{"as_of":"2026-08-14T11:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ab4dbbb0b41a11ab5e50b9abd83a49ae667b1a4dec3c8d83967f84ee8a1e6ff7","coverage":[{"denominator":268,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T17:39:18.459913Z","state":"measured"},{"denominator":111,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":111,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":11,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":11,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:52:02.256519Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T21:58:58.243453Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":"2411.12377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-07-03T21:58:58.243453Z","title":"arXiv preprint arXiv:2411.12377 , year=","venue":null,"work_id":"31ef6dc6-b09d-4b09-b2e0-cb5603fdf061","year":2024},"citing_paper":{"arxiv_id":"2506.21095","last_updated":"2026-05-09T09:53:47Z","snapshot_observed_at":"2026-08-14T01:14:36.935167Z","submitted_at":"2025-06-26T08:43:12Z","title":"FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-19T08:07:52.498347Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2506.21095"},"observation_digest":"sha256:60fd22e6fb2a9b930a4b5c4b57d6d7aa80b94d8bd8e8547851e62cbd726bf3e2","observation_id":"e0a6f746-fa38-438a-980b-7a5cdbc77ed7","resolution":{"observed_at":"2026-05-19T08:12:10.720018Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-08-06T23:52:02.256519Z","title":"Non-iid data in federated learning: A survey with taxonomy, metrics, methods, frameworks and future directions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.00037","last_updated":"2026-05-28T11:41:22Z","snapshot_observed_at":"2026-08-06T23:42:18.711932Z","submitted_at":"2025-06-18T23:31:05Z","title":"Model Fusion via Retrofitting","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T23:52:02.256519Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2507.00037"},"observation_digest":"sha256:25bb9bcb174396c6525d1c7c8b357f761ce808f2030ec873eb938d4d3aa5e001","observation_id":"c7625bcf-85a5-41f0-86d2-8cd18dd50912","resolution":{"observed_at":"2026-08-06T23:52:02.256519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-08-03T11:57:34.165445Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.04930","last_updated":"2026-06-30T10:12:41Z","snapshot_observed_at":"2026-08-09T03:00:01.245986Z","submitted_at":"2026-01-08T13:27:53Z","title":"Privacy-Preserving Federated Averaging with Byzantine Aggregators in Asynchronous Networks","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T11:57:34.165445Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2601.04930"},"observation_digest":"sha256:e793307787007bf0254123de2557399a597b83f8825201d653c8b40dde7bd046","observation_id":"ce364021-0b8a-4cf9-b95c-ec525c77f02c","resolution":{"observed_at":"2026-08-03T11:57:34.165445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":"2411.12377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-07-03T21:58:58.243453Z","title":"arXiv preprint arXiv:2411.12377 , year=","venue":null,"work_id":"31ef6dc6-b09d-4b09-b2e0-cb5603fdf061","year":2024},"citing_paper":{"arxiv_id":"2604.10849","last_updated":"2026-04-12T22:48:51Z","snapshot_observed_at":"2026-07-06T22:59:23.126963Z","submitted_at":"2026-04-12T22:48:51Z","title":"Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T15:18:01.426404Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2604.10849"},"observation_digest":"sha256:2b7f1f85b7a41ccfd52286fa462ef60ca6c98cf899d8a8655308c0f32ab449bb","observation_id":"27ec88a5-efc3-4959-af7d-8132f654bdaf","resolution":{"observed_at":"2026-05-11T10:51:03.018242Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":"2411.12377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-07-03T21:58:58.243453Z","title":"arXiv preprint arXiv:2411.12377 , year=","venue":null,"work_id":"31ef6dc6-b09d-4b09-b2e0-cb5603fdf061","year":2024},"citing_paper":{"arxiv_id":"2605.08992","last_updated":"2026-05-09T15:22:08Z","snapshot_observed_at":"2026-08-14T09:31:10.872580Z","submitted_at":"2026-05-09T15:22:08Z","title":"When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-12T02:40:49.297092Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2605.08992"},"observation_digest":"sha256:6879d22a6436002caf8bf733279b49f27c29c25c6638214d8818d02f3ea0c1f6","observation_id":"36e5ebd7-98e7-4df0-baec-c4e7177277b0","resolution":{"observed_at":"2026-05-12T02:41:17.228267Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":"2411.12377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-07-03T21:58:58.243453Z","title":"arXiv preprint arXiv:2411.12377 , year=","venue":null,"work_id":"31ef6dc6-b09d-4b09-b2e0-cb5603fdf061","year":2024},"citing_paper":{"arxiv_id":"2605.17508","last_updated":"2026-05-17T15:42:33Z","snapshot_observed_at":"2026-08-13T23:28:10.440187Z","submitted_at":"2026-05-17T15:42:33Z","title":"BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-05-20T14:27:28.152992Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2605.17508"},"observation_digest":"sha256:f10127cfa6021ca0262e7101720d5b7419b6c682426b2d3b9ee47a3d46c1aeb1","observation_id":"7f5d33ee-1fd9-4bc9-9a7a-cddde85d37bd","resolution":{"observed_at":"2026-05-20T14:28:21.185575Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":"2411.12377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-07-03T21:58:58.243453Z","title":"arXiv preprint arXiv:2411.12377 , year=","venue":null,"work_id":"31ef6dc6-b09d-4b09-b2e0-cb5603fdf061","year":2024},"citing_paper":{"arxiv_id":"2606.08197","last_updated":"2026-06-06T14:28:36Z","snapshot_observed_at":"2026-08-07T12:12:32.562655Z","submitted_at":"2026-06-06T14:28:36Z","title":"AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-27T19:50:03.055481Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2606.08197"},"observation_digest":"sha256:17458e92030fd53d2cd909702217023e27475cffe6e9d55d706482f96b067ad1","observation_id":"983792d9-7157-4f4a-9186-08603eb461b0","resolution":{"observed_at":"2026-07-02T21:17:24.956943Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":"2411.12377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-07-03T21:58:58.243453Z","title":"arXiv preprint arXiv:2411.12377 , year=","venue":null,"work_id":"31ef6dc6-b09d-4b09-b2e0-cb5603fdf061","year":2024},"citing_paper":{"arxiv_id":"2607.00275","last_updated":"2026-06-30T23:51:44Z","snapshot_observed_at":"2026-08-12T11:51:16.097216Z","submitted_at":"2026-06-30T23:51:44Z","title":"Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-02T19:21:15.792499Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2607.00275"},"observation_digest":"sha256:247aee6939828685931d32021b17ca1785710167107fdfea60ecd3a6a72723e4","observation_id":"d2b9acd5-96a3-4388-82f9-1243cf3fbb3d","resolution":{"observed_at":"2026-07-02T19:27:18.633389Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":"2411.12377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-07-03T21:58:58.243453Z","title":"arXiv preprint arXiv:2411.12377 , year=","venue":null,"work_id":"31ef6dc6-b09d-4b09-b2e0-cb5603fdf061","year":2024},"citing_paper":{"arxiv_id":"2607.01272","last_updated":"2026-06-30T20:12:27Z","snapshot_observed_at":"2026-07-07T00:06:49.412663Z","submitted_at":"2026-06-30T20:12:27Z","title":"Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-03T21:58:30.339002Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2607.01272"},"observation_digest":"sha256:c21d125f603969250f95312385eba6197a4a5181915a311126456171e33f53a2","observation_id":"eab8db7e-eb97-47f4-9859-17932070a184","resolution":{"observed_at":"2026-07-03T21:58:58.245623Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-08-01T02:30:36.253345Z","title":"arXiv