{"as_of":"2026-08-11T22:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3529999d61f76967f63966a6833a5b6b49b7e68e487b89ad291059161689660b","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T17:51:28.728550Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.11848/citation-record","integrity":"/paper/2501.11848/integrity","json":"/paper/2501.11848/citation-record.json","paper":"/paper/2501.11848"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:51:29.536011Z","title":"Secure and efficient federated learning with provable performance guarantees via stochastic quantization,","venue":null,"work_id":"9cf1afa7-0545-4597-adfd-bb6bfdf28d17","year":2024},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.513062Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:5632c81490ec88d19d0a2adc2107630c66538f5fe85a626c2e83869da4a3e743","observation_id":"7c3a330e-409c-453e-9a0f-e821bd1d9e3b","resolution":{"observed_at":"2026-08-10T17:51:29.542299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.515900Z","title":"Towards secure and verifiable hybrid federated learning,","venue":null,"work_id":"9c502691-69ac-4ccd-925d-d4cd031212b9","year":2024},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.518755Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:a7e91b5a2dc8911b9b8b9db0ef95b3e160e5a8843388015a2680b1fc0c6dfa1f","observation_id":"42a1ffdd-4b3d-4f9f-a871-3fba46325194","resolution":{"observed_at":"2026-08-10T17:51:29.521489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.497273Z","title":"Reliable and in- terpretable personalized federated learning,","venue":null,"work_id":"0e762cbe-cd32-4b35-90d0-f9a243c21c5d","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.523859Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:3b5f775ca8817ddeaa4dc7d54738ef41127b6c6b662f7ca33a15af3c92cc6cd7","observation_id":"dcbbca1c-ed86-4cf2-ae62-2e86fb1dc9a2","resolution":{"observed_at":"2026-08-10T17:51:29.502801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.479337Z","title":"Revisiting weighted aggregation in federated learning with neural networks,","venue":null,"work_id":"aa6b3682-db77-483e-a511-2326a87d8247","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.529259Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:eb468bc4b4696772f2eb69a77acfe9e213a60b4df21b2121c9d4e99697801544","observation_id":"eff83b40-dcc4-4090-b4bd-84b97e12e74e","resolution":{"observed_at":"2026-08-10T17:51:29.484343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.459089Z","title":"Feder- ated conformal predictors for distributed uncertainty quantification,","venue":null,"work_id":"02ca3c4b-89da-4927-bcae-d601d515a205","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.534643Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:be71e312a830808b3fb16244a4152b6f933d881b9eed9e6c1d68e35a5edde36e","observation_id":"45f6af30-9b95-414a-96cb-934d3bdc3fad","resolution":{"observed_at":"2026-08-10T17:51:29.465457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.440643Z","title":"Multimodal federated learning via contrastive representation ensemble,","venue":null,"work_id":"8c3444e1-93f8-489e-8c5d-cee86158891f","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.539757Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:4a9e68ea463e9853a3588df46991044472ba15490e1ffc1507f874a22bf0b9ce","observation_id":"4c7ed5f8-2d85-444d-a30c-beb685b3a264","resolution":{"observed_at":"2026-08-10T17:51:29.446366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.545052Z","title":"The eu general data protection regu- lation (gdpr),","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.545052Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:5ea0b1d66f006e83701fa835bf8687c3762609240b536986c8ff647b15a9c698","observation_id":"31559b7b-7916-4cbf-8956-6276220bf629","resolution":{"observed_at":"2026-08-10T17:51:28.545052Z","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":"2026-08-10T17:51:29.405240Z","title":"Understanding the scope and impact of the california consumer privacy act of 2018,","venue":null,"work_id":"34999dde-74cc-45d2-9387-fa17f0ae4a11","year":2018},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.549578Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:e53179cc34ee7728bc745b1afd4a0e72dc66483c74ea592510917a1cea9ac7f6","observation_id":"35e583d5-4398-4b98-aade-e328256eec3e","resolution":{"observed_at":"2026-08-10T17:51:29.412375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.554101Z","title":"Verifi: Towards verifiable federated unlearning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.554101Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:559c27247ff9653b4f59e30293b5af52fc9ffdb5144c641119ffe47e9692d56c","observation_id":"02b4d96d-4c63-4573-9a9d-1e51f51e04ec","resolution":{"observed_at":"2026-08-10T17:51:28.554101Z","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":"2026-08-10T17:51:29.374653Z","title":"Federaser: