{"as_of":"2026-08-23T07:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a749ee50b3eb058c0463ff78a19000035cf8477ae7438286be49df2cde85b969","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T16:20:23.398486Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2508.18737/citation-record","integrity":"/paper/2508.18737/integrity","json":"/paper/2508.18737/citation-record.json","paper":"/paper/2508.18737"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:20:23.229261Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.229261Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:d92288dea8615180d5dd00c341901740a880c70a0888f7b5bc8f74ec1eece481","observation_id":"381d9cb3-a51c-49c2-abec-9532463295d8","resolution":{"observed_at":"2026-08-05T16:20:23.229261Z","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":"2026-08-05T16:20:23.910401Z","title":"Federated machine learning: Concept and applications,","venue":null,"work_id":"7650e02e-684a-4400-a601-f9ecc9fd648e","year":2019},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.233506Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:e6f6158f5420293fc215b4d9ccb01c1bb6cbd7baaa742237d6906e97194f77a4","observation_id":"2a8313c4-2ec0-4bf9-b022-480e2384d4d4","resolution":{"observed_at":"2026-08-05T16:20:23.914839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.895536Z","title":"The eu general data protection regulation (gdpr): Eu- ropean regulation that has a global impact,","venue":null,"work_id":"3dd09551-f421-4b35-a212-c6478effa859","year":2017},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.237294Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:1705dcdbc1f8072890a7916ce0c2a37398fcd91835883248e9817324e1202d0a","observation_id":"a04a6390-60bb-40dd-8bcc-d404cf2db3cc","resolution":{"observed_at":"2026-08-05T16:20:23.900489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.241079Z","title":"Ma- chine learning with adversaries: Byzantine tolerant gradient descent,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.241079Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:f79f77dd6696b4301c1dd1ef922e7fbc2f81ea51b1282bb42b2c8506123a7e03","observation_id":"a06057ec-871d-44a6-a396-ef3736bff5c1","resolution":{"observed_at":"2026-08-05T16:20:23.241079Z","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":"2026-08-05T16:20:23.875644Z","title":"Can machine learning be secure?","venue":null,"work_id":"7ce049ce-30c5-4e74-9019-5c74df6f4118","year":2006},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.244549Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:015c4f935512c3bbcb6db7b0b7effcf98ee4a23d7a2a0873e8066b5c2189320f","observation_id":"e0e50ca1-ae20-4525-9ce1-8881a736a465","resolution":{"observed_at":"2026-08-05T16:20:23.880046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.863622Z","title":"How to backdoor federated learning,","venue":null,"work_id":"5c855c26-7fd8-4125-948f-fb0581d91201","year":2020},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.248271Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:17fea0250e04682b7e916b16379badceec8a62d463b3f4a02a968361de30f734","observation_id":"f5389eb4-e418-43c8-a276-e0f2801d487f","resolution":{"observed_at":"2026-08-05T16:20:23.868054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.853444Z","title":"A comprehensive survey on poisoning attacks and countermeasures in machine learning,","venue":null,"work_id":"30cdcc0d-2a55-4ed6-b529-f77fbdf74e1d","year":2022},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.252206Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:97360f482595283632fbdefa7aad54070e971ef422b162bc945f3083753d11a4","observation_id":"c474600c-7d07-49f6-b4f9-71debefa8883","resolution":{"observed_at":"2026-08-05T16:20:23.857057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.843003Z","title":"Poisoning attacks in federated learning: A survey,","venue":null,"work_id":"890e76b0-b67f-4459-b972-6cea822f1b0d","year":2023},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.255548Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:ef1995d12e66b66461e2cbeceeef616ea3c20691b2b2183a3806b34b8cf0f379","observation_id":"e7693f2b-cb57-4db3-8947-addb45ffa6d6","resolution":{"observed_at":"2026-08-05T16:20:23.846464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.259036Z","title":"Local model poisoning attacks to {Byzantine-Robust} federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.259036Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:aa918c52eadd9db5a36c294aaf9f2d2b37a465e298e767c49e8e1269b03d9c23","observation_id":"47d1746e-ef28-4dea-8ba8-05c549496350","resolution":{"observed_at":"2026-08-05T16:20:23.259036Z","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":"2026-08-05T16:20:23.826678Z","title":"On the byzantine robustness of clustered federated learning,","venue":null,"work_id":"179909a7-8e72-4cd0-8102-3166582da2a7","year":2020},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.262685Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:a4c35bf7003d797d77dc5eaca692704c6a418c45317dcec4a0598c1a787f8a8e","observation_id":"599e9319-3925-410d-92a2-62243fb96428","resolution":{"observed_at":"2026-08-05T16:20:23.830514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.816460Z","title":"A symbolic representation of time series, with implications for streaming algorithms,","venue":null,"work_id":"d34b61e4-d466-4f37-ac92-b0bc4e667079","year":2003},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.266586Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:c41d7e730fd89ebbdae4291d280e3a5c1a8a76844e5659619a7079ff1d69f2d8","observation_id":"43e6b741-960f-4d19-be1e-96de679bb75d","resolution":{"observed_at":"2026-08-05T16:20:23.820127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.805273Z","title":"Chapter 11 - recommendation engines,","venue":null,"work_id":"c80b5bdd-7b42-4d9d-b678-3dcd294af149","year":2019},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.270280Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:22611a15cd3c2324765c93f234fbbb863f591b83fc973d3fdc847339389330fa","observation_id":"5e9db837-0d2b-4ecb-98a7-3cfee1fe8ecc","resolution":{"observed_at":"2026-08-05T16:20:23.809183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.794724Z","title":null,"venue":null,"work_id":"6a6420aa-9b20-4c43-837d-c8de3907db19","year":2021},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.273583Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:1fd35887898ef87010e2fabadbf99adc5c070b596c7426feef30148176e23071","observation_id":"f313b629-9853-4a0e-b419-37c32c4d5d2a","resolution":{"observed_at":"2026-08-05T16:20:23.797909Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.784430Z","title":"Fedrdf: A robust and dynamic aggregation function against poisoning attacks in federated learning,","venue":null,"work_id":"d0573c59-d7c2-458e-963b-3da16f2b7610","year":2024},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.277069Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:01bddd0f89a3ae5fa17a6206d096eb6c58679480c78d9a1aa2dda390245f0b2c","observation_id":"87d73c1c-515a-4afd-993e-cd3a9d7b6e0d","resolution":{"observed_at":"2026-08-05T16:20:23.788033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.02133","last_updated":"2020-03-04T15:30:10Z","snapshot_observed_at":"2026-08-20T18:18:06.136301Z","submitted_at":"2020-03-04T15:30:10Z","title":"Threats to Federated Learning: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.02133","snapshot_observed_at":"2026-08-05T16:20:23.280461Z","title":"Threats to federated learning: A survey,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.280461Z"},"links":{"cited_paper":"/paper/2003.02133","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:6e1452f1b4f38f64c558dc62d31b1c3b00a16982e2c5ba0deb061169c25417be","observation_id":"7b5ef8d4-baa1-4ce1-a1c5-7b73bdf0cf26","resolution":{"observed_at":"2026-08-05T16:20:23.280461Z","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":"2026-08-05T16:20:23.773638Z","title":"Wavelet transform application for/in non-stationary time-series analysis: A re- view,","venue":null,"work_id":"538b2359-77e1-4e22-9b57-052b63207a03","year":2019},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.284290Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:c862a4f2b6b231b21ef0b26264acda4d081f4cf86bd5340d7cdf49f708db0745","observation_id":"64142875-b930-4b86-b09e-e68e2945c6d3","resolution":{"observed_at":"2026-08-05T16:20:23.778098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.762818Z","title":"Discrete wavelet transform-based time series analysis and mining,","venue":null,"work_id":"73e73224-07f7-4976-a436-afbc71c43127","year":2011},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.288057Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:59dafd6651c765c2b1b52e66c6d481a6067e94627ab7618676f4c500f3096b65","observation_id":"63bef37c-27ba-445b-80d5-ce5a43784291","resolution":{"observed_at":"2026-08-05T16:20:23.766564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.752604Z","title":"Beats: Blocks of eigenvalues algorithm for time series