preprint arXiv:2411.12377 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25441","last_updated":"2026-07-28T08:33:04Z","snapshot_observed_at":"2026-08-14T09:23:14.907206Z","submitted_at":"2026-07-28T08:33:04Z","title":"PIcsC: Partitioning-Induced Covariate Shift Correction","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T02:30:36.253345Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2607.25441"},"observation_digest":"sha256:2c190fedad08f9b1d34a4036a5dbe7efb2622ea49050c711880fcca76eecf148","observation_id":"916dc3ef-bbf1-40f8-a953-0d1cf145ddf8","resolution":{"observed_at":"2026-08-01T02:30:36.253345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.12377","snapshot_observed_at":"2026-08-06T16:34:05.008101Z","title":"Non-IID data in federated learning: A survey with taxonomy, metrics, methods, frameworks and future directions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04791","last_updated":"2026-08-05T12:57:13Z","snapshot_observed_at":"2026-08-14T08:42:04.667576Z","submitted_at":"2026-08-05T12:57:13Z","title":"On the Effectiveness of Adaptation Strategies for VLM-Based Federated Learning in Remote Sensing","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T16:34:05.008101Z"},"links":{"cited_paper":"/paper/2411.12377","citing_paper":"/paper/2608.04791"},"observation_digest":"sha256:c2cf1bda00ef267b0681eea272c64bc80e63c67a1cc4bfcb2b246e7b7a0fe268","observation_id":"606089d8-7a43-491e-91c5-326c009cd949","resolution":{"observed_at":"2026-08-06T16:34:05.008101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2411.12377/citation-record","integrity":"/paper/2411.12377/integrity","json":"/paper/2411.12377/citation-record.json","paper":"/paper/2411.12377"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T17:39:18.041545Z","title":"Communication-efficient learning of deep networks from decentral- ized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.041545Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:c3b5c4ed5f8d7e03bd312e53607236f847bc1cbb6ba4c3468795a924f3e15087","observation_id":"79b81cc0-4f0a-4ffa-87a6-2f18225c9363","resolution":{"observed_at":"2026-08-12T17:39:18.041545Z","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":"2026-08-12T17:39:18.047415Z","title":"A survey for federated learning evaluations: Goals and measures,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.047415Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:2da408b9a2e08092f86a7810e9c5ac05bf53f38ebb2b267944df2e3ad3220dac","observation_id":"8a0ed0ee-1162-473e-9b6a-192103567aa7","resolution":{"observed_at":"2026-08-12T17:39:18.047415Z","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":"2026-08-12T17:39:18.052852Z","title":"Gdpr: Reshaping the landscape of digital transformation and business strategy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.052852Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:e0245086d4f3ea9c4dd1afcebc9a1a7a4ff9cc30bea57a1dddb07c897a04fa24","observation_id":"582d7af5-9346-44fc-b9ae-391ae33d1f2e","resolution":{"observed_at":"2026-08-12T17:39:18.052852Z","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":"2026-08-12T17:39:18.058221Z","title":"Complying with hipaa and hitech,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.058221Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:03a8cc94d1da9466b1db59b0c0acb18046917b16fc1dd2a8a98f763d6be1ca24","observation_id":"1b9149ff-21fb-4137-a886-d07eb0a3c9e2","resolution":{"observed_at":"2026-08-12T17:39:18.058221Z","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":"2026-08-12T17:39:18.063525Z","title":"Application of federated learning techniques for arrhythmia classification using 12-lead ecg signals,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.063525Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:4c02eea3cc27b5a52505df967f5ee49f42d38facb4ac2a2861ef891fd5dabe1d","observation_id":"49c29d9b-6724-4074-bb76-7ea85963539d","resolution":{"observed_at":"2026-08-12T17:39:18.063525Z","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":"2026-08-12T17:39:18.068184Z","title":"Transparency and privacy: the role of explainable ai and federated learning in financial fraud detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.068184Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:33bd7cef9205a6501278e7ee3a7bcc7f80cde7ebab46b6399032bae72b9c4a19","observation_id":"4c790696-b629-4c80-a342-8520b2042e59","resolution":{"observed_at":"2026-08-12T17:39:18.068184Z","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":"2026-08-12T17:39:18.072537Z","title":"Fedasa: A personalized federated learning with adaptive model aggregation for heterogeneous mobile edge computing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.072537Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:7860dacea6b0311680b5e93ac7f5f7f9f2bad4760a3b854a45f00cd370abf0b7","observation_id":"4cb67460-45e4-438f-a1d9-e6f9b8e12ae6","resolution":{"observed_at":"2026-08-12T17:39:18.072537Z","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":"2026-08-12T17:39:18.075783Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.075783Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:bc181bdb8a9307dc2db651b382e5f822284b09f974d64f6a53f915514886559b","observation_id":"0a71a5eb-52b0-41c9-afe8-8d6787afcbbb","resolution":{"observed_at":"2026-08-12T17:39:18.075783Z","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":"2026-08-12T17:39:18.079478Z","title":"Mnist hand- written digit database,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.079478Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:f9f9806f83780195e9f2497816a595bf40a01a25805efdc9ede821952332a6eb","observation_id":"9a9f19e6-eb5f-4e35-a9cc-d379d5060ab3","resolution":{"observed_at":"2026-08-12T17:39:18.079478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-12T17:39:18.083719Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.083719Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:5639b2a2a72f1a8803740cc79ea15de66bf4b3b12fd40f68118258ae2c8abb80","observation_id":"1ea9f682-7be5-4dff-9df2-c1e44997aec7","resolution":{"observed_at":"2026-08-12T17:39:18.083719Z","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":"2026-08-12T17:39:18.087904Z","title":"Enhancing generalization in federated learning with heterogeneous data: A comparative literature review,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.087904Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:cb85e464aacd8c1bc85fd4c7dc806c599a9e5fd28f2942ea1f5b4fd93a32bfa4","observation_id":"6862e343-12f0-469c-96ed-14ceec9713ee","resolution":{"observed_at":"2026-08-12T17:39:18.087904Z","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":"2026-08-12T17:39:18.093133Z","title":"Federated learning with non-iid data: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.093133Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:5b35bff5e930eb1076446a27ed982ddccab172d275143508da9bdde27f174d1b","observation_id":"5b0307e2-5221-4320-8dd9-5b1cd06681fd","resolution":{"observed_at":"2026-08-12T17:39:18.093133Z","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":"2026-08-12T17:39:18.096961Z","title":"A review of federated learning methods in heterogeneous