{"as_of":"2026-08-22T13:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a97cb3a36a5be33c3d49da02d5277ecd9f298c5647daa119d69464299f36f2bc","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:11:26.623601Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2504.13462/citation-record","integrity":"/paper/2504.13462/integrity","json":"/paper/2504.13462/citation-record.json","paper":"/paper/2504.13462"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:11:26.876770Z","title":"The cost of training machine learning models over distributed data sources,","venue":null,"work_id":"77c7c0ef-a933-4a0a-8d4a-51a4e2513d42","year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.532962Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:4c3fa5d6199f721cbcc5d5a03747b43c7aec108de701bde395330f66705456fc","observation_id":"31cdb0b4-b79f-4199-b3f5-5901b0e2e891","resolution":{"observed_at":"2026-08-16T12:11:26.881394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.537625Z","title":"Federated learning with hierarchical clustering of local updates to improve training on non-IID data,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.537625Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:cbac9bac5dd11182b51ef05ca4202d214e474d1e6583c57dde2697ffa6977034","observation_id":"fb7c7d76-d905-4d96-9370-6c2f9bec0e9a","resolution":{"observed_at":"2026-08-16T12:11:26.537625Z","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":"2026-08-16T12:11:26.856516Z","title":"Federated learning under distributed concept drift,","venue":null,"work_id":"f7c53959-c82c-4410-bf5a-4b0d50324c9e","year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.542382Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:90c2d0fb4955528e341f68d2dadebe98c867e2d54c79dd602017dbf3337748f8","observation_id":"a94f0014-debd-45e4-941a-e9a6da1bc350","resolution":{"observed_at":"2026-08-16T12:11:26.860565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.546982Z","title":"Efficient distribution similarity identification in clustered federated learning via principal angles between client data subspaces,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.546982Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:af39876c99f768e73465d3006055a2de61944b746e6a455a868830d616a14f94","observation_id":"5c6918a0-0b76-4f5b-b0e9-7502221c8dfe","resolution":{"observed_at":"2026-08-16T12:11:26.546982Z","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":"2026-08-16T12:11:26.838211Z","title":"Clustered federated multi-task learning with non-IID data,","venue":null,"work_id":"a6f1e17e-a483-4b3b-b69e-0c12b43a6608","year":2021},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.551451Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:df72ea97b9721c3f57325ce51ca9d3b4850bc2707b125deac59ff9e533726834","observation_id":"cb144cb1-c88d-412d-98bb-18af7bb163f5","resolution":{"observed_at":"2026-08-16T12:11:26.842085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.556000Z","title":"Per- sonalized cross-silo federated learning on non-iid data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.556000Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:61c0cf8cf476c6597d2c7faf7c8b54e77fb76c28c210b1e96dc217b000f559a9","observation_id":"76a8cc6e-5d54-4dc6-833c-8d83d2bd6e71","resolution":{"observed_at":"2026-08-16T12:11:26.556000Z","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":"2026-08-16T12:11:26.560899Z","title":"Adapt to adaptation: Learning personalization for cross-silo federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.560899Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:0437c721693c0846b057d98ea62b39f9047523c35d03990476c2eac4e61969a8","observation_id":"4ef8fc40-bb34-4bd4-afc6-ff9d608bd273","resolution":{"observed_at":"2026-08-16T12:11:26.560899Z","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":"2026-08-16T12:11:26.812683Z","title":"FRAug: Tackling federated learning with Non-IID features via representation augmentation,","venue":null,"work_id":"13067105-881d-4e07-8b76-f581257f38bd","year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.564951Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:78c4182a9e55125f837a14f859ae5bdfd2936ae9e036934b682897373b4d71a1","observation_id":"b56d0437-72ca-42cd-9b33-58d92bfc27ee","resolution":{"observed_at":"2026-08-16T12:11:26.817066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.800582Z","title":"Feature matching data synthesis for non-iid federated learning,","venue":null,"work_id":"da788e14-bcf7-40a8-a551-23ce6dbfc9da","year":2024},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.568817Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:e30f9b89374c2a994e57f84cc357d4ccf328b065ed3912c68bc45c1da340de3c","observation_id":"b13f0aa9-15ab-443b-93bc-6349c13d4e76","resolution":{"observed_at":"2026-08-16T12:11:26.804522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.572928Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.572928Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:eb2c5ae3927a1ce2d307f72c4773fa9cd7d2617b79df69885f8c3784e7c8bf8f","observation_id":"77208d47-2c30-4000-a52f-ed18d93cbcfc","resolution":{"observed_at":"2026-08-16T12:11:26.572928Z","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":"2026-08-16T12:11:26.778838Z","title":"Coordinating momenta for cross-silo federated learning,","venue":null,"work_id":"b122930b-bc15-42b4-8b83-b26c8cf250c4","year":2022},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.576903Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:d1fc998fd84ad4ec066f29541022d3d99a186f7dc09812ef9e57902923b05c08","observation_id":"7d6359f3-665b-47d4-9aac-61bd8ed53ad4","resolution":{"observed_at":"2026-08-16T12:11:26.783908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.580584Z","title":"Scaffold: Stochastic controlled averaging for federated