{"as_of":"2026-08-09T13:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d42b35bb8ee16358c45a6a82e89658f3ef145074f53e64cea95894ccd300ef0d","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:59:37.558240Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T16:34:00.285002Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.20485","snapshot_observed_at":"2026-08-04T16:34:00.285002Z","title":"P.; and Li, A","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.18171","last_updated":"2026-07-30T06:29:57Z","snapshot_observed_at":"2026-08-08T00:42:05.608636Z","submitted_at":"2025-09-17T13:04:11Z","title":"Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysis","version":5},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T16:34:00.285002Z"},"links":{"cited_paper":"/paper/2505.20485","citing_paper":"/paper/2509.18171"},"observation_digest":"sha256:b123e99da16906a6231bbe8761eca1050d1f8de019101bf17b6a61eceed9750e","observation_id":"08dc3db0-6aa5-4d5a-9076-589c5b19fc0c","resolution":{"observed_at":"2026-08-04T16:34:00.285002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.20485/citation-record","integrity":"/paper/2505.20485/integrity","json":"/paper/2505.20485/citation-record.json","paper":"/paper/2505.20485"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2111.04263","last_updated":"2021-11-09T16:37:10Z","snapshot_observed_at":"2026-08-06T07:03:02.521207Z","submitted_at":"2021-11-08T03:58:28Z","title":"Federated Learning Based on Dynamic Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.04263","snapshot_observed_at":"2026-08-07T13:59:33.793400Z","title":"Federated learning based on dynamic regularization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:33.793400Z"},"links":{"cited_paper":"/paper/2111.04263","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:defaf00717c6d6d1788cc8abdbb7727b69191ad97352469d517c1897bfab094e","observation_id":"cac5a2d5-0cf6-4f7c-9634-0c96c30bb052","resolution":{"observed_at":"2026-08-07T13:59:33.793400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1508.05326","last_updated":"2015-08-21T16:17:01Z","snapshot_observed_at":"2026-08-05T22:08:24.004344Z","submitted_at":"2015-08-21T16:17:01Z","title":"A large annotated corpus for learning natural language inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1508.05326","snapshot_observed_at":"2026-08-07T13:59:33.831292Z","title":"A large annotated corpus for learning natural language inference","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:33.831292Z"},"links":{"cited_paper":"/paper/1508.05326","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:9b9f2be00003355ed1b671498fe2b23cb3223a6325d46f9ddcbec7b29a1972d6","observation_id":"9457d201-6acf-4671-93ea-3f1ab7fa42b3","resolution":{"observed_at":"2026-08-07T13:59:33.831292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:42.777840Z","title":"On the convergence of decentralized federated learning under imperfect information sharing","venue":null,"work_id":"af675739-5a9f-4012-b1bd-e6c71d45401f","year":2023},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:33.903593Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:266fe8c34da7828a4daa265304ff420afd8dfcd8164acf9958ae897837e2e6f1","observation_id":"50ab88fe-ebcb-4daf-ae5c-d975b6ab1ff8","resolution":{"observed_at":"2026-08-07T13:59:42.884356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:42.580413Z","title":"Brinton, Stanislaw H Zak, and Zi- ran Wang","venue":null,"work_id":"fa357110-3cea-4363-8082-5c62c1cd2b2d","year":2023},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:33.968893Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:21e2fa34503fcba7098de4be58fb3e902a1d14f04948079702f7c33b9ca9b642","observation_id":"317de3dc-92b0-45da-9ef2-e31941edb084","resolution":{"observed_at":"2026-08-07T13:59:42.658333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10677","last_updated":"2023-03-19T14:44:37Z","snapshot_observed_at":"2026-08-07T22:25:55.022265Z","submitted_at":"2023-03-19T14:44:37Z","title":"A Survey of Federated Learning for Connected and Automated Vehicles","version":1},"cited_work":{"arxiv_id":"2303.10677","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.10677","snapshot_observed_at":"2026-08-07T13:59:38.183465Z","title":"A Survey of Federated Learning for Connected and Automated