{"as_of":"2026-08-16T23:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2d92ae926ef3470fd34b9c2311bcbd2bd1b6527730385929f2e8cb7744f22363","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T04:21:00.547075Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:15:44.535038Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T12:15:46.518013Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"cited_work":{"arxiv_id":"2505.01874","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.01874","snapshot_observed_at":"2026-08-07T12:15:46.518013Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","venue":"cs.LG","work_id":"8e71603d-0239-403b-b015-a3799f1cb4aa","year":2025},"citing_paper":{"arxiv_id":"2505.24802","last_updated":"2025-05-30T17:08:15Z","snapshot_observed_at":"2026-08-15T04:45:35.506929Z","submitted_at":"2025-05-30T17:08:15Z","title":"ByzFL: Research Framework for Robust Federated Learning","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:44.535038Z"},"links":{"cited_paper":"/paper/2505.01874","citing_paper":"/paper/2505.24802"},"observation_digest":"sha256:65dcf4af03f4565e17b970db659caf012ac57bb1cfb553fa1ab6152ca29e40da","observation_id":"36ffd402-0f88-447a-9ef9-d1aa524a184e","resolution":{"observed_at":"2026-08-07T12:15:46.623048Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.01874/citation-record","integrity":"/paper/2505.01874/integrity","json":"/paper/2505.01874/citation-record.json","paper":"/paper/2505.01874"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.249698Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.249698Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:faf239ef95d833e7058fe38c13bb671853866a876b8efdb85ad8bbafb24f8716","observation_id":"25896afc-4893-4e0b-88df-83adf7ae211e","resolution":{"observed_at":"2026-08-16T04:21:00.249698Z","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":"2026-08-16T04:21:02.048918Z","title":"Robust testing and estimation under manipulation attacks","venue":null,"work_id":"d120a783-8b56-4ac4-b5b9-1c63c59161bb","year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.255891Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:3c7f2dfe54ea77bbba3322b4480fb6bc15f77351e25bacf1a0400e5f922f19d2","observation_id":"c6696cf4-2cb4-4d59-88e0-f4f58088f541","resolution":{"observed_at":"2026-08-16T04:21:02.052739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:02.037040Z","title":"T., Yu, F","venue":null,"work_id":"2e2b8965-bcee-4990-8bdf-f9faa14dec8e","year":2018},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.260441Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:91216e054603bb6519c4f165714b6f53713e6ff5ddd447257d330024a9401abc","observation_id":"f3061f2b-5da5-41a0-8b3a-f4c74fc325c2","resolution":{"observed_at":"2026-08-16T04:21:02.040616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:02.024749Z","title":"K., Tankala, P., Venkat, P., and Zhang, F","venue":null,"work_id":"d3dde1d1-ca3b-48b7-9ebf-7942808cd511","year":2023},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.264229Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:fa5485cffbe18f67532f7478baccb9fc756bc7fa0bc896599c3b147b1a7732a3","observation_id":"33f01c2d-e2e3-4988-906e-18cc08866f07","resolution":{"observed_at":"2026-08-16T04:21:02.028467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:02.011422Z","title":"B yzantine-resilient non-convex stochastic gradient descent","venue":null,"work_id":"e630b9ff-58d7-4228-a8ee-3704b5181362","year":2020},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.267936Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:8c05bf262fd9ee64048d297c5fa0bc26a41b989e867da1df349220fe1a513dde","observation_id":"645e7aae-b3e4-4b01-b60d-29dc59071714","resolution":{"observed_at":"2026-08-16T04:21:02.015836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.995821Z","title":"Fixing by mixing: A recipe for optimal byzantine ml under heterogeneity","venue":null,"work_id":"04331cab-ade5-426e-ae00-18ebe96d1530","year":2023},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.271875Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:31ac2789da0edfd0971b7ca7b466dff0fb6ad8010e21869a4548698c732b62cf","observation_id":"35c1e86c-b89f-4b6c-b861-0fe031a22ac6","resolution":{"observed_at":"2026-08-16T04:21:02.000776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.980215Z","title":"Robust distributed learning: Tight error bounds and breakdown point under data heterogeneity","venue":null,"work_id":"2a843627-e900-4e78-b054-36081e6868d7","year":2023},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.275533Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:a196f361f3ec0f6f1a078d7861dd01fcb90311e6bc74b38789a10ea9bb1f5e8c","observation_id":"09f2e326-fb50-4e2c-ba44-091012142c9a","resolution":{"observed_at":"2026-08-16T04:21:01.984858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.965797Z","title":"On