Enabling efficient client-level data removal from federated learning models,","venue":null,"work_id":"1b39cae5-ebe6-49aa-a99b-a6ab5b8e03c8","year":2021},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.558599Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:228909197bc20a9b7e7d2b8027c670b07b21fb0012c2df59a79393cf1400b4a7","observation_id":"6b985249-a411-4737-aeda-d806b6061045","resolution":{"observed_at":"2026-08-10T17:51:29.380248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.563251Z","title":"Asynchronous federated unlearning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.563251Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:3ed6793047c6dcb5a87a2d5797675d5faf36b08fca52a8594f6378c801a16b1f","observation_id":"ed1cab67-6595-424c-ab5d-5a79fb1c3a40","resolution":{"observed_at":"2026-08-10T17:51:28.563251Z","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":"2026-08-10T17:51:29.343620Z","title":"Fast federated machine unlearning with nonlinear functional theory,","venue":null,"work_id":"112e746d-11b0-4296-a1ea-0c6b542d248c","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.567668Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:9345fc8dd53e160d1d9a2ead8b20e8ee6c01423052ab9ce416f784d42003f5d6","observation_id":"8549fc27-1599-4a59-93a9-b9eea65183c8","resolution":{"observed_at":"2026-08-10T17:51:29.348398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.328056Z","title":"Fedrecovery: Differentially private machine unlearning for federated learning frame- works,","venue":null,"work_id":"d4c39c5d-1259-4469-8b90-e4afbac91c0f","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.572307Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:06211b4d233739c268b66debb07d8be26ec744ba5f26eb27a75118a66fd00a38","observation_id":"c015681d-c523-42f4-b5bb-b034b171da64","resolution":{"observed_at":"2026-08-10T17:51:29.332962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.311734Z","title":"Understanding black-box predictions via influence functions,","venue":null,"work_id":"bb674a0b-80d6-49d3-964e-d6386d62323a","year":2017},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.576796Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:b603268048b0d7c8dd36e245b919604013948b659819e23dbb4573ad00e0d8e4","observation_id":"6c4677ad-ac7a-4645-8a42-db6a6b0e0a43","resolution":{"observed_at":"2026-08-10T17:51:29.316955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12709","last_updated":"2022-05-25T12:20:02Z","snapshot_observed_at":"2026-07-06T13:13:48.138379Z","submitted_at":"2022-05-25T12:20:02Z","title":"VeriFi: Towards Verifiable Federated Unlearning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.12709","snapshot_observed_at":"2026-08-10T17:51:28.581312Z","title":"Ver- ifi: Towards verifiable federated unlearning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.581312Z"},"links":{"cited_paper":"/paper/2205.12709","citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:7c2b3c998770e1c1f00c191ba0377433c6f1c1fbade7181629c3b595831ffe38","observation_id":"84173715-e060-4fc9-94e3-a649cfabfa7f","resolution":{"observed_at":"2026-08-10T17:51:28.581312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.09441","last_updated":"2022-01-24T03:56:20Z","snapshot_observed_at":"2026-08-09T04:32:24.004839Z","submitted_at":"2022-01-24T03:56:20Z","title":"Federated Unlearning with Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.09441","snapshot_observed_at":"2026-08-10T17:51:28.586716Z","title":"Federated unlearning with knowledge distillation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.586716Z"},"links":{"cited_paper":"/paper/2201.09441","citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:e77d29d528e60174ada8da771fa04e7ca89cf43152165560369e39fc45f60f39","observation_id":"45fd55e1-3aaf-45c0-b542-237365f28f5f","resolution":{"observed_at":"2026-08-10T17:51:28.586716Z","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":"2026-08-10T17:51:29.295462Z","title":"Federated unlearning via class- discriminative pruning,","venue":null,"work_id":"363ec137-3f4a-4c4f-935d-faa9f32dfa35","year":2022},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.592127Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:6acb6ea1136aabc9264a948843967e05ac4a9982113462b6b1a37e858a000239","observation_id":"0d50959b-0e43-4b4b-bfbb-90fa43b61eb9","resolution":{"observed_at":"2026-08-10T17:51:29.300452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.279273Z","title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining,","venue":null,"work_id":"bf99b1eb-f68e-4f72-bd20-2a3f35e2eeef","year":2022},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.597167Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:f0b29c223e184a3e26a4bbb03684a7348a9175471c4a65a35d61bb5dc35bccbc","observation_id":"3c678194-aae7-48d6-8a26-1a190ba0f08d","resolution":{"observed_at":"2026-08-10T17:51:29.284482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.261695Z","title":"Hidden