{"as_of":"2026-08-17T15:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a368e3a08a999a26ed3e917cc7210499656f2920e8da6c2ebdb82de2b5ca0d63","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":"2026-08-16T11:48:16.414971Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2504.14694/citation-record","integrity":"/paper/2504.14694/integrity","json":"/paper/2504.14694/citation-record.json","paper":"/paper/2504.14694"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:48:16.208604Z","title":"The eu general data protec- tion regulation (gdpr),","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.208604Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:708b5a69358e4df6934269bcc214fd7f1abd50c4404f4fb2fe25fda65baaec4a","observation_id":"bf520b51-6394-4016-96f1-7864a7532a5e","resolution":{"observed_at":"2026-08-16T11:48:16.208604Z","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":"2026-08-16T11:48:16.213591Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.213591Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:41ea1d5cac0fe88b002520c4c5f62a42a3cb3690d52da271f6359cf951cf9582","observation_id":"95edcf43-dfc6-4830-8ac0-07ea356d9b7c","resolution":{"observed_at":"2026-08-16T11:48:16.213591Z","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":"2026-08-16T11:48:17.086015Z","title":"Tighter theory for local sgd on identical and heterogeneous data,","venue":null,"work_id":"b36887b0-7bad-48b1-95d0-1593dbdcf85a","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.217773Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:35a4359767e92095e51e402ce33aa6eed80531b878dfb9d191674f8d0e317cf6","observation_id":"0590d20e-daac-4116-ac09-4e094a91b3bf","resolution":{"observed_at":"2026-08-16T11:48:17.090579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:17.071541Z","title":"On the conver- gence of fedavg on non-iid data,","venue":null,"work_id":"5eb0f13c-cab7-489a-994a-64f1d0c8cefd","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.222132Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:abf3e7986e252cda4dbb3329872ce11f8ba680770494526ae807409112dd8414","observation_id":"7cc43d94-1820-4afa-8846-b570c5a677e9","resolution":{"observed_at":"2026-08-16T11:48:17.076324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-08-15T04:44:38.370440Z","submitted_at":"2018-06-02T04:45:58Z","title":"Federated Learning with Non-IID Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00582","snapshot_observed_at":"2026-08-16T11:48:16.226700Z","title":"Feder- ated learning with non-iid data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.226700Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:9355b7ae52fd1a9f69ba7c9792d1a100dc27af4db264a5d6b3c4c5752d310d90","observation_id":"672fa826-12cb-450f-9361-f6ab3768d729","resolution":{"observed_at":"2026-08-16T11:48:16.226700Z","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":"2026-08-16T11:48:17.057651Z","title":"Federated learning: Challenges, methods, and future directions,","venue":null,"work_id":"0ff70a1b-612c-435e-8b8a-8ca32cf7de90","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.231278Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:02b76c83d562dbb746337b2fe8585a24c78ff018bf9b2860bd583df2fe6c9975","observation_id":"a225be1d-469c-42b5-be50-f68c0020976c","resolution":{"observed_at":"2026-08-16T11:48:17.062101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:17.043842Z","title":"Scaffold: Stochastic controlled averaging for federated learning,","venue":null,"work_id":"32ede1e3-08a3-459c-8fa6-76e9b1365f7c","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.236026Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:b7eeb2e2e62fbbc55f64bbb27d91e46d741f4ca5fe890f4f3a2f3f2e3af0ea7f","observation_id":"a8b9f2f5-2408-42a3-979c-3fe0c716af0d","resolution":{"observed_at":"2026-08-16T11:48:17.048378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.240075Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.240075Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:d5a24875bd2e6eb4dcc53bb2e50b95bdc9fece7b01c2e8cd31bf9ee65190e7b1","observation_id":"744ea170-b1b2-4744-a8d9-b86c19e48206","resolution":{"observed_at":"2026-08-16T11:48:16.240075Z","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":"2026-08-16T11:48:17.021377Z","title":"Model-contrastive