the privacy-robustness-utility trilemma in distributed learning","venue":null,"work_id":"2e90c22e-f326-4949-b6e5-6ad7b276a7e5","year":2023},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.279443Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:46f6b92990c772072f10431c094782c38ffed7238350660ae5f41e8b1c49af4d","observation_id":"9b454248-2b98-4201-ad2f-465709dfae41","resolution":{"observed_at":"2026-08-16T04:21:01.970487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.951697Z","title":"The privacy power of correlated noise in decentralized learning","venue":null,"work_id":"121d5c4a-f3b3-44d5-b263-4bfa3a7cded6","year":2024},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.283008Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:4a5b67b7a3f10046fe916c7f9622527f9d017aeb219d75a4f860f58086a057a1","observation_id":"dbb81095-8bc9-4962-bd73-b34565ff44b2","resolution":{"observed_at":"2026-08-16T04:21:01.956657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.937403Z","title":"A little is enough: Circumventing defenses for distributed learning","venue":null,"work_id":"b2901c96-e8c6-4915-a8d4-3c7c8d96d61d","year":2019},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.286292Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:a5ea282e9035fff79daf0bdfd20ff6a2d70d1e12c39a200d1c28119fc33d403c","observation_id":"bc7858e0-b30e-4a40-9c8d-a6aad80534a7","resolution":{"observed_at":"2026-08-16T04:21:01.942050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.289893Z","title":"Private empirical risk minimization: Efficient algorithms and tight error bounds","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.289893Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:48a9b921c73a8b4a007df513ece03c3b07b3ea990c7cfe65581f46639f34691d","observation_id":"8ab1fba5-2e45-4bed-9f99-e2fc930068e8","resolution":{"observed_at":"2026-08-16T04:21:00.289893Z","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":"2026-08-16T04:21:01.914307Z","title":"and Tsitsiklis, J","venue":null,"work_id":"04a97f1b-1537-4978-9520-00d206c27491","year":2015},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.293251Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:86bcdcec3cdfd837874b9f32f970e3d0973f981844a42909e1f7cf3604f7e166","observation_id":"aceee6f6-9133-4a65-b881-7d1dd9faacbe","resolution":{"observed_at":"2026-08-16T04:21:01.918924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.899887Z","title":"M., Guerraoui, R., and Stainer, J","venue":null,"work_id":"2c49f738-f9b3-43e4-9788-41ab9382348b","year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.296615Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:869ceb38d94643bb0b9fce015791d944b56e0c61e479b9b269ca2bc1874e7573","observation_id":"77260611-0386-47ab-a6a0-4e537255f950","resolution":{"observed_at":"2026-08-16T04:21:01.904559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.299964Z","title":"B., Patel, S., Ramage, D., Segal, A., and Seth, K","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.299964Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:91a517b49342bb0260717648b70542ab3ac9f0569993602bf1119098c6599a5e","observation_id":"be90e061-2754-403d-96ab-2ef4d9fb00b0","resolution":{"observed_at":"2026-08-16T04:21:00.299964Z","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":"2026-08-16T04:21:01.876372Z","title":"Distributed statistical machine learning in adversarial settings: B yzantine gradient descent","venue":null,"work_id":"1d8265dd-1e7c-4990-a29e-5aba9750edde","year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.303149Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:7cc54c298d27cb4d60b990f9c8228d40d09c470f2c76366e8cf58e40c4844d9d","observation_id":"8afa0318-6c0f-4f82-beac-92936ff84989","resolution":{"observed_at":"2026-08-16T04:21:01.881064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.861177Z","title":"Distributed differential privacy via shuffling","venue":null,"work_id":"1df17e93-9439-44e7-b279-bf9f2107f40b","year":2019},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.307159Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:2e585fed6db86b13665348a7b05fd0a922c7ce426235417c4fd882e21e5a4bbb","observation_id":"3e4f45eb-f94d-4830-aa44-c6bd475e2a58","resolution":{"observed_at":"2026-08-16T04:21:01.866213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.846218Z","title":"Manipulation attacks in local differential privacy","venue":null,"work_id":"44c8403a-74a9-4a6a-9edd-0b79eb86e1b7","year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.311111Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:de2a774e7b0c3753e468582bd7dbeb699fa177b308707d1895fb5eab5a893ca9","observation_id":"d53ac042-b492-4a36-a711-375544037693","resolution":{"observed_at":"2026-08-16T04:21:01.850960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.315102Z","title":"Towards