{"as_of":"2026-08-19T15:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:50b3aa850308d4aa7201a531b41bd1094e13019d3bc1189ebdfcb39151b9fe9d","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:44:37.005945Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2504.17528/citation-record","integrity":"/paper/2504.17528/integrity","json":"/paper/2504.17528/citation-record.json","paper":"/paper/2504.17528"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:36.813064Z","title":"Edge intelligence: Paving the last mile of artificial intelligence with edge computing,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.813064Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:1af46481606f6e32e2635ad1efd5c0240368c25181f72f62b763c029e0c0e4fe","observation_id":"562ae191-0cdc-46a6-8b3f-5b89b4346c4f","resolution":{"observed_at":"2026-08-16T10:44:36.813064Z","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":"2026-08-16T10:44:37.550041Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":"8a731353-0c8f-4116-80c0-a0a55fdf38f9","year":2017},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.818513Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:0da969481b1646ca86b0b8b8881775be3890cd37ef281a96a57e6fa57ccfbc1c","observation_id":"03bcc2f7-39e5-4ebc-b693-11ea026bb326","resolution":{"observed_at":"2026-08-16T10:44:37.554692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:36.823853Z","title":"Accelerating federated learning with data and model parallelism in edge computing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.823853Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:f7a360fe69d72b296cced8197822ea7835c4970ca19e7acc9c18e36472e07422","observation_id":"179347fa-16cb-4060-9fc6-b8f89f60bdcc","resolution":{"observed_at":"2026-08-16T10:44:36.823853Z","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":"2026-08-16T10:44:36.828381Z","title":"Federated learning over wireless networks: Convergence analysis and resource allocation,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.828381Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:f9641fe9c4dbf24e97d99ea322b21cf39e22682e868efef2bea2674072025c63","observation_id":"2dbb5237-77b8-409c-814c-da7bb9bb0eeb","resolution":{"observed_at":"2026-08-16T10:44:36.828381Z","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":"2026-08-16T10:44:37.516486Z","title":"Accelerating and securing federated learning with stateless in-network aggregation at the edge,","venue":null,"work_id":"e9176364-82d6-4154-94f8-9cd76de5a369","year":2024},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.833374Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:8fe69e8906638d6930c6ab916dab8050b439444cd8adca2742f9121ccf6f52b1","observation_id":"befd62a2-1124-4808-a248-70bfc985c524","resolution":{"observed_at":"2026-08-16T10:44:37.521505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:36.837871Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.837871Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:be15b4dd8ebead16189ed2f485eb7320c5b39edc06a83d343d54fd10245c5b01","observation_id":"151b3220-cff3-4bc1-9214-8de15043fd2d","resolution":{"observed_at":"2026-08-16T10:44:36.837871Z","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":"2026-08-16T10:44:36.843178Z","title":"The limitations of federated learning in sybil settings,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.843178Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:6c392e1de441c8a478fd3e3175b78eb15aefd6ed5cfb2bffcbcb0f6dfe65d61e","observation_id":"05aea188-3076-4d0c-ab73-39b2900eef5e","resolution":{"observed_at":"2026-08-16T10:44:36.843178Z","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":"2026-08-16T10:44:36.847507Z","title":"Scaffold: Stochastic controlled averaging for federated learn- ing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.847507Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:10cabab3d220f47a7ca46299f33f9eec77d5b827ff540ee697c59bb3b51e5e4f","observation_id":"d97fbf88-30e9-4fe1-a815-82ee5f03fce9","resolution":{"observed_at":"2026-08-16T10:44:36.847507Z","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":"2026-08-16T10:44:37.473056Z","title":"Stem: A stochastic two-sided momentum algorithm achieving near-optimal sample and communication complexities for federated learning,","venue":null,"work_id":"2e1d66f6-3826-4619-83db-923195f61fd9","year":2021},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.851906Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:a52bd794770c76f784045d148f6810e3f486e8f53859851324b90e6e1ccc7b81","observation_id":"6d2fe4af-a5e8-43a8-8690-237907e866b3","resolution":{"observed_at":"2026-08-16T10:44:37.478138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:37.454493Z","title":"Communication-efficient