{"as_of":"2026-08-13T08:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:239efa08d1f8e5611562c3501d20b0dea4a7ed93210785cc2548af436aec1a9d","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T13:11:06.158140Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"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/2412.13466/citation-record","integrity":"/paper/2412.13466/integrity","json":"/paper/2412.13466/citation-record.json","paper":"/paper/2412.13466"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:11:05.750468Z","title":"Communication- efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.750468Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:c84aaa6d3ca64f5628c08de3efc36ec96ee79f563e7ad9c8e8ea350cd8022ada","observation_id":"df342aaa-947a-4ff3-ade8-820f7105dc94","resolution":{"observed_at":"2026-08-11T13:11:05.750468Z","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":"2026-08-11T13:11:07.420473Z","title":"A survey on federated learning.Knowledge- Based Systems, 216:106775, 2021","venue":null,"work_id":"dbc43767-ddd2-4c33-92ac-f016425ff00d","year":2021},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.761428Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:5652464342bd801e19f65387e59b1d8e14065105d76d6cbfad7d728c65f51b71","observation_id":"058b2a1b-1a5f-4795-85b5-35784fdeb8cf","resolution":{"observed_at":"2026-08-11T13:11:07.433772Z","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":"2026-08-11T13:11:07.398515Z","title":"A survey on federated unlearning: Challenges, methods, and future directions","venue":null,"work_id":"abfa61fa-67c9-4c5b-b200-20555a33fbb9","year":2023},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.771882Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:427f8081d3506865a0c9468f2b6ceb9870d2b09658dcce0ac256c809cc4916fa","observation_id":"eaa2787d-d08b-4bfa-9e43-e7c484c2e635","resolution":{"observed_at":"2026-08-11T13:11:07.404953Z","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":"2401.05146","last_updated":"2024-11-05T13:47:50Z","snapshot_observed_at":"2026-08-13T04:45:17.813380Z","submitted_at":"2024-01-10T13:26:19Z","title":"Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics","version":3},"cited_work":{"arxiv_id":"2401.05146","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.05146","snapshot_observed_at":"2026-08-11T13:11:06.472656Z","title":"Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics","venue":"cs.LG","work_id":"d032abce-a363-4782-87be-0797d2e0de5e","year":2024},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.778519Z"},"links":{"cited_paper":"/paper/2401.05146","citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:c82ed29933d5e1feb2d7481a1b7160eb218760443a8ce07986e9d7996ef305fb","observation_id":"7131dc2e-5829-43ed-af5f-97ac84ba574d","resolution":{"observed_at":"2026-08-11T13:11:06.491280Z","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":{"arxiv_id":"2403.02437","last_updated":"2025-04-07T19:55:57Z","snapshot_observed_at":"2026-08-13T04:03:39.287770Z","submitted_at":"2024-03-04T19:35:08Z","title":"A Survey on Federated Unlearning: Challenges and Opportunities","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02437","snapshot_observed_at":"2026-08-11T13:11:05.789169Z","title":"SoK: Challenges and opportunities in federated unlearning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.789169Z"},"links":{"cited_paper":"/paper/2403.02437","citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:d931c6951e1e5126d310e99019d8c6de4dd0e0003353271ffefcc5baf44f1957","observation_id":"882e7331-2901-4bdc-9029-18c91b6aa21d","resolution":{"observed_at":"2026-08-11T13:11:05.789169Z","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":"2026-08-11T13:11:07.365131Z","title":"Federated unlearning and its privacy threats","venue":null,"work_id":"090bb9b8-fac6-43b0-b72f-1ea28dc80add","year":2023},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.811895Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:7a88e11af6e1424e94794317112fe90426c9e33d39f1a426e0c04e78dcc75372","observation_id":"97b00df8-53ed-4ad8-a8fa-7700568fd41f","resolution":{"observed_at":"2026-08-11T13:11:07.379729Z","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":"2026-08-11T13:11:07.338050Z","title":"Modeling global distribution for federated learning with label distribution skew","venue":null,"work_id":"84e3cb03-f1ee-45ce-8d9f-fb8b8bfcc8ba","year":2023},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.823893Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:8845d1a80ceafe7232847bec362880eca2e2e0bc41637e1b368dbea3df0b76be","observation_id":"00496eeb-bfd6-45ef-84fb-1e85916302af","resolution":{"observed_at":"2026-08-11T13:11:07.346290Z","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":"2026-08-11T13:11:07.305547Z","title":"Federated