning via generative gradient leakage,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.786798Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:f89179a2a9e58f5ad3ab31f2223527fccda8e349d70e5d772b0062cc23e84537","observation_id":"43776a61-a3db-446e-bfab-2fb0a4573c21","resolution":{"observed_at":"2026-08-11T20:44:14.786798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.07557","last_updated":"2018-03-01T10:12:27Z","snapshot_observed_at":"2026-07-06T06:15:22.497001Z","submitted_at":"2017-12-20T16:28:37Z","title":"Differentially Private Federated Learning: A Client Level Perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.07557","snapshot_observed_at":"2026-08-11T20:44:14.792543Z","title":"Differentially private federated learning: A client level perspective,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.792543Z"},"links":{"cited_paper":"/paper/1712.07557","citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:e4ee3323efb460273e2369702bef124433ef8d4116223b333d02c8d3c7dc8f2d","observation_id":"3feea60a-bd28-41f8-aa06-959f9a8d91ea","resolution":{"observed_at":"2026-08-11T20:44:14.792543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.801216Z","title":"Federated learning with differential privacy: Algorithms and performance analysis,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.801216Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:11c1a056b6918addace28ebee0000e4126190d3126218263d88ca4539007b4b7","observation_id":"bdd2d18d-b990-4ac1-af65-dcf554057adc","resolution":{"observed_at":"2026-08-11T20:44:14.801216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.807920Z","title":"Regulation (eu) 2016/679 of the european parliament and of the council,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.807920Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:e855d09bd1a0bd9ab765be9f64aa89e76ac122995a83efa27eaa6062cb831c6c","observation_id":"94ec30c2-8545-4e82-bd68-5e73d444de84","resolution":{"observed_at":"2026-08-11T20:44:14.807920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.813990Z","title":"The eu general data protection regu- lation (gdpr),","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.813990Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:15fda56d1021856e7415c968dccb391862ffeb7072af59ff2c5505fbd5f32bba","observation_id":"67405c83-6542-44ff-814f-56df01380f12","resolution":{"observed_at":"2026-08-11T20:44:14.813990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.820247Z","title":"Federaser: Enabling efficient client-level data removal from federated learning models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.820247Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:ccb445630dadc074b3341d2ea33e2b061722d656e2c35d498441b5dfc506849e","observation_id":"f2cc29b6-2f3b-4d83-8d9e-80978f786f7c","resolution":{"observed_at":"2026-08-11T20:44:14.820247Z","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":"2026-08-11T20:44:15.596581Z","title":"Federated unlearning with momentum degradation,","venue":null,"work_id":"929a0c84-6bd2-4995-a00c-0b60ca39f071","year":2023},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.825824Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:3f7363d7af6bcb5f2c21e8f457c6bd168152c4bb77e9a057e2e907d91aef9e78","observation_id":"e1969a9b-43c1-4865-9c8c-1f7ad4e73a95","resolution":{"observed_at":"2026-08-11T20:44:15.602672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T20:44:15.577399Z","title":"Federated unlearning for on-device recommendation,","venue":null,"work_id":"4a97a45a-0a68-43c8-af33-4ec03d5498fd","year":2023},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.831006Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:56d0a7601af776ba9fd8cede56b1dc758c6b514b28b54c3cb366df3ef8d7e7e9","observation_id":"1e37bb5d-b343-4767-bef5-c6e1b9d811be","resolution":{"observed_at":"2026-08-11T20:44:15.583855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.836416Z","title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.836416Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:f8d0b45b3cf3b86df52c84e4e2f39d4301f8500f4b4a13255299f82cefccfc84","observation_id":"80899c1a-ae06-437a-9a26-ea55e9b4a9fb","resolution":{"observed_at":"2026-08-11T20:44:14.836416Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05521","last_updated":"2023-10-20T19:57:54Z","snapshot_observed_at":"2026-08-02T18:22:39.662676Z","submitted_at":"2022-07-12T13:24:23Z","title":"Federated Unlearning: How to Efficiently Erase a Client in FL?