{"as_of":"2026-08-09T00:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:36ffb0108e5c125b7968ba584696d2adc48d2ca71203f3e197a465d3c7ae0431","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":"2026-08-04T16:44:27.686079Z","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":"2026-08-08T06:32:00.761636+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/2509.11974/citation-record","integrity":"/paper/2509.11974/integrity","json":"/paper/2509.11974/citation-record.json","paper":"/paper/2509.11974"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T16:44:24.356871Z","title":"Baffle: Backdoor detection via feedback-based federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.356871Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:a39864217ce9750b324d3538106443f6cf5f90828801e5f8f0f306dce5393d31","observation_id":"b1ddf1f2-b099-48c0-bbb3-86e80e9416a2","resolution":{"observed_at":"2026-08-04T16:44:24.356871Z","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":"2026-08-04T16:44:24.412845Z","title":"How to backdoor federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.412845Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:d27445221fdd0c4d262b586a1f81af9caa40da06c94a847ff47e880acbcb9e7a","observation_id":"c9da7df6-a00e-4f21-ab35-2bf7b27a9760","resolution":{"observed_at":"2026-08-04T16:44:24.412845Z","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":"2026-08-04T16:44:24.488746Z","title":"Reconstructing training data with informed adversaries","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.488746Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:c07427fe7e65a180824bea4cc3ed4ddf4add03558654d99625eb1f51a8e9e770","observation_id":"0dfdc32c-336a-4eb2-95e4-c2fb2fc81021","resolution":{"observed_at":"2026-08-04T16:44:24.488746Z","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":"2026-08-04T16:44:24.533283Z","title":"Reconstruction attacks on machine unlearning: Simple models are vulnerable.Advances in Neural Information Processing Systems, 37:104995–105016, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.533283Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:af7b0311e05a7128277517fe24dad55b171ae4bd5183f87c38ce5cd96c2ce63e","observation_id":"aaa62736-c0c5-4727-8fce-26a4705e81a4","resolution":{"observed_at":"2026-08-04T16:44:24.533283Z","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":"2026-08-04T16:44:24.597537Z","title":"Poisoning attacks against support vector machines","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.597537Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:28511e0d64172a0983fb8d56cbb341eec5b7ed9ddb613c11c7c9ea24a4a55125","observation_id":"85d596fd-78b9-448e-b49b-a8820cfd5412","resolution":{"observed_at":"2026-08-04T16:44:24.597537Z","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":"2026-08-04T16:44:24.658937Z","title":"Machine learning with adver- saries: Byzantine tolerant gradient descent","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.658937Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:0aa6e2ceca5e51fa526280dc3151bf537b22f8d65ff47b5bed3e17dde4f4a3a0","observation_id":"47b73e4d-c7d6-44c3-84e9-46a3707317cb","resolution":{"observed_at":"2026-08-04T16:44:24.658937Z","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":"2026-08-04T16:44:24.720242Z","title":"Federated learning attacks and defenses: A survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.720242Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:ded838d47d4ee0abbbd8fbeba3e91cc9cc70f8187d465815ed99b8851939f0b3","observation_id":"2c7610e2-c6b7-4e58-853c-19f982af5bad","resolution":{"observed_at":"2026-08-04T16:44:24.720242Z","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":"2026-08-04T16:44:24.777357Z","title":"The mnist database of handwritten digit images for machine learning research [best of the web].IEEE signal processing magazine, 29(6):141–142, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.777357Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:1718019b130ab4a28a6950de14577f6ca526a4c14f44c96511033df8fc57174c","observation_id":"ad02c309-f576-4710-989d-6f63cec1c178","resolution":{"observed_at":"2026-08-04T16:44:24.777357Z","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":"2026-08-04T16:44:24.868196Z","title":"Local model poisoning attacks to Byzantine-Robust federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.868196Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:c8f9e2b915e1121c21bcb2eaadb7a75b221520ee6e7cd74d2376879b62f3a778","observation_id":"5b80a8dc-0737-470c-9b46-e000c55ae549","resolution":{"observed_at":"2026-08-04T16:44:24.868196Z","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":"2026-08-04T16:44:24.965785Z","title":"Model inversion attacks that exploit confidence infor- mation and basic countermeasures","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:24.965785Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:788882fc639094cea14e950d078377bb5147511080b2ada8e7dcb8fcbedd071c","observation_id":"8d11c0e2-a2f5-4495-b060-2e890fafe40c","resolution":{"observed_at":"2026-08-04T16:44:24.965785Z","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":"2026-08-04T16:44:25.034138Z","title":"A