Vehicles","venue":"cs.LG","work_id":"7203791f-7697-498a-9528-9ad73f3d574a","year":2023},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.059476Z"},"links":{"cited_paper":"/paper/2303.10677","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:9473e553fd053a661225b2f0ddb18ee102669049ab9b0f0bbd6f9e8131a1f309","observation_id":"c5d2cf0c-1a84-4aac-b0f3-1aa7852893b0","resolution":{"observed_at":"2026-08-07T13:59:38.288096Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13247","last_updated":"2024-03-24T20:58:50Z","snapshot_observed_at":"2026-08-04T17:51:09.127768Z","submitted_at":"2024-03-20T02:17:47Z","title":"FedNMUT -- Federated Noisy Model Update Tracking Convergence Analysis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13247","snapshot_observed_at":"2026-08-07T13:59:34.146113Z","title":"Fednmut – federated noisy model update tracking convergence analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.146113Z"},"links":{"cited_paper":"/paper/2403.13247","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:796ecef739dbbb3f1315819a7acb4c155952b1e4789a38c0d4227d36c8cc2655","observation_id":"c33538eb-4ecb-46f5-9a8e-c4ff2585f200","resolution":{"observed_at":"2026-08-07T13:59:34.146113Z","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":"2026-08-07T13:59:34.281252Z","title":"Fedgems: Federated learning of larger server models via selective knowledge fusion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.281252Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:69e56f4118ae4fbdb4d7991128dd4eab6e3b912816c66749f1d33b1d2aa9e132","observation_id":"978f7bb1-de79-4757-8ea0-334a7457815c","resolution":{"observed_at":"2026-08-07T13:59:34.281252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.12703","last_updated":"2022-04-27T05:18:32Z","snapshot_observed_at":"2026-08-07T22:26:19.590175Z","submitted_at":"2022-04-27T05:18:32Z","title":"Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.12703","snapshot_observed_at":"2026-08-07T13:59:34.389977Z","title":"Hetero- geneous ensemble knowledge transfer for training large models in federated learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.389977Z"},"links":{"cited_paper":"/paper/2204.12703","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:9d6f9a9fcb4863f393b7a69c20ef86b84438493eaa968ca44aa17fba6fb9979f","observation_id":"e0b50cb5-274e-43e7-8a67-0e34baf24910","resolution":{"observed_at":"2026-08-07T13:59:34.389977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:42.416197Z","title":"Exploiting shared representations for personalized federated learning","venue":null,"work_id":"bad76cba-3b8b-4eae-9767-beb94eaaa0a7","year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.479251Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:dd5f007b3b02b7155eb544232c8f63e676c27d6afdcdfb3a73de66f1130dc000","observation_id":"448b0324-f9e2-4ce7-af21-7e483e91b41c","resolution":{"observed_at":"2026-08-07T13:59:42.500261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.03505","last_updated":"2018-10-02T21:20:09Z","snapshot_observed_at":"2026-08-07T01:38:08.346703Z","submitted_at":"2018-10-02T21:20:09Z","title":"CINIC-10 is not ImageNet or CIFAR-10","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.03505","snapshot_observed_at":"2026-08-07T13:59:34.586652Z","title":"Cinic-10 is not imagenet or cifar-10","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.586652Z"},"links":{"cited_paper":"/paper/1810.03505","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:dee4cb265c193a1006febdefc4feb3b453f7be5d9c5f5e1bae6c07b270fb8612","observation_id":"b8035556-628d-4be1-8936-a51d5e9fc11d","resolution":{"observed_at":"2026-08-07T13:59:34.586652Z","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":"2026-08-07T13:59:34.699970Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.699970Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:727abdb1375a4b13fdf794b90b4c2299f77ad226e13c42d18a981ab1fee51ac0","observation_id":"62c68f9f-c8eb-4653-8a28-facd5209c654","resolution":{"observed_at":"2026-08-07T13:59:34.699970Z","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":"2026-08-07T13:59:34.827634Z","title":"Orthogonal gradient descent for continual learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.827634Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:b60d374f239f4d46087889f28092b08f27afdd2b6a5190f52ea007253b5a42a8","observation_id":"cba6f21b-ea04-4aec-81a5-4ab34c197215","resolution":{"observed_at":"2026-08-07T13:59:34.827634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:42.192964Z","title":"Sharp bounds for federated averaging (local sgd) and continuous