federated learn- ing with accelerated client gradient,","venue":null,"work_id":"09273b0d-217b-42b6-8050-b29cb672214b","year":2024},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.856361Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:f0509528cdad8ec3d7753a8aa678120aeccc7177d9dc13860fd08aeda39da156","observation_id":"75f2608f-583f-4cdb-9b18-04b2f112558a","resolution":{"observed_at":"2026-08-16T10:44:37.459503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:36.861075Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.861075Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:9f511ed10654041ce25aedb44cdddb377834c3a42454c154f7abb1d150f1ccd4","observation_id":"cead38d8-260b-4b1e-b8f5-5b596229efae","resolution":{"observed_at":"2026-08-16T10:44:36.861075Z","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":"2026-08-16T10:44:36.865599Z","title":"Tackling the objective inconsistency problem in heterogeneous federated optimiza- tion,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.865599Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:0b5397df16c4fe3c3052384e55acfb18ffed87830b30a7375b12fda6312485af","observation_id":"a9a2731d-0728-4485-aca6-454c669b4406","resolution":{"observed_at":"2026-08-16T10:44:36.865599Z","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":"2026-08-16T10:44:37.420300Z","title":"To talk or to work: Dynamic batch sizes assisted time efficient federated learn- ing over future mobile edge devices,","venue":null,"work_id":"00a510fa-5055-4b35-9d42-a75eff618a6c","year":2022},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.870600Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:0bb44b580e2c1f6c062b2ce10c494c5ade5ad17bb78acc61e6ec055358220d97","observation_id":"4e60a937-d410-4997-afcb-3428b5fac64f","resolution":{"observed_at":"2026-08-16T10:44:37.425151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:36.875314Z","title":"Reading digits in natural images with unsupervised feature learning,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.875314Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:eeb45fc61aea75a84a5858515a7cd0493b1207bec340eeb9b0458a76c3ec100b","observation_id":"ba1db47c-377d-4fbd-9deb-1bba3c53e34b","resolution":{"observed_at":"2026-08-16T10:44:36.875314Z","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":"2026-08-16T10:44:37.395747Z","title":"Free-rider attacks on model aggregation in federated learning,","venue":null,"work_id":"ac1a4fca-6832-4fe8-adf0-8dfff1b7d14c","year":2021},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.879835Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:6224d3f5f9290eb51ec7220db720245e07af86cafe66471a52f4d5612cc32f8d","observation_id":"69cc9cf8-9aee-401c-bb24-9052d1f2f888","resolution":{"observed_at":"2026-08-16T10:44:37.400437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:37.380171Z","title":"Enabling long-term cooperation in cross-silo federated learning: A repeated game perspective,","venue":null,"work_id":"05a19851-ec81-4640-b922-19981da42468","year":2022},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.884158Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:25961b4cae8d88cb6078df274384a5a2cb3faa4deffd140827b4f37158a0c344","observation_id":"37596750-69a7-460d-b96c-1f37c42a36ed","resolution":{"observed_at":"2026-08-16T10:44:37.385067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.12560","last_updated":"2019-11-28T07:13:48Z","snapshot_observed_at":"2026-07-06T08:40:33.992386Z","submitted_at":"2019-11-28T07:13:48Z","title":"Free-riders in Federated Learning: Attacks and Defenses","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.12560","snapshot_observed_at":"2026-08-16T10:44:36.888363Z","title":"Free-riders in federated learning: Attacks and defenses,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.888363Z"},"links":{"cited_paper":"/paper/1911.12560","citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:443c7b634c09a8e2716320cde66b2b0809c805b59167f14c7ac014eb5ad35b93","observation_id":"7e6281c4-d24f-4458-8962-e2cfeabb83d7","resolution":{"observed_at":"2026-08-16T10:44:36.888363Z","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":"2026-08-16T10:44:37.364195Z","title":"Toward free-riding attack on cross-silo federated learning through evolutionary