novel data poisoning attack in federated learning based on inverted loss function.Computers & Security, 130:103270, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.034138Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:c5f87176c4f7e08ef87c03aeb60a27add86724ce3cc958268240fb40fd6297a1","observation_id":"ec5d26cb-3ae3-4681-8daa-8630f37888b1","resolution":{"observed_at":"2026-08-04T16:44:25.034138Z","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":"2026-08-04T16:44:25.153404Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.153404Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:05e944e9638debccf0887dac44f75ef613e96caa055a63d302b7a05aa3c55bec","observation_id":"3185a756-0949-4746-bb08-0c2b55b0e660","resolution":{"observed_at":"2026-08-04T16:44:25.153404Z","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":"2026-08-04T16:44:25.226812Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.226812Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:966dfd072179adcf20ac8ce47564b1b65bf530e2231dc66bf1ab9b5286aaf7c9","observation_id":"c6b2399e-9bd6-492b-9d86-01ddd030fd88","resolution":{"observed_at":"2026-08-04T16:44:25.226812Z","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":"2026-08-04T16:44:25.273175Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.273175Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:ae2c7a1d65c2fe928a856e0707e1be2d9879cfc33fcfb29578e6e9ccfc8b3fe9","observation_id":"66004497-8def-4f5d-aa36-d1c8ff2c5d6d","resolution":{"observed_at":"2026-08-04T16:44:25.273175Z","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":"2026-08-04T16:44:25.344840Z","title":"Loadaboost: Loss-based adaboost federated machine learning with reduced computational complexity on iid and non-iid intensive care data.Plos one, 15(4):e0230706, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.344840Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:7869cddee567b9dd28c09480adc7149e3feb2cfd3e80961c3065dbb747c64821","observation_id":"652ba506-895d-4af8-9d6c-b87b3b196be6","resolution":{"observed_at":"2026-08-04T16:44:25.344840Z","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":"2026-08-04T16:44:25.418980Z","title":"Advances and open problems in federated learning.Foundations and trends® in machine learning, 14(1–2):1–210, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.418980Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:a9b1220f8dd5c5a43308e3615bb59b3e33626ef0fc1e5918027102575c02baf8","observation_id":"dcb4696e-306c-40dd-b191-912707932ea2","resolution":{"observed_at":"2026-08-04T16:44:25.418980Z","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":"2026-08-04T16:44:25.465675Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.465675Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:172e5c57c1d0b02dc7692c232ce7c995b8c64167669256d24ee2a59025b5ea29","observation_id":"04e1260a-f441-45f8-a6f7-79659b6cd150","resolution":{"observed_at":"2026-08-04T16:44:25.465675Z","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":"2026-08-04T16:44:25.514625Z","title":"Schaefer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.514625Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:64d574652197f3a9cc1fd67c6e75ff45f5cae6dedc9c8e76ce4cb6a772a89a5a","observation_id":"9b80ed15-4625-4d2a-be78-5b64713b26b9","resolution":{"observed_at":"2026-08-04T16:44:25.514625Z","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":"2026-08-04T16:44:25.589952Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.589952Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:732238c3f193891810896e79b1aef8eb0391fba05f146e6e513dda4a1d413c2d","observation_id":"0761e092-50cd-46cf-b99a-ecb9702402e8","resolution":{"observed_at":"2026-08-04T16:44:25.589952Z","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":"2026-08-04T16:44:25.684654Z","title":"Learning multiple layers of features from tiny images.(2009), 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.684654Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:dd17bf237f0bf9e873a3afdc4ff46700007c1a4220268a00270c0ba44aae665f","observation_id":"7a23c01a-3994-47f0-8a25-146f60f2de30","resolution":{"observed_at":"2026-08-04T16:44:25.684654Z","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":"2026-08-04T16:44:25.756096Z","title":"Data poisoning attacks on factorization-based collaborative filtering.