{"as_of":"2026-08-18T09:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ce7eeca7acc96ef78ee6e2f7fede9f3f087111ed3315c1b0f61401b8923fed4e","coverage":[{"denominator":77,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":77,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T05:31:11.973765Z","state":"measured"},{"denominator":77,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":77,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.03231/citation-record","integrity":"/paper/2502.03231/integrity","json":"/paper/2502.03231/citation-record.json","paper":"/paper/2502.03231"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T05:31:13.228259Z","title":"Advances and open problems in federated learning.Foundations and Trends® in Machine Learning, 14(1–2):1–210, 2021","venue":null,"work_id":"19783fb9-af39-4116-b354-32e243673bf3","year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.536835Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:56afc664de2b9bb90900c7400bc2f4800a03890aa4d9313aeab532ccbab323e2","observation_id":"0bda1dda-a4fc-4d92-96f9-1624d803acf1","resolution":{"observed_at":"2026-08-09T05:31:13.233696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:11.542598Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.542598Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:a58c7e03a928d2bea4884ef1aa48d45ee721df047d3b1bcd5f280a8f110101d6","observation_id":"db1ed7c0-b592-4618-82c0-79e03ff36843","resolution":{"observed_at":"2026-08-09T05:31:11.542598Z","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":"2026-08-09T05:31:11.547817Z","title":"Federated learning based on dynamic regularization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.547817Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:b0246e4875b22b4283e5aec9cab608952e3f89e542581b7e679d20f7c6f9d25b","observation_id":"636eb726-5ecf-42fd-8e50-8e17d8e8ee88","resolution":{"observed_at":"2026-08-09T05:31:11.547817Z","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":"2026-08-09T05:31:11.561249Z","title":"Federated optimization in heterogeneous networks.Proceedings of Machine learning and systems, 2:429–450, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.561249Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:33db3564c68c13908e8b393b63fe201bf61a7a196db97d53c1165ebd188a2329","observation_id":"aff3a6a3-b7d6-4213-a3a2-ec185ce7da5f","resolution":{"observed_at":"2026-08-09T05:31:11.561249Z","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":"2026-08-09T05:31:11.566929Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.566929Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:27aea2c3855a46ad19a4a398a079c15df73b34a6d13bad867deeb41408f904b8","observation_id":"0fa9d4f4-3960-44cb-9f05-f0ae2f010d26","resolution":{"observed_at":"2026-08-09T05:31:11.566929Z","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":"2026-08-09T05:31:13.170307Z","title":"Personal- ized edge intelligence via federated self-knowledge distillation.IEEE Transactions on Parallel and Distributed Systems, 34(2):567–580, 2022","venue":null,"work_id":"64a0ebcb-82ea-487f-8133-fb91d43027a7","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.572114Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:6c682fff93f84eff38e52149e74b1d55b55ddbe48060ad025617e8140e7e26f8","observation_id":"ed306b32-f224-4181-a90a-94782d1c50de","resolution":{"observed_at":"2026-08-09T05:31:13.175741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:13.152367Z","title":"Preservation of the global knowledge by not-true distillation in federated learning.Advances in Neural Information Processing Systems, 35:38461–38474, 2022","venue":null,"work_id":"f99212dd-2c73-4308-a958-2b19d306e666","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.578052Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:0d18c2451a191fd15379752dce12c660f2f204239c636d8efbc991e2f6e4a48f","observation_id":"c6631a33-957e-4b07-98ad-34ce95e263ff","resolution":{"observed_at":"2026-08-09T05:31:13.158395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:13.136458Z","title":"Rethinking personalized federated learning from knowledge perspective","venue":null,"work_id":"57602e51-f0e8-4196-b3cc-62f908b44cfd","year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.583014Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:b39e61ec954381117742a979c4eb1c7c98d084afe91b5da7ba222bc67a68b6b6","observation_id":"06353927-137e-456d-b867-e36aca61c8ba","resolution":{"observed_at":"2026-08-09T05:31:13.141574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:13.117739Z","title":"Federated learning on non-iid data: A survey.Neurocomputing, 465:371–390, 2021","venue":null,"work_id":"5cd433ae-24e5-435c-a7cb-93a5171a1259","year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.590029Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:9f4aea0bab4c9df5b57a958b31ff5780b84a006a60a3d4a84b2e2b21476c8427","observation_id":"4158ffae-1e46-4b6c-81c1-9d682d9f4e6e","resolution":{"observed_at":"2026-08-09T05:31:13.124814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:13.101170Z","title":"Fedbn: Federated learning on non-iid features via local batch normalization","venue":null,"work_id":"ed32e3bc-f9ec-447b-b7b8-6c36e28fe766","year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.595252Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:8e8b218d8e8611071d867b88bdb956b1b88b181a9322c29c1b6ccfbe3ca205c4","observation_id":"63fc7af5-9e1e-4e3e-9be6-ae29151b0cf6","resolution":{"observed_at":"2026-08-09T05:31:13.106256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:13.085271Z","title":"Bold but cautious: Unlocking the potential of personalized federated learning through cautiously aggressive collab- oration","venue":null,"work_id":"1da3e1aa-06e1-4374-a651-d2d6c4285f11","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.600227Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:8dbb0ef183ae48549adf1e6e4b5992597e60de34a2dc2abb25aa4cc6ea9268e3","observation_id":"37f67c61-635a-4faf-9edf-eda2df170644","resolution":{"observed_at":"2026-08-09T05:31:13.090229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:11.607018Z","title":"Model-contrastive federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.607018Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:aac76e94ac20d180186ccc08db33f368f52ed9fffdee905c25bf843d9f1d8620","observation_id":"cdf67db7-cbc4-458c-a7fa-b01c947a56ea","resolution":{"observed_at":"2026-08-09T05:31:11.607018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.00818","last_updated":"2019-12-02T14:29:00Z","snapshot_observed_at":"2026-08-16T08:02:37.158308Z","submitted_at":"2019-12-02T14:29:00Z","title":"Federated Learning with Personalization Layers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.00818","snapshot_observed_at":"2026-08-09T05:31:11.611967Z","title":"Federated learning with personalization layers.arXiv preprint arXiv:1912.00818, 2019","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.611967Z"},"links":{"cited_paper":"/paper/1912.00818","citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:96dce06bbb71fe2fd37b2fa86ea63f4ffb7f6032a5a0a7c7e593bad776babf00","observation_id":"f40a6aea-1c65-494c-b826-3631f65cbf0c","resolution":{"observed_at":"2026-08-09T05:31:11.611967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.01523","last_updated":"2020-07-14T08:12:35Z","snapshot_observed_at":"2026-08-14T23:16:03.815025Z","submitted_at":"2020-01-06T12:40:21Z","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.01523","snapshot_observed_at":"2026-08-09T05:31:11.618558Z","title":"Think locally, act globally: Federated learning with local and global representations.arXiv preprint arXiv:2001.01523, 2020","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.618558Z"},"links":{"cited_paper":"/paper/2001.01523","citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:d702a173f5cce34376b437a4b317a818ebab8b032e2591993b1e0cdef42d7b0f","observation_id":"e019f625-530b-4d3a-837e-496338fe917c","resolution":{"observed_at":"2026-08-09T05:31:11.618558Z","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":"2026-08-09T05:31:13.059507Z","title":"Partialfed: Cross-domain personalized federated learning via partial initialization.Advances in Neural Information Processing Systems, 34:23309–23320, 2021","venue":null,"work_id":"4c42b08f-0eca-4398-8e53-ead8e0bf472e","year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.624379Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:b0c6b7761428ee5385f9e8bafe809be7bd28aedfef172dfa085e67c8bfc10d3c","observation_id":"f3ca8171-5356-4088-9ff0-7b0795d1128e","resolution":{"observed_at":"2026-08-09T05:31:13.063956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:13.043468Z","title":"Where to begin? on the impact of pre-training and initialization in federated learning","venue":null,"work_id":"53a4fb16-8da2-41fd-8716-7882bb949aae","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.629890Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:ddc4d0ba131f0a34080a2176dfde081cd1b4a9ec306ccfe78f7d77b35831d95a","observation_id":"5f684fce-790b-47a8-9a7f-32800f6f4b9c","resolution":{"observed_at":"2026-08-09T05:31:13.049103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:13.025502Z","title":"On the importance and applicability of pre-training for federated learning","venue":null,"work_id":"aaf1f06c-ee7c-4c43-ab49-aa0d3d1dbdc0","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.635040Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:7ba7ea6b756a1955b9822a419090192e7564ad3ab5b50b015404a79af51ccfb8","observation_id":"de366663-79b0-4f74-b222-337e5f373c35","resolution":{"observed_at":"2026-08-09T05:31:13.030519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:13.009289Z","title":"Fedbabu: Toward enhanced representation for federated image classification","venue":null,"work_id":"42b6c043-90c7-42b3-8deb-aa13c976f58e","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.639682Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:62bd611875d776b23664d9b203616b89a3d886314521737e68a50eda1e0bb433","observation_id":"0d484260-363c-4205-baed-a72025e1d8e9","resolution":{"observed_at":"2026-08-09T05:31:13.014313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.992422Z","title":"No