learning with label distribution skew via logits calibration","venue":null,"work_id":"5ce631e5-af4a-4b1c-b0b2-07d74073c543","year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.835015Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:3bc1038adc36f3b852e3059d6e31b535ddfff2756896146254de6ddcaf5675b1","observation_id":"128163b1-c905-42a4-976c-ff3bde52a871","resolution":{"observed_at":"2026-08-11T13:11:07.317576Z","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":"2026-08-11T13:11:07.273568Z","title":"Fedrs: Federated learning with restricted softmax for label distribution non-iid data","venue":null,"work_id":"9f6d6e10-f62d-44da-a925-08741530e671","year":2021},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.847390Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:6ed53b40de9b27f1f042ef466993baafffec619c0629eaa61b58e2e7cd65f426","observation_id":"4a3fe97f-71eb-4481-af92-f4ee5b936e0f","resolution":{"observed_at":"2026-08-11T13:11:07.282499Z","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":"2311.15603","last_updated":"2024-12-06T13:11:19Z","snapshot_observed_at":"2026-08-13T05:17:18.555794Z","submitted_at":"2023-11-27T07:53:44Z","title":"QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation","version":2},"cited_work":{"arxiv_id":"2311.15603","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.15603","snapshot_observed_at":"2026-08-11T13:11:06.393020Z","title":"QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation","venue":"cs.LG","work_id":"76480122-8e4e-4546-84aa-980194de82ca","year":2023},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.857541Z"},"links":{"cited_paper":"/paper/2311.15603","citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:59b23410c490f04d3ca3f67d4fbba464ed6679ecee362204593fcd28ad1b5040","observation_id":"191812c5-fa64-45c0-8a38-6c8cb27b9ec9","resolution":{"observed_at":"2026-08-11T13:11:06.403723Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:11:07.247575Z","title":"Deepsmote: Fusing deep learning and smote for imbalanced data","venue":null,"work_id":"147df456-cab0-4433-aa3d-511612c05a64","year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.865400Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:343f7392f8b1992b4898a954a6b4694d8e5850b091a6f83594700376a8b41525","observation_id":"2331dda3-6168-48d8-acf8-bf9faac5de5d","resolution":{"observed_at":"2026-08-11T13:11:07.253015Z","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":"2026-08-11T13:11:07.203641Z","title":"The eu general data protection regulation (gdpr).A Practical Guide, 1st Ed., Cham: Springer International Publishing, 10(3152676):10–5555, 2017","venue":null,"work_id":"b268809e-986d-4a9b-8cb5-555ca00a68c5","year":2017},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.873162Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:0c6029267be1dfbd77a7221f37e494d8a0a90509e8a07172c92b4458b0533e92","observation_id":"63b1a850-7116-4fbb-b8aa-1fa091b27cd2","resolution":{"observed_at":"2026-08-11T13:11:07.219928Z","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":"2026-08-11T13:11:07.180602Z","title":"The california consumer privacy act of 2018","venue":null,"work_id":"546eb95c-ab28-488d-bd5e-7be7c69d589d","year":2018},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.883900Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:d2f2b066dd938fff978a977cb7684394a8878f4cab0d225fa022403606e5d38d","observation_id":"7e44bfcc-6b5d-4ce9-9159-d8d7bb94714c","resolution":{"observed_at":"2026-08-11T13:11:07.187099Z","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":"2026-08-11T13:11:07.152756Z","title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining","venue":null,"work_id":"c5ce22b4-fa0c-447a-b0ed-22f4a51174e2","year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.896835Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:27a7ebb97b7e0c1a9dccf38c0932babf665174266bb2ecf492955e63aafe4c18","observation_id":"254d52ec-59c7-4b23-a6bf-4744845e4c8f","resolution":{"observed_at":"2026-08-11T13:11:07.163609Z","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":"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":"2026-08-11T13:11:05.908451Z","title":"Federated unlearning: How to efficiently erase a client in fl? arXiv preprint arXiv:2207.05521, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.908451Z"},"links":{"cited_paper":"/paper/2207.05521","citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:f24f68bcb4707a56fd4366e619420a1248b730307846f50bd39f905f0c46180e","observation_id":"687a0534-cb2b-43b9-b208-38c14cc3de07","resolution":{"observed_at":"2026-08-11T13:11:05.908451Z","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":"2026-08-11T13:11:07.111111Z","title":"Federated unlearning: Guarantee the right of clients to