poison: Machine unlearning enables camouflaged poisoning attacks,","venue":null,"work_id":"ec06fd13-5ca7-4cee-ac92-7f84f1fa4a40","year":2022},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.602653Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:92c4e93b7890dfa195ae88a5e1930c02848b22b31ce5cc9ddef7178af635be84","observation_id":"a57cc11a-8c51-47c3-b313-241062042862","resolution":{"observed_at":"2026-08-10T17:51:29.267047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.244073Z","title":"Towards understanding and enhancing robustness of deep learning models against malicious unlearning attacks,","venue":null,"work_id":"fc46732b-d1b2-47bb-aaad-6f816a2241ac","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.607714Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:c0d8e82aa2d611773f48749b5557284c9e2e837ee2ec8f6dd284f216efc1cf9b","observation_id":"c6eb1dd0-434c-4da7-b757-b3bd6cda9e9d","resolution":{"observed_at":"2026-08-10T17:51:29.249794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.227643Z","title":"Static and sequential malicious attacks in the context of selective forgetting,","venue":null,"work_id":"fa654150-28d8-49ef-90fe-bd1dc04cd73f","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.612662Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:25c4a62ebe33cb353e6fbd0491ab966325d8a932f20c52666625a520d5fbf975","observation_id":"df5cded7-810a-4e8c-a749-bf0056e0bc3a","resolution":{"observed_at":"2026-08-10T17:51:29.232988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.211776Z","title":"A duty to forget, a right to be assured? exposing vulnerabilities in machine unlearning services,","venue":null,"work_id":"4b5eaad8-d22c-4203-9e08-1219ca817b63","year":2024},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.617347Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:204b7bb8d8fb0d307d202d1e70451ae269ce37c3d0ae546469eb29417ea516c6","observation_id":"2dbc439f-05a5-4e64-9cd4-a40138e3254f","resolution":{"observed_at":"2026-08-10T17:51:29.216585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.195272Z","title":"Resolving training biases via influence-based data relabeling,","venue":null,"work_id":"450ef555-b41a-49d5-99b5-79034f2141e3","year":2021},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.621896Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:0cc008e02c4cfd7f2f6812b24ae4483ed400a47918f010ab2c4a5ccd0f86be6b","observation_id":"98693db6-d4d4-4f9f-b475-90ffbec3d9a1","resolution":{"observed_at":"2026-08-10T17:51:29.200863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.179192Z","title":"Regularizing second-order influences for continual learning,","venue":null,"work_id":"8fb46801-3cc9-4ce8-a0e7-ba257d6a0552","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.626358Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:21f1a236bc621f7a0751e54d57bfd173bb9e26ad00dcfac78da71c9615424d9e","observation_id":"875151f9-b209-4e10-9040-86c0a7899fcb","resolution":{"observed_at":"2026-08-10T17:51:29.184373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.163783Z","title":"Understanding influence functions and data models via harmonic analysis,","venue":null,"work_id":"8e5ad586-e749-4ae8-97f5-2a8ec194c63e","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.630788Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:88d83f03f16f3684d7b73d68c0a353ebe21a0e109bb872f66cef42a25b2c9a5a","observation_id":"03b48881-1d5d-499c-80e8-b15711dc1f81","resolution":{"observed_at":"2026-08-10T17:51:29.168618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.147111Z","title":"Representer point selection for explaining regularized high- dimensional models,","venue":null,"work_id":"05df5c65-737b-405e-b6df-92339368e6ee","year":2023},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.635371Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:e246c22440db6105f0bcbe83f6d12c7258e22198fa81a056fb59d8011ad89dc5","observation_id":"f129cd37-02e4-4e9a-a012-97690b74e50a","resolution":{"observed_at":"2026-08-10T17:51:29.152188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.130433Z","title":"Hydra: Hypergradient data relevance analysis for interpreting deep neural networks,","venue":null,"work_id":"7eba8d4a-c2c6-43e0-90a3-da5d4b549751","year":2021},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.639961Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:8dca9de6d7462f7fedfac337eb0a53dc43f8582920890336ad125cb925a151f0","observation_id":"1a2cc957-2b1a-493b-a2cb-931bd2a57941","resolution":{"observed_at":"2026-08-10T17:51:29.135428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.114448Z","title":"Fastif: Scalable influence functions for efficient model interpretation and debugging,","venue":null,"work_id":"315ca1ba-7615-4120-bc43-924466ba2eca","year":2021},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.644726Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:a115159f5f91451e96450be829203aa3d1ce2d79bff772d16aaa34d507c4263c","observation_id":"03743097-972f-49e3-b14f-549b9e6e0857","resolution":{"observed_at":"2026-08-10T17:51:29.119266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.098364Z","title":"Scaling up influence functions,","venue":null,"work_id":"12c625e6-d5ce-4d94-b067-d88c4dc6e222","year":2022},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.649321Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:660f8d9766ee898e628f14daaf4a1c0bfda1cec08a559ccf8378a4ba2cb4d5d3","observation_id":"8e3ceded-da6e-444a-9cca-9084f34ee1ea","resolution":{"observed_at":"2026-08-10T17:51:29.103216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.082505Z","title":"Flpu- rifier: Backdoor defense in federated learning via decoupled contrastive training,","venue":null,"work_id":"1895efa8-e420-4e9f-81cc-7ea7f5b5fca5","year":2024},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.653679Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:1091e7a4a4259b0a57a71eeb7099d547c75c6dc0a4f297aef1bdfcec4fc73e4e","observation_id":"b543a86d-029d-494c-9d96-18a443cf61eb","resolution":{"observed_at":"2026-08-10T17:51:29.087264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.066747Z","title":"Reverse backdoor distillation: Towards online backdoor attack detection for deep neural network models,","venue":null,"work_id":"949e9aab-8325-4034-b198-0353beb7d3ff","year":2024},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.658235Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:683fccd1f7082a5c530692ba196ad09193b2fce6aa39be4fc8eb337b60475376","observation_id":"15f63d70-9bfe-4327-a053-49a4d9db0bbb","resolution":{"observed_at":"2026-08-10T17:51:29.071859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.049995Z","title":"Can we mitigate backdoor attack using adversarial detection methods?","venue":null,"work_id":"7d34ae14-0639-43d9-ab28-926b0cb879d5","year":2022},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.662933Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:42d6d65d280bb33f8edb80046b7061c56d315c2ffa99db70c55830776dc556ae","observation_id":"d68b33a8-f1c7-4e6e-b835-8443358ad99e","resolution":{"observed_at":"2026-08-10T17:51:29.055297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.033255Z","title":"Anti-backdoor learning: Training clean models on poisoned data,","venue":null,"work_id":"94d95c64-53fc-4cce-a925-0f1e8c1e3107","year":2021},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.667690Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:e254bb6c4cdd5d29b4b004ba8b21c2e89126a5030be3f147f2bff77ca14c3c01","observation_id":"f37aec9f-814f-45d4-bf98-9a5d2f7fa49d","resolution":{"observed_at":"2026-08-10T17:51:29.038222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:29.015374Z","title":"De-pois: An attack- agnostic defense against data poisoning attacks,","venue":null,"work_id":"0bc8c330-1aaf-4d98-a44a-8c63ce9f7756","year":2021},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.672399Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:5d8bfb11d881bcd29800a1b12dce7417c8df0caca66a507416212f6003e81458","observation_id":"1b1def8b-4d2e-4b29-8bb4-355f8b77fa0c","resolution":{"observed_at":"2026-08-10T17:51:29.020717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.997758Z","title":null,"venue":null,"work_id":"6542b0a5-a75a-4bff-a254-c634503539ce","year":2017},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.677313Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:c1e2d13d97fe6727532bf3a55200d6e4449c31d39a83b4b77ef0ac4a2dfdc660","observation_id":"a9257c17-44d4-4e7a-8ff0-fd0a3097f31f","resolution":{"observed_at":"2026-08-10T17:51:29.003506Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.980715Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":"e5034345-77c9-4b83-ba51-3f6433e34599","year":2017},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.682317Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:c9adb787bc76b00628e0bffbad05c3d8dda154a6b3417f98f8c571381669de4d","observation_id":"b0a69c57-41f1-4b8a-b906-3de27735db53","resolution":{"observed_at":"2026-08-10T17:51:28.985822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.960663Z","title":"Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models,","venue":null,"work_id":"6a260c20-6c40-4653-ab02-850d5b0ce7f5","year":2019},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