{"as_of":"2026-08-08T20:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e0a151a4fc7120d56cdd85e509895e96d06328a8e0700d11b26471b53d54613e","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:21:58.335796Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.15579/citation-record","integrity":"/paper/2505.15579/integrity","json":"/paper/2505.15579/citation-record.json","paper":"/paper/2505.15579"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1909.12488","last_updated":"2023-01-18T08:30:06Z","snapshot_observed_at":"2026-07-06T08:25:04.636524Z","submitted_at":"2019-09-27T04:26:37Z","title":"Improving Federated Learning Personalization via Model Agnostic Meta Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.12488","snapshot_observed_at":"2026-08-07T15:21:58.256225Z","title":"Kairouz, P., McMahan, H","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.256225Z"},"links":{"cited_paper":"/paper/1909.12488","citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:8946ebb1e568ea4ed320b26100d9f7958021f990a15e00c95ff6c4ece8ee5af8","observation_id":"20bcf3ed-de00-458a-be58-dcc9321f1101","resolution":{"observed_at":"2026-08-07T15:21:58.256225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.19067","last_updated":"2025-05-21T12:59:55Z","snapshot_observed_at":"2026-07-06T20:28:57.453439Z","submitted_at":"2025-01-31T11:53:16Z","title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.19067","snapshot_observed_at":"2026-08-07T15:21:58.289655Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.289655Z"},"links":{"cited_paper":"/paper/2501.19067","citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:9f496fa3356ea05f83e598cbaa6ac0405eb138e1a055c572bbe1f507d8af283b","observation_id":"4e2b1fda-f970-46d1-b360-1d182824253f","resolution":{"observed_at":"2026-08-07T15:21:58.289655Z","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":"2026-08-07T15:21:58.707448Z","title":"we have a distribution D, and the goal is to generalize from training data to the unseen data","venue":null,"work_id":"de323b80-1f38-4280-9c0c-7812e858a60e","year":2014},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.303576Z"},"links":{"citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:4fa132562140a60196e5a03bef30eccee19bb66cb296f93c17722f48623e02fd","observation_id":"f3ae8cfe-c3ad-4fc1-8ed8-a49576c459c2","resolution":{"observed_at":"2026-08-07T15:21:58.714601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:21:58.649763Z","title":"Parameter decomposition-approaches (Arivazhagan et al., 2019; Collins et al., 2021; Marfoq et al., 2022; Chen et al., 2023; Wu et al.,","venue":null,"work_id":"7b48bccc-38f9-4ba1-9318-d54a04fd5c37","year":2019},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.324754Z"},"links":{"citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:7cf4c73b31a8fc07eb17a93a5ec236e6a1c7debeb33bd4519c00c81e1f849bff","observation_id":"683a7fff-98c3-40ab-94cb-f783b4f871b8","resolution":{"observed_at":"2026-08-07T15:21:58.655870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:21:58.630136Z","title":"Federated multi-task approaches (Smith et al., 2017; Dinh et al., 2020; Hanzely et al., 2020; Marfoq et al., 2021; Li et al., 2021; Lin et al., 2022; Ye et al., 2023; Zhang et al.,","venue":null,"work_id":"d28824ea-cf47-4b4d-af36-f5b6ad9a3aca","year":2017},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.330562Z"},"links":{"citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:fa746eb93bb3900152ffa391f983b9b747e4dd82cae8086ddf67f5559f99f3a4","observation_id":"7d38b384-062c-468e-a2bb-4ab7b7aa9f83","resolution":{"observed_at":"2026-08-07T15:21:58.637140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:21:58.609943Z","title":"All of the above approaches, however, require a client to have labeled data in order to obtain a personalized model","venue":null,"work_id":"e2750a32-3b6b-4c09-a877-e1673d09be2a","year":2018},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.335796Z"},"links":{"citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:4381c8d26d599493785004b7adbd5b30d4d7e35e3811fe3ccbe94e7197ed57a4","observation_id":"3187630c-3fdc-4538-b29c-5f423de28c4e","resolution":{"observed_at":"2026-08-07T15:21:58.617094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:21:58.669515Z","title":null,"venue":null,"work_id":"814ee006-8665-4597-854c-40069a8ecf53","year":2019},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":256,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.318864Z"},"links":{"citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:55c95beef325bac65f832cf15e3b658d8fa5712ba8e84924a113a6b88cf5c0c5","observation_id":"47c1cf87-81e8-4b0d-8d7f-34f0588db62f","resolution":{"observed_at":"2026-08-07T15:21:58.674967Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:21:58.688505Z","title":"For