game,","venue":null,"work_id":"572f2380-e266-431f-a576-cb4c75c53141","year":2024},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.893275Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:82b9c54bd0c75c4350fc5765119e9f1886bbbd05fd6c36da841d38f346c444fc","observation_id":"e2d3a061-9179-464a-b0b2-35946128d1d8","resolution":{"observed_at":"2026-08-16T10:44:37.370009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.10874","last_updated":"2021-06-21T06:16:19Z","snapshot_observed_at":"2026-08-16T18:15:44.894036Z","submitted_at":"2021-06-21T06:16:19Z","title":"FedCM: Federated Learning with Client-level Momentum","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.10874","snapshot_observed_at":"2026-08-16T10:44:36.897604Z","title":"Fedcm: Federated learning with client-level momentum,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.897604Z"},"links":{"cited_paper":"/paper/2106.10874","citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:50f4fe4b43a65cbd40ee6e6d5022bed70a9aa530ea8305dffb1bc5897bb8cf56","observation_id":"66576304-dbd7-4ac5-95d2-1346eea524c5","resolution":{"observed_at":"2026-08-16T10:44:36.897604Z","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":"2026-08-16T10:44:36.902499Z","title":"Optimization methods for large- scale machine learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.902499Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:be041c40e59427a43d22613337a8fb53446b2e58cda855854d8b829aa06c107d","observation_id":"80420934-1983-491e-a7c3-d6bdfbdf5a43","resolution":{"observed_at":"2026-08-16T10:44:36.902499Z","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":"2026-08-16T10:44:36.907446Z","title":"Adaptive federated learning in resource constrained edge computing systems,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.907446Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:6e217965d889949e0a62a6d4bb0a176ba61dcc2553123c33f4f3a23036ca73c4","observation_id":"38b5ba8f-a5be-4d18-a331-e9621460fa1b","resolution":{"observed_at":"2026-08-16T10:44:36.907446Z","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":"2026-08-16T10:44:36.912215Z","title":"Feder- ated learning under heterogeneous and correlated client availability,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.912215Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:c3aad46151bd67baa507ff3c8fb29afe4bab31f50fa6eeaa1b9f130a28144fac","observation_id":"519435eb-3837-4338-9182-aa173b3bc155","resolution":{"observed_at":"2026-08-16T10:44:36.912215Z","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":"2026-08-16T10:44:37.319729Z","title":"Federated learning with flexible control,","venue":null,"work_id":"9edf8aca-940f-48ee-9db3-ea6386f518f1","year":2023},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.916862Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:464b6152b366cefd11f550e618c90418d80eedc041bdb9a00f031db1e188a0a7","observation_id":"b9b610cd-9bb9-4914-b0f4-f04ed7c3abb7","resolution":{"observed_at":"2026-08-16T10:44:37.324428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:37.304250Z","title":"Dynamite: Dynamic interplay of mini-batch size and aggregation frequency for federated learning with static and streaming dataset,","venue":null,"work_id":"6e89b69e-a13c-4962-8c96-bca052ea5595","year":2023},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.921412Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:910fe665aa6d15a568145738dad4ecb8da9c60e4234bc0e5cedfd5a5932180ac","observation_id":"62b6c532-2c82-4724-a264-16ecf3c23005","resolution":{"observed_at":"2026-08-16T10:44:37.309398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:36.925973Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.925973Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:b7bb891cdd6961d220a0be3d863c543e453e7a422a59328ed9cd7a3d0d3b81b3","observation_id":"cdcee5c8-b92f-45b1-bcef-8813e32b1885","resolution":{"observed_at":"2026-08-16T10:44:36.925973Z","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":"2026-08-16T10:44:37.279906Z","title":"Fedmos: Taming client drift in federated learning with double momentum and adaptive selection,","venue":null,"work_id":"9cb02f90-a900-46b9-80fc-2b276d1e70fd","year":2023},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.930570Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:40eb61452b8281b1112433115d20881d9cb67ffa0f8f88b640a6ae46b2b84685","observation_id":"b7c989b5-cfa1-4e29-b181-e9ea2e3822d1","resolution":{"observed_at":"2026-08-16T10:44:37.284683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02189","last_updated":"2020-06-25T06:45:52Z","snapshot_observed_at":"2026-08-14T16:08:56.121684Z","submitted_at":"2019-07-04T02:04:56Z","title":"On