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05521","snapshot_observed_at":"2026-08-11T20:44:14.845803Z","title":"Federated unlearning: How to efficiently erase a client in fl?","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.845803Z"},"links":{"cited_paper":"/paper/2207.05521","citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:f9b4185530ee9807ff781493f5bdb91bd258a79430b6138a074d4a91249e4c18","observation_id":"7beb68d1-6086-4543-9d81-cc6590b1b662","resolution":{"observed_at":"2026-08-11T20:44:14.845803Z","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":"2026-08-11T20:44:15.547464Z","title":"Fedrecover: Recovering from poisoning attacks in federated learning using historical information,","venue":null,"work_id":"91d0df4d-9cd7-4581-88b9-517da1788b76","year":2023},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.852595Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:f46f9d15b71b41fd029d1013bf45ad87bbc3f2d702a4b7dffe1acb24c90b281b","observation_id":"795e2b57-5d38-4d52-8e19-d51238d5eed2","resolution":{"observed_at":"2026-08-11T20:44:15.553383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.858195Z","title":"Incentive mechanism design for federated learning and unlearning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.858195Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:afe81c6cbc9de7c892b13cef0f94c22bdd731d7eddbc71f5d8ef223125628486","observation_id":"67e8da69-616f-4194-86b3-3590720f980f","resolution":{"observed_at":"2026-08-11T20:44:14.858195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.09441","last_updated":"2022-01-24T03:56:20Z","snapshot_observed_at":"2026-08-09T04:32:24.004839Z","submitted_at":"2022-01-24T03:56:20Z","title":"Federated Unlearning with Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.09441","snapshot_observed_at":"2026-08-11T20:44:14.863494Z","title":"Federated unlearning with knowledge distillation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.863494Z"},"links":{"cited_paper":"/paper/2201.09441","citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:cf7eaa1f731d6fafd145f52cf0309b7587adb97edd4c7c8dcf54ab7e24768c69","observation_id":"ebea0d29-39f8-4186-a3b6-fd1c963c60d5","resolution":{"observed_at":"2026-08-11T20:44:14.863494Z","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":"2026-08-11T20:44:15.516432Z","title":"Federated unlearning via class- discriminative pruning,","venue":null,"work_id":"3ef798e2-beb9-485b-ae04-5f28d9c480aa","year":2022},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.868784Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:117b289235aac9ada13305bbba9b2f3517970fb8f783922d933a5c61b07d5589","observation_id":"55927ed6-e838-4f94-8e98-fdf7ab2974da","resolution":{"observed_at":"2026-08-11T20:44:15.522459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T20:44:15.498532Z","title":"Fedme 2: Memory evaluation & erase promoting federated unlearning in dtmn,","venue":null,"work_id":"83dbca3f-1323-47f9-8a8e-a86908199b84","year":2023},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.873672Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:d1ce3920b9812ce029c9f66b62068ae1bc95b9fbaea0229d1ceaf48462686077","observation_id":"0f8e2733-d62c-428c-89ce-0d2a180e6f51","resolution":{"observed_at":"2026-08-11T20:44:15.504119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T20:44:15.478853Z","title":"Fedrecovery: Dif- ferentially private machine unlearning for federated learning frameworks,","venue":null,"work_id":"a114e596-7551-4f8d-9345-d64ed63e1b44","year":2023},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.879535Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:fc557b9b0caaa9f354ccfd1c3ec237b1a967ed971c61d067160fd9a20856ce10","observation_id":"b69605e7-7626-40d5-9a37-7692f7fceead","resolution":{"observed_at":"2026-08-11T20:44:15.486101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10638","last_updated":"2023-04-20T20:32:40Z","snapshot_observed_at":"2026-08-13T11:58:27.045725Z","submitted_at":"2023-04-20T20:32:40Z","title":"Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10638","snapshot_observed_at":"2026-08-11T20:44:14.888169Z","title":"Get rid of your trail: Remotely erasing backdoors in federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.888169Z"},"links":{"cited_paper":"/paper/2304.10638","citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:7f5c9aa0e7fc54602af941867666ea3fc9ac48cfac9437e5a2b3d220c8967aa2","observation_id":"2a5c48ab-40a0-4dff-a86c-1e23cf042584","resolution":{"observed_at":"2026-08-11T20:44:14.888169Z","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":"2026-08-11T20:44:15.460330Z","title":"Bayesian variational federated learning and unlearning in decentralized networks,","venue":null,"work_id":"d1349f89-cd89-4f26-84c4-22f72180f0c7","year":2021},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.894425Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:2fe75977b8a6bf95d49c32f85ccf447ea3e16a2bed5789a6f75749a43e44f535","observation_id":"817bbde7-dbc1-4cf5-a8bb-94efc7e55ac6","resolution":{"observed_at":"2026-08-11T20:44:15.465569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.899258Z","title":"On