perspective","venue":null,"work_id":"fb7b5f1d-e8be-45bf-af59-84ed4f1f2a9d","year":2022},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:34.917851Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:9cee785e30f648a54e746342ca41ef9f0a4e093c01046230c7b78efec864bfe5","observation_id":"e1fd35af-e470-46dd-b4a4-e45a30706d40","resolution":{"observed_at":"2026-08-07T13:59:42.277027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:41.989046Z","title":"Twitter sentiment classification using distant super- vision","venue":null,"work_id":"5e6a768c-8baa-4945-8e09-f14551fb412d","year":2009},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.012801Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:e03e4816b174bf11e4b6f3ead49ac07c152ab60b0938a97d7b515aa137fe0e0a","observation_id":"08f58f76-ceda-4e9b-9702-0be807c300c4","resolution":{"observed_at":"2026-08-07T13:59:42.105336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:41.773450Z","title":"Preserving privacy in federated learning with ensemble cross-domain knowledge distillation","venue":null,"work_id":"e62d44b0-f34c-4b8b-8705-f2f65a3e2221","year":2022},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.084338Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:cddbf01a12ca527dcfc7e47acf544ee7873755fb8689bf5fff7622ac51cf0c24","observation_id":"fea23de7-c818-4d6b-9978-a1e1f1a61cfb","resolution":{"observed_at":"2026-08-07T13:59:41.870180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:41.595694Z","title":"On calibration of modern neural networks","venue":null,"work_id":"a378610e-78dc-4628-a01f-03e1f3c4ff1a","year":2017},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.152875Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:d67dbc7ab40df23472af3d59bfdebd94d88cabbee2d2a44320a6d60f3b4a7984","observation_id":"5b9e2017-6370-406e-bd0d-d5d93a257c36","resolution":{"observed_at":"2026-08-07T13:59:41.687214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:41.409889Z","title":"Group knowledge transfer: Fed- erated learning of large cnns at the edge","venue":null,"work_id":"7b485810-79f8-4be0-a452-acd3b251efde","year":2020},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.241042Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:fc279ec01ce48c0b3fa4d6c3a727547149011b312f722a9d59af61072ed66b2a","observation_id":"b1361187-aa70-491e-8b64-06973978318e","resolution":{"observed_at":"2026-08-07T13:59:41.490765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06335","last_updated":"2019-09-13T17:26:20Z","snapshot_observed_at":"2026-08-02T11:40:53.964079Z","submitted_at":"2019-09-13T17:26:20Z","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06335","snapshot_observed_at":"2026-08-07T13:59:35.283569Z","title":"Measuring the effects of non-identical data distribution for federated visual classification","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.283569Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:b560b7fdac87a1d1375ec9ec942abec6aff5fbc46bf72056904bca356bab86ca","observation_id":"c40d31ab-a174-490d-9d57-0f81f56d7194","resolution":{"observed_at":"2026-08-07T13:59:35.283569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.10351","last_updated":"2020-10-16T02:12:46Z","snapshot_observed_at":"2026-08-07T22:21:53.513424Z","submitted_at":"2019-09-23T13:05:35Z","title":"TinyBERT: Distilling BERT for Natural Language Understanding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.10351","snapshot_observed_at":"2026-08-07T13:59:35.328167Z","title":"Tinybert: Distilling bert for natural language understanding","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.328167Z"},"links":{"cited_paper":"/paper/1909.10351","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:aec1a433bc8c73398c58082a54b5d71425a28ad507ef9a388092c5d90e6b520c","observation_id":"413efbf6-1e51-488b-8506-895164dbe1c2","resolution":{"observed_at":"2026-08-07T13:59:35.328167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:41.278317Z","title":"Advances and open problems in federated learning.Foundations and trends® in machine learning, 14(1–2):1–210, 