fear of classifier biases: Neural collapse inspired federated learning with synthetic and fixed classifier","venue":null,"work_id":"2996a714-33c0-488a-b801-042ca0274cad","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.645294Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:0f8ee951b711ebfa0349f3e6c3a0c34060b8711113031ebf4b5bc115e28e6102","observation_id":"73936ff4-1f26-4ab6-8a55-fbf2426d744f","resolution":{"observed_at":"2026-08-09T05:31:12.997714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.976974Z","title":"Methods for interpreting and understanding deep neural networks.Digital signal processing, 73:1–15, 2018","venue":null,"work_id":"d7fd224c-ee2c-4a24-955c-738975173d91","year":2018},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.650725Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:16555b153dc18339f1c01e3a7e579a7a6ffe05227f50b0f7494c32685d572416","observation_id":"ba40726c-d861-483b-91df-e261bca06bc3","resolution":{"observed_at":"2026-08-09T05:31:12.981843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.961098Z","title":"Explaining deep neural networks and beyond: A review of methods and applications.Proceedings of the IEEE, 109(3):247–278, 2021","venue":null,"work_id":"3ae70935-03d5-4780-b02d-17608dd6c2df","year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.657140Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:dba5929646835ce1ce7292911051c4b66c03040032655fcb90f7d00feaabf6ab","observation_id":"c5658e8e-e819-4463-acdc-d4f604370870","resolution":{"observed_at":"2026-08-09T05:31:12.966055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:11.662376Z","title":"How transferable are features in deep neural networks?Advances in neural information processing systems, 27, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.662376Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:4f94586d63cd1d280dd023031c0f240e34ce0562cfaa587585f40e0d1479930e","observation_id":"0ac80532-369e-4307-9293-ce2aa2cbb24e","resolution":{"observed_at":"2026-08-09T05:31:11.662376Z","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":"2026-08-09T05:31:11.667453Z","title":"Feature visualization.Distill, 2(11): e7, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.667453Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:2f699e557b8c218cc4a78f71a7c2d0807455b6b318a7ca8a7399443b6bad71c8","observation_id":"e54a3903-521e-4b3f-a2b8-156fab0673e2","resolution":{"observed_at":"2026-08-09T05:31:11.667453Z","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":"2026-08-09T05:31:11.672473Z","title":"The tunnel effect: Building data representations in deep neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.672473Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:f8a5afc0ab3e61f39c038c1eb2918bea5d4ecaeed19de28e1961c0f85f176db6","observation_id":"8642235a-7023-4316-aa2e-bf4b0d98842c","resolution":{"observed_at":"2026-08-09T05:31:11.672473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.02960","last_updated":"2026-07-02T02:35:50Z","snapshot_observed_at":"2026-08-16T14:45:44.903399Z","submitted_at":"2023-11-06T09:00:38Z","title":"Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.02960","snapshot_observed_at":"2026-08-09T05:31:11.677699Z","title":"Under- standing deep representation learning via layerwise feature compression and discrimination","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.677699Z"},"links":{"cited_paper":"/paper/2311.02960","citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:c2578737e168fdef537b5a7381e101bebc7f89fb2fe31efe7fc5a2c3b403839d","observation_id":"5495f630-d2ac-42ce-9efc-885884e1843b","resolution":{"observed_at":"2026-08-09T05:31:11.677699Z","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":"2026-08-09T05:31:11.683291Z","title":"Visualizing and understanding convolutional networks","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.683291Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:989fb866ca39abcb7aee3902349b91f0d1b0d95a9f1b39d969fccf0d0b9c3050","observation_id":"e0ac99a8-005f-4d67-9d72-b9f793001728","resolution":{"observed_at":"2026-08-09T05:31:11.683291Z","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":"2026-08-09T05:31:12.903196Z","title":"Feature learning in deep classifiers through intermediate neural collapse","venue":null,"work_id":"87a437ad-c327-4851-97c5-e1d8856352fb","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.688576Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:9eca4466bc3d77939a2e86cb747ee31566174744439a1cf3f4cbf1471ce8afe5","observation_id":"b09781fa-5a9a-4068-a028-c36a63fa84d2","resolution":{"observed_at":"2026-08-09T05:31:12.908871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.885956Z","title":"No fear of hetero- geneity: Classifier calibration for federated learning with non-iid data.Advances in Neural Information Processing Systems, 34:5972–5984, 