practical homomorphic aggregation in byzantine-resilient distributed learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.315102Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:f8d0ac5d81d5340507b52559b1fb55b5fc3f34f2ea3fd9daa26580609caddd23","observation_id":"539e8232-01ff-4a45-8d19-c32b44d87489","resolution":{"observed_at":"2026-08-16T04:21:00.315102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.02578","last_updated":"2020-02-27T15:59:56Z","snapshot_observed_at":"2026-08-16T17:02:43.551502Z","submitted_at":"2019-10-07T02:10:30Z","title":"Differential Privacy-enabled Federated Learning for Sensitive Health Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.02578","snapshot_observed_at":"2026-08-16T04:21:00.319408Z","title":"Differential privacy-enabled federated learning for sensitive health data","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.319408Z"},"links":{"cited_paper":"/paper/1910.02578","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:b7a481eca821fe89c2bc1fa5b0e7ce6ff705b9638df2ee61582abffbc3fa9c78","observation_id":"aaed6396-0268-4332-9eae-0bd5aac4fd83","resolution":{"observed_at":"2026-08-16T04:21:00.319408Z","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":"2026-08-16T04:21:01.833463Z","title":"and Boneh, D","venue":null,"work_id":"d3425615-dcd9-4d2f-a7a3-1f274217be35","year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.324225Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:f6650bed0f426f8bf70f0251d12a9184e5de16e4bfe3406c8092cbb8cbcc1f52","observation_id":"1b84d317-0992-4c33-9cb2-9f13c3fc75a1","resolution":{"observed_at":"2026-08-16T04:21:01.837262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.820570Z","title":"a., Senior, A., Tucker, P., Yang, K., Le, Q., and Ng, A","venue":null,"work_id":"a04af02c-b80b-4098-9edf-9fb5f6652b27","year":2012},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.328348Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:1ba10ddd45c5b1427beec4c19d74bfd529b5e6c7b7d02211cdc4b2514b782371","observation_id":"c8472cdd-5adc-4d4d-b9a5-4d713540f12e","resolution":{"observed_at":"2026-08-16T04:21:01.824484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.807273Z","title":"M., Li, J., Moitra, A., and Stewart, A","venue":null,"work_id":"8c7cead4-f57f-4967-98e4-19068089334f","year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.332577Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:a97b5f738a7129fe0e29148052ee585e3c3d608f305d6e0d76bd81f7f56c2bf9","observation_id":"95c92eb9-1f61-4c67-a5da-fbba7e3d54f6","resolution":{"observed_at":"2026-08-16T04:21:01.811063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.792823Z","title":"C., Jordan, M","venue":null,"work_id":"507f9477-4eb4-44a1-9d89-58de90921509","year":2013},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.336658Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:742214b13565c703f4ba99cc20e0761c0097e2c408f063df6fbbfee5ffa167a2","observation_id":"631c8814-5e99-4bc0-a133-623d3233c829","resolution":{"observed_at":"2026-08-16T04:21:01.797568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.340906Z","title":"C., Jordan, M","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.340906Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:8e2c7e01e37524ceaa41b0e8b524a390e01d2d12b668b8913c6a56569baeab86","observation_id":"7161a1db-d429-4f29-8a0e-fc664783ca99","resolution":{"observed_at":"2026-08-16T04:21:00.340906Z","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":"2026-08-16T04:21:01.769041Z","title":"Amplification by shuffling: From local to central differential privacy via anonymity","venue":null,"work_id":"c125ff7e-e575-4587-9dfc-67a9daf86dd5","year":2019},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.345469Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:1eb8ec4160b15868b6483d8e6373bd673d6d4c527fcacd5ca903cfc63bd83b60","observation_id":"0030b0ce-eee2-429a-80a5-3d2ae6155b3e","resolution":{"observed_at":"2026-08-16T04:21:01.773836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.753789Z","title":"B yzantine machine learning made easy by resilient averaging of momentums","venue":null,"work_id":"8ea1ee72-360b-4fc9-973a-52d108e04b3b","year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.350052Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:58ff7388091fab6768b0ff0fe936eee47059f87622f5071fdd3e8fd9cd4590b5","observation_id":"d929e3c6-f0f2-437f-8921-b5c6f21ab45e","resolution":{"observed_at":"2026-08-16T04:21:01.759053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.739299Z","title":"Distributed robust learning, 