segmentation,","venue":null,"work_id":"80decce6-cc71-4fe5-ad8d-2db3b992af65","year":2051},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.291606Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:ec554a8898df136b417d32946396e6e0348519fdb1e9374c402bcff4bbf2ca67","observation_id":"a93b9fb8-c63a-40be-a418-712d02c0c669","resolution":{"observed_at":"2026-08-05T16:20:23.756069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.742039Z","title":"Multibeats: Blocks of eigenvalues algorithm for multivariate time series dimension- ality reduction,","venue":null,"work_id":"7ced8fce-b4cd-414b-a416-cbedbec0feef","year":2024},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.295140Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:b1dced2dae939b75ef5c2c530fa25c14ff6046b481f79884000347c51fb1dfe8","observation_id":"26dd89fb-107e-46de-b749-3d8cda4c060c","resolution":{"observed_at":"2026-08-05T16:20:23.745999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.731870Z","title":"Dimensionality reduction for fast similarity search in large time series databases,","venue":null,"work_id":"18ab07fb-4baf-4587-b691-411b396fac5d","year":2001},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.298894Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:ff3ba92482bda348b519cbdef5b044dbcfe39cf6dc355c6db55d51cb96a66288","observation_id":"c774bb3f-b250-4290-9697-f47bd441b0d1","resolution":{"observed_at":"2026-08-05T16:20:23.735381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.721796Z","title":"Least squares quantization in pcm,","venue":null,"work_id":"e3dab53b-2098-4da3-9009-b5ab1fd7d90a","year":1982},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.302297Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:429f16bad6838e9ffda2f693be84d551e38dc74769fc0f4ef893ba7e08914e29","observation_id":"bd19dd00-c828-40ef-b1ab-c1f25f5065b5","resolution":{"observed_at":"2026-08-05T16:20:23.725299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.710402Z","title":"Gaussian mixture models,","venue":null,"work_id":"da76aa1b-c876-45ef-9001-7097e9c38f12","year":2015},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.305627Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:6e5ed5aeee64b935ed76d233b60a9b9c4c2730ef579d4b1d170775b194abf650","observation_id":"db17e440-12df-414d-b8da-d4e20d53f9d8","resolution":{"observed_at":"2026-08-05T16:20:23.713742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.700312Z","title":"Spectral clustering,","venue":null,"work_id":"c8539ae2-2d04-482a-ad0c-87b08a5f2034","year":2018},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.308947Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:a5ff1ceb6d730eb05effd0d32e9ae63b650324a5cd718a2059c70dec19e8b143","observation_id":"4a9e022f-a975-4af0-9e80-d91dcddae1b6","resolution":{"observed_at":"2026-08-05T16:20:23.703971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.690406Z","title":"A tutorial on spectral clustering,","venue":null,"work_id":"2ac2b6e0-de9b-4c6d-add8-f6bdc6d096ea","year":2007},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.312217Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:d1f5e88af9924b01c5cf3b2f70ea68a218a37c0b5b630f0b99fc8233a8705a01","observation_id":"42960f1a-c0c9-4de1-9f9f-951717d56db0","resolution":{"observed_at":"2026-08-05T16:20:23.693674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.679738Z","title":"Learning spectral clustering,","venue":null,"work_id":"fea2ada2-1d9a-400d-b62e-e9b8d7e05a69","year":2003},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.315914Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:154941a010b516d2d02ea5a34bc6cd3d4412ca1cf0a7c14b8fe96d8f9901dd2c","observation_id":"2955c048-6ed6-41f2-873b-aa48855b6e93","resolution":{"observed_at":"2026-08-05T16:20:23.683539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.670095Z","title":null,"venue":null,"work_id":"dcb7ea28-3cd9-4309-9160-f825d3a3be2d","year":2012},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.319062Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:e1528bdd52a5795f4d6f6fa9045b3aff78705854039192296ccc3fed4dc658bc","observation_id":"1231c7e1-66fb-4069-a8c1-e02f4f90065f","resolution":{"observed_at":"2026-08-05T16:20:23.673386Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.659991Z","title":"Byzantine-robust dis- tributed learning: Towards optimal statistical