2021","venue":null,"work_id":"a7b952d4-f86a-4303-bf38-a14a83f92ba8","year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.693868Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:242d0f64028dfe885ecced9a2b7f798ba61cc712e541f84b6f2d0dc937e1e582","observation_id":"f5e846bc-161d-44b2-a86e-87c87e1814c1","resolution":{"observed_at":"2026-08-09T05:31:12.891986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.869286Z","title":null,"venue":null,"work_id":"8bb9da41-dcfa-4955-a9ae-548ee8e12f42","year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.699279Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:1673c7290ffdaa9dd6485ebe1570c6749caeaba4d4b22d10526305696987505e","observation_id":"5ad1b099-cc6f-4b47-9c8c-3faab7da2c36","resolution":{"observed_at":"2026-08-09T05:31:12.874532Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.851516Z","title":"Layer-wise linear mode connectivity","venue":null,"work_id":"2c170a3a-135d-4bbb-ac09-4e6165d3ccf4","year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.704795Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:160ab42719e913aa6142a7a7953b9272cf811cecb7636c4d6404372215428224","observation_id":"af0c4494-4ee7-4dc9-bc8a-4e900a00cf78","resolution":{"observed_at":"2026-08-09T05:31:12.857108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:11.709907Z","title":"Deeper, broader and artier domain generalization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.709907Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:479c14a7b07d97fceb0686126d169ea606068f6834c67a88f6a8c51d993fd8c5","observation_id":"eb7e8dae-5974-437f-aea8-8b990731cd04","resolution":{"observed_at":"2026-08-09T05:31:11.709907Z","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":"2026-08-09T05:31:11.715010Z","title":"Moment matching for multi-source domain adaptation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.715010Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:3700b688a9500eb7d71ad03dcf45d8df012806dc637750a087c302617bcb675c","observation_id":"e04a3dd5-0579-45dc-936a-d05378be0c70","resolution":{"observed_at":"2026-08-09T05:31:11.715010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-09T05:31:11.719948Z","title":"Very deep convolutional networks for large-scale image recognition.arXiv preprint arXiv:1409.1556, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.719948Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:ca630a189ed11b3ed9da45639c1a2d5fb2a452f45cb4bd77ba355d645dc8de51","observation_id":"a7798712-6dc8-4404-9356-b8a0d781deba","resolution":{"observed_at":"2026-08-09T05:31:11.719948Z","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":"2026-08-09T05:31:11.725427Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.725427Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:2140bccaf95587c897b7c80f21c1ad7c9bc6dc0e7cc4a25241a87e2640cd983c","observation_id":"fbdfb82b-1b55-411f-8e13-2f01b8dbd53f","resolution":{"observed_at":"2026-08-09T05:31:11.725427Z","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":"2026-08-09T05:31:11.730750Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.730750Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:ec02f4c2667bc7e37e547626475ec9250ffa57e219d559385566f1d493423841","observation_id":"26ce4162-ae09-48d3-8967-7bfae7564d59","resolution":{"observed_at":"2026-08-09T05:31:11.730750Z","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":"2026-08-09T05:31:11.735924Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.735924Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:626da278769e20fb6bc992687db481ef8c97b9f531f04437f9a2ecf59feb7825","observation_id":"2d88f982-18dd-4b5e-bd2f-34b848b2285c","resolution":{"observed_at":"2026-08-09T05:31:11.735924Z","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":"2026-08-09T05:31:11.741705Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.741705Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:e91f5b209561cb07ac40e6e1ead5f41cb81117a545f2ef3851a462caaf7c168d","observation_id":"342da9dd-5c02-4c0b-9761-f286aea4f210","resolution":{"observed_at":"2026-08-09T05:31:11.741705Z","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":"2026-08-09T05:31:12.770412Z","title":"Does learning from decentralized non-iid unlabeled data benefit from self supervision? InThe Eleventh International Conference on Learning Representations, 2023","venue":null,"work_id":"c49a4bc3-eec0-493b-8e87-4b9a25ee3aed","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.747201Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:0518b82a757280a6cd6e186c5551b856d8d69a6a8ef24f905070012477a0f9b9","observation_id":"5257a6fc-229c-4952-b0ee-a76acc53dd20","resolution":{"observed_at":"2026-08-09T05:31:12.775676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.754611Z","title":"Essai sur la géométrie à n dimensions.Bulletin de la Société mathématique de France, 3:103–174, 1875","venue":null,"work_id":"c65ff32d-8d1f-47eb-8f57-b79a1a5d6a21","year":null},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.752514Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:95f56791a42a29f113d050924c436db140a48c4ce40b571c26c273bde2dff4d0","observation_id":"dab14f03-99d4-47c6-a108-1e88b8be1c62","resolution":{"observed_at":"2026-08-09T05:31:12.759895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.738046Z","title":"Numerical