2021","venue":null,"work_id":"c3d1d870-fb75-41e3-b3ec-cc5a033b8a56","year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.383760Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:9dbfbf80787941da63f99f276cc352dc165be7438f0d7e2c0dd6791b1237005e","observation_id":"0408cb9e-6d7c-4e9e-8e57-fdb95922b328","resolution":{"observed_at":"2026-08-07T13:59:41.334379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:59:35.411476Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.411476Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:5fefec4b71e4569055e8c63cee46a7732e0e286f4e8b29a8bc0cab16ec4c48a1","observation_id":"839c3832-b04a-4d73-ab57-c5fe28ee1d8a","resolution":{"observed_at":"2026-08-07T13:59:35.411476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02573","last_updated":"2020-10-06T09:34:01Z","snapshot_observed_at":"2026-08-07T22:26:18.442373Z","submitted_at":"2020-10-06T09:34:01Z","title":"The Multilingual Amazon Reviews Corpus","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02573","snapshot_observed_at":"2026-08-07T13:59:35.455016Z","title":"The multilingual amazon reviews corpus","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.455016Z"},"links":{"cited_paper":"/paper/2010.02573","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:6091ecac8bebef75ea532bba20a0c42788becc3612b9750e76226b43899e5d38","observation_id":"b3baf98f-ce9a-4923-a93c-fae5250b06e9","resolution":{"observed_at":"2026-08-07T13:59:35.455016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:41.063845Z","title":"Learning multiple layers of features from tiny im- ages.(2009), 2009","venue":null,"work_id":"d3bed1e6-112e-4608-b380-ecc177b51bd7","year":2009},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.529421Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:c0a7a0ab33f2b2606e0fee80afa70b977aef9114cf78a1490b2b3a2cc67a89b9","observation_id":"cfce5ad8-63ca-405d-95d5-ac7ec2fe944c","resolution":{"observed_at":"2026-08-07T13:59:41.166083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.03581","last_updated":"2019-10-08T18:00:00Z","snapshot_observed_at":"2026-08-08T12:31:54.297762Z","submitted_at":"2019-10-08T18:00:00Z","title":"FedMD: Heterogenous Federated Learning via Model Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.03581","snapshot_observed_at":"2026-08-07T13:59:35.585281Z","title":"Fedmd: Heterogenous federated learning via model distillation","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.585281Z"},"links":{"cited_paper":"/paper/1910.03581","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:2a9c258f3d25577e1904233bdef6240dde9ca80e797d5f8090649796dd6d6366","observation_id":"c437739f-4c3e-4780-b3e2-6ada7878efc0","resolution":{"observed_at":"2026-08-07T13:59:35.585281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:40.856513Z","title":"Model-contrastive federated learning","venue":null,"work_id":"ef098db6-3581-4e48-b7be-594a8c5759f6","year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.641623Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:25f4b4f7b246fa8d227b1fd2d8d91d93724f83c84bd59ca5df6f9cb385792b9e","observation_id":"c56f7612-8da8-4255-a950-702e513cabaa","resolution":{"observed_at":"2026-08-07T13:59:40.966501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:59:35.692486Z","title":"Federated optimization in heterogeneous networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.692486Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:8771db54e7b11393303f339a1096f0360ebcada9dc7a391d7441ffc615832b1e","observation_id":"0b941f71-8b78-404f-81e1-7f37ffe83d42","resolution":{"observed_at":"2026-08-07T13:59:35.692486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:40.622639Z","title":"Ditto: Fair and robust feder- ated learning through personalization","venue":null,"work_id":"27ed6c57-9b96-4185-9ab1-2fc38c214dcd","year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.810852Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:34c4de2e67e617a65a1b95dc25c9c414f713f788a9c7e1e9b2220d0a61fe2aa9","observation_id":"aac05f73-3376-482f-a7de-df85fb22c697","resolution":{"observed_at":"2026-08-07T13:59:40.722406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02189","last_updated":"2020-06-25T06:45:52Z","snapshot_observed_at":"2026-08-06T15:26:37.394053Z","submitted_at":"2019-07-04T02:04:56Z","title":"On the Convergence of FedAvg on Non-IID Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02189","snapshot_observed_at":"2026-08-07T13:59:35.872136Z","title":"On the conver- gence of fedavg on non-iid data","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.872136Z"},"links":{"cited_paper":"/paper/1907.02189","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:94326ce569ee56fde82fbdcba384250f60524d542662c0894b275d8565c3ef06","observation_id":"02f2599e-baf8-4bd5-a8bc-d366c63f0d3e","resolution":{"observed_at":"2026-08-07T13:59:35.872136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.07623","last_updated":"2021-05-11T14:21:00Z","snapshot_observed_at":"2026-07-06T10:41:31.563193Z","submitted_at":"2021-02-15T16:04:10Z","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.07623","snapshot_observed_at":"2026-08-07T13:59:35.911364Z","title":"Fedbn: Federated learning on non-iid features via local batch normalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.911364Z"},"links":{"cited_paper":"/paper/2102.07623","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:dc380a921ad521c029d6d73ac2bf83a22b5c67c1ec8e0553f11006136114e85e","observation_id":"bf91abac-08d4-4df1-89ac-f10f13e6fe43","resolution":{"observed_at":"2026-08-07T13:59:35.911364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.02931","last_updated":"2022-02-07T04:21:54Z","snapshot_observed_at":"2026-08-07T22:26:19.378637Z","submitted_at":"2022-02-07T04:21:54Z","title":"TRGP: Trust Region Gradient Projection for Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.02931","snapshot_observed_at":"2026-08-07T13:59:35.950368Z","title":"Trgp: Trust region gradient projection for continual learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:35.950368Z"},"links":{"cited_paper":"/paper/2202.02931","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:7dc5298c0679edaa6cab10b948226262ebd2cb72f7088676afe40db0ff7598c1","observation_id":"ae2d2532-fb25-4b6c-8534-ae39de721872","resolution":{"observed_at":"2026-08-07T13:59:35.950368Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:40.440599Z","title":"Ensemble distillation for robust model fusion in federated learning","venue":null,"work_id":"54c1bc85-ce55-45e1-8176-8307956f698a","year":2020},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.064655Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:2c873dd76973500b144c840d1e4fe9960be7e59bf360c897c2d6086c719cdc22","observation_id":"93b1f40b-20c3-4ba8-892d-196d94af0aad","resolution":{"observed_at":"2026-08-07T13:59:40.533934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:40.304012Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"a86a701f-5bf4-4145-9620-e6ae26545a1e","year":2017},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.136004Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:cfe402cfca541c4e5d206dfc47006d57860974c8498f7b826dfced519b45e4aa","observation_id":"14686114-5018-42fa-802a-b828b7ed7a30","resolution":{"observed_at":"2026-08-07T13:59:40.352439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:40.150763Z","title":"A practical recipe for federated learning under statistical heterogeneity experimental design","venue":null,"work_id":"422250a6-cd71-420c-984b-dc4f01ad97e8","year":2023},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.228418Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:1d5b1570a272eb0485013216df205941c04646c065331b2b881ea5285f2d6cd7","observation_id":"71ef67d9-cb7c-4a42-b44a-2083ef3b1e3f","resolution":{"observed_at":"2026-08-07T13:59:40.207354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:40.048050Z","title":"Large scale delocalized federated learning over a huge diversity of devices in emerging next-generation edge intelligence environments","venue":null,"work_id":"7ea70b08-ab04-430c-97f9-da6ba1f9d1cf","year":2024},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.301350Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:db3aca8df4a9098ebdd9ec43643202247af241ca3dbac9a0c80a963ef05eb173","observation_id":"c0d13421-51c4-4637-baec-fe6d8bb06a4c","resolution":{"observed_at":"2026-08-07T13:59:40.087893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07925","last_updated":"2024-05-13T16:57:48Z","snapshot_observed_at":"2026-08-06T22:23:29.763267Z","submitted_at":"2024-05-13T16:57:48Z","title":"Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07925","snapshot_observed_at":"2026-08-07T13:59:36.385938Z","title":"Stable diffusion-based data augmentation for federated learning with non-iid data.arXiv preprint arXiv:2405.07925, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.385938Z"},"links":{"cited_paper":"/paper/2405.07925","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:a45dfe3492735f093719f10e0f8a42fddcf6dd0fe29e39e81dd2ce6c92ff1477","observation_id":"6f35b7b6-efaf-43b9-b5e0-8cd2915e27f9","resolution":{"observed_at":"2026-08-07T13:59:36.385938Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:39.913885Z","title":"Clustered federated learning: A