2015","venue":null,"work_id":"6c248013-2c5e-4eaf-b862-5a01822c5089","year":2015},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.354534Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:e9e29d4e4400bcdb6ff354b90fac1b4473c561f27f1c45793b667e769a5e5796","observation_id":"e13bff53-132c-45ab-b9c6-8133a6ac3b13","resolution":{"observed_at":"2026-08-16T04:21:01.744074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.358847Z","title":"Model inversion attacks that exploit confidence information and basic countermeasures","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.358847Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:ac57c12c99897c347608b24fc3c376694376bb503ec18b46235f307927b77fed","observation_id":"5746a607-e5ae-4bc2-ab23-d3fb30a85ba8","resolution":{"observed_at":"2026-08-16T04:21:00.358847Z","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":"2026-08-16T04:21:01.724959Z","title":"R \\'e nyi divergence measures for commonly used univariate continuous distributions","venue":null,"work_id":"52701b34-6284-4f5b-89ec-83c40eda0fa1","year":2013},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.363078Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:b41f62bdbff1d0c452986c9e4d5dd836bc587f3f6a428603c1ce9b3ff86848b9","observation_id":"e86b333a-d8dd-44d4-8c50-63f901ce446f","resolution":{"observed_at":"2026-08-16T04:21:01.730039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.12608","last_updated":"2024-12-14T21:25:00Z","snapshot_observed_at":"2026-08-16T15:22:05.387986Z","submitted_at":"2023-06-22T00:11:53Z","title":"DP-BREM: Differentially-Private and Byzantine-Robust Federated Learning with Client Momentum","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.12608","snapshot_observed_at":"2026-08-16T04:21:00.367137Z","title":"Dp-brem: differentially-private and byzantine-robust federated learning with client momentum","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.367137Z"},"links":{"cited_paper":"/paper/2306.12608","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:cf3619b6ead33d8184b46e4ba30a570f75c2298ad4b2cfc04f78fcc1e049b8b9","observation_id":"f21be6d1-2087-4d2d-82cf-a35ece9f04ea","resolution":{"observed_at":"2026-08-16T04:21:00.367137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.371772Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.371772Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:a2b1fe5bb778fd7b442f58e2872fbf563bce3a67a900dec9c15f6ddb5a85a896","observation_id":"e82f1e3d-6a75-48d8-b5d1-502e172a2c07","resolution":{"observed_at":"2026-08-16T04:21:00.371772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.375963Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.375963Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:dd902315422a9436219b61d2156bbc2e4599c56beaedbdf2fdb08e546ea467a6","observation_id":"a5bb5cf2-619f-40ed-b5c5-533ad5b3d1b9","resolution":{"observed_at":"2026-08-16T04:21:00.375963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.380134Z","title":"Deep models under the gan: Information leakage from collaborative deep learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.380134Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:44c383a48af1e40ed1e4a0bc003ae6abfd0b3c85123709b1a6e025cc52faea0d","observation_id":"c8d2b670-9769-4d53-8824-c11c7c599041","resolution":{"observed_at":"2026-08-16T04:21:00.380134Z","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":"2026-08-16T04:21:01.701909Z","title":"B., Kamath, G., and Majid, M","venue":null,"work_id":"5d9eca8d-5ac8-44d4-acf6-90618d9f345b","year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.384258Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:9c49bd2e12324675ded4bc4e313d62f21e45d6e5de1b4218775763eb3318f679","observation_id":"af0283c0-e540-48bb-93c5-de24be782a3d","resolution":{"observed_at":"2026-08-16T04:21:01.706397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06335","last_updated":"2019-09-13T17:26:20Z","snapshot_observed_at":"2026-08-16T05:00:17.345539Z","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":"2026-08-16T04:21:00.388632Z","title":"H., Qi, H., and Brown, M","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.388632Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:4bcd4f38ad30b78c118c1d74117933145869ffed39b4e18d522bebdb142fcd54","observation_id":"3f3679d2-7dc9-48f5-af15-9206db660f1e","resolution":{"observed_at":"2026-08-16T04:21:00.388632Z","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":"2026-08-16T04:21:01.688327Z","title":"Personalized federated learning with differential