scenarios,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.096961Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:789a970d9f6421c2e2895e373ff8ad90c51e49c6d22c7213a0527ab7e7cfb35c","observation_id":"adb680e3-8903-455f-87bb-5e8cf31d8d1e","resolution":{"observed_at":"2026-08-12T17:39:18.096961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09839","last_updated":"2025-03-08T13:53:07Z","snapshot_observed_at":"2026-08-13T00:06:07.000307Z","submitted_at":"2024-05-16T06:35:42Z","title":"Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations","version":2},"cited_work":{"arxiv_id":"2405.09839","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.09839","snapshot_observed_at":"2026-08-12T17:39:19.749228Z","title":"Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations","venue":"cs.LG","work_id":"3cf2d32f-72f0-416c-990c-f7d534eb179c","year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.100845Z"},"links":{"cited_paper":"/paper/2405.09839","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:0226ddc90d452f25b8e55aff64d8b0801602916cfa6b6dfa753b1f5bc4b626af","observation_id":"76fc1ff4-747c-411a-88a6-daf47317eeeb","resolution":{"observed_at":"2026-08-12T17:39:19.753433Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T17:39:18.109034Z","title":"Non-iid data and continual learning processes in federated learning: A long road ahead,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.109034Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:289bf21dafc4138a25c7061358d3abc996de481efe1be9d62e7fdf339ec09448","observation_id":"b0eade91-ae6a-47e5-9450-1d54539b3437","resolution":{"observed_at":"2026-08-12T17:39:18.109034Z","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":"2026-08-12T17:39:18.113193Z","title":"A state-of-the-art survey on solving non-iid data in federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.113193Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:4f4fb671f1ae3b8251a8c76b539b7df1829c2625806a52a0c7c4c8121c09bde7","observation_id":"70d468dc-9f36-42b6-89c3-a4598d712439","resolution":{"observed_at":"2026-08-12T17:39:18.113193Z","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":"2026-08-12T17:39:18.117500Z","title":"Federated learning on non-iid data: A survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.117500Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:3cf46775f1cec034ee262e8a7f274866e53eab1d9df3b3a209382e1db000fece","observation_id":"53ee4ce7-b877-4d67-87c9-4df3f26d704a","resolution":{"observed_at":"2026-08-12T17:39:18.117500Z","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":"2026-08-12T17:39:18.121912Z","title":"Decentralized federated averaging,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.121912Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:6b4cbdcf334577146edd8b431100a974038a28844c8614ecae1abfea62312ca5","observation_id":"353334d2-af8a-4dee-855b-02ad55d270f3","resolution":{"observed_at":"2026-08-12T17:39:18.121912Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05428","last_updated":"2021-01-14T02:44:28Z","snapshot_observed_at":"2026-08-13T19:08:59.420258Z","submitted_at":"2021-01-14T02:44:28Z","title":"Federated Learning: Opportunities and Challenges","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05428","snapshot_observed_at":"2026-08-12T17:39:18.126395Z","title":"Federated learning: Opportunities and challenges,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.126395Z"},"links":{"cited_paper":"/paper/2101.05428","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:adb3a9af20e320a0bbe9aa3665edea2dc16540c976ccce29f9b53d90195ba601","observation_id":"85b5521d-246a-4615-9abb-39e26132afe3","resolution":{"observed_at":"2026-08-12T17:39:18.126395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.12949","last_updated":"2022-06-26T19:49:41Z","snapshot_observed_at":"2026-08-13T15:16:03.869966Z","submitted_at":"2022-06-26T19:49:41Z","title":"Cross-Silo Federated Learning: Challenges and Opportunities","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.12949","snapshot_observed_at":"2026-08-12T17:39:18.131190Z","title":"Cross-silo federated learning: Challenges and opportunities,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.131190Z"},"links":{"cited_paper":"/paper/2206.12949","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:8f33428b27c6e23c0d8a6712299c72be07b5b77bdf2af8aade1eb15c41159ad1","observation_id":"21dd0a19-8809-4f0d-85ef-d21b87e0c43e","resolution":{"observed_at":"2026-08-12T17:39:18.131190Z","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":"2026-08-12T17:39:18.136177Z","title":"Federated learning for internet of things: A comprehensive survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.136177Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:1de9f7cc8afe9ef1cfc7d0cf9742c795e6fed729729b289129093eb03bf0c1b3","observation_id":"491feb2b-8e27-4f72-abcb-464dbcf33412","resolution":{"observed_at":"2026-08-12T17:39:18.136177Z","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":"2026-08-12T17:39:18.140001Z","title":"Client-edge-cloud hierarchical federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.140001Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:2a36d827264db77a09342fd443edbb89920f796b3a4bd2f3f3db75550a3cee8a","observation_id":"87eeb499-2f5a-4a59-8eb4-3edc3923d704","resolution":{"observed_at":"2026-08-12T17:39:18.140001Z","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":"2026-08-12T17:39:18.145161Z","title":"A survey on federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.145161Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:09005c9069c799c273679e86f6732eeb88f77c78a606dae010e7003f51622ddc","observation_id":"e34b377f-0954-403d-ae0a-92aef0e2940f","resolution":{"observed_at":"2026-08-12T17:39:18.145161Z","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":"2026-08-12T17:39:18.151012Z","title":"Federated learning review: Fundamentals, enabling technologies, and future applications,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.151012Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:ef8af7e887979840c876934c3207ed52ebce11a48f833c1b732d8d5bc5043477","observation_id":"a2e4c138-e6ee-4b74-934e-5e7e217ef44e","resolution":{"observed_at":"2026-08-12T17:39:18.151012Z","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":"2026-08-12T17:39:18.155828Z","title":"Vertical federated learning: Concepts, advances, and challenges,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.155828Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:467d3aef0faa43b14582b39c92c743b60176d6b9a137578b2683feab29827004","observation_id":"33f37153-2fd9-48d5-b394-eb2a0b4902a0","resolution":{"observed_at":"2026-08-12T17:39:18.155828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.06731","last_updated":"2019-05-16T13:23:49Z","snapshot_observed_at":"2026-07-06T07:53:29.215855Z","submitted_at":"2019-05-16T13:23:49Z","title":"BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.06731","snapshot_observed_at":"2026-08-12T17:39:18.159219Z","title":"Braintorrent: A peer-to-peer environment for decentralized federated learning,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.159219Z"},"links":{"cited_paper":"/paper/1905.06731","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:81e42ef368ed597b9a31fc0a770714032561177862e208f9b026d902161a926e","observation_id":"8492fbff-8dbb-49a9-afcf-80e97ef7c41c","resolution":{"observed_at":"2026-08-12T17:39:18.159219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-07-06T06:42:35.645776Z","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":"2026-08-12T17:39:18.163339Z","title":"Federated learning with non-iid