review","venue":null,"work_id":"32337f4f-94e4-4698-8696-ef28d0060470","year":2025},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.443527Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:1760169a678c11ecd78b2c29cde32138d7a299a9fc7b08072050dd77ebdec333","observation_id":"c0cb30ed-bd4e-4558-9930-31635beadf23","resolution":{"observed_at":"2026-08-07T13:59:39.969160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:39.794648Z","title":"Continual learning with scaled gradient projection","venue":null,"work_id":"d8c4f6e3-b015-4974-b735-52eb099235b0","year":2023},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.521793Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:6b20765043ca44fb867e90774eeff28e60fa813778501db0ebedd667268e2aa5","observation_id":"ff934c8b-7da8-4fc8-b754-61b17a4aa5a4","resolution":{"observed_at":"2026-08-07T13:59:39.848179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.09762","last_updated":"2021-03-17T16:31:29Z","snapshot_observed_at":"2026-08-07T22:26:17.816043Z","submitted_at":"2021-03-17T16:31:29Z","title":"Gradient Projection Memory for Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.09762","snapshot_observed_at":"2026-08-07T13:59:36.608853Z","title":"Gradient projection memory for continual learn- ing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.608853Z"},"links":{"cited_paper":"/paper/2103.09762","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:778d7a8d9a69405909b1b8892c3d9523a5b39fc1a0159bf1fd689a9ef5be3162","observation_id":"d7fb2d79-5ee2-499f-9e3a-27fb651f01a5","resolution":{"observed_at":"2026-08-07T13:59:36.608853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:39.692583Z","title":"Relaxed contrastive learning for federated learning","venue":null,"work_id":"a6a93397-3509-48f0-919c-b6e29975517c","year":2024},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.661812Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:8332ddf831b69dd2caa2de431abcfe546ca12b5af9fdc5afa7120bc5aa6d272f","observation_id":"630efbda-a6f8-482e-a2db-595533601df0","resolution":{"observed_at":"2026-08-07T13:59:39.740207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:39.568672Z","title":"Personalized federated learning using hypernetworks","venue":null,"work_id":"2c026d32-b5c6-43e8-bc5b-3786b7114723","year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.725437Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:8d7cf5040320e4f981ef737b364ff562fad6aa7f97c5c81ddb84309a95303e03","observation_id":"2ef1389e-fa43-49ed-8938-dd0cb70e8b77","resolution":{"observed_at":"2026-08-07T13:59:39.618982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:39.451586Z","title":"Recursive deep models for semantic compositionality over a sen- timent treebank","venue":null,"work_id":"ad06e576-d174-4325-abe5-0fca0367fdca","year":2013},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.808240Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:f1e83974227d35789f9c4eefca01e5056e7b1d21f2c55d134202ed699cd50b62","observation_id":"fa71d575-0e07-4ef5-80dc-e39baee38eca","resolution":{"observed_at":"2026-08-07T13:59:39.491056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:39.348160Z","title":"Tackling the ob- jective inconsistency problem in heterogeneous federated optimization","venue":null,"work_id":"8fc6a7c4-74a9-47dc-a2cc-5faddd4528b1","year":2020},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.864320Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:427ea822dcaa792087b4e4d9d8446aa14b3c0fd5d02728b98421ffcbd2e2fee3","observation_id":"38849513-a452-44bc-bd95-c175f7a3560d","resolution":{"observed_at":"2026-08-07T13:59:39.400874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:39.232576Z","title":"Uncertainty estimation and reduction of pre-trained models for text regression","venue":null,"work_id":"802a494d-31f1-4bdd-9e54-108fcaf29dd4","year":2022},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:36.926075Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:6b2db48f9f515322416bc4d1e7c770c52cb2e4d2b4ff9f0b4e7cf38f4d1085b6","observation_id":"aef5c240-f3f9-4071-8c15-b97a1d2d2904","resolution":{"observed_at":"2026-08-07T13:59:39.294833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.05426","last_updated":"2018-02-19T19:19:51Z","snapshot_observed_at":"2026-08-08T22:26:58.590242Z","submitted_at":"2017-04-18T17:10:13Z","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.05426","snapshot_observed_at":"2026-08-07T13:59:37.018886Z","title":"A broad-coverage challenge corpus for sentence understanding through