privacy","venue":null,"work_id":"0383fa94-da52-4d5c-96e7-4d01072df28c","year":2020},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.393299Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:920a3988a1c09cffa7b6226fbbac6762d776a572b20f94445d00acc025f0bb55","observation_id":"4a6a2931-5dc4-4077-8b8b-dc910d9bf267","resolution":{"observed_at":"2026-08-16T04:21:01.692654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2021.31265","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:01.001155Z","title":"M., Sarwate, A","venue":null,"work_id":"16730ef2-96d6-4d2c-a119-4bb632f7c8c3","year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.397532Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:1454541c57aa227d81072f5bb228802617ac0242e8f4c508d2aa9423ea523552","observation_id":"5f602c0a-7f4e-4f21-b33b-02993242d5e4","resolution":{"observed_at":"2026-08-16T04:21:01.008382Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.674182Z","title":"Distributed learning without distress: Privacy-preserving empirical risk minimization","venue":null,"work_id":"7fc8d291-ab19-4452-b641-2227bf931869","year":2018},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.401922Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:8c97f2fa05a54d1150367151a9308786995864c5dc211abc4f1d6a84d2904dfc","observation_id":"458393b5-ee35-49a1-9b94-ef267107cad4","resolution":{"observed_at":"2026-08-16T04:21:01.678914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.406495Z","title":"B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.406495Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:eac49d4b4d4dc4d035853c229011bceb7f94234d40449970d90f5834881cb087","observation_id":"bd308d2b-b50d-4773-8a9c-b9e0d7e89056","resolution":{"observed_at":"2026-08-16T04:21:00.406495Z","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":"2026-08-16T04:21:01.649162Z","title":"A., Makowski, M","venue":null,"work_id":"c97183ac-db5e-4b0e-ab31-766ea9e71a88","year":2020},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.410535Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:76bd7293658a65ffa0c3a29a8bacf9632f1e4c63a545fb84dcb3a1b3a4ebf16c","observation_id":"d1c9645c-7912-4195-9ed1-2c494219e22c","resolution":{"observed_at":"2026-08-16T04:21:01.653835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.635563Z","title":"Linear convergence of gradient and proximal-gradient methods under the polyak- ojasiewicz condition","venue":null,"work_id":"20a4bf23-649c-4e39-b47c-a285e6b96b0e","year":2016},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.414869Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:c8806ad224c8984b96cb1ecb515aaa66b74f8f824eb365ca477e2b83da8670a4","observation_id":"2d2c5d7f-81f2-48a4-b48f-aeb202b13dcb","resolution":{"observed_at":"2026-08-16T04:21:01.639660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.623285Z","title":"P., Kale, S., Mohri, M., Reddi, S., Stich, S., and Suresh, A","venue":null,"work_id":"7d524a7c-172e-4366-9244-2595f9dfbbd0","year":2020},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.418975Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:695eb63ac45ba494fbdb1b5cbedb843e8d9031bda379abfe045db215775bb80d","observation_id":"3ff06b01-e254-434b-bc7b-e7ae12d8640d","resolution":{"observed_at":"2026-08-16T04:21:01.626926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.609701Z","title":"P., He, L., and Jaggi, M","venue":null,"work_id":"5a90c31e-9de3-47da-810d-0b573ffbbbb8","year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.423076Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:b94049ab5e428241a42cc4f54e1eee038269cbd92a1ab29191c7e09d1e219b6a","observation_id":"e8a50679-36b1-40d8-ab10-96901cd4688f","resolution":{"observed_at":"2026-08-16T04:21:01.614673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.595480Z","title":"P., He, L., and Jaggi, M","venue":null,"work_id":"1b85f8cb-cda7-4010-9f81-4f8a171dd59c","year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.427135Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:8bb3eeb58cb2a2e6387ba391ffb94b52759f5b0e31a7af751056b71d22b07e16","observation_id":"d84edfd7-fd2e-4335-8c7d-9647e11b709e","resolution":{"observed_at":"2026-08-16T04:21:01.600195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.430827Z","title":"P., Lee, H","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.430827Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:63e51da7de3f4379921ed35123aeee88180753e4945c8b6a3c4fe7a4adbbc879","observation_id":"b82143f9-ba59-4134-865e-c4e1e25f58a3","resolution":{"observed_at":"2026-08-16T04:21:00.430827Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.434369Z","title":"The B yzantine generals problem","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.434369Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:19e64f324272e600edf614533ae5b2d4110d49138a93994ec13d442c5f96c3d4","observation_id":"5b88d548-e7e5-4e1c-ac15-d98cec71b013","resolution":{"observed_at":"2026-08-16T04:21:00.434369Z","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":"2026-08-16T04:21:01.572588Z","title":"and