federated learning,","venue":null,"work_id":"ec1d3640-b36a-4322-bac4-a4f8e5344cc7","year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.244124Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:656ab27a19892e37755242ab2a50cf7e9343b3f78b591498545671415ee5a1fd","observation_id":"53d9ab20-819c-4414-a122-af71db5645ab","resolution":{"observed_at":"2026-08-16T11:48:17.026026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07796","last_updated":"2019-10-17T09:53:16Z","snapshot_observed_at":"2026-08-17T04:20:43.030971Z","submitted_at":"2019-10-17T09:53:16Z","title":"Overcoming Forgetting in Federated Learning on Non-IID Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07796","snapshot_observed_at":"2026-08-16T11:48:16.248193Z","title":"Overcoming forgetting in federated learning on non-iid data,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.248193Z"},"links":{"cited_paper":"/paper/1910.07796","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:0e8e6485eef468ca3425cc88889fa7e81a96633c0847cbdd49c987f424c1b7f7","observation_id":"0caa370d-8011-47da-a8d6-10f3d8ce8c52","resolution":{"observed_at":"2026-08-16T11:48:16.248193Z","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":"2026-08-16T11:48:17.007749Z","title":"Class-wise adaptive self distillation for heterogeneous federated learning,","venue":null,"work_id":"513aac44-62d4-4cd2-84de-cf636e8b1cd5","year":2022},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.252465Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:cd2c3ee321d558f84ccb8237ca4982986ba11b2aad2b46a3073361a01ec451d1","observation_id":"1bbad6b2-3d3f-46bd-8bfa-101578cd0151","resolution":{"observed_at":"2026-08-16T11:48:17.012500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.256477Z","title":"Tackling the objective inconsistency problem in heterogeneous federated optimization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.256477Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:5a35400dc8a836c63c517ca7ea6dc6554d4f7c0b16b30c9f506078a5be33b934","observation_id":"7f36ac90-6544-4896-b0ed-09cb24801aba","resolution":{"observed_at":"2026-08-16T11:48:16.256477Z","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":"2026-08-16T11:48:16.260496Z","title":"Overcoming catastrophic forgetting in neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.260496Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:f2048e96abf90edf3f5268acb89814960c1721af4df77e461c367a0dbcd8154e","observation_id":"7d8bcafd-28d3-41a7-b425-d776b63c8bd6","resolution":{"observed_at":"2026-08-16T11:48:16.260496Z","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":"2026-08-16T11:48:16.976602Z","title":"Bayesian nonparametric federated learning of neural networks,","venue":null,"work_id":"22f0eb36-08fa-4d9b-b9fb-9373478cd22b","year":2019},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.264413Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:516e3729296fdf606b768a1d9b25ab1dc50a2fb6b23d837d395cf860445fab97","observation_id":"e78f0079-f97d-47c2-a131-6bc831f914d9","resolution":{"observed_at":"2026-08-16T11:48:16.980788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.963383Z","title":"Federated learning with matched averaging,","venue":null,"work_id":"f13d890b-ba95-480f-b6d2-78d7e02a5a97","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.268466Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:8280eb7bf63eba54845f76cf59076d26be561e43b06e78a62903b556b97c8425","observation_id":"54280d81-1339-428c-847d-525fc62d587b","resolution":{"observed_at":"2026-08-16T11:48:16.967692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.947905Z","title":"Inverse distance aggregation for federated learning with non-iid data,","venue":null,"work_id":"891e2172-c0dc-4a2b-9e99-6d22e1bf31a3","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.272615Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:e99ba0c3f4d7112e2a7811efa21c50fa92220f677b5edf1617fa9d3c7b2c242a","observation_id":"ae91fe55-825e-44d2-9f2a-8deed183c9d3","resolution":{"observed_at":"2026-08-16T11:48:16.953357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.13461","last_updated":"2020-11-06T04:07:31Z","snapshot_observed_at":"2026-08-02T16:42:32.296692Z","submitted_at":"2020-03-30T13:19:37Z","title":"Adaptive