data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.163339Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:685419a1a9508ec4d30f1786d1cf2126d6b9548fc5397d34344e5413d5be87c2","observation_id":"c33f09f8-f80a-4da6-80b6-1f0e31061799","resolution":{"observed_at":"2026-08-12T17:39:18.163339Z","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":"2026-08-12T17:39:18.167329Z","title":"A review: Data pre- processing and data augmentation techniques,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.167329Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:22ff3dfbb0adfe9a215cd5aef1707b8f85ff33fd693e503d23ee7ec59c2ab4aa","observation_id":"73f810d6-4064-4fc5-8734-1292ca094105","resolution":{"observed_at":"2026-08-12T17:39:18.167329Z","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":"2026-08-12T17:39:18.170872Z","title":"Resampling strategies for imbalanced regression: a survey and empirical analysis,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.170872Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:887a0832bfc15e5b072406ac542fc55a1a748fdeb94a4d9d628883c6899e9bd1","observation_id":"bcd69740-6777-4f3f-8cf4-94be172825ba","resolution":{"observed_at":"2026-08-12T17:39:18.170872Z","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":"2026-08-12T17:39:18.174514Z","title":"Evaluating machine learning models and their diagnostic value,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.174514Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:9e4dcc65ee89c6471a00a9f9c69f8ed69ca402f8025f108d11fbad37d415c7c0","observation_id":"7333437b-0ea0-4dc1-be9e-d6e2c3060f92","resolution":{"observed_at":"2026-08-12T17:39:18.174514Z","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":"2026-08-12T17:39:18.178051Z","title":"Internet of things intrusion detection: Centralized, on-device, or federated learning?","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.178051Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:f4537cc925aefa1196ab066dd13015275286dd4e3e923234de7c0374f41530a6","observation_id":"72038959-0db5-4924-9f16-cfb32bdddca5","resolution":{"observed_at":"2026-08-12T17:39:18.178051Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.16460","last_updated":"2024-03-29T08:46:16Z","snapshot_observed_at":"2026-08-14T01:46:37.937346Z","submitted_at":"2024-03-25T06:43:28Z","title":"FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.16460","snapshot_observed_at":"2026-08-12T17:39:18.181490Z","title":"Fedac: A adaptive clustered federated learning framework for heterogeneous data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.181490Z"},"links":{"cited_paper":"/paper/2403.16460","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:3f86f72c5ff694143d4e596c06efdc6ab692d58eb140c213849047238bc45c02","observation_id":"679f5ee8-8422-4ea8-93f1-5ba5818c9134","resolution":{"observed_at":"2026-08-12T17:39:18.181490Z","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":"2026-08-12T17:39:18.185515Z","title":"Node selection toward faster convergence for federated learning on non-iid data,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.185515Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:6bb8bcff15194b2e328bef5cdaeef9490d2afadfe927c6e50d6bb9df6572cd62","observation_id":"b8bb5fd6-e120-4525-974b-cba3911619b7","resolution":{"observed_at":"2026-08-12T17:39:18.185515Z","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":"2026-08-12T17:39:18.189314Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.189314Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:866710747f6be76d21bb083809d5905ed001a40eb5920ec3764c68bbd4099362","observation_id":"3e1d7e7f-481e-42fb-b8bc-85da66d16ad3","resolution":{"observed_at":"2026-08-12T17:39:18.189314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.09412","last_updated":"2021-08-21T01:14:27Z","snapshot_observed_at":"2026-08-12T19:53:50.220171Z","submitted_at":"2021-08-21T01:14:27Z","title":"SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.09412","snapshot_observed_at":"2026-08-12T17:39:18.193688Z","title":"Semifed: Semi-supervised federated learning with consistency and pseudo-labeling,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.193688Z"},"links":{"cited_paper":"/paper/2108.09412","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:e5ccd6a14827344519a01b35a566cb98b1cac2ff42636ff38530b4ec1dd61733","observation_id":"4447f102-5de1-4a4c-8112-fbaaf6f93f36","resolution":{"observed_at":"2026-08-12T17:39:18.193688Z","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":"2026-08-12T17:39:18.198746Z","title":"Client selection in federated learning under imperfections in environment,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.198746Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:e2c37209f111b663491548163492a8249e4300e4b12c0acceb05196f19324513","observation_id":"c5a7ec4c-7d3d-47e3-9fd3-91b0775d1eb4","resolution":{"observed_at":"2026-08-12T17:39:18.198746Z","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":"2026-08-12T17:39:18.203479Z","title":"Evaluating the commu- nication efficiency in federated learning algorithms,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.203479Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:ceb33250343964131cdc6a51918455287262a26c1ad83b10c6ecee9b287d959d","observation_id":"d983c078-540d-4570-ae4b-4449f7c33f57","resolution":{"observed_at":"2026-08-12T17:39:18.203479Z","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":"2026-08-12T17:39:18.207369Z","title":"On safeguarding privacy and security in the framework of federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.207369Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:03497bcb698c2cc4b9b56947d2f7e6411a0fe70b5ba887e7fdb339eade1318fb","observation_id":"27723f4d-27b4-4ae6-b0ad-10ebf4bc0b01","resolution":{"observed_at":"2026-08-12T17:39:18.207369Z","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":"2026-08-12T17:39:18.211717Z","title":"Poisoning attacks in federated learning: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.211717Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:2a9854d0f3a4e4ce9bcceea7ac04dedfc733a2dfb0f1c6f5d0f46a887cdddcff","observation_id":"128f9d7d-4645-4796-9daf-b355703693e2","resolution":{"observed_at":"2026-08-12T17:39:18.211717Z","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":"2026-08-12T17:39:18.216745Z","title":"Addressing heterogeneity in federated learning with client selection via submodular optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.216745Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:be48e918a54e3338f963f9240068b73db8302fff3cb14a223ca01b9bba386dce","observation_id":"a2ffa4d6-2e0f-44f3-9a83-0cad827c24d4","resolution":{"observed_at":"2026-08-12T17:39:18.216745Z","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":"2026-08-12T17:39:18.220745Z","title":"Wscc: A weight-similarity- based client clustering approach for non-iid federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.220745Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:b528c087532a058cb0618ca9bdf3a13a318e219fd441332893f893231c2b92bb","observation_id":"4057133d-663f-47c7-8f55-59b24aec05ff","resolution":{"observed_at":"2026-08-12T17:39:18.220745Z","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":"2026-08-12T17:39:18.224547Z","title":"A contribution-based device selection scheme in federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.224547Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:a8c3570ebc3d7f16d90ceafd3e03f4b2c15bdfc19543f1fa66ef679582b95125","observation_id":"5d84e7fa-76f0-4f45-a147-d2f2486b7e17","resolution":{"observed_at":"2026-08-12T17:39:18.224547Z","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":"2026-08-12T17:39:18.227757Z","title":"Towards