rates,","venue":null,"work_id":"892bf554-dc39-4896-b9f0-329f0e223f5f","year":2018},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.322463Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:ba7d03b02ae0e5b1ab9dcae582d99a275218fda36c2b58372634e47d632f0510","observation_id":"8f3e2de0-af02-4fdf-88df-8645bf7cdc79","resolution":{"observed_at":"2026-08-05T16:20:23.663616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1808.04866","last_updated":"2020-07-15T15:35:17Z","snapshot_observed_at":"2026-08-18T14:49:43.852586Z","submitted_at":"2018-08-14T19:20:35Z","title":"Mitigating Sybils in Federated Learning Poisoning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.04866","snapshot_observed_at":"2026-08-05T16:20:23.326364Z","title":"Mitigating sybils in federated learning poisoning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.326364Z"},"links":{"cited_paper":"/paper/1808.04866","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:319d2316597dedb2cfa93762f98d80da1fd44fb1bafad5fccf108549fba0acfa","observation_id":"6b0bb8f5-f2eb-49f5-bd66-87ce00e78300","resolution":{"observed_at":"2026-08-05T16:20:23.326364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13995","last_updated":"2022-04-12T01:56:47Z","snapshot_observed_at":"2026-08-22T02:13:41.384665Z","submitted_at":"2020-12-27T18:43:39Z","title":"FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.13995","snapshot_observed_at":"2026-08-05T16:20:23.330213Z","title":"Fltrust: Byzantine- robust federated learning via trust bootstrapping,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.330213Z"},"links":{"cited_paper":"/paper/2012.13995","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:abc57173d397a846f997c83f1fe83eef5ade100d77440662bbefdaf3d15b801e","observation_id":"bbf413fc-ed2e-4818-8584-667e88063656","resolution":{"observed_at":"2026-08-05T16:20:23.330213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.00211","last_updated":"2020-02-01T14:09:48Z","snapshot_observed_at":"2026-08-21T19:59:09.602336Z","submitted_at":"2020-02-01T14:09:48Z","title":"Learning to Detect Malicious Clients for Robust Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.00211","snapshot_observed_at":"2026-08-05T16:20:23.334034Z","title":"Learning to de- tect malicious clients for robust federated learning,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.334034Z"},"links":{"cited_paper":"/paper/2002.00211","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:aa0a9d2cdf3d794d6bb073a49d4ee3bdbf6d3e56202f47792d69c5a32cc6ecac","observation_id":"4bdafc3c-fe5c-4bc3-9770-019cd40190f2","resolution":{"observed_at":"2026-08-05T16:20:23.334034Z","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":"2026-08-05T16:20:23.650050Z","title":"Fldetector: Defending federated learning against model poisoning attacks via detecting ma- licious clients,","venue":null,"work_id":"da92ca2d-5ad8-4094-ac84-03cbfb0de876","year":2022},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.337706Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:90243e7c86b9cb001451171b04799025f1cce8a49a74e79b6218cb4dafb7321d","observation_id":"32260704-5f17-494c-a07d-080789b5bf11","resolution":{"observed_at":"2026-08-05T16:20:23.653677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08097","last_updated":"2024-09-04T08:27:17Z","snapshot_observed_at":"2026-08-16T14:52:48.284638Z","submitted_at":"2023-10-12T07:45:18Z","title":"Sentinel: An Aggregation Function to Secure Decentralized Federated Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08097","snapshot_observed_at":"2026-08-05T16:20:23.341029Z","title":"Sentinel: An aggregation function to secure decentralized federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.341029Z"},"links":{"cited_paper":"/paper/2310.08097","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:c565bb089f6b03eb0f0b483511ed523ccaf0896b9ca4904abefd9afda831db2e","observation_id":"1468ceec-54b1-4361-b304-a23d3f116390","resolution":{"observed_at":"2026-08-05T16:20:23.341029Z","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":"2026-08-05T16:20:23.640443Z","title":"Lomar: A local defense against poisoning attack on federated learning,","venue":null,"work_id":"c94d10a5-d164-4982-a5bf-81562d2df55e","year":2021},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.344530Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:b1576d6a0eeaac58ccdb04d74298fabd6e105f0285c29322c96d8b12959aed0e","observation_id":"7fda1ab3-96ea-4943-ab5a-3a8a38bc3dff","resolution":{"observed_at":"2026-08-05T16:20:23.643991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.629574Z","title":"Feddmc: Efficient and robust federated learning via detecting malicious