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.756096Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:e887e3f51596ab1555ed4ee7be2d953ca4365895054cd8c85aca594e2e7bec4a","observation_id":"7f0c1db1-e934-4b85-9a99-8262f9643185","resolution":{"observed_at":"2026-08-04T16:44:25.756096Z","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":"2026-08-04T16:44:25.828733Z","title":"Federated learning: Challenges, methods, and future directions.IEEE signal processing magazine, 37(3):50–60, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.828733Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:495c0d76d99b2c014b6ff886f743d081b4730cef2ab1d5d9ec91ddb6f9e5d775","observation_id":"16160177-e856-41b3-b9c8-a195e9b99715","resolution":{"observed_at":"2026-08-04T16:44:25.828733Z","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":"2026-08-04T16:44:25.898438Z","title":"A blockchain-based decentralized federated learning framework with committee consensus.IEEE Network, 35(1):234–241, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.898438Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:4ad0c12e47cfc5b030a196f515261fe18ea8ef8d07ed808a332c51f0294e91ad","observation_id":"b9ce9b48-3158-4f0f-9742-d4e74c77adad","resolution":{"observed_at":"2026-08-04T16:44:25.898438Z","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":"2026-08-04T16:44:25.994865Z","title":"On the over-memorization during natural, robust and catastrophic overfitting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:25.994865Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:8b52240c95744059c6ed335fc6edfd8ca927ce31794c99d626c905edb1ca50cc","observation_id":"b3694855-e0af-4d4b-a6c7-a3c0fcb966f6","resolution":{"observed_at":"2026-08-04T16:44:25.994865Z","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":"2026-08-04T16:44:26.097672Z","title":"Springer International Publishing, Cham, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.097672Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:d376f88dacc5dd12ec9625e00202127d834bfeeb893c0acc44200b6ef4b80bec","observation_id":"a784d84b-7721-4abf-b2db-e2dd2f2b292e","resolution":{"observed_at":"2026-08-04T16:44:26.097672Z","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":"2026-08-04T16:44:26.194887Z","title":"Communication- efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.194887Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:91bf753267360547d3a8aa3fae4043dc9111120d35c8b2d5b2f789df754e4ce2","observation_id":"85ba3964-e6e3-474c-af03-12a673ac0ce0","resolution":{"observed_at":"2026-08-04T16:44:26.194887Z","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":"2026-08-04T16:44:26.302350Z","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.302350Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:435932cbd85c7343a0fd61deddda77881c22c05191f811531fe9f4a33f2c8a7a","observation_id":"d860451f-cc8c-40ae-bc33-d385bac5af2c","resolution":{"observed_at":"2026-08-04T16:44:26.302350Z","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":"2026-08-04T16:44:26.416097Z","title":"Dataset reconstruction attack against language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.416097Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:d60f448dc5992752a54a5d2bb6e8531040a30bccfce82fb285c57c3254339dfb","observation_id":"0364b8fd-cceb-435c-bd6c-c16e3bed3772","resolution":{"observed_at":"2026-08-04T16:44:26.416097Z","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":"2026-08-04T16:44:26.496515Z","title":"Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Koneˇcný, Sanjiv Kumar, and Hugh Brendan McMahan","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.496515Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:30e2b6b0964f5c47f7203fa00e05f6346a107efef1b13db6695ab94e43d21172","observation_id":"545bc633-ddc9-447c-a42d-8e794f251603","resolution":{"observed_at":"2026-08-04T16:44:26.496515Z","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":"2026-08-04T16:44:26.604259Z","title":"Fetchsgd: Communication-efficient federated learning with sketching","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.604259Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:e77c3e4f0133ad407d9d2d5ca1dff372ea6920a9c034d9212ece418232610d83","observation_id":"74a4d7f6-2c0b-40d8-8de8-5c014d6ce422","resolution":{"observed_at":"2026-08-04T16:44:26.604259Z","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":"2026-08-04T16:44:26.696935Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.696935Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:721692ce33bad0a6f00cc1c9d9697e171f8967a6f61bcd97383a9f058f739ed8","observation_id":"d9707490-ea9d-47f1-a2bf-676f848f0677","resolution":{"observed_at":"2026-08-04T16:44:26.696935Z","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":"2026-08-04T16:44:26.752882Z","title":"Data poisoning attacks against federated learning systems","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.752882Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:eb740608cdae7643dfe72a5074fe2326d6a5e68e25e044e2cfca531285137e25","observation_id":"5f8e3db9-1b2e-40fa-8ce6-50da1715a604","resolution":{"observed_at":"2026-08-04T16:44:26.752882Z","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":"2026-08-04T16:44:26.838704Z","title":"Beyond inferring class representatives: User-level privacy leakage from federated learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.838704Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:37dfb8c5b2fb9d04f1735bd6007c2921c45dd088d725fe8848fbf9fe77889ef0","observation_id":"602e4b50-460b-4c3a-9e6b-84f6914ae097","resolution":{"observed_at":"2026-08-04T16:44:26.838704Z","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":"2026-08-04T16:44:26.917504Z","title":"Naughton","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:26.917504Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:377051682fc3590fc9b56d014c95c1aed897b0d826ac07333e6b0ebf2f072c3e","observation_id":"2710a76f-78b1-48e2-b879-70a568f76d6f","resolution":{"observed_at":"2026-08-04T16:44:26.917504Z","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":"2026-08-04T16:44:27.001357Z","title":"Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification.Scientific