forget","venue":null,"work_id":"2fb7d394-7a72-4375-9848-65f76cca92ba","year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.915352Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:ff45a0b65ceab673af5b4dc49b2f1a720ced65b30a58efd6e33634fb22edc177","observation_id":"3b7bc3e2-8289-40a2-957e-1dafe4ecebcb","resolution":{"observed_at":"2026-08-11T13:11:07.128060Z","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":"2003.10933","last_updated":"2021-08-02T09:06:41Z","snapshot_observed_at":"2026-07-06T09:07:01.613811Z","submitted_at":"2020-03-24T15:46:38Z","title":"Learn to Forget: Machine Unlearning via Neuron Masking","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.10933","snapshot_observed_at":"2026-08-11T13:11:05.927348Z","title":"Learn to forget: User-level memorization elimination in federated learning","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.927348Z"},"links":{"cited_paper":"/paper/2003.10933","citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:e569b6c00896fccd8cf0744d32ce5812863b326e05eb7b246f148042c44b8dd5","observation_id":"75d79f22-d787-4a6c-9fde-d78ece1f98d4","resolution":{"observed_at":"2026-08-11T13:11:05.927348Z","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":"2026-08-11T13:11:07.087188Z","title":"Exact-fun: An exact and efficient federated unlearning approach","venue":null,"work_id":"c6afe89d-ea47-4cf1-ba41-a9a93a0f255d","year":2023},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.938635Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:73ea92d7c71db00f362bb5a9497c97d70dd44579d9b680397a5f21bd20f34b33","observation_id":"99243288-9ee9-4e1e-a261-c2b7bf0e07cd","resolution":{"observed_at":"2026-08-11T13:11:07.094016Z","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":"2026-08-11T13:11:07.063367Z","title":"Forget-svgd: Particle-based bayesian federated unlearning","venue":null,"work_id":"e3cf949a-4d87-4c28-bacb-31038df7bc35","year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.944724Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:0cbb27c18aac98a6a9cb087ec5f76a45ead76f4649ec4697d505dce9ecd6b662","observation_id":"42a17178-36ce-44c0-8805-540c8841f588","resolution":{"observed_at":"2026-08-11T13:11:07.069610Z","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":"2026-08-11T13:11:07.026699Z","title":"Fedrecovery: Differentially private machine unlearning for federated learning frameworks","venue":null,"work_id":"a82b47fb-216c-431b-b68d-4ad0e2dd775b","year":2023},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.953859Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:201a420cee7093fce823d92164a2f65f70d52433c69652cc7f4dbef271662314","observation_id":"a6989471-3d30-4b8c-9164-8beb4c6ed211","resolution":{"observed_at":"2026-08-11T13:11:07.036749Z","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":"2026-08-11T13:11:06.987897Z","title":"Verifi: Towards verifiable federated unlearning","venue":null,"work_id":"6560d467-9016-4303-80e1-15956263dfd9","year":2024},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.961825Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:b284e30d9b7624852fae8b5204cdd753a07c5015642e5b5db7b90bcf653ed7f9","observation_id":"5b429a33-1758-45e7-8e2a-c2ced7e053e8","resolution":{"observed_at":"2026-08-11T13:11:06.997197Z","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":"2026-08-11T13:11:05.972559Z","title":"Sifu: Sequential informed federated unlearning for efficient and provable client unlearning in federated optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.972559Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:474f9960f0038b8d218489b868eae627a4da13b6a98ec699349d10f098e44e46","observation_id":"07bdb259-f218-48a5-9303-30397afefc0f","resolution":{"observed_at":"2026-08-11T13:11:05.972559Z","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":"2026-08-11T13:11:05.980385Z","title":"Federated unlearning via class-discriminative pruning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.980385Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:a14cc609bf10de80b827460a7da6045980a7bfabb7e6c05baef6053a0763de84","observation_id":"0281922a-f8f2-493a-a729-1d5fbc96debb","resolution":{"observed_at":"2026-08-11T13:11:05.980385Z","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":"2026-08-11T13:11:06.912497Z","title":"A state-of-the-art survey on solving non-iid data in federated learning","venue":null,"work_id":"5386f6cf-ed7f-40bc-93c1-579a1d5b6cf3","year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.990189Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:d6f4032ea0693722d1b847a7f2c43616705db7a0a44ab87064ca3c5d5bf3e227","observation_id":"9f36a7ea-a379-4309-995b-bfb3d36ccd0b","resolution":{"observed_at":"2026-08-11T13:11:06.922816Z","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":"2026-08-11T13:11:05.998941Z","title":"Federated