methods for computing angles between linear subspaces.Mathematics of computation, 27(123):579–594, 1973","venue":null,"work_id":"0b5476ef-1a00-4995-afec-789a089c14b6","year":1973},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.758425Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:2ecac34350a5275a646a7dadff7257f752d9a651930229c5697f32639a9dbf69","observation_id":"eab1a85f-2c24-4fb1-b4df-7e0b7acae070","resolution":{"observed_at":"2026-08-09T05:31:12.743220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:11.763662Z","title":"Visualizing data using t-sne.Journal of machine learning research, 9(11), 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.763662Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:4b2d75dc900293b5e1464453b4b97ea07f6349c66ba50b06a31e55dca4da8a6d","observation_id":"de25ea6c-ec7a-478f-83e3-4530947897f7","resolution":{"observed_at":"2026-08-09T05:31:11.763662Z","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":"2026-08-09T05:31:12.713494Z","title":"Local sgd converges fast and communicates little","venue":null,"work_id":"0e53efe5-4c6e-4669-9cba-1ae46042128e","year":2018},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.769582Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:e7d21cca296b89694d43ea1c828d7512ba3a504fe55dfca051c37fa0c4161a22","observation_id":"99396f21-d047-4dfa-8eaa-cfa4d60cf456","resolution":{"observed_at":"2026-08-09T05:31:12.717888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.699047Z","title":"Is local sgd better than minibatch sgd? In International Conference on Machine Learning, pages 10334–10343","venue":null,"work_id":"fc5b7bee-71bb-4cf9-a725-7832a59cc828","year":2020},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.775179Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:b1603722e36397363ab7158ba1f52dab457186af1be67ad585f89bc1025f1fcd","observation_id":"8cbdbd3f-b389-4c90-869d-587f0e07b479","resolution":{"observed_at":"2026-08-09T05:31:12.703351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-08-15T04:44:38.370440Z","submitted_at":"2018-06-02T04:45:58Z","title":"Federated Learning with Non-IID Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00582","snapshot_observed_at":"2026-08-09T05:31:11.780627Z","title":"Federated learning with non-iid data.arXiv preprint arXiv:1806.00582, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.780627Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:6af4fe7b436cb3fd56d93add806988afe6ba1fe2105a82f367abe70bd3e5c6ca","observation_id":"ab53ad29-c14a-44bf-887c-8bd072e925b9","resolution":{"observed_at":"2026-08-09T05:31:11.780627Z","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":"2026-08-09T05:31:12.684558Z","title":"pfedgf: Enabling personalized federated learning via gradient fusion","venue":null,"work_id":"23b81959-793a-485f-bb17-29c3909980ac","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.786402Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:0caa72db61d30d3ad23bbf64f52fc1cbaf676bd43db912aefad4bcfc1b71ad94","observation_id":"eb1dc7f5-c1aa-4170-8984-835809a24cb7","resolution":{"observed_at":"2026-08-09T05:31:12.689352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.669187Z","title":"Exploiting shared representations for personalized federated learning","venue":null,"work_id":"07339e9f-e7be-4855-8fb2-2ca6c57fbb6c","year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.791537Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:97a14a28ba55ce78eff1537368abaffe989d7e0418ed43aad56bd493d4f766cb","observation_id":"31520e58-1a43-4cff-a99b-47fa64fbe027","resolution":{"observed_at":"2026-08-09T05:31:12.674757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.653482Z","title":"Channelfed: Enabling personalized federated learning via localized channel attention","venue":null,"work_id":"e1e4ead6-de0c-4ea3-baa4-8c9525d93bd5","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.797270Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:bbdcac8185873aa80cfd9be369d4cef33a1438505fcf383038f080d569b87eef","observation_id":"789f24c0-a844-4abd-abaf-fd72fbb8bd0e","resolution":{"observed_at":"2026-08-09T05:31:12.658654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.19931","last_updated":"2024-10-11T11:30:01Z","snapshot_observed_at":"2026-08-16T13:38:44.113215Z","submitted_at":"2024-06-28T14:01:22Z","title":"Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition","version":2},"cited_work":{"arxiv_id":"2406.19931","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.19931","snapshot_observed_at":"2026-08-09T05:31:12.024063Z","title":"Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition","venue":"cs.LG","work_id":"a6ff3088-389c-435a-92a2-2ab3b04b1f02","year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.802551Z"},"links":{"cited_paper":"/paper/2406.19931","citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:43a91f3ae2ed4d9f237727eeb1be5ec78b4cc1ba77320e49affc4fabd1b768fa","observation_id":"de5e1f3b-6799-4d19-8630-d6dd19f4aceb","resolution":{"observed_at":"2026-08-09T05:31:12.032325Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.637219Z","title":"Fedproto: Federated prototype learning across heterogeneous clients","venue":null,"work_id":"8c044274-5cf3-4735-b3a3-5ae6c5b0f03f","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.808279Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:2975a85d6769a0761e8e2935cbe265f6279ff814d21104963a427de0be0782e4","observation_id":"47dafa7f-5c20-4a05-b9d8-5e80ba5ed1ef","resolution":{"observed_at":"2026-08-09T05:31:12.642771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.621233Z","title":"Aligning before aggregating: Enabling cross-domain federated learning via consistent feature extraction","venue":null,"work_id":"61d16b6f-2a8a-48f3-b13e-05d9b98db755","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.813218Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:a1406006c9ad08c291fdfff00d29e9938b3ce4067777e58ba947aa52dc801f1c","observation_id":"6407f486-f0fc-4cdf-9af5-75ed2fc0fbdb","resolution":{"observed_at":"2026-08-09T05:31:12.626413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.605560Z","title":"Aligning before aggregating: En- abling communication efficient cross-domain federated learning via consistent feature extraction","venue":null,"work_id":"3992ea79-66c3-4636-94ff-396bcffe323a","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.818801Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:92acdc1fb1ab2d9ffa9fb45cae1f9be652ee3605e37840143ba54c3f8987f3ce","observation_id":"bda56b59-a44b-449a-b05a-964e0833caf6","resolution":{"observed_at":"2026-08-09T05:31:12.610585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.588699Z","title":"Fedfa: Federated learning with feature anchors to align features and classifiers for heterogeneous data.IEEE Transactions on Mobile Computing, 2023","venue":null,"work_id":"51e1c230-18d6-4f38-ae4e-7be76f58b1ae","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.824408Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:5ef3913a775b2647a020772ceb17842af618d29571dc76b43fbeac0bdd7f4739","observation_id":"feb68c36-b578-4a1c-80ac-1a37ed380d26","resolution":{"observed_at":"2026-08-09T05:31:12.594372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.571627Z","title":"Rethinking federated learning with domain shift: A prototype view","venue":null,"work_id":"bf35a9da-ddab-49e9-bd93-a95a6591ab22","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.830231Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:ec58a15c6fb0c1aad0fa86c35543a4428e19319e71870b11d91a7d3532bb9a81","observation_id":"1fdd65c8-8e3b-4da1-985c-361cfe99540e","resolution":{"observed_at":"2026-08-09T05:31:12.576867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.554161Z","title":"Spherefed: Hyperspherical federated learning","venue":null,"work_id":"de5301d1-b831-43c1-9a35-4cdf74325299","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.835552Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:db57be8a0514b4c51f098fd6e66462e1ac980e9259ba994cbbc962367914b365","observation_id":"4cc6de8f-1721-4e9f-afb7-30493245eb74","resolution":{"observed_at":"2026-08-09T05:31:12.559241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.538122Z","title":"Towards understanding and mitigating dimensional collapse in heterogeneous federated learning","venue":null,"work_id":"b2b37b17-5895-41c0-a1f1-2c375572782f","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.841235Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:d01bb0ffd9b2d3a4e79d2059595ee35d821fa93b39ac419bcb7f89ec43a079fb","observation_id":"97da3618-4345-4dd5-bc67-65f1921132ff","resolution":{"observed_at":"2026-08-09T05:31:12.543706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.521769Z","title":"Under- standing and mitigating dimensional collapse in federated learning.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023","venue":null,"work_id":"996947d3-802c-4927-98ef-f729381d85c1","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.845996Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:3ee1a199804537f9f83805ec6ccded52ce8af884f1e45b09393125c0d7d30b90","observation_id":"882c2162-4da8-41da-a9b6-3e5a6507b450","resolution":{"observed_at":"2026-08-09T05:31:12.527301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.506037Z","title":"Taming cross-domain rep- resentation variance in federated prototype learning with heterogeneous data domains","venue":null,"work_id":"cf234303-c073-4f9e-8590-b5e6c5946e2a","year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.851048Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:ed8ed5af10fccb4d888d7f1c0d79392c04205835209cd8543ac8eef17ab0819a","observation_id":"88f9523c-faec-4b6d-b758-877b3c895c1f","resolution":{"observed_at":"2026-08-09T05:31:12.510800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:11.855925Z","title":"Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.855925Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:109be93753c91e2f6b7a8dd4799063420aa828edb25368342f0d924aef0ca705","observation_id":"8a6a6513-0a4c-40a3-9cb5-5a0e1c4cc283","resolution":{"observed_at":"2026-08-09T05:31:11.855925Z","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":"2026-08-09T05:31:12.480857Z","title":"Backward