the limited memory bfgs method for large scale optimization,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.899258Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:dd68ddc75ff508cb7d6b732d0fce95cd5d247f8e15404df22c9e69e368e93315","observation_id":"318cdc6e-e5b0-4f26-a7bd-e6c894882ab3","resolution":{"observed_at":"2026-08-11T20:44:14.899258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06963","last_updated":"2018-02-24T00:40:30Z","snapshot_observed_at":"2026-08-10T06:02:31.713188Z","submitted_at":"2017-10-18T23:46:57Z","title":"Learning Differentially Private Recurrent Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06963","snapshot_observed_at":"2026-08-11T20:44:14.904405Z","title":"Learn- ing differentially private recurrent language models,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.904405Z"},"links":{"cited_paper":"/paper/1710.06963","citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:679d267bf924fb0e0cae0b8e3dc79fa23c4eeaddcf228254073ace849e3777fd","observation_id":"30fa1a94-181a-4878-8950-7948184e4e06","resolution":{"observed_at":"2026-08-11T20:44:14.904405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.909343Z","title":"Ldp-fed: Federated learning with local differential privacy,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.909343Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:861dd059c56721afd2ae3f187f477eda9dff1550b56576fec122e3b394dbe0e8","observation_id":"3f5dc7b5-3805-4b9b-8c9a-eb06105f6cce","resolution":{"observed_at":"2026-08-11T20:44:14.909343Z","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":"2026-08-11T20:44:15.413555Z","title":"Shuffled model of differential privacy in federated learning,","venue":null,"work_id":"ba8a1954-3493-43eb-bd6c-bdeadebba146","year":2021},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.914070Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:d131023b4d167765d8a0cb3c8301d7c258dfb3298f18f8da92304794c21f8754","observation_id":"72fa6660-a668-421a-a030-7db6c9488dc0","resolution":{"observed_at":"2026-08-11T20:44:15.420552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T20:44:15.392636Z","title":"Federated learning with differential privacy for resilient vehicular cyber physical systems,","venue":null,"work_id":"0759789d-6ca3-41ea-8bc4-22a20a04f34c","year":2021},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.919668Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:3d7b44689a690e4121e0da3bc8e6f8fbe727c518ce1c94eec855aae258ae716d","observation_id":"b2d808f8-ca36-463d-a11f-b9090b779540","resolution":{"observed_at":"2026-08-11T20:44:15.397716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.925520Z","title":"Local differential privacy-based federated learning for internet of things,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.925520Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:90acb7bad0d7b7f70d355afc713d571a7fa44b5357bb95062e17387f38599592","observation_id":"0938c75e-69ef-4b1a-8b5e-f6cd9261174e","resolution":{"observed_at":"2026-08-11T20:44:14.925520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.02578","last_updated":"2020-02-27T15:59:56Z","snapshot_observed_at":"2026-07-06T08:27:18.884047Z","submitted_at":"2019-10-07T02:10:30Z","title":"Differential Privacy-enabled Federated Learning for Sensitive Health Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.02578","snapshot_observed_at":"2026-08-11T20:44:14.931901Z","title":"Differential privacy-enabled federated learning for sensitive health data,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.931901Z"},"links":{"cited_paper":"/paper/1910.02578","citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:515a6fdae33b8dd230ad0a30da69d4af4e8da10451ede1303e5bf0dc08676e0c","observation_id":"d12f95aa-e51a-4a6a-956b-49bfafb0751a","resolution":{"observed_at":"2026-08-11T20:44:14.931901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.938090Z","title":"Federated learning and differential privacy for medical image analysis,","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.938090Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:bf19defcf710a3f2715173884da62d14d171c206e096e5bb31df815c03efeca5","observation_id":"85164e09-6b28-4671-a8e4-ff9d7e466023","resolution":{"observed_at":"2026-08-11T20:44:14.938090Z","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":"2026-08-11T20:44:15.354000Z","title":"Federated quantum machine learning with differential privacy,","venue":null,"work_id":"8d81b9a9-866d-4d7b-bea1-077674184e2b","year":2024},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.943741Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:65eb99c402fc07a2f20ad3d7bf093047449fc90637d473a029cd03d77d455d18","observation_id":"f48fa5aa-fd62-4e14-9d92-55083489fd4c","resolution":{"observed_at":"2026-08-11T20:44:15.358872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.948687Z","title":"Concentrated