learning on non-iid data silos: An experimental study","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:05.998941Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:d5ef6ec5c586c89db3fc7e0b0c69f2ac24a500735fa528f8aa9ca396f5827381","observation_id":"0c67964a-9659-40a4-bf82-3895f78fe4f7","resolution":{"observed_at":"2026-08-11T13:11:05.998941Z","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":"2026-08-11T13:11:06.866873Z","title":"Federated learning with non-iid data: A survey","venue":null,"work_id":"259807d3-b766-481a-92ad-8e1f550a2933","year":2024},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.007354Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:2bb2b94a04a2abdb5cff20b54bdcf732df2e1ff4013466926efe47b811a47eaf","observation_id":"3233527f-ba26-4d87-bc16-432468404048","resolution":{"observed_at":"2026-08-11T13:11:06.873548Z","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":"2026-08-11T13:11:06.832977Z","title":"Robust and communication- efficient federated learning from non-iid data","venue":null,"work_id":"6dfc856a-8b7d-46a4-b275-daf1d0d3ead2","year":2019},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.016752Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:f75b250bb76cc6cf2009f1a00c971ab0c7114e48cd9f2d5502d9e9135da62c97","observation_id":"f504bf26-deeb-4959-93dd-3dc90b3f6529","resolution":{"observed_at":"2026-08-11T13:11:06.846304Z","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":"2026-08-11T13:11:06.023709Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.023709Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:b325c5abbed5f0f53522196dcb67ced27c0ed27e8aafec7077c4c8904b5ed011","observation_id":"bd3c3e7f-c6c8-45e4-8e31-992e59da55e9","resolution":{"observed_at":"2026-08-11T13:11:06.023709Z","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":"2026-08-11T13:11:06.035700Z","title":"Model-contrastive federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.035700Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:c9ad02b6e82e77b88f7fba6895b04fb9d37f554e88329fec06fdaffaf0fc2821","observation_id":"19cbb49a-a998-4037-9003-d371894d88ba","resolution":{"observed_at":"2026-08-11T13:11:06.035700Z","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":"2026-08-11T13:11:06.769683Z","title":"Data distribution-aware online client selection algorithm for federated learning in heterogeneous networks","venue":null,"work_id":"1eee5c83-c0fd-427a-8d38-8a1d4f30a1f2","year":2022},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.042866Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:eb2efe72b0e1dfce3a9cc121425ed28cd69146450ff9467f75ff1ab6467870c5","observation_id":"6576f15f-dcc6-4d09-9106-6a3fe409cf1e","resolution":{"observed_at":"2026-08-11T13:11:06.778478Z","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":"2026-08-11T13:11:06.748547Z","title":"Adaptive federated learning on non-iid data with resource constraint","venue":null,"work_id":"ad6a5c96-d3f9-4d99-bc5d-039fce5c5fcf","year":2021},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.051529Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:455e4ae69096438019221110bcd130a967e018beb6f1950aeed7fa5d64d8fc3c","observation_id":"55ac99d0-3d60-452c-b008-a8bbdf452c17","resolution":{"observed_at":"2026-08-11T13:11:06.754585Z","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":"2026-08-11T13:11:06.723308Z","title":"Federated learning enabled hotel customer classification towards imbalanced data","venue":null,"work_id":"3ac76e38-439f-458d-b2c8-113b8ec3505c","year":2024},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.066011Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:2a25c4f81cf5902c444cbaff1c1f7262b50d9398fae4d62f7f77026864d5ced4","observation_id":"d6dea941-b5d7-4132-aa81-a2af5e12a116","resolution":{"observed_at":"2026-08-11T13:11:06.731038Z","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":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-07-06T06:42:35.645776Z","submitted_at":"2018-06-02T04:45:58Z","title":"Federated Learning with Non-IID Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00582","snapshot_observed_at":"2026-08-11T13:11:06.078743Z","title":"Federated learning with non-iid data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.078743Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:7c76bd726281501b2c507a45f1fd11624592bb295fcd3b78d70c0a93c6fa9121","observation_id":"662364df-21da-46fb-a808-6ccdaac8f629","resolution":{"observed_at":"2026-08-11T13:11:06.078743Z","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":"2026-08-11T13:11:06.699015Z","title":"Distillation-based semi-supervised federated learning for communication-efficient collaborative training with non-iid private