Personalized Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.13461","snapshot_observed_at":"2026-08-16T11:48:16.276468Z","title":"Adaptive personalized federated learning,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.276468Z"},"links":{"cited_paper":"/paper/2003.13461","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:152d26f06a0bc6407180fa07989988fef9bb88f2263314e9621adbc36080e101","observation_id":"6831540d-4c81-47b8-b8e7-14447d335016","resolution":{"observed_at":"2026-08-16T11:48:16.276468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.01009","last_updated":"2021-07-21T02:28:19Z","snapshot_observed_at":"2026-08-16T18:20:20.481926Z","submitted_at":"2021-06-02T08:10:50Z","title":"FedHealth 2: Weighted Federated Transfer Learning via Batch Normalization for Personalized Healthcare","version":2},"cited_work":{"arxiv_id":"2106.01009","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.01009","snapshot_observed_at":"2026-08-16T11:48:16.625851Z","title":"FedHealth 2: Weighted Federated Transfer Learning via Batch Normalization for Personalized Healthcare","venue":"cs.LG","work_id":"4c9eba75-1d5b-4d32-93cd-64f067b187ff","year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.280635Z"},"links":{"cited_paper":"/paper/2106.01009","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:0581d9fd4ee3ea12817f0ebe4ef080e600d660eb941c504011b89bf1b85569f7","observation_id":"d08a1f01-6e64-456c-b696-9b18c9899009","resolution":{"observed_at":"2026-08-16T11:48:16.630731Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.933837Z","title":"Personalized cross-silo federated learning on non-iid data,","venue":null,"work_id":"d2c1f218-17b4-4d2d-94ec-c7085c2ce59a","year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.284923Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:82782b021bec960a927ee5188dcc3f3a1785946734102064fa29e52efc792b3c","observation_id":"c39e7098-c6ff-4da6-9ac7-936ed9986c84","resolution":{"observed_at":"2026-08-16T11:48:16.938463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-16T11:48:16.288900Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.288900Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:1f65d7eb8d164e3a416957fbf7d18b8a0c5594e2aca2728b066c19f3ea6268de","observation_id":"9dab1a60-4dbc-4634-ba4c-7de473cfbbcd","resolution":{"observed_at":"2026-08-16T11:48:16.288900Z","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":"2026-08-16T11:48:16.919057Z","title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers,","venue":null,"work_id":"5b2c87af-644c-46c8-9230-f2ad7c339097","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.293077Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:0ee018c22a5af1e3709a804d9235c2a53e76ea5fe2511ee36554374ff261c11d","observation_id":"e095c766-b07f-4c5e-a694-af41f8b2006a","resolution":{"observed_at":"2026-08-16T11:48:16.924404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.904552Z","title":"Patient knowledge dis- tillation for bert model compression,","venue":null,"work_id":"981bc697-cede-41bd-8b1f-9ffcfc3a89ad","year":2019},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.297237Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:e7aa7ecfdd87a0577abb957fb6737c5eb9a7994f57bb2630ae4a754d79f4d157","observation_id":"3f6ad9f3-8744-4bf0-9052-677f99443193","resolution":{"observed_at":"2026-08-16T11:48:16.908822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.890491Z","title":"Be your own teacher: Improve the performance of convolutional neural networks via self distillation,","venue":null,"work_id":"f9ff9d27-5178-4754-9241-e404d0ee0cc9","year":2019},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.301359Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:6daf61460fbcc9fa4fe557b39fac9e085afc778d8ea9b1a133fc113e00eaf430","observation_id":"58233138-360f-4cbb-a8aa-f3cb5c8f8dcd","resolution":{"observed_at":"2026-08-16T11:48:16.894883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.876596Z","title":"Regularizing class-wise predictions via self-knowledge