clients,","venue":null,"work_id":"7ccbb1bd-a401-42a2-bc6e-6d848861c794","year":2024},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.347686Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:d95e07b92fcf802ae7e03b9cd2c852cbe286fcab2fbbb0d2ca64d8653c08e1a1","observation_id":"2a4c808a-a298-4864-a3d0-3602aa68a380","resolution":{"observed_at":"2026-08-05T16:20:23.633585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.618456Z","title":"Byzantine-robust federated learning through collaborative malicious gradient filtering,","venue":null,"work_id":"1e0387d8-1d47-4c30-b071-644ba16969bf","year":2022},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.350732Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:a5f01809d226b419e7fcb330621bce1b712f776dc82a29b8c08e046b867f4df6","observation_id":"1e00fb4c-97fe-48c3-ad79-66d8edfac3e8","resolution":{"observed_at":"2026-08-05T16:20:23.622099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.13256","last_updated":"2023-08-07T07:31:46Z","snapshot_observed_at":"2026-08-16T17:04:04.273562Z","submitted_at":"2022-04-28T02:22:53Z","title":"Shielding Federated Learning: Robust Aggregation with Adaptive Client Selection","version":4},"cited_work":{"arxiv_id":"2204.13256","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.13256","snapshot_observed_at":"2026-08-05T16:20:23.458125Z","title":"Shielding Federated Learning: Robust Aggregation with Adaptive Client Selection","venue":"cs.CR","work_id":"3ed3b195-8836-4160-8445-efc49fd8b0cc","year":2022},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.354912Z"},"links":{"cited_paper":"/paper/2204.13256","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:a318e91d9689e02150c718773a70f9a5fb210754b26f7d4e49e0f65b35f19bb1","observation_id":"08270032-b270-469e-9116-774d70adf632","resolution":{"observed_at":"2026-08-05T16:20:23.464015Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.607487Z","title":"The sybil attack,","venue":null,"work_id":"c3ada0c7-3c69-426f-8dcf-5fc77cb124d5","year":2002},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.358725Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:0fe557b4e4a49fd69d43afea5e95833db50ed1ab44d541151b059e8b6ccea93e","observation_id":"1e13b958-5973-499b-bb5f-69487489e97d","resolution":{"observed_at":"2026-08-05T16:20:23.611088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.595690Z","title":"Fully decentralized federated learning,","venue":null,"work_id":"8d40408e-e04f-4e55-b1dd-7ae417cd48d7","year":2018},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.362119Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:cc7b5095636456a72fd00d4a95fa7416d63eeb90ba3cd808b10296d5fb784a2b","observation_id":"b0345689-8b3b-4463-a97e-93abe1a1d322","resolution":{"observed_at":"2026-08-05T16:20:23.599994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.584247Z","title":"Back to the drawing board: A critical evaluation of poisoning attacks on production federated learning,","venue":null,"work_id":"2273f059-8298-4bd7-97c7-8b9caa351edf","year":2022},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.365607Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:28440975f863b9b809a97aa40d8f364e599958c3fd95084cb41d24ae259bf8f9","observation_id":"0008192c-8c78-465d-993c-59221b284f48","resolution":{"observed_at":"2026-08-05T16:20:23.588165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.571421Z","title":"A little is enough: Circumvent- ing defenses for distributed learning,","venue":null,"work_id":"828bf642-9e41-4178-91e7-9dcf66aa5146","year":2019},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.368967Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:b5669e9862d59994fb1be821b2376267514f3076ff643edeab6992aee4b8d2aa","observation_id":"e3283ec4-26ce-46ef-a250-138694173d90","resolution":{"observed_at":"2026-08-05T16:20:23.575820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.14390","last_updated":"2022-03-05T20:30:32Z","snapshot_observed_at":"2026-07-06T09:42:35.058716Z","submitted_at":"2020-07-28T17:59:07Z","title":"Flower: A Friendly Federated Learning Research Framework","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.14390","snapshot_observed_at":"2026-08-05T16:20:23.372278Z","title":"Flower: A friendly federated learning research framework,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.372278Z"},"links":{"cited_paper":"/paper/2007.14390","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:e03378444e94612b027b538caa396bf565c22936ad5f07c073ea76377ac0a259","observation_id":"1881814b-3e7c-403f-b10f-579b6d34383b","resolution":{"observed_at":"2026-08-05T16:20:23.372278Z","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":"2026-08-05T16:20:23.560928Z","title":"Emnist: Extending mnist to handwritten letters,","venue":null,"work_id":"3d583874-7950-4e62-808e-a64095360d4d","year":2017},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.376122Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:02b115c45e71b1b3f52eb1d5079bd7d9da13fad286fabfab9b3e63c05cbdf27e","observation_id":"808826a2-3f88-4789-b1f1-d1a1b2008698","resolution":{"observed_at":"2026-08-05T16:20:23.564285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01097","last_updated":"2019-12-09T20:02:37Z","snapshot_observed_at":"2026-08-16T19:49:29.879809Z","submitted_at":"2018-12-03T21:59:41Z","title":"LEAF: A Benchmark for Federated Settings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01097","snapshot_observed_at":"2026-08-05T16:20:23.380270Z","title":"Leaf: A benchmark for federated settings,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.380270Z"},"links":{"cited_paper":"/paper/1812.01097","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:550eba658b670ab5fbe0cebbc1808814c9145606f2fb6d7ffa87ded957b22475","observation_id":"4cbee77e-8b8c-4a68-b685-1ab839bde23c","resolution":{"observed_at":"2026-08-05T16:20:23.380270Z","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":"2026-08-05T16:20:23.551044Z","title":"Entropy estimates of small data sets,","venue":null,"work_id":"632c4b2a-9e4b-403e-8857-d1c7a861cd31","year":2008},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.383986Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:2a68659611444164383a0a7e3cf59e906fc517f447200a70b58c1ad0671c90ab","observation_id":"1abdb28c-441c-4ffc-84f8-7bbe8db205fa","resolution":{"observed_at":"2026-08-05T16:20:23.554368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.540638Z","title":"Sageflow: Robust federated learning against both stragglers and adversaries,","venue":null,"work_id":"b5502abe-f9ae-4b8a-bf79-568efc8ed389","year":2021},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.388199Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:ba3b069cdebdaa940805ff2a36b673a8b54173f63b8cc939261f0bf62c396f0e","observation_id":"bf324a23-5d54-469d-ad5b-a8c8b1690282","resolution":{"observed_at":"2026-08-05T16:20:23.544099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-05T16:20:23.530362Z","title":"Trojdrl: evaluation of back- door attacks on deep reinforcement learning,","venue":null,"work_id":"397917e0-208d-442a-9ae7-84936909a92f","year":2020},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.391555Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:9cb889c10ecd043bb2b02040ba87f19c2c3ba043ca7112a253c44f8ee4c314bc","observation_id":"9ab789eb-755b-4c16-95ed-704b4bbe9b2b","resolution":{"observed_at":"2026-08-05T16:20:23.534060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.09365","last_updated":"2023-11-22T09:08:15Z","snapshot_observed_at":"2026-08-07T05:21:15.626151Z","submitted_at":"2020-06-16T17:58:53Z","title":"Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.09365","snapshot_observed_at":"2026-08-05T16:20:23.394900Z","title":"Byzantine-robust learning on heterogeneous datasets via bucketing,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.394900Z"},"links":{"cited_paper":"/paper/2006.09365","citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:b1e1aa039317f734a89e5f743c6a5d21831779fd16d1d50b99f894fa8311c23e","observation_id":"cbcaf4ec-d996-48ae-89ca-58a22d56fa55","resolution":{"observed_at":"2026-08-05T16:20:23.394900Z","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":"2026-08-05T16:20:23.520019Z","title":"Manipulating the byzantine: Opti- mizing model poisoning attacks and defenses for federated learning,","venue":null,"work_id":"3c6b1159-1a1a-4311-aae5-5019187617ec","year":2021},"citing_paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:23.398486Z"},"links":{"citing_paper":"/paper/2508.18737"},"observation_digest":"sha256:86485fe6dc31cbcd31a610d2faafe8e71c5669de00ae6cbda8b030cf1a41bbb2","observation_id":"4cf9adc4-b4d3-4643-bfe8-19b8bcc4ff0e","resolution":{"observed_at":"2026-08-05T16:20:23.523759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.18737","last_updated":"2025-08-26T07:09:15Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T19:49:28.840335Z","submitted_at":"2025-08-26T07:09:15Z","title":"FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":34},"total_outbound_references":48},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2508.18737."}