Cortes, C","venue":null,"work_id":"135a44e3-969a-43ec-88d3-7d636bf777ce","year":2010},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.438004Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:915678d9c9567187e81e882998130f9d6cd9a6fd730ca6628b46c18852bba28a","observation_id":"7613655c-6e20-46d5-84e3-d65c903a3638","resolution":{"observed_at":"2026-08-16T04:21:01.577556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.558649Z","title":"Robust and differentially private mean estimation","venue":null,"work_id":"fcbbb7a7-9d27-4499-aa6d-11d0766bf7ae","year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.441573Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:82c67182321dbd74a9ef67c606eaea14341453f3d155b3402e2d34f179c14f87","observation_id":"f7f1d325-351c-4b63-91d1-473e80c61a36","resolution":{"observed_at":"2026-08-16T04:21:01.563288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.543715Z","title":"Differentially private B yzantine-robust federated learning","venue":null,"work_id":"858aae7a-6752-49d2-a9c5-712bc75ac9d1","year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.444934Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:bfb5e1055bcb7ec8e4bc052735fbfafc13465b38640f00d0bb8f3b7a50750c24","observation_id":"a4b28c01-0231-4082-8eaa-d8185a469935","resolution":{"observed_at":"2026-08-16T04:21:01.548479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.448453Z","title":"D., and Shmatikov, V","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.448453Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:1a754a4e2789ae92a5313348d65087314ece07575f2c169239646addf3f5b201","observation_id":"07b23795-2292-4aa3-8073-05a8c158ca32","resolution":{"observed_at":"2026-08-16T04:21:00.448453Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.452221Z","title":"R \\'e nyi differential privacy","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.452221Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:9c67fc57d6f735a91c97d07a565eb660812b7e39f9185614a3f76ad1e64ff8e4","observation_id":"bf9e9843-9f85-4f99-b7f0-87a9d648ad0d","resolution":{"observed_at":"2026-08-16T04:21:00.452221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.455644Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.455644Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:8fa07931f218ca9b02077ca4b947d91280524fed7ccd7853667676d37eb67172","observation_id":"6adae7b2-9d8d-43b8-aa1a-3905c85e47c8","resolution":{"observed_at":"2026-08-16T04:21:00.455644Z","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":"2026-08-16T04:21:01.511279Z","title":"Differentially private federated learning on heterogeneous data","venue":null,"work_id":"65e5f64e-56c8-42a8-af5e-1e979bc84703","year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.459020Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:7f15f5071c139d9dd68c9c5b857cda0ede89c8c8fe977c277e52ee0af367d18f","observation_id":"b512f7c9-9986-4723-8d00-587b7c77c7d7","resolution":{"observed_at":"2026-08-16T04:21:01.516448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.496148Z","title":"Lecture notes: Statistics, optimization and algorithms in high dimension, 2020","venue":null,"work_id":"c3228bc0-d307-47d9-9f9e-c0fef2a73b38","year":2020},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.462983Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:89414fff629124954058c4e428050acb53cbef270cd213561ff0aea1f8120845","observation_id":"6debd4fd-f4b7-4cfc-8cd3-b4e4e39f39e2","resolution":{"observed_at":"2026-08-16T04:21:01.500820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.482135Z","title":"T., Aono, Y., Hayashi, T., Wang, L., and Moriai, S","venue":null,"work_id":"1f168098-8528-492f-8678-aa524bbf19b8","year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.467333Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:f60e0dc7d2fe6387541c9a3b940c19fb690e5af8174d517edc05cdf7c8c32ab4","observation_id":"bbcd3a2c-b97a-4971-9f73-2800e7ab4076","resolution":{"observed_at":"2026-08-16T04:21:01.487034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.469597Z","title":null,"venue":null,"work_id":"0a354281-7b06-483b-a4f7-40c03ab51621","year":2006},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.471465Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:3a03ccb57c50f5379d7b68ccab061f1ca14271a77d47f32140c0ac2b193e70bf","observation_id":"e5b4dc14-84c5-40ac-a089-03420d40e864","resolution":{"observed_at":"2026-08-16T04:21:01.473626Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.455477Z","title":"and H \\\"u tter, J.