distillation,","venue":null,"work_id":"72862e7e-4d0e-4cdd-bf19-0468f6d0a7c4","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.305383Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:4f47016d70f4afb843f36adce976ad2611bf52a05405f7f05c3f2e1819cdbe9b","observation_id":"090e41ac-068a-4eb0-b17c-a01bf6dae3e7","resolution":{"observed_at":"2026-08-16T11:48:16.881037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.863679Z","title":"Fitnets: Hints for thin deep nets,","venue":null,"work_id":"53c42527-2e14-4433-a2c2-515b274a407f","year":2015},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.309987Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:dd0b54c2673b3187a4c17aced11031b31af2121115fb87c94eaed59ae5bb3b84","observation_id":"d1c44ed6-249e-49ba-a96f-f6cf8af9e5c6","resolution":{"observed_at":"2026-08-16T11:48:16.868138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.850152Z","title":"A comprehensive overhaul of feature distillation,","venue":null,"work_id":"c1c77dfd-ed7f-4aa6-a843-60683ab8814d","year":2019},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.313954Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:88963fac69fb6d7f7d0260876728906b7857fe213716251655021f76c4b71ef8","observation_id":"7da074ff-4e3c-4a17-8464-35b194f3cf1a","resolution":{"observed_at":"2026-08-16T11:48:16.854449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.835586Z","title":"Paraphrasing complex network: Network compression via factor transfer,","venue":null,"work_id":"dabd0baf-e574-4fc1-b7ce-b2615c989e39","year":2018},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.317838Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:946f0f1af6efaf735951ecca773a8f4ca7f84a57ccc2bec2da241aacb14566a0","observation_id":"4eb13eea-ae2a-4262-beb1-662fe947f15e","resolution":{"observed_at":"2026-08-16T11:48:16.840163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.03532","last_updated":"2021-02-28T23:31:44Z","snapshot_observed_at":"2026-08-16T14:32:52.889638Z","submitted_at":"2020-02-10T04:21:41Z","title":"Understanding and Improving Knowledge Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.03532","snapshot_observed_at":"2026-08-16T11:48:16.322016Z","title":"Understanding and improving knowledge distillation,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.322016Z"},"links":{"cited_paper":"/paper/2002.03532","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:1c91a724deab216899b6d16c070acdeae566a09d1df6ddedb562890bc8298f40","observation_id":"341be8ec-5b28-4432-bb47-d66fa29093ea","resolution":{"observed_at":"2026-08-16T11:48:16.322016Z","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":"2026-08-16T11:48:16.822333Z","title":"Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective,","venue":null,"work_id":"7f001970-ad62-4fb3-a14a-880c625cd335","year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.326515Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:6380b4de7ee738817b7db444c0fa3106f48163282b07ee0c002bba14b258c879","observation_id":"b9c86823-08ec-4fb7-9fce-90853510aece","resolution":{"observed_at":"2026-08-16T11:48:16.826734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.808859Z","title":"Knowledge distillation as semiparametric inference,","venue":null,"work_id":"55378a72-b2b4-4ba3-a254-2187825ffaec","year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.330413Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:f9df13186a1b4486bafb2443a690c871b316a2a7888618469945284f275ba083","observation_id":"01489a03-7a50-4779-9469-2f954df96489","resolution":{"observed_at":"2026-08-16T11:48:16.813511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.10494","last_updated":"2021-07-08T14:28:34Z","snapshot_observed_at":"2026-08-16T18:15:56.149467Z","submitted_at":"2021-06-19T13:06:25Z","title":"Teacher's pet: understanding and mitigating biases in distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.10494","snapshot_observed_at":"2026-08-16T11:48:16.334150Z","title":"Teacher’s pet: understanding and mitigating biases in distilla- tion,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.334150Z"},"links":{"cited_paper":"/paper/2106.10494","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:8a0d5beb15e291152820f34bd7d996ca1b59b4ed49dadaf30c08b10bd39b4fba","observation_id":"3117d652-f687-4022-8742-4c1aa33d588c","resolution":{"observed_at":"2026-08-16T11:48:16.334150Z","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":"2026-08-16T11:48:16.795364Z","title":"Selective