federated learning: An overview of methods and applications,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.227757Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:3d9345565fc6a75eb1ad6cbac922dd84a3ecc8b51ee03371a036770463e25711","observation_id":"d9c1db4c-1080-4e83-927d-162bc65a7ee5","resolution":{"observed_at":"2026-08-12T17:39:18.227757Z","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":"2026-08-12T17:39:18.231257Z","title":"How to do a systematic review: a best practice guide for conducting and reporting narrative reviews, meta-analyses, and meta-syntheses,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.231257Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:3cbda98100905d3b807bf149a613669501f891d399c470eca7d4f033f2a68a01","observation_id":"ff6bb2f0-88ff-41cd-9a29-c8053d267e52","resolution":{"observed_at":"2026-08-12T17:39:18.231257Z","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":"2026-08-12T17:39:18.234837Z","title":"(2004) Google scholar","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.234837Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:49736755ba9eec2c48fad7a28a94cf4cfb6ee898ffa539b9a8a4808808e6fd5c","observation_id":"5670782c-6e01-4cfc-aa75-3b3f522ae8e7","resolution":{"observed_at":"2026-08-12T17:39:18.234837Z","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":"2026-08-12T17:39:18.238071Z","title":"(2000) Ieee xplore","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.238071Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:989b25c0ae484a1673f796ffcfbcae02544cdd2959f9e942bd88a3cbee85d67b","observation_id":"b08a6fdd-055d-4ca2-96f5-3166bded768a","resolution":{"observed_at":"2026-08-12T17:39:18.238071Z","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":"2026-08-12T17:39:18.241678Z","title":null,"venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.241678Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:f6b680c4e349fea11deec415b5adfa28a8db070cb48a90d0c9ab7a5dc30f9ef6","observation_id":"5a84ac94-db3e-419c-bd61-0e648667dce7","resolution":{"observed_at":"2026-08-12T17:39:18.241678Z","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":"2026-08-12T17:39:18.245161Z","title":"(2004) Scopus","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.245161Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:d83cf5f7783439c3e96795e36bbec0b924c4964b2dd13af749b4d7638d1aaf80","observation_id":"58713925-9491-4fca-ba25-3c2cf0c59060","resolution":{"observed_at":"2026-08-12T17:39:18.245161Z","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":"2026-08-12T17:39:18.248657Z","title":"(1997) Web of science","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.248657Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:67d5641a60d24e8b660f51c875cda945d5ed2104ef69712809a7c2d4bccf4ad0","observation_id":"48c09253-991c-49c2-ab85-563141a9d08d","resolution":{"observed_at":"2026-08-12T17:39:18.248657Z","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":"2026-08-12T17:39:18.253054Z","title":null,"venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.253054Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:de7d429d21bc76fa5caa81a6aa755471fbd6801f5f4afdd9709164544feb7dc3","observation_id":"178661a7-2f2d-45e2-a38b-22c8e5ce9b97","resolution":{"observed_at":"2026-08-12T17:39:18.253054Z","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":"2026-08-12T17:39:18.257027Z","title":"Fedel: Federated ensemble learning for non-iid data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.257027Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:42deff070bee105de6591c8c61b7aef05fb123d759984592fb9bde589f5ef760","observation_id":"ca47621a-3942-492d-97b6-30485a7aff40","resolution":{"observed_at":"2026-08-12T17:39:18.257027Z","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":"2026-08-12T17:39:18.260895Z","title":"Aedfl: efficient asynchronous decentralized federated learning with heterogeneous devices,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.260895Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:5b26c40e5ba3d7f414725555585330c807a0f6db913f8ba50ea24b3382c90df4","observation_id":"a935bb1b-7e53-4069-8f6a-0c69c4d80aed","resolution":{"observed_at":"2026-08-12T17:39:18.260895Z","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":"2026-08-12T17:39:18.264805Z","title":"Federated learning with a balanced heterogeneous-yoke and loose restriction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.264805Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:cb4c07652df07795d48f33cf2a6921c18d346e0d4942ec5c0d87d4193f9a48a0","observation_id":"63576dfd-7186-4dc7-bb61-d1754ae7c8cb","resolution":{"observed_at":"2026-08-12T17:39:18.264805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02803","last_updated":"2024-03-05T09:18:29Z","snapshot_observed_at":"2026-08-14T08:09:51.841686Z","submitted_at":"2024-03-05T09:18:29Z","title":"Towards Robust Federated Learning via Logits Calibration on Non-IID Data","version":1},"cited_work":{"arxiv_id":"2403.02803","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.02803","snapshot_observed_at":"2026-08-12T17:39:19.667255Z","title":"Towards Robust Federated Learning via Logits Calibration on Non-IID Data","venue":"cs.CV","work_id":"d5273cba-d06f-4d1a-a6dc-b71e6e968433","year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.268600Z"},"links":{"cited_paper":"/paper/2403.02803","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:99f5e72c5b9b4d06b56cead82c31c5eabe9fd2d2ccc11ea66608fb8615125f81","observation_id":"9c329997-fa0c-4c00-990c-d91338ed68d9","resolution":{"observed_at":"2026-08-12T17:39:19.671126Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T17:39:18.273036Z","title":"On the effectiveness of partial variance reduction in federated learning with heterogeneous data,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.273036Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:9aa38012cd8ea64ff8d4b429b2a259669ca98f6066f40150533f64f67459859c","observation_id":"16d46551-b919-4a5b-896e-7ab6b72b5b10","resolution":{"observed_at":"2026-08-12T17:39:18.273036Z","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":"2026-08-12T17:39:18.276964Z","title":"Tackling data heterogeneity in federated learning with class prototypes,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.276964Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:affef52f586405cb52d68a835220665a7ed3b75589ab8fb659038f994bf79c78","observation_id":"083dc585-7bba-483f-bf55-58160356377a","resolution":{"observed_at":"2026-08-12T17:39:18.276964Z","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":"2026-08-12T17:39:18.280797Z","title":"Label-efficient self-supervised federated learning for tackling data heterogeneity in medical imaging,","venue":null,"work_id":null,"year":1932},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.280797Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:ad59914e5ecb1fd04d7de0f47341da2781d6fdb2954f6cd86f50448dc730e628","observation_id":"07ea319f-2d8e-4488-bcb6-53077dc7a982","resolution":{"observed_at":"2026-08-12T17:39:18.280797Z","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":"2026-08-12T17:39:18.286506Z","title":"Feder- ated learning with label distribution skew via logits