the Convergence of FedAvg on Non-IID Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02189","snapshot_observed_at":"2026-08-16T10:44:36.935281Z","title":"On the convergence of fedavg on non-iid data,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.935281Z"},"links":{"cited_paper":"/paper/1907.02189","citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:54f73590d00ce14eaa9966fe7db287e789628138cae7299bdc9c839d5d18c5f5","observation_id":"5e60c3cd-4fba-43f9-a7e2-0eb454329000","resolution":{"observed_at":"2026-08-16T10:44:36.935281Z","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":"2026-08-16T10:44:36.940149Z","title":"Becker and R","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.940149Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:4d2f8fa3a4aefce18c5320dcb1b4ae0ccd7ced986c13bb717d6cab093feb5124","observation_id":"01a3f9f2-164b-4f1f-a5b1-4727ffa4baec","resolution":{"observed_at":"2026-08-16T10:44:36.940149Z","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":"2026-08-16T10:44:36.944791Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.944791Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:d21ecbba4c021ca6c81254ea798ec2aca6a91b60d50508e1416c4e0e580cfa2d","observation_id":"adb55a71-80b8-4309-ba3f-d27689a906d3","resolution":{"observed_at":"2026-08-16T10:44:36.944791Z","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":"2026-08-16T10:44:37.255263Z","title":"Autofl: A bayesian game approach for autonomous client participation in federated edge learning,","venue":null,"work_id":"d6301656-10f8-4441-91ff-c7e35a33d272","year":2022},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.949482Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:91515e03eb0e33686578771388cc1e116ce2babd3d39bfa549e8a5b9b2b89ef6","observation_id":"c288386a-383b-48ea-88f7-79fead8ae4da","resolution":{"observed_at":"2026-08-16T10:44:37.260038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01097","last_updated":"2019-12-09T20:02:37Z","snapshot_observed_at":"2026-08-16T19:49:29.879809Z","submitted_at":"2018-12-03T21:59:41Z","title":"LEAF: A Benchmark for Federated Settings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01097","snapshot_observed_at":"2026-08-16T10:44:36.953770Z","title":"Leaf: A benchmark for federated settings,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.953770Z"},"links":{"cited_paper":"/paper/1812.01097","citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:80c3f14567388051e3562f4c07cefaa8c5b9a8f034b8055ff32d115281ce9163","observation_id":"91bd3d68-75c6-4621-b67b-47ccc50dcbee","resolution":{"observed_at":"2026-08-16T10:44:36.953770Z","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":"2026-08-16T10:44:36.958526Z","title":"A hierarchical knowledge transfer framework for heterogeneous federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.958526Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:502985a9d6152d6e420777e945f68f839ca0c006a6147f476a9b0ec4b6fd51e3","observation_id":"cb358c5c-041a-4e4d-91f7-42a31981cd5d","resolution":{"observed_at":"2026-08-16T10:44:36.958526Z","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":"2026-08-16T10:44:37.230642Z","title":"Distributionally robust federated learning for network traffic classification with noisy labels,","venue":null,"work_id":"98843823-400c-4779-b10d-bd60b646e0b5","year":2023},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.962923Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:21614c7f1b29b3d0c0722630cd08454a323a30d81a174137c55c2ac1691e95de","observation_id":"79d49283-0cde-436c-b3f1-58d26e4792c3","resolution":{"observed_at":"2026-08-16T10:44:37.235505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:37.214929Z","title":"Heterogeneity- aware federated learning with adaptive client selection and gradient compression,","venue":null,"work_id":"20231e1c-6ccd-46b2-95a9-80afe73bec62","year":2023},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.967330Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:483c2907c68022b35ff3872b216966383aa1a7d586867ffc23269d222089c3e2","observation_id":"6bc4f8ae-1723-4984-99ea-c4af1f72a742","resolution":{"observed_at":"2026-08-16T10:44:37.220293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:37.199279Z","title":"Internal cross-layer gradients for extending homogeneity to heterogeneity in federated