differential privacy: Simplifications, extensions, and lower bounds,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.948687Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:7c5d7145018b82a6d37dec2eb083643ea7c0a35ed253022ccc6980d243b9d63f","observation_id":"a43665e0-671b-4676-aefd-c8a395605d3c","resolution":{"observed_at":"2026-08-11T20:44:14.948687Z","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":"2026-08-11T20:44:15.324092Z","title":"Independent component analysis in the presence of gaussian noise by maximizing joint likelihood,","venue":null,"work_id":"54951f09-aeea-4851-b60e-0ca8f7406568","year":1998},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.953293Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:fb10dba80dcfbef33084a6be6e4ff3d780f2c85f2f8132d3bb35e8427983c9d9","observation_id":"aa24e83c-be71-4c55-bfcf-1308f569e88d","resolution":{"observed_at":"2026-08-11T20:44:15.329158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T20:44:15.305528Z","title":"The value of collaboration in convex machine learning with differential privacy,","venue":null,"work_id":"db84b386-4e56-47c5-a976-05ef9514bb1e","year":2020},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.958436Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:33f8a0fb0a3921fded1ac1efd030ea96f36f2dfc7dfc9c028bc6a3226b4e6543","observation_id":"b3811597-10da-4455-b1dc-dac656480cf2","resolution":{"observed_at":"2026-08-11T20:44:15.311718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.01235","last_updated":"2023-12-06T23:03:23Z","snapshot_observed_at":"2026-08-13T05:11:46.554982Z","submitted_at":"2023-12-02T21:57:44Z","title":"Strategic Data Revocation in Federated Unlearning","version":2},"cited_work":{"arxiv_id":"2312.01235","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.01235","snapshot_observed_at":"2026-08-11T20:44:15.065619Z","title":"Strategic Data Revocation in Federated Unlearning","venue":"cs.GT","work_id":"cc554da5-2dbd-4f9b-be46-0eb2f3f4854d","year":2023},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.963464Z"},"links":{"cited_paper":"/paper/2312.01235","citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:73b249aebb73ca8b25e85857c944bce464edb53a77aa413ad5a53118da75bd2a","observation_id":"f5865211-c00e-417f-98ca-5850ab0360a4","resolution":{"observed_at":"2026-08-11T20:44:15.073931Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.968942Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.968942Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:ade11d8f2eddb316e954a02a660b6ee1099d0129065b64d00ee6b1959a466ae0","observation_id":"e9147450-f388-4844-99c7-313845833777","resolution":{"observed_at":"2026-08-11T20:44:14.968942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.974435Z","title":"Becker and R","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.974435Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:b7d02fd96d6cec9830dd5819a296902fcaa7bb97a07c3e84f5c0133072e4599a","observation_id":"49426451-eb98-45bc-90c0-8b35f08c6742","resolution":{"observed_at":"2026-08-11T20:44:14.974435Z","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":"2026-08-11T20:44:15.269206Z","title":"Acquire valued shoppers challenge,","venue":null,"work_id":"42a13a14-99be-4b9c-b76c-838e57d58b9b","year":2014},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.979879Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:241f95a4ecb5af88ec3cb3b49c9273b564aa26ba711eb6f2e250c8fcb122b208","observation_id":"5473b50d-e603-4ca9-8827-f35b8f6c5cd6","resolution":{"observed_at":"2026-08-11T20:44:15.275404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.985434Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.985434Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:58a271e3c467756133cced98782a2c7a5e91f1e2dea32fa08b4af2e77c24de4c","observation_id":"26ee0f61-0583-4211-b85c-1f4c0cb2d3bc","resolution":{"observed_at":"2026-08-11T20:44:14.985434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:44:14.990803Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T20:44:14.990803Z"},"links":{"citing_paper":"/paper/2412.05529"},"observation_digest":"sha256:3c197c594072b0fce14e23484067456b21535bd7cf55e5fd4c74d2a085e01164","observation_id":"6ffee009-8733-4d2b-83db-49c5ea9411ce","resolution":{"observed_at":"2026-08-11T20:44:14.990803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.05529","last_updated":"2024-12-07T04:07:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T20:35:47.304201Z","submitted_at":"2024-12-07T04:07:40Z","title":"Upcycling Noise for Federated Unlearning"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":1,"verified_fuzzy":15},"total_outbound_references":39},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2412.05529."}