feature correction: How deep learning performs deep (hierarchical) learning","venue":null,"work_id":"5787daf4-8e07-4d56-bba4-0312c0fea536","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.861006Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:84521e2ddf2003201f83ccd887710f5ab4680c01084cc3fadf7d0c82224dcd5c","observation_id":"b6ac0471-df80-4f88-a7de-2f43f1541688","resolution":{"observed_at":"2026-08-09T05:31:12.485350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.466385Z","title":"Dualfed: enjoying both generalization and personalization in federated learning via hierachical representations","venue":null,"work_id":"cb44d217-fcd6-4bf5-a283-a028756663b2","year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.866060Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:a5fe76fc13f16a3a2adec1b915a9bc1d50fb2044b8ce0a3281f813df699af038","observation_id":"ea66d40e-a0ea-4a5b-a87f-84df673813e7","resolution":{"observed_at":"2026-08-09T05:31:12.470833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.450610Z","title":"Head2toe: Utilizing intermediate representations for better transfer learning","venue":null,"work_id":"c8bee3c2-adc8-41a3-988f-1f9009421090","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.871113Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:8a8b14756725147b087e91d84049d5cdd74db0e9aa2a888630847223dd1eaf10","observation_id":"a61a5ecc-106d-46bf-9c7c-987178b364ac","resolution":{"observed_at":"2026-08-09T05:31:12.455677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.434517Z","title":"Fine- tuning can distort pretrained features and underperform out-of-distribution","venue":null,"work_id":"1b5ef637-cd9f-4d33-b630-d2fc4ee6c987","year":2022},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.876031Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:90792844dbfc3cf9bdc1a5f1b780904c776bd7e18d6bc0cba827a52d03af3627","observation_id":"3b557289-d079-4721-aa48-a2a5e2441861","resolution":{"observed_at":"2026-08-09T05:31:12.439923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:11.881533Z","title":"Understanding intermediate layers using linear classifier probes, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.881533Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:177143aa44e263d09784ab49e5bd46a8933b6c1faedff42eb1d50a99f130532a","observation_id":"97789a19-29b3-4195-a36f-64b26e167236","resolution":{"observed_at":"2026-08-09T05:31:11.881533Z","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":"2026-08-09T05:31:11.887070Z","title":"Prevalence of neural collapse during the terminal phase of deep learning training.Proceedings of the National Academy of Sciences, 117 (40):24652–24663, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.887070Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:ff38eb042c4a062f461fb4ccd72e79ed9ed2193b54d79b5793bcc8104e371eaa","observation_id":"bc296108-587c-4799-a74c-364973c0e1d0","resolution":{"observed_at":"2026-08-09T05:31:11.887070Z","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":"2026-08-09T05:31:11.892446Z","title":"Intrinsic dimension of data representations in deep neural networks.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.892446Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:a79a3b7ee0e8db5c5a5ea142ea78f1c2ef4363c6609d3fae328feca92cb63fa6","observation_id":"700fd133-a1a1-495a-9937-38afe7270743","resolution":{"observed_at":"2026-08-09T05:31:11.892446Z","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":"2026-08-09T05:31:12.386901Z","title":"Understanding and improving transfer learning of deep models via neural collapse.Transactions on Machine Learning Research, 2024","venue":null,"work_id":"e04b912d-dd41-4411-b42d-053d042abc05","year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.897590Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:2379d421b0fc99d5e0f524f24655aa8072e82d44909d5993045c3a9f72b19d8b","observation_id":"ccb3c3f3-8f48-4924-80ab-5069370abebb","resolution":{"observed_at":"2026-08-09T05:31:12.392614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.370632Z","title":"Lempitsky","venue":null,"work_id":"2c02aeb9-cc20-4a77-8a2f-3509d6e31191","year":2015},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.902570Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:44fe2ff88b9980b960e8d62270c9fb1c4550301aa526e9135d953517aebd4a0b","observation_id":"e87b90a2-f6c8-4681-9905-51ab3791d3ec","resolution":{"observed_at":"2026-08-09T05:31:12.375756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.353849Z","title":"Gradient-based learning applied to document