learning,","venue":null,"work_id":"9cca5591-1ab1-4e28-a5b8-e52a02f1341b","year":2024},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.972200Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:97b1af043ee5cdc4eaa4b4b81b5ce8da28fc57e368729aba33179e79e9b07159","observation_id":"be3ce388-467e-4dac-a78e-6c8b821db0c6","resolution":{"observed_at":"2026-08-16T10:44:37.204351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T10:44:37.183454Z","title":"Can federated learning clients be lightweight? a plug-and-play symmetric conversion module,","venue":null,"work_id":"78f7de94-08f4-458f-94f2-2c806ba52a62","year":2024},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.976299Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:79d2a5858b46ec871a883e6f7fdb9519a2bcc5475bf645838541457025d9e6a5","observation_id":"40757bab-9ab8-405d-bbf3-7fa4d4f208ff","resolution":{"observed_at":"2026-08-16T10:44:37.188392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.04263","last_updated":"2021-11-09T16:37:10Z","snapshot_observed_at":"2026-08-16T17:43:23.177413Z","submitted_at":"2021-11-08T03:58:28Z","title":"Federated Learning Based on Dynamic Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.04263","snapshot_observed_at":"2026-08-16T10:44:36.981084Z","title":"Federated learning based on dynamic regularization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.981084Z"},"links":{"cited_paper":"/paper/2111.04263","citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:2d3d94fc964b6fc4206460a6d0fa684297ebb3817e0f2b5e489b47732e0fd827","observation_id":"b205056e-e0e6-48a2-832b-a6f6d1a480f5","resolution":{"observed_at":"2026-08-16T10:44:36.981084Z","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":"2026-08-16T10:44:36.985766Z","title":"Feddc: Federated learning with non-iid data via local drift decoupling and correction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.985766Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:3020fb6934102dc645717a7a5d3b83076eaf917620b2e88c3049963ee10dfcea","observation_id":"7cb39173-c24e-400c-b25f-ba940013d9cb","resolution":{"observed_at":"2026-08-16T10:44:36.985766Z","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":"2026-08-16T10:44:37.156759Z","title":"Towards flexible device participation in federated learning,","venue":null,"work_id":"1293b967-1a27-4fea-a9f5-1f8aa74570d0","year":2021},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.990119Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:d6434a5e17f9531ede67405a6a28b0c50e09a92b55ac58660fb798fe4778f6f8","observation_id":"b155831c-96a9-48f8-bc24-915e22618d25","resolution":{"observed_at":"2026-08-16T10:44:37.163663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.03606","last_updated":"2021-06-08T08:14:57Z","snapshot_observed_at":"2026-08-18T14:46:29.950624Z","submitted_at":"2020-08-08T21:55:07Z","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.03606","snapshot_observed_at":"2026-08-16T10:44:36.995604Z","title":"Mime: Mimicking centralized stochastic algorithms in federated learning,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:36.995604Z"},"links":{"cited_paper":"/paper/2008.03606","citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:d51f43fd7a726af31d128855b12814c5948f876cf073128172757a579c7e7b2a","observation_id":"18b85d2e-b026-49c4-b0d9-86e5c8d14a2f","resolution":{"observed_at":"2026-08-16T10:44:36.995604Z","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":"2026-08-16T10:44:37.000441Z","title":"Ma- chine learning with adversaries: Byzantine tolerant gradient descent,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:37.000441Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:df8544435d56c29b47336db4c5901e33f0d4d9a52ab7914b427fe25613296248","observation_id":"3e4b7f57-d295-4e35-8c94-2f96762ad109","resolution":{"observed_at":"2026-08-16T10:44:37.000441Z","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":"2026-08-16T10:44:37.005945Z","title":"Feder- ated learning with compression: Unified analysis and sharp guarantees,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:37.005945Z"},"links":{"citing_paper":"/paper/2504.17528"},"observation_digest":"sha256:5f6c79b112e68da60ade51659225cfbee6cf641a52e2bda0061aeaa916a65ed1","observation_id":"28c9835a-3182-4499-8bd3-384f5017bd9c","resolution":{"observed_at":"2026-08-16T10:44:37.005945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.17528","last_updated":"2025-04-24T13:16:21Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T10:35:43.926152Z","submitted_at":"2025-04-24T13:16:21Z","title":"TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":0,"verified_fuzzy":17},"total_outbound_references":42},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2504.17528."}