learn- ing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.580584Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:65283b17bec242e5dbd043de1dbdc1461d7a170867b210eab5098eae2e9fd7fc","observation_id":"88cbb59e-2f23-4e62-be94-1c9eb6070a55","resolution":{"observed_at":"2026-08-16T12:11:26.580584Z","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":"2026-08-16T12:11:26.759600Z","title":"Ensemble federated learning with non-iid data in wireless networks,","venue":null,"work_id":"d24efd11-8944-4841-8181-24fb29b0fd79","year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.584841Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:3fc397488f88cf80ce81da19d7d4cbf0d04e46dd5deb470cbad8f1312242728f","observation_id":"4a8804a3-2ff9-489e-b9ff-15d3d0304759","resolution":{"observed_at":"2026-08-16T12:11:26.763673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.747379Z","title":"Fed-ensemble: Ensemble models in federated learning for improved generalization and uncertainty quantification,","venue":null,"work_id":"99044380-cc8a-410c-8a74-1d596919fce6","year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.588877Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:ad0eef81c30b923562e54c252290e64c5b0d0d8983eab379630cf6be2117f944","observation_id":"a5cf9278-fb6c-48ab-99fe-9c3e3731b303","resolution":{"observed_at":"2026-08-16T12:11:26.751317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.592604Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.592604Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:18f6bb9fc61889482efcd72b1985bb73646ca00431adefa1574a8488aaa46731","observation_id":"16728b18-a140-4f44-8d95-b981aa00c25a","resolution":{"observed_at":"2026-08-16T12:11:26.592604Z","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":"2026-08-16T12:11:26.728172Z","title":null,"venue":null,"work_id":"8ae8fe95-fc7c-40f6-b2d8-4cea70ca14bb","year":2012},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.596211Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:a72cdc9adea169d128883a6a3aad2ab2d2c5d1548d9efa3b260e29cd3e5ffb27","observation_id":"4f8f6713-a0d7-4f16-ac68-c3d7ff2ba02a","resolution":{"observed_at":"2026-08-16T12:11:26.732230Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.599623Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.599623Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:b514a3076ad93373a7d342f8c72a0f2753035a923c4131feec88b59e2d16b1a0","observation_id":"3684c5fe-dd5b-4076-9a12-e7edf4563d2a","resolution":{"observed_at":"2026-08-16T12:11:26.599623Z","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":"2026-08-16T12:11:26.603769Z","title":"Optimizing the collaboration structure in cross-silo federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.603769Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:23fb59b1da7f2a093e07673a41e08b1282bbd95e8816f0fb8cbad10a4bc880aa","observation_id":"7b6be35d-5446-4111-9c58-4bd9bf780fd1","resolution":{"observed_at":"2026-08-16T12:11:26.603769Z","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":"2026-08-16T12:11:26.701388Z","title":"Clustered sampling: Low-variance and improved representativity for clients selection in federated learning,","venue":null,"work_id":"1f3f0e5e-12b3-447b-8e39-479a2481601f","year":2021},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.607156Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:c331fc27caf6e8be2f71c30f79dfa07b9077026e08acc40aa5f785d0c340f994","observation_id":"46ef1280-0894-41b2-bba1-a9ed75572eeb","resolution":{"observed_at":"2026-08-16T12:11:26.705351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.688252Z","title":"Fedsts: A stratified client selection framework for consistently fast federated learning,","venue":null,"work_id":"dcd11559-af5d-4117-a724-a70759b83703","year":2024},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.610442Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:322da812975875aec143316866659917e39d779acf3118af8da9751bee73d2f4","observation_id":"a09be62c-95a4-4e32-8648-6befc00cd993","resolution":{"observed_at":"2026-08-16T12:11:26.693339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.674545Z","title":"Convergence analysis of sequential federated learning on heterogeneous data,","venue":null,"work_id":"a13dd719-2cbf-4e54-9c83-bc122a37bbb6","year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.614902Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:965c31beec10745e671fe99e13839c55bcaea1159ccf5b25a81a8c2f3b4117c9","observation_id":"aa757b5a-2563-4acf-ae5d-295e2279b057","resolution":{"observed_at":"2026-08-16T12:11:26.679072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.660178Z","title":"Why batch normalization damage federated learning on non-iid data?","venue":null,"work_id":"7dc658be-7a2f-4f9a-9263-9e65c7aed424","year":2023},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.619663Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:08d1c5a225e126c957892cc8f0a0040fbb9ee74fa571ee5e3622fc3a491f193d","observation_id":"e94739a5-a234-42cf-b872-674bf212d19e","resolution":{"observed_at":"2026-08-16T12:11:26.666204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T12:11:26.623601Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T12:11:26.623601Z"},"links":{"citing_paper":"/paper/2504.13462"},"observation_digest":"sha256:09c13b0672bb526f4af4e1549a55d95838bf54265937c0a618dadf8ab0636f65","observation_id":"f4994f2b-355c-44bd-9f6a-71fa2dc7910f","resolution":{"observed_at":"2026-08-16T12:11:26.623601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.13462","last_updated":"2025-04-18T04:44:41Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T02:23:41.697187Z","submitted_at":"2025-04-18T04:44:41Z","title":"Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":12},"total_outbound_references":23},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2504.13462."}