Data, 10(1):41, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:27.001357Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:ccacb660afc93f5eaef0c754db50c051887643fbc3bf04a4368020e4e1545966","observation_id":"12df26d2-e570-4034-bfbc-214e2c263d65","resolution":{"observed_at":"2026-08-04T16:44:27.001357Z","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":"2026-08-04T16:44:27.109418Z","title":"Robust federated learning with noisy labels.IEEE Intelligent Systems, 37(2):35–43, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:27.109418Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:0fa318fa8635b5e357a1c003b398cedf9f35d7742e83623196b4475fb237fa62","observation_id":"a1c4d22f-4830-4347-8428-326f09f15e48","resolution":{"observed_at":"2026-08-04T16:44:27.109418Z","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":"2026-08-04T16:44:27.218191Z","title":"Deep learning model inversion attacks and defenses: a comprehensive survey.Artificial Intelligence Review, 58(8):1–52, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:27.218191Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:f966dfaa8801f4cbe5b721432bab44d0976a519c011369191f11ef106ad670af","observation_id":"c216426f-4216-47b5-9cb7-c7c7cbb774cb","resolution":{"observed_at":"2026-08-04T16:44:27.218191Z","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":"2026-08-04T16:44:27.323994Z","title":"Privacy risk in machine learning: Analyzing the connection to overfitting","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:27.323994Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:a49c587c65d838c6d40f5c24443cd2004b6ea5562c2aed0a6b3965d418aadca1","observation_id":"1a65abb4-6410-4675-b9f2-60107c0568e2","resolution":{"observed_at":"2026-08-04T16:44:27.323994Z","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":"2026-08-04T16:44:27.410218Z","title":"Curse or redemption? how data heterogeneity affects the robustness of federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:27.410218Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:f93a15e14350f690f62b54ec95115a12c96b22a10540ecc0d2e91aefbd511495","observation_id":"de3f1f51-247d-43d6-a7b6-0a4a4e22c382","resolution":{"observed_at":"2026-08-04T16:44:27.410218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.11673","last_updated":"2023-03-21T08:34:23Z","snapshot_observed_at":"2026-08-03T00:40:22.757496Z","submitted_at":"2023-03-21T08:34:23Z","title":"A Survey on Class Imbalance in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.11673","snapshot_observed_at":"2026-08-04T16:44:27.497858Z","title":"A survey on class imbalance in federated learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:27.497858Z"},"links":{"cited_paper":"/paper/2303.11673","citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:ac1c580989b1fc9d06ce0b9a7addbe3837b5bccfaedf5bbdf055de3fd5f43336","observation_id":"8be0ac16-f47d-4e9e-baff-735daee0f0e5","resolution":{"observed_at":"2026-08-04T16:44:27.497858Z","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":"2026-08-04T16:44:27.570164Z","title":"Fldetector: Defending federated learning against model poisoning attacks via detecting malicious clients","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:27.570164Z"},"links":{"citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:b5c948ce853afe6dfc09f009dd638b5c07459ebc756923d8ef8fa30d5be3b89d","observation_id":"aaaf2108-cdde-4df4-a769-d029234f1df7","resolution":{"observed_at":"2026-08-04T16:44:27.570164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.17748","last_updated":"2026-06-16T19:59:45Z","snapshot_observed_at":"2026-08-07T17:51:37.422334Z","submitted_at":"2025-02-25T00:56:47Z","title":"FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.17748","snapshot_observed_at":"2026-08-04T16:44:27.686079Z","title":"Finp: Fairness-in-privacy in federated learning by addressing disparities in privacy risk.arXiv preprint arXiv:2502.17748, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T16:44:27.686079Z"},"links":{"cited_paper":"/paper/2502.17748","citing_paper":"/paper/2509.11974"},"observation_digest":"sha256:3af72f18c231b79bda9ef63d778cfb93e927dc7c1c1a2c6b32d83e18ab7b48e4","observation_id":"85464e48-e712-4bbe-bb21-0a659ec74480","resolution":{"observed_at":"2026-08-04T16:44:27.686079Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.11974","last_updated":"2026-07-27T03:49:11Z","latest_version":3,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-08T23:48:03.781837Z","submitted_at":"2025-09-15T14:23:39Z","title":"Poison to Detect: Detection of Targeted Overfitting in Federated Learning"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":42,"verified_exact":0,"verified_fuzzy":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2509.11974."}