recognition.Proc","venue":null,"work_id":"f1624e44-282f-4cd4-8bec-eafb47a98637","year":1998},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.907641Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:9423dc18699773f06505fabdf3a84ea47bf4202ec7bf894c2804c78c96b849f4","observation_id":"fe564079-7c00-4944-98ab-fe36b0398ead","resolution":{"observed_at":"2026-08-09T05:31:12.359173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.338257Z","title":null,"venue":null,"work_id":"3933672f-9823-465f-827b-56260682fcdf","year":1994},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.913572Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:10470fd02de9d514fb74218b1865415ebc37c6b6d4f47dd20251e5b924981f0a","observation_id":"f32bcb30-399b-4794-a9d5-a68f3b743abe","resolution":{"observed_at":"2026-08-09T05:31:12.342999Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:11.918387Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.918387Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:6c3118bc3d4a0ab8ce3f5f3b1767b48f3f11744ae8c90ab64e12a0d825278a2a","observation_id":"5bff1c22-3090-4969-9cef-2ca011a3aa1d","resolution":{"observed_at":"2026-08-09T05:31:11.918387Z","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":"2026-08-09T05:31:11.923067Z","title":"Pytorch: An imperative style, high-performance deep learning library.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.923067Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:e5aa36d38ad497119ab40daa6dd97e65c2e4b1b110acb36b125a16bf13caef13","observation_id":"9229ed98-c7eb-473d-86c5-ff44100c8b4c","resolution":{"observed_at":"2026-08-09T05:31:11.923067Z","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":"2026-08-09T05:31:12.298832Z","title":"Simulated annealing in early layers leads to better generalization","venue":null,"work_id":"641cd2fa-c2c9-4986-be6a-7103aae1dd76","year":2023},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.927498Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:b9cbe4fb374110b4af7251b9506b6f63fba81f580c04d1fa3208693094c5a445","observation_id":"949abb2d-7a22-43ec-899b-6b3a472a16f3","resolution":{"observed_at":"2026-08-09T05:31:12.303933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.280760Z","title":"What variables affect out-of-distribution generalization in pretrained models? InThe Thirty- eighth Annual Conference on Neural Information Processing Systems, 2024","venue":null,"work_id":"37a8f518-8160-4b3b-841d-516ffe418558","year":2024},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.932528Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:f1ed363d7adfcf0632e2f0c12ad0f566770234f2f16386f566429f31c99ee96a","observation_id":"0950afde-7f0c-4a10-a9fb-28df6b480e14","resolution":{"observed_at":"2026-08-09T05:31:12.286163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.262777Z","title":"Do vision transformers see like convolutional neural networks?Advances in neural information processing systems, 34:12116–12128, 2021","venue":null,"work_id":"baee195d-3cc9-49e4-9d1c-912b808fcc27","year":2021},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.937662Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:6f929edf8a12483b2bc79184b6bc6c8594c4103d7ddc71daa5c907200c46f018","observation_id":"dbfb1ee4-4ce0-4b0c-bc2b-7e6d60c87f8e","resolution":{"observed_at":"2026-08-09T05:31:12.268801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.242193Z","title":"Let the features of the pre-aggregated and post-aggregated models be denoted as Z ℓ pre and Z ℓ post, respectively","venue":null,"work_id":"2a29b2d5-a932-4b8e-8b76-62bf1eba2356","year":null},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.943917Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:fce1db0ce0502376955fbf9bc80dfbf6d3ac82ed5586615c9a2ba81600a946c5","observation_id":"f43b4b53-2ec8-42bf-8353-b179a78b43e3","resolution":{"observed_at":"2026-08-09T05:31:12.249633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.218547Z","title":"Discussions and Limitations","venue":null,"work_id":"9b54bc76-4b9f-4b6d-9253-5cd4349aa29a","year":null},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.967671Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:3bf3026067504e0a1597a9d8b024d0bd967238234f6ece05bb1724b77802b31d","observation_id":"524c6a23-9f9b-4252-8708-2de069d82373","resolution":{"observed_at":"2026-08-09T05:31:12.224337Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T05:31:12.140070Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"e9b0953f-f591-482c-b10c-6930a891053d","year":2025},"citing_paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-09T05:31:11.973765Z"},"links":{"citing_paper":"/paper/2502.03231"},"observation_digest":"sha256:0c15f49d30260df8b8548648e8f42564af05b6efefb97bc192de97b43ce2458e","observation_id":"9f3b3098-0605-43b2-a012-2a90ea8c52bb","resolution":{"observed_at":"2026-08-09T05:31:12.184901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.03231","last_updated":"2025-06-09T15:11:13Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T07:52:55.088027Z","submitted_at":"2025-02-05T14:45:56Z","title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective"},"reference_resolution":{"displayed":77,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":1,"verified_fuzzy":46},"total_outbound_references":77},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 0 inbound Pith citation observations for arXiv:2502.03231."}