calibration,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.286506Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:815af348568d91b4c61520cebf4475750deddea6c8b2b81e442111110f395b26","observation_id":"62f20e3e-3589-4ea7-9e10-1f9ed4d53dee","resolution":{"observed_at":"2026-08-12T17:39:18.286506Z","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":"2026-08-12T17:39:18.290283Z","title":"Learning critically: Selective self-distillation in federated learning on non-iid data,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.290283Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:1483a2cd91ed4dcb645811f4de84bf90e6a2bec521fe8f81b59955156cfc0ce7","observation_id":"eca85175-86cc-49d9-a0b5-718c36e9e41d","resolution":{"observed_at":"2026-08-12T17:39:18.290283Z","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":"2026-08-12T17:39:18.293986Z","title":"Fedpd: A federated learning framework with adaptivity to non-iid data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.293986Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:7cb43fdc0c016b8f2b29af43f62070c756eb26e0d1a8cbd99c4e6262dd338331","observation_id":"60b0fafc-fb1d-4f0f-af70-0aa870d4c125","resolution":{"observed_at":"2026-08-12T17:39:18.293986Z","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":"2026-08-12T17:39:18.297535Z","title":"Ferrari: A personalized federated learning framework for heterogeneous edge clients,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.297535Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:ede8b5d15b6f9a71ba25d615c9729df27f47934180fe860d759ac4d780e1cf83","observation_id":"e297ad24-c00d-4d3f-9db0-133229b84add","resolution":{"observed_at":"2026-08-12T17:39:18.297535Z","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":"2026-08-12T17:39:18.302074Z","title":"Towards reliable participation in uav-enabled federated edge learning on non-iid data,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.302074Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:18db270f8070e862357a67bb8a19f46cb61e83de5709f8014a2e7a56e50fef09","observation_id":"3e0a6ed0-d099-4a11-8a45-be1cbac1f6b6","resolution":{"observed_at":"2026-08-12T17:39:18.302074Z","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":"2026-08-12T17:39:18.307529Z","title":"Federated learning with taskonomy for non-iid data,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.307529Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:b133a01a37f64cbf327b080f57fed00c0c6aa706bda9eeef1012a2dfeaa58ba8","observation_id":"de9a3883-fe53-404c-9228-239562daedf8","resolution":{"observed_at":"2026-08-12T17:39:18.307529Z","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":"2026-08-12T17:39:18.311837Z","title":"Per- sonalized cross-silo federated learning on non-iid data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.311837Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:4e36050792f6fe7bdbfb19ccf04acc41144ff5aee7c3bbc4517094466d1e1989","observation_id":"330b1190-a56c-4287-afb1-5050b8e3a6a3","resolution":{"observed_at":"2026-08-12T17:39:18.311837Z","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":"2026-08-12T17:39:18.315942Z","title":"Exploiting label skews in federated learning with model concatenation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.315942Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:cbd557bb8f2d985a4a431e60ddb3f87c932023c8b11ac6e5e9089e8c86296810","observation_id":"eb27a837-acd4-4574-9f44-96b0fc0a2808","resolution":{"observed_at":"2026-08-12T17:39:18.315942Z","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":"2026-08-12T17:39:18.319647Z","title":"Flgan: Gan-based unbiased federated learning under non-iid settings,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.319647Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:ec330e184dbd2f2525d364565c738f2c3985944c0c47c4571004d13d8c2ebbed","observation_id":"0e850fd8-a4f9-42bb-b658-c1ee52b6f59c","resolution":{"observed_at":"2026-08-12T17:39:18.319647Z","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":"2026-08-12T17:39:18.323264Z","title":"Ringsfl: An adaptive split federated learning towards taming client heterogeneity,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.323264Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:f8d9ea441c60d9b47201a795005889de66f099a971dbeb96a51af4920cceafd1","observation_id":"aea896ca-4d82-41ae-99b8-c8982354be57","resolution":{"observed_at":"2026-08-12T17:39:18.323264Z","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":"2026-08-12T17:39:18.327542Z","title":"Byzantine-robust variance- reduced federated learning over distributed non-iid data,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.327542Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:dea5d4f7ea306a23214a8f9bf3b241a9821fdf21956deb756801de03785e9937","observation_id":"77bfb0cc-2527-4326-92f1-bb80d280c9b3","resolution":{"observed_at":"2026-08-12T17:39:18.327542Z","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":"2026-08-12T17:39:18.332108Z","title":"Lfighter: Defending against the label-flipping attack in federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.332108Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:bb8b1b9e22116619045a8561b2b1732b4c0f9991ad4036451d3760eaec5ce4fb","observation_id":"84aea243-1a6d-49c8-b553-a3f2bb06db1c","resolution":{"observed_at":"2026-08-12T17:39:18.332108Z","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":"2026-08-12T17:39:18.336099Z","title":"Cross- to-merge training with class balance strategy for learning with noisy labels,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.336099Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:e077861c1aa223b080004c4cd11d963e0b8b014725d214ff7148193680ee39ce","observation_id":"bbfc3d22-27a8-4323-8d07-93559cca9e60","resolution":{"observed_at":"2026-08-12T17:39:18.336099Z","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":"2026-08-12T17:39:18.340222Z","title":"Blockchain-based fairness- enhanced federated learning scheme against label flipping attack,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.340222Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:72d2506c74142b3ed5d22ba19daa8449eeb36e04c8f945a22b76bef4a0a9b2b5","observation_id":"58bf414d-c32e-43ee-aeea-190c01306116","resolution":{"observed_at":"2026-08-12T17:39:18.340222Z","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":"2026-08-12T17:39:18.344081Z","title":"Fedcir: Client- invariant representation learning for federated non-iid features,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.344081Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:1c24fd4a3212d34731511330956666de2826943b2877368b21aa28c7af013184","observation_id":"4fb38d7f-06cd-48ab-a619-614089c6981f","resolution":{"observed_at":"2026-08-12T17:39:18.344081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.12130","last_updated":"2024-04-18T12:31:48Z","snapshot_observed_at":"2026-08-13T00:27:27.656005Z","submitted_at":"2024-04-18T12:31:48Z","title":"One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity","version":1},"cited_work":{"arxiv_id":"2404.12130","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.12130","snapshot_observed_at":"2026-08-12T17:39:19.651076Z","title":"One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity","venue":"cs.LG","work_id":"bee7a4df-f4e7-42e0-a366-68f0285cba04","year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.348583Z"},"links":{"cited_paper":"/paper/2404.12130","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:df05450f15f38547b1da4fc41d076c6203ffbf0f792d25417de3d84589a3d22e","observation_id":"834db2b5-9a35-4e0d-9c7b-86b32b39c595","resolution":{"observed_at":"2026-08-12T17:39:19.655791Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T17:39:18.353064Z","title":"Fairfed: Enabling group fairness in federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.353064Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:dba9dfd90ec6b134a0302fe8bee0630577b2d9877dcd6e843640435e04e05cfc","observation_id":"eb67e342-d872-40c4-8473-287dc503c602","resolution":{"observed_at":"2026-08-12T17:39:18.353064Z","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":"2026-08-12T17:39:18.356955Z","title":"Fairness and accuracy in horizontal federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.356955Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:a75118123740633e35ca14a76df7eb553feaf879739bd379cb06e69b15f17332","observation_id":"07ee95ca-deec-4c5f-b80b-2e8c592b41c5","resolution":{"observed_at":"2026-08-12T17:39:18.356955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.08517","last_updated":"2021-07-20T13:53:58Z","snapshot_observed_at":"2026-08-13T18:44:01.148226Z","submitted_at":"2021-07-18T19:05:44Z","title":"Decentralized federated learning of deep neural networks on non-iid data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.08517","snapshot_observed_at":"2026-08-12T17:39:18.360901Z","title":"Decentralized federated learning of deep neural networks on non-iid data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.360901Z"},"links":{"cited_paper":"/paper/2107.08517","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:53b83d7cbca7f708391f6a96882fef568799bbf0038c1f5e3219f82906eaca08","observation_id":"84567b48-a197-48fb-88ea-0b618cb213f4","resolution":{"observed_at":"2026-08-12T17:39:18.360901Z","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":"2026-08-12T17:39:18.364755Z","title":"Robust federated learning: The case of affine distribution shifts,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.364755Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:7812f92321503c8d44b468f6e0c918fcf75a0f8abc9c5e8aeb8589fc62d583cf","observation_id":"f8d88a8b-e864-4614-884c-bcd758e67020","resolution":{"observed_at":"2026-08-12T17:39:18.364755Z","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":"2026-08-12T17:39:18.368023Z","title":"Fairtrade: Achieving pareto-optimal trade-offs between balanced accuracy and fairness in federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.368023Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:237cbd6de0e3e336c5a1a6f722fe5b0c8f810d02a1d7b30636d2aa4f36f020f8","observation_id":"68a99cb1-e527-437f-8024-da7df078a645","resolution":{"observed_at":"2026-08-12T17:39:18.368023Z","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":"2026-08-12T17:39:18.371735Z","title":"Fraug: Tackling federated learning with non-iid features via representation augmenta- tion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.371735Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:944cd4c9cfabb0420c7c7d746625d6991b0c9df6b79f71443bec5bc1f09226ab","observation_id":"29b84d34-cbb7-47c6-9433-b3e7860421f1","resolution":{"observed_at":"2026-08-12T17:39:18.371735Z","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":"2026-08-12T17:39:18.376043Z","title":"Clustered federated learning with adaptive local differential privacy on heterogeneous iot data,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.376043Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:15545db0a620dfebb89a7b45ca940a352a5b01b2f705acd17350606d59aaf3ac","observation_id":"3df59505-ed38-4a45-9092-19856187bfa1","resolution":{"observed_at":"2026-08-12T17:39:18.376043Z","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":"2026-08-12T17:39:18.379791Z","title":"Federated learning for dis- tribution skewed data using sample weights,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.379791Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:6ca570397785f4c94d4c64be8cda85668033aa88bfcae89b41e2f6253b459619","observation_id":"a507c197-775a-4bd3-9b33-b765cea3e4eb","resolution":{"observed_at":"2026-08-12T17:39:18.379791Z","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":"2026-08-12T17:39:18.383392Z","title":"Federated learning on non-iid graphs via structural knowledge sharing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.383392Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:07cb1af0cbbdb576b81d889c308a951fb65829fc3ccb618f166bed42828a043b","observation_id":"65cc7a42-c45e-4d4d-a443-61df6674305e","resolution":{"observed_at":"2026-08-12T17:39:18.383392Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09363","last_updated":"2024-12-06T05:35:09Z","snapshot_observed_at":"2026-08-13T11:17:43.730555Z","submitted_at":"2023-06-14T05:46:52Z","title":"A Simple Data Augmentation for Feature Distribution Skewed Federated Learning","version":2},"cited_work":{"arxiv_id":"2306.09363","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.09363","snapshot_observed_at":"2026-08-12T17:39:19.624402Z","title":"A Simple Data Augmentation for Feature Distribution Skewed Federated Learning","venue":"cs.LG","work_id":"4a633e31-edcf-481b-ac64-34efa86a0c66","year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.387027Z"},"links":{"cited_paper":"/paper/2306.09363","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:27796f0b438fd3bd30241cdfcc52e59908642e49a27ae438a1ce0be8feec71b3","observation_id":"9afaaed7-f8d0-4d34-b752-2c1c52bd16b7","resolution":{"observed_at":"2026-08-12T17:39:19.628677Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T17:39:18.391466Z","title":"Fl-enhance: A federated learning framework for balancing non-iid data with aug- mented and shared compressed samples,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.391466Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:80803d2d7a66edd12c86c8faecab13786921d03f85b4caad7efa52d32ece1d58","observation_id":"d1e93105-80c0-4bde-8b5d-cf09a265a4e3","resolution":{"observed_at":"2026-08-12T17:39:18.391466Z","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":"2026-08-12T17:39:18.397106Z","title":"Cross-silo federated learning for multi-tier networks with vertical and horizontal data partitioning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.397106Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:6daa1270d1e3c5c7bdcf9438bac03ccc4dc36c95460d99cac2450ceb18b72e26","observation_id":"dd000b70-e0fd-4719-8433-271ae9521d44","resolution":{"observed_at":"2026-08-12T17:39:18.397106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.01340","last_updated":"2022-09-03T06:14:20Z","snapshot_observed_at":"2026-08-13T14:33:39.160463Z","submitted_at":"2022-09-03T06:14:20Z","title":"Federated XGBoost on Sample-Wise Non-IID Data","version":1},"cited_work":{"arxiv_id":"2209.01340","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.01340","snapshot_observed_at":"2026-08-12T17:39:19.608574Z","title":"Federated XGBoost on Sample-Wise Non-IID Data","venue":"cs.LG","work_id":"8e5d7f85-279f-46f6-849c-9803a75ef6f8","year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.401243Z"},"links":{"cited_paper":"/paper/2209.01340","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:fc2964c7cff79b1e0fc54d68e3af0ac5cb4916ef95ae909981d1d17cbe4b212e","observation_id":"8e5db74d-f07a-4d7b-9a3a-6ce77d5f315d","resolution":{"observed_at":"2026-08-12T17:39:19.613154Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T17:39:18.405936Z","title":"Fedmultimodal: A benchmark for multimodal federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.405936Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:7dc3f77609a0f0400d6af94721224999600d1dbe258b3d9928ff21765f31c0c0","observation_id":"be1eb54c-7b7b-4f55-902f-c7ef179366bf","resolution":{"observed_at":"2026-08-12T17:39:18.405936Z","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":"2026-08-12T17:39:18.409851Z","title":"Towards