data","venue":null,"work_id":"d310fe70-d35f-49d3-9061-47e3f9d0780f","year":2023},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.087114Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:0ae2c962f1fa5bb90df2122c41bfe0d823d1a73531d4abcd5a700731af57ffcc","observation_id":"8de86cfc-7c98-477b-b5e5-d33e2f476051","resolution":{"observed_at":"2026-08-11T13:11:06.709819Z","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":"2026-08-11T13:11:06.676226Z","title":"Towards asynchronous federated learning based threat detection: A dc-adam approach","venue":null,"work_id":"47e19166-118c-4921-a9c0-ef6aecd48cbf","year":2021},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.093870Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:494a15b768155088d05d923890a725efbeb9566f3504064255026257bfaf788b","observation_id":"7d5856df-3a45-4f9f-8aff-8c51924c7a68","resolution":{"observed_at":"2026-08-11T13:11:06.683068Z","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":"2026-08-11T13:11:06.655877Z","title":"Dynamic margin for federated learning with imbalanced data","venue":null,"work_id":"a0663699-b598-436e-bd68-57babdd4d553","year":2021},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.104084Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:5a78b36722ca43fb1a8045687f16c37966a9f5f80a3f77ba78f815584b66dfed","observation_id":"484696f2-fe50-4c5a-ac54-bf4d436b7527","resolution":{"observed_at":"2026-08-11T13:11:06.661770Z","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":"2026-08-11T13:11:06.627631Z","title":"Lof: identifying density-based local outliers","venue":null,"work_id":"4e962704-7869-4fe8-998a-feacddb7b544","year":2000},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.110978Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:b36c00837b26e17c75f59325231f27e75d13bdb86b62646980ba4cfbcab5b0e6","observation_id":"b7c0d537-1cbf-422e-8ff0-69bd2d7a4171","resolution":{"observed_at":"2026-08-11T13:11:06.635878Z","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":"2026-08-11T13:11:06.119421Z","title":"Anomaly detection: A survey","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.119421Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:cc3fb646357a6ffefb20de7585e93a6ced20c43fd642e599e06279c8c83e4848","observation_id":"5d07d23f-93e8-4aad-a2d8-33adac93ae3f","resolution":{"observed_at":"2026-08-11T13:11:06.119421Z","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":"2026-08-11T13:11:06.580228Z","title":"Loci: Fast outlier detection using the local correlation integral","venue":null,"work_id":"e006097a-b92e-4963-a66d-60a73819003e","year":2003},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.133546Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:6c86c24f4b588190656b4b8b8fdcfbb4fcef43f66eb493d32f5a989714b2c7d4","observation_id":"21e213b0-845f-42e6-b86a-e7ff552dd60d","resolution":{"observed_at":"2026-08-11T13:11:06.589877Z","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":"2026-08-11T13:11:06.140190Z","title":"The mnist database of handwritten digit images for machine learning research [best of the web]","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.140190Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:4489873faa1a2a06ed160987e87e94747f0811ef6911aae584ba734107ab1c75","observation_id":"58b99f3d-6353-4218-b9bc-ac2cfea87141","resolution":{"observed_at":"2026-08-11T13:11:06.140190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","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":"2026-08-11T13:11:06.149440Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.149440Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:4005f2b356d9e2e462d4a64d42be5019398fb3ba8eaf3d9d0bc8243c46ff1078","observation_id":"7cda0168-3ed3-438c-a7f2-8f1d37310eba","resolution":{"observed_at":"2026-08-11T13:11:06.149440Z","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":"2026-08-11T13:11:06.518155Z","title":null,"venue":null,"work_id":"77008400-f426-43fb-bcfe-b4ea968eb5ca","year":1994},"citing_paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T13:11:06.158140Z"},"links":{"citing_paper":"/paper/2412.13466"},"observation_digest":"sha256:ffe0f55123499ee839fa4ccd94f664cc246532cc7130b813604392409bcf623f","observation_id":"d7f9b5d9-75cf-43a4-9f2f-6ef3befbe6dd","resolution":{"observed_at":"2026-08-11T13:11:06.525707Z","resolver_source":"raw_fallback","status":"unresolved"},"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"}}],"paper":{"arxiv_id":"2412.13466","last_updated":"2024-12-20T11:03:45Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T13:04:07.795215Z","submitted_at":"2024-12-18T03:25:11Z","title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":2,"verified_fuzzy":26},"total_outbound_references":42},"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 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2412.13466."}