knowledge dis- tillation for neural machine translation,","venue":null,"work_id":"981b8df8-59f9-42a6-be3e-67eeb4eb31e4","year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.338170Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:caba7f7efcd2fe558ddc69a16b10268af09c67ce3d9a7b86770dafce97e194af","observation_id":"71a5d59b-f097-4084-9a3c-257734d4b26a","resolution":{"observed_at":"2026-08-16T11:48:16.799957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.781973Z","title":"Online distilling from checkpoints for neural machine translation,","venue":null,"work_id":"016bba3c-1930-4129-a030-855618c3a86f","year":2019},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.342163Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:2f4738bfc0584daf34e761a46e6cc404d7216d47b9e91c24bc6eeafb37ce26a2","observation_id":"0821e2c4-17d8-4917-93a3-32d3e39f4f2c","resolution":{"observed_at":"2026-08-16T11:48:16.786046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.768376Z","title":"Multilingual neural machine translation with knowledge distillation,","venue":null,"work_id":"a4e6483f-a19a-42bb-b273-9f36be781b48","year":2019},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.346039Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:e79f31b03d0d9df66d95743d5a6380a61137871ef5a4eb330b84d5ce9907153b","observation_id":"120d4b30-fad9-477b-abcb-69942ee02734","resolution":{"observed_at":"2026-08-16T11:48:16.772607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.08919","last_updated":"2021-05-19T04:40:53Z","snapshot_observed_at":"2026-08-16T18:23:45.896069Z","submitted_at":"2021-05-19T04:40:53Z","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.08919","snapshot_observed_at":"2026-08-16T11:48:16.350073Z","title":"Comparing kullback- leibler divergence and mean squared error loss in knowledge distillation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.350073Z"},"links":{"cited_paper":"/paper/2105.08919","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:81cb67c2949ef299cd0afdd55837707e4955cc4d8d681e7ab04df0c9007ff6bd","observation_id":"0a6558c6-8f78-42e0-a7cc-78b74fe931fb","resolution":{"observed_at":"2026-08-16T11:48:16.350073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.11479","last_updated":"2023-10-19T14:11:11Z","snapshot_observed_at":"2026-08-14T17:52:08.881217Z","submitted_at":"2018-11-28T10:16:18Z","title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.11479","snapshot_observed_at":"2026-08-16T11:48:16.354292Z","title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-iid private data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.354292Z"},"links":{"cited_paper":"/paper/1811.11479","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:c3a496ba32bca646ef6045ed979c5dc569a9ea862051734474f41712647934aa","observation_id":"cf80ca7c-cf5c-4b47-a42e-a58516c5d1e1","resolution":{"observed_at":"2026-08-16T11:48:16.354292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.02367","last_updated":"2020-11-04T15:56:13Z","snapshot_observed_at":"2026-08-16T19:08:08.655694Z","submitted_at":"2020-11-04T15:56:13Z","title":"Federated Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.02367","snapshot_observed_at":"2026-08-16T11:48:16.358797Z","title":"Federated knowledge distillation,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.358797Z"},"links":{"cited_paper":"/paper/2011.02367","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:cd9d8d53fecebed578ea0c8217ee8245cbfdbbcf6404e8a05608c17e42974e95","observation_id":"b5cc40c8-0e78-45fa-a067-d0e588a08ac7","resolution":{"observed_at":"2026-08-16T11:48:16.358797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.03581","last_updated":"2019-10-08T18:00:00Z","snapshot_observed_at":"2026-08-14T20:20:16.604226Z","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":"2026-08-16T11:48:16.362788Z","title":"Fedmd: Heterogenous federated learning via model