optimal multi-modal federated learning on non-iid data with hierarchical gradient blending,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.409851Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:ab935d3270bdc7009bb90ce6c62eaa93b22cbec65215aaf4f79c08645e41a690","observation_id":"5c79ad69-81d7-4517-9e8c-4ce159277fa5","resolution":{"observed_at":"2026-08-12T17:39:18.409851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.03609","last_updated":"2024-10-08T14:52:18Z","snapshot_observed_at":"2026-08-14T10:35:17.976321Z","submitted_at":"2024-01-07T23:45:01Z","title":"Multi-Modal Federated Learning for Cancer Staging over Non-IID Datasets with Unbalanced Modalities","version":3},"cited_work":{"arxiv_id":"2401.03609","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.03609","snapshot_observed_at":"2026-08-12T17:39:19.591582Z","title":"Multi-Modal Federated Learning for Cancer Staging over Non-IID Datasets with Unbalanced Modalities","venue":"cs.LG","work_id":"6898c189-a17c-4904-af6d-de4b70ae6e6a","year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.414390Z"},"links":{"cited_paper":"/paper/2401.03609","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:cd72816953eac6d21900b469b49f55e2113d783c22a1537bb83592a2802f4589","observation_id":"85f95679-9706-4755-b6ed-f7d586edfeec","resolution":{"observed_at":"2026-08-12T17:39:19.596698Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T17:39:18.418553Z","title":"Harmony: Heterogeneous multi-modal federated learn- ing through disentangled model training,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.418553Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:0cb7c6c026fa20bd899a6dc0d03c064cbf36ca8f2516c7fd54708a2771fed68a","observation_id":"18f42c6a-3e20-4482-977e-86358b9658a2","resolution":{"observed_at":"2026-08-12T17:39:18.418553Z","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":"2026-08-12T17:39:18.423254Z","title":"Fault diagnosis based on federated learning driven by dynamic ex- pansion for model layers of imbalanced client,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.423254Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:3921a4b48e10a674378f2c12eea019ee5a2ae105e717c6855eb0bd4644998f7d","observation_id":"a9e231f6-2453-4ad6-a62f-92e92be964b7","resolution":{"observed_at":"2026-08-12T17:39:18.423254Z","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":"2026-08-12T17:39:18.428133Z","title":"Ada- ffl: Adaptive computing fairness federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.428133Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:90d8183cd03f78ca3ec73a9c917f07af468e39a31e7373cf73a71727fbf9fab2","observation_id":"7a5c51b0-1e80-40a9-a905-6729f8594130","resolution":{"observed_at":"2026-08-12T17:39:18.428133Z","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":"2026-08-12T17:39:18.432298Z","title":"Experimenting with normalization layers in federated learning on non- iid scenarios,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.432298Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:375f1bcd468734ce2473f01a0f5bbe97b24270100ac06f535cc4f2a1d09132e4","observation_id":"6987bbc2-3e39-481b-a9d4-04dda63ffbed","resolution":{"observed_at":"2026-08-12T17:39:18.432298Z","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":"2026-08-12T17:39:18.436026Z","title":"Fedproc: Prototypical contrastive federated learning on non-iid data,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.436026Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:dff24bfd92a006feae9399fdccb6cdda28df38c29da6a660ac7161c026d3f35c","observation_id":"ff6b00c0-4b85-4a1f-8de5-ff25797647b6","resolution":{"observed_at":"2026-08-12T17:39:18.436026Z","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":"2026-08-12T17:39:18.439894Z","title":"Distribution-regularized federated learning on non-iid data,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.439894Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:efefbb2d0fa1624500b2f7f382658ecf0764e90554cfb814ff88a60ce67cb9c3","observation_id":"5f8ef272-9f52-44b9-aedd-e4122d521c08","resolution":{"observed_at":"2026-08-12T17:39:18.439894Z","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":"2026-08-12T17:39:18.443891Z","title":"Flis: Clustered federated learning via inference similarity for non-iid data distribution,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.443891Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:073c8a1ffee3d23332fcd6df0898f745baea840ff49d32451d1ab2e27c71af8f","observation_id":"025946fb-f922-44b4-aa8b-8ac4f9319d2e","resolution":{"observed_at":"2026-08-12T17:39:18.443891Z","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":"2026-08-12T17:39:18.448778Z","title":"Blockchain- based two-stage federated learning with non-iid data in iomt system,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.448778Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:c04f6958026b0a249ce8aa54dc17a1f0c5d7e5f5b4beb9aa06324a34f1a22ba3","observation_id":"704ffbdc-b5ec-4328-8a3c-33fb85fb460a","resolution":{"observed_at":"2026-08-12T17:39:18.448778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.09979","last_updated":"2022-06-20T19:47:43Z","snapshot_observed_at":"2026-08-13T16:17:31.466117Z","submitted_at":"2022-06-20T19:47:43Z","title":"Mitigating Data Heterogeneity in Federated Learning with Data Augmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.09979","snapshot_observed_at":"2026-08-12T17:39:18.452254Z","title":"Mitigating data heterogeneity in federated learning with data augmentation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.452254Z"},"links":{"cited_paper":"/paper/2206.09979","citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:af15f126f1984279ece994da72cf55e68fd127305e05789feb1f5d56df74e90a","observation_id":"0051b108-409a-4a04-9e0b-a74796194a84","resolution":{"observed_at":"2026-08-12T17:39:18.452254Z","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":"2026-08-12T17:39:18.455872Z","title":"Privacy threat and defense for federated learning with non-iid data in aiot,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.455872Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:2ad7de2562003a605c79f24daa0c155262a866e5be47e4cac290ecc579cc9eea","observation_id":"9aa737a2-a905-4b7e-a0d8-e88f444de077","resolution":{"observed_at":"2026-08-12T17:39:18.455872Z","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":"2026-08-12T17:39:18.459913Z","title":"Safari: Sparsity-enabled federated learning with limited and unreliable communications,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-12T17:39:18.459913Z"},"links":{"citing_paper":"/paper/2411.12377"},"observation_digest":"sha256:7c5de34184b8a3897f7a3758cb4177ca3271efc0e4ea09e002b2f94586d25b51","observation_id":"82e07177-5d97-40e0-aa5f-3f5c87b0d74b","resolution":{"observed_at":"2026-08-12T17:39:18.459913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.12377","last_updated":"2024-12-12T18:16:23Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T11:10:02.873974Z","submitted_at":"2024-11-19T09:53:28Z","title":"Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":94,"verified_exact":6,"verified_fuzzy":0},"total_outbound_references":268},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 100 of 268 outbound references and 11 inbound Pith citation observations for arXiv:2411.12377."}