.687764Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:9da299d09a1aa88489b60d983cce673cea5760c1f3b1202648a715e799a2ee96","observation_id":"c81c5871-5573-4ffc-a365-6bb8d521be98","resolution":{"observed_at":"2026-08-10T17:51:28.966533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.943878Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":"5d582539-4c7b-44c8-88cf-35e52a6af9cd","year":2017},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.692461Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:3b59358843c3a9edf968e70b920f15c80c0acaf58890730f32e177711e3dfdf0","observation_id":"eb2d3030-9820-4c52-a359-3d4e3435b63d","resolution":{"observed_at":"2026-08-10T17:51:28.948954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.925279Z","title":"Byzantine-robust dis- tributed learning: Towards optimal statistical rates,","venue":null,"work_id":"9ab00177-b9f4-4f15-bb03-544ff44ea547","year":2018},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.697972Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:8d1c10ba9a648d9ead8da4878e387f452beceb46a4a7d7d753fcc1fcfde1ac4e","observation_id":"70123c4f-dc34-4b10-835e-3839a3b2387d","resolution":{"observed_at":"2026-08-10T17:51:28.931416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.905162Z","title":"Machine learning with adversaries: Byzantine tolerant gradient descent,","venue":null,"work_id":"14b387cb-7a56-45d4-82d5-e5a63b17e15d","year":2017},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.702712Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:71532b03ee1f1a98d292bd8c0351581ed4e8a2388575b8ab1415f068dce0888e","observation_id":"6f8d44ad-d8ad-4d1c-b75c-1ba4e2700db8","resolution":{"observed_at":"2026-08-10T17:51:28.910677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.886898Z","title":"Fat: Federated adversarial training,","venue":null,"work_id":"cfcdc442-3437-4d29-b8f1-fe200c1ad92f","year":2020},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.707596Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:17713655fbdceaecf5f778fc108b25c6d6f472ed57e8747e985f0d601425aa9e","observation_id":"8430ca6a-f6cb-496f-b07a-1915336802fd","resolution":{"observed_at":"2026-08-10T17:51:28.892155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.866555Z","title":"Fadngs: Federated learning for anomaly detection,","venue":null,"work_id":"f0651425-b070-4aae-bd8a-e4324392d961","year":2024},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.712320Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:65189591baca75002399bd33fb11314c6243ed457b87ace22cbcef07ffd6292a","observation_id":"496f81ef-2bee-4bac-bd12-ddeb59a6bbca","resolution":{"observed_at":"2026-08-10T17:51:28.872023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.847288Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":"4b2a2e52-765b-438b-98ab-3c7587d9b69c","year":2015},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.716978Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:7580a13b169fc5b69731d2ec4f5d4dd4c65fbaa9d5a3c7374ef60a0db4aa84f1","observation_id":"91145747-f93d-4574-9109-671b5c2fc3f0","resolution":{"observed_at":"2026-08-10T17:51:28.852565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T17:51:28.828044Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"868db3fd-766d-4f0f-b134-8f8c46c89ef2","year":2016},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.721863Z"},"links":{"citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:45d5219e3206a28df3aae43bf7b036db6eecab026c518e2b0dc43c1e5e3136a6","observation_id":"8a9f5da6-ef54-442b-bc05-99d4f8ec0518","resolution":{"observed_at":"2026-08-10T17:51:28.834901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06335","last_updated":"2019-09-13T17:26:20Z","snapshot_observed_at":"2026-08-02T11:40:53.964079Z","submitted_at":"2019-09-13T17:26:20Z","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06335","snapshot_observed_at":"2026-08-10T17:51:28.728550Z","title":"Measuring the effects of non- identical data distribution for federated visual classification,","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T17:51:28.728550Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2501.11848"},"observation_digest":"sha256:910c09db3c05caf2ed57989c70737df630e673b90e69a97cc748ea137f75decf","observation_id":"f2bbd228-29f5-493c-a08d-50ab2631ec0e","resolution":{"observed_at":"2026-08-10T17:51:28.728550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.11848","last_updated":"2025-01-21T03:07:03Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-10T17:45:23.956554Z","submitted_at":"2025-01-21T03:07:03Z","title":"FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":0,"verified_fuzzy":38},"total_outbound_references":45},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2501.11848."}