-C","venue":null,"work_id":"e4be91f0-b014-45ad-b0bf-5eba9efd4308","year":2015},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.475645Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:74f014b7b3c27707d8759069be542cf1a6fca1a47c7fa925f0f490ae6f9037c8","observation_id":"6cedb57a-b0a0-4046-b024-23844cb2f034","resolution":{"observed_at":"2026-08-16T04:21:01.460354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.430650Z","title":"An accurate, scalable and verifiable protocol for federated differentially private averaging","venue":null,"work_id":"71428acf-bdd2-4302-863c-54ab3d6d09ae","year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.479832Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:e0f4eb087b7cfa84cf31e888b586974f48ff21d5844233c796406bcd8b340e94","observation_id":"2370fae9-69ee-4ce3-bd7e-51e9d692c4df","resolution":{"observed_at":"2026-08-16T04:21:01.446167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:00.484189Z","title":"How to share a secret","venue":null,"work_id":null,"year":1979},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.484189Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:399428476ee478049c3371e22f51971a6ed70039ae14b3f56235f259458fe589","observation_id":"e6a848f2-6138-4d72-975e-934da7be7d33","resolution":{"observed_at":"2026-08-16T04:21:00.484189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.05820","last_updated":"2017-03-31T22:17:07Z","snapshot_observed_at":"2026-08-14T21:34:36.777438Z","submitted_at":"2016-10-18T22:38:33Z","title":"Membership Inference Attacks against Machine Learning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.05820","snapshot_observed_at":"2026-08-16T04:21:00.488254Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.488254Z"},"links":{"cited_paper":"/paper/1610.05820","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:2bf3fd4054cc8a1d0802a741ade2d4e095d7c3d3197604b7c1296f0a1985bcc3","observation_id":"fe0715e7-12cc-484c-a923-ef771eeea1c3","resolution":{"observed_at":"2026-08-16T04:21:00.488254Z","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":"2026-08-16T04:21:01.408612Z","title":"Resilience: A criterion for learning in the presence of arbitrary outliers","venue":null,"work_id":"4fe8309c-fee9-410e-a637-6efc22452f70","year":2018},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.492952Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:90a677650a555c22cdfa4e5e8f3007af158ebc913b4a95597c3ca797b35443c5","observation_id":"2632eb07-1470-4830-8d5f-7234f66bbab6","resolution":{"observed_at":"2026-08-16T04:21:01.412390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1011.3027","last_updated":"2011-11-23T21:11:38Z","snapshot_observed_at":"2026-08-15T05:03:06.028283Z","submitted_at":"2010-11-12T20:20:28Z","title":"Introduction to the non-asymptotic analysis of random matrices","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1011.3027","snapshot_observed_at":"2026-08-16T04:21:00.496985Z","title":"Introduction to the non-asymptotic analysis of random matrices","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.496985Z"},"links":{"cited_paper":"/paper/1011.3027","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:175ceb837a776d1c44c733dd875c2739d3ed92d662277b4520ec2db7fbc3219f","observation_id":"9c5cc2da-6e0e-4c7f-b291-47aae463d49f","resolution":{"observed_at":"2026-08-16T04:21:00.496985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.501823Z","title":"Beyond inferring class representatives: User-level privacy leakage from federated learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.501823Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:485eeb2d12a74f23a3e5d787a088145405ef126d8c953767308bf555d6e66aae","observation_id":"3d05033b-3031-4f2d-a511-ae4800665825","resolution":{"observed_at":"2026-08-16T04:21:00.501823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.00665","last_updated":"2023-02-17T22:45:05Z","snapshot_observed_at":"2026-08-16T16:27:26.897753Z","submitted_at":"2022-10-03T00:44:09Z","title":"Distributed Non-Convex Optimization with One-Bit Compressors on Heterogeneous Data: Efficient and Resilient Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.00665","snapshot_observed_at":"2026-08-16T04:21:00.505987Z","title":"and Su, L","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.505987Z"},"links":{"cited_paper":"/paper/2210.00665","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:f75991d74910ffb9c11667f1cd26cf85c008a0e2ed4012383a27783f300691cc","observation_id":"da12245c-c25a-4b63-a853-bb3102e1889d","resolution":{"observed_at":"2026-08-16T04:21:00.505987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-16T04:21:00.510505Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.510505Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:e83d560e7c3c4f9fbfab97a67aa148fe506c0d2da8d58e377ab9d8e6d2afc7a3","observation_id":"62cade4a-07ed-43d6-afba-325e5590da82","resolution":{"observed_at":"2026-08-16T04:21:00.510505Z","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":"2026-08-16T04:21:01.395991Z","title":"Generalized B yzantine-tolerant sgd","venue":null,"work_id":"52a99a91-45ea-4e8f-b400-397983968c20","year":2018},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.514822Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:526ed6094a9a6365c0a28e279f009bf8bb5a7d6a3c2644219f8bde797b0c7863","observation_id":"69040a6b-4f98-47d9-b5ad-bd123d053ea8","resolution":{"observed_at":"2026-08-16T04:21:01.400146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.380319Z","title":"Fall