inference","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:37.018886Z"},"links":{"cited_paper":"/paper/1704.05426","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:aeb5a5a5056816a3e472bee64d0f2ebb29cf86b3f4ee67fc3b5d2e54037981cb","observation_id":"520dcb42-ff90-4898-88bc-bf59bb231252","resolution":{"observed_at":"2026-08-07T13:59:37.018886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:39.099388Z","title":"Minibatch vs local sgd for het- erogeneous distributed learning","venue":null,"work_id":"9716865f-603f-470c-a89d-3650b178c852","year":2020},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:37.094972Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:535d69029f606d4e36dcc130f5b0af83cef6349675ce7a4ece090ef3bbd49c83","observation_id":"156182f8-f328-4f3d-8615-1b81b366a341","resolution":{"observed_at":"2026-08-07T13:59:39.154562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.04714","last_updated":"2022-10-14T07:17:10Z","snapshot_observed_at":"2026-08-07T22:26:19.951857Z","submitted_at":"2022-10-10T14:16:01Z","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.04714","snapshot_observed_at":"2026-08-07T13:59:37.172775Z","title":"Uncertainty quantification with pre-trained language models: A large-scale empirical analysis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:37.172775Z"},"links":{"cited_paper":"/paper/2210.04714","citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:dcc6de1da2b5ff1c06ae519620675f3a423f1f4a90bb18836f68a137c765dbe3","observation_id":"b7a14054-79b5-40d6-8c98-6510d3976544","resolution":{"observed_at":"2026-08-07T13:59:37.172775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:38.910165Z","title":"Federated continual learning via knowledge fusion: A survey","venue":null,"work_id":"fdd810b6-e01c-4e5c-85e5-fbcd01e352f3","year":2024},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:37.212252Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:f4c762ef7db928f0622325b8b19400389082b7c90a232ef7a999ce82964c0656","observation_id":"67b5dbed-d048-4550-aa76-23c72eda8d01","resolution":{"observed_at":"2026-08-07T13:59:39.023029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:59:37.289598Z","title":"Continual learning of context-dependent processing in neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:37.289598Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:68a8de102967b41b13e6fa72c55e3d82c5b8803524cc7986d4f7289816b968d1","observation_id":"31ac9f1c-c774-4eb7-8f6c-03abe6279fbc","resolution":{"observed_at":"2026-08-07T13:59:37.289598Z","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":"2026-08-07T13:59:37.381792Z","title":"Character-level convolutional networks for text classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:37.381792Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:33e0da69f151f1568c448c8d3dd0eb0b8d3dedc69226092292e5de057004876b","observation_id":"e90dd7df-adae-4bdb-a667-64171455a25a","resolution":{"observed_at":"2026-08-07T13:59:37.381792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:38.672910Z","title":"Data-free knowledge distillation for hetero- geneous federated learning","venue":null,"work_id":"08917000-0391-4b1c-8ed6-d83adbc308cf","year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:37.458398Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:f83f326a9a54eeae411ff8f299007747db4d4adea9acbdbac8f1a01f79769649","observation_id":"b974d752-c876-47d9-a259-f35c6febcc88","resolution":{"observed_at":"2026-08-07T13:59:38.762928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:38.455535Z","title":"Data-free knowledge distillation for hetero- geneous federated learning","venue":null,"work_id":"8d669b37-627b-4962-b2c7-d66124168153","year":2021},"citing_paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:37.558240Z"},"links":{"citing_paper":"/paper/2505.20485"},"observation_digest":"sha256:622e0450202f91ef52415a5ba752fc8a56226825fbef26aa7fba769c9c15ca93","observation_id":"3fb6f0a8-624d-4f55-89cb-e48958d75463","resolution":{"observed_at":"2026-08-07T13:59:38.544349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.20485","last_updated":"2025-06-30T19:20:31Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T22:25:20.793479Z","submitted_at":"2025-05-26T19:43:11Z","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":1,"verified_fuzzy":27},"total_outbound_references":51},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 1 inbound Pith citation observation for arXiv:2505.20485."}