distillation,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.362788Z"},"links":{"cited_paper":"/paper/1910.03581","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:225fb23ac38f2a72ddbbe404b8d81e6c4306a3bfab69ffc2e7265596febcb328","observation_id":"3acaddbe-03c1-492e-ac6c-140130e253fc","resolution":{"observed_at":"2026-08-16T11:48:16.362788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.11279","last_updated":"2019-12-24T10:20:38Z","snapshot_observed_at":"2026-08-15T11:54:59.323344Z","submitted_at":"2019-12-24T10:20:38Z","title":"Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.11279","snapshot_observed_at":"2026-08-16T11:48:16.366961Z","title":"Cronus: Robust and heterogeneous collaborative learning with black-box knowledge transfer,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.366961Z"},"links":{"cited_paper":"/paper/1912.11279","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:f408d7d10274dac3a57b56d83be4a199ea15db3b8cb3452c1e8a3f8a7bb29e68","observation_id":"ea0dca16-f28c-4409-8933-36f858bd98b6","resolution":{"observed_at":"2026-08-16T11:48:16.366961Z","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":"2026-08-16T11:48:16.754944Z","title":"Ensemble distillation for robust model fusion in federated learning,","venue":null,"work_id":"28270fae-dc9e-4f1e-b8a5-cf81d92c271a","year":2020},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.371073Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:a64456c0f77bce6ae515917e29b51c731e86808aa8947b94e74bfd92bd536c26","observation_id":"b1899388-74ca-4b9c-8142-98e64f287042","resolution":{"observed_at":"2026-08-16T11:48:16.759385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03097","last_updated":"2022-11-29T15:06:41Z","snapshot_observed_at":"2026-08-16T18:19:21.067373Z","submitted_at":"2021-06-06T11:51:47Z","title":"Preservation of the Global Knowledge by Not-True Distillation in Federated Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03097","snapshot_observed_at":"2026-08-16T11:48:16.374901Z","title":"Preservation of the global knowledge by not-true self knowledge distillation in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.374901Z"},"links":{"cited_paper":"/paper/2106.03097","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:4fade7b4e1633b70e7465bd27736f2a2d150cb7e872fe6adc3c876827f16ab1b","observation_id":"a57944a6-6465-4f8c-9555-559cde290fba","resolution":{"observed_at":"2026-08-16T11:48:16.374901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.00051","last_updated":"2021-09-13T02:13:18Z","snapshot_observed_at":"2026-08-16T18:13:12.736432Z","submitted_at":"2021-06-30T18:14:24Z","title":"Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.00051","snapshot_observed_at":"2026-08-16T11:48:16.378813Z","title":"Local-global knowledge distillation in heterogeneous federated learning with non-iid data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.378813Z"},"links":{"cited_paper":"/paper/2107.00051","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:86458550b66eff0a6a211932a326ffaf989c5f186211aea60fbdf6e81fc2a5f6","observation_id":"3a8f593b-e53c-4a76-a3f7-6259c38ed325","resolution":{"observed_at":"2026-08-16T11:48:16.378813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.02645","last_updated":"2022-03-05T02:31:32Z","snapshot_observed_at":"2026-08-16T17:16:48.748639Z","submitted_at":"2022-03-05T02:31:32Z","title":"Acceleration of Federated Learning with Alleviated Forgetting in Local Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.02645","snapshot_observed_at":"2026-08-16T11:48:16.383049Z","title":"Acceleration of federated learning with alleviated forgetting in local training,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.383049Z"},"links":{"cited_paper":"/paper/2203.02645","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:8b3c4dbab3019d016ac50000dc5158c2f0c60786c6cba3aa2a4a03f4a04b83f3","observation_id":"e60bf9f9-af7b-4533-a8e8-4449587cae4b","resolution":{"observed_at":"2026-08-16T11:48:16.383049Z","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":"2026-08-16T11:48:16.741138Z","title":"The stability-plasticity dilemma: Investigating the continuum from catastrophic forget- ting to age-limited learning