of empires: Breaking byzantine-tolerant sgd by inner product manipulation","venue":null,"work_id":"52c8fc41-a2e3-49b2-ba4e-93a3ad939b93","year":2020},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.519771Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:575b36514b7e70862ee81d518cb4a6b7328af42189a0c75afc5d8cd7c483d8f7","observation_id":"21cb9a30-b70c-4dc0-9e7e-6f7ff3c8b447","resolution":{"observed_at":"2026-08-16T04:21:01.385193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.365570Z","title":"Unraveling the connections between privacy and certified robustness in federated learning against poisoning attacks","venue":null,"work_id":"26dc4ce0-7dc4-4d5f-86cb-6d1cf952675e","year":2023},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.524016Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:afc103331fdc2473c10f2286924b214996eac3a8ddbcf119a73c396c2c870551","observation_id":"f202fe13-f029-40d6-9eea-10fa578994f7","resolution":{"observed_at":"2026-08-16T04:21:01.370138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.351156Z","title":"B yzantine-robust distributed learning: Towards optimal statistical rates","venue":null,"work_id":"3b8897c8-136b-4324-859a-e8cc86e776f6","year":2018},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.528015Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:bc884aee135e317916abdbf7a8109d8ac8196918eb979c66164312a2ca3920e7","observation_id":"fe30d771-680d-441d-a217-093ab2148ec6","resolution":{"observed_at":"2026-08-16T04:21:01.355689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-16T17:54:08.474823Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-16T04:21:00.532103Z","title":"Opacus: User-friendly differential privacy library in pytorch, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.532103Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:32f01513686436147e6b87c9979f7a3c3b423e73d39fb93ec0f2965e55db33a0","observation_id":"c27c6d70-14a4-4f42-bff6-9ab15aba4889","resolution":{"observed_at":"2026-08-16T04:21:00.532103Z","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":"2026-08-16T04:21:01.336877Z","title":"BatchCrypt : Efficient homomorphic encryption for Cross-Silo federated learning","venue":null,"work_id":"2ce2a09e-79cf-4f0a-b4fe-4629fea05591","year":2020},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.536474Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:c2040505f5d7728462b9de4f6ce37657bd69882c7e06b5fb8639f10f7497b971","observation_id":"9f38fa0c-4c3d-4f79-b505-34a7878e0a97","resolution":{"observed_at":"2026-08-16T04:21:01.341593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.322302Z","title":"Robust estimation via generalized quasi-gradients","venue":null,"work_id":"6031aa3a-140e-48df-8f80-ced9f80cf37f","year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.540025Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:0742de8c2209e22b7cc8eb1606584270c9a7b08eaa5d67a8d9c4198a07a4b873","observation_id":"62964878-98c8-4ebb-ba70-812874d0dd25","resolution":{"observed_at":"2026-08-16T04:21:01.327515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.24963/ijcai.2022/337","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:21:00.577669Z","title":"and Ling, Q","venue":null,"work_id":"29c3aa09-2145-4541-8cfd-634bf958a616","year":2022},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.543622Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:4eaf3ac5e8e00b562f8155b7df3ae724f99bb2c6999a7bb00f5b29649a518604","observation_id":"0606d51a-86cb-41e3-a76b-82a6ec1580d0","resolution":{"observed_at":"2026-08-16T04:21:00.582307Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T04:21:01.306845Z","title":"Deep leakage from gradients","venue":null,"work_id":"daefc423-70bb-4ef9-ac21-8596a6de93f0","year":2019},"citing_paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-16T04:21:00.547075Z"},"links":{"citing_paper":"/paper/2505.01874"},"observation_digest":"sha256:e6a328a59506d9fde487ad4766e8e6d8119040fce1a06b2ed315597d65e266b1","observation_id":"b0318781-333a-4373-83f6-769ae224c20e","resolution":{"observed_at":"2026-08-16T04:21:01.310990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.01874","last_updated":"2025-06-04T15:22:18Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T17:02:54.162538Z","submitted_at":"2025-05-03T17:35:47Z","title":"Towards Trustworthy Federated Learning with Untrusted Participants"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":26,"verified_exact":1,"verified_fuzzy":46},"total_outbound_references":74},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 1 inbound Pith citation observation for arXiv:2505.01874."}