effects,","venue":null,"work_id":"6c3b59af-e9c9-4cdc-8540-077c47db89be","year":2013},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.387224Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:15a39e967bec06493600093597f45b3c3996b003c13ca893552b77151a77bc85","observation_id":"7b218dc2-c5c1-4d87-90dc-7cdb9f72ded3","resolution":{"observed_at":"2026-08-16T11:48:16.745822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10775","last_updated":"2022-04-24T07:06:49Z","snapshot_observed_at":"2026-08-16T17:33:18.007583Z","submitted_at":"2021-12-20T13:25:48Z","title":"HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images","version":3},"cited_work":{"arxiv_id":"2112.10775","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.10775","snapshot_observed_at":"2026-08-16T11:48:16.463903Z","title":"HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images","venue":"eess.IV","work_id":"6dee7535-44ef-4907-8926-fdadf39bb82b","year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.391536Z"},"links":{"cited_paper":"/paper/2112.10775","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:2f2e447a73f4f9bdb2d176d52f1506ade7cc234f69719b9041fcaf4dd8439ea2","observation_id":"d83c97e2-81fe-4975-a3ad-cce313ab9a95","resolution":{"observed_at":"2026-08-16T11:48:16.470406Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.726725Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"077e737b-18ee-408b-b6fd-ededf78a7497","year":2009},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.395579Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:67cdd74336488dfcedbf8db5ba7fa4603b6a4b58daca8961a6cf405e340925cd","observation_id":"bff2a7f0-37fb-417f-80cb-bb8a1c00b0ed","resolution":{"observed_at":"2026-08-16T11:48:16.731411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.399656Z","title":"Tiny imagenet visual recognition challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.399656Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:a7a9db22b169debee8e86bbe0f535d4d3b7ebae51ec4d714cdca3c3b54a3003a","observation_id":"d0cbfc15-5889-4af7-a6be-ef9d4549bccd","resolution":{"observed_at":"2026-08-16T11:48:16.399656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.02079","last_updated":"2021-10-28T15:22:21Z","snapshot_observed_at":"2026-08-16T18:48:01.249829Z","submitted_at":"2021-02-03T14:29:09Z","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.02079","snapshot_observed_at":"2026-08-16T11:48:16.403483Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.403483Z"},"links":{"cited_paper":"/paper/2102.02079","citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:66d31c4137cccce1d7414cd6d5a3ec1255c86f0c7f89bfffba5030d9dd0d2c78","observation_id":"3c870c53-c5cc-4155-8195-81adb64ddf8c","resolution":{"observed_at":"2026-08-16T11:48:16.403483Z","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":"2026-08-16T11:48:16.407424Z","title":"Addressing class imbalance in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.407424Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:8207a3e1c4474a7c782eb6711950ec1e55ea8c38032a646b84a194380c5a9b0b","observation_id":"f87895a8-0dcd-4521-8612-09d845f0fdbe","resolution":{"observed_at":"2026-08-16T11:48:16.407424Z","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":"2026-08-16T11:48:16.695811Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"4f2a9e77-0f67-4894-a162-8f680a74a235","year":2016},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.411188Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:3c501ffdbbed5d03ebc47e0cfa22be8be39322ce52769210b0e38238d878446e","observation_id":"067513bc-b258-4e7f-b1ca-495ca02fc199","resolution":{"observed_at":"2026-08-16T11:48:16.700322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T11:48:16.681416Z","title":"Pytorch: An im- perative style, high-performance deep learning library,","venue":null,"work_id":"d7350786-2651-4316-b7b0-c4f738846990","year":2019},"citing_paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T11:48:16.414971Z"},"links":{"citing_paper":"/paper/2504.14694"},"observation_digest":"sha256:8a18b30833355efb043502ba480e7e7ad5000a24d672a313a9947eac5f201fd0","observation_id":"93fc931e-409c-4fb0-b54c-34a3f152d54e","resolution":{"observed_at":"2026-08-16T11:48:16.686381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.14694","last_updated":"2025-04-20T18:06:55Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:33:25.268725Z","submitted_at":"2025-04-20T18:06:55Z","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":2,"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2504.14694."}