all methods we tune the local learning rate ηl on validation clients","venue":null,"work_id":"168538b7-7176-4078-84ac-fde20e31557c","year":2020},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":500,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.311903Z"},"links":{"citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:c2346d3458babae804363581ffe9bb845ade254a1ff58cdf9f55b8583b354e56","observation_id":"7cd3859c-009f-447c-8740-14304e9f3b09","resolution":{"observed_at":"2026-08-07T15:21:58.694004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"cs.lg/0411099","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:21:58.503211Z","title":"Maurer, A","venue":null,"work_id":"288697f3-8468-4af9-8e63-e3e2683ac13a","year":null},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":2004,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.270502Z"},"links":{"citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:fffc1826a998dbb856a75a23ca215234b2377ccd17f97e15519ccd644d382fe5","observation_id":"0e8628c4-e175-40ad-b57b-696d303af5cc","resolution":{"observed_at":"2026-08-07T15:21:58.514559Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-07T15:21:58.276318Z","title":"Ye, R., Ni, Z., Wu, F., Chen, S., and Wang, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.276318Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:03fc7d00fa4b5dfedc72db5eeaed32186a0aa677e4c9786687d93ae94e901ab4","observation_id":"d72e80ed-6648-4454-bf9c-1243e4c0dd4d","resolution":{"observed_at":"2026-08-07T15:21:58.276318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01097","last_updated":"2019-12-09T20:02:37Z","snapshot_observed_at":"2026-08-06T00:22:10.318064Z","submitted_at":"2018-12-03T21:59:41Z","title":"LEAF: A Benchmark for Federated Settings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01097","snapshot_observed_at":"2026-08-07T15:21:58.242251Z","title":"Caruana, R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.242251Z"},"links":{"cited_paper":"/paper/1812.01097","citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:a28ea329adb3f8d562515b0cd192f7310117ec0e3f96c93fa1e436e21db55475","observation_id":"40a6c29a-a711-4c79-ad40-0a60a0cb95bf","resolution":{"observed_at":"2026-08-07T15:21:58.242251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.00818","last_updated":"2019-12-02T14:29:00Z","snapshot_observed_at":"2026-07-06T08:41:25.156353Z","submitted_at":"2019-12-02T14:29:00Z","title":"Federated Learning with Personalization Layers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.00818","snapshot_observed_at":"2026-08-07T15:21:58.233966Z","title":"Bartlett, P","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.233966Z"},"links":{"cited_paper":"/paper/1912.00818","citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:c8a6a6bbdc14fa742bff50981dc25be551c66b7365af88767b81de8dd8f24b8d","observation_id":"bb507a23-fe5e-497a-a65f-5daebd455102","resolution":{"observed_at":"2026-08-07T15:21:58.233966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.08982","last_updated":"2020-10-18T13:28:30Z","snapshot_observed_at":"2026-07-06T10:05:29.439402Z","submitted_at":"2020-10-18T13:28:30Z","title":"Federated Unsupervised Representation Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.08982","snapshot_observed_at":"2026-08-07T15:21:58.297379Z","title":"Zhang, H., Li, C., Dai, W., Zou, J., and Xiong, H","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.297379Z"},"links":{"cited_paper":"/paper/2010.08982","citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:b34194144e7ba024abd7c95b739fcb5d912558d20b734a8f6d341842859f56ee","observation_id":"811bb885-22d9-4a8b-ae52-e2f79ee43c8d","resolution":{"observed_at":"2026-08-07T15:21:58.297379Z","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":"2026-08-07T15:21:58.728415Z","title":"UPFL: unsupervised personalized federated learning towards new clients","venue":null,"work_id":"9a610f72-d7bf-41e6-8449-8e555ab3bdc2","year":2024},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.282698Z"},"links":{"citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:c1161cd9785ee958204b004df96e6edd63ff8cd8adcbba8ddf4b5cdb3490997d","observation_id":"4102585d-f249-44c5-b469-5a1929002de0","resolution":{"observed_at":"2026-08-07T15:21:58.734575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06430","last_updated":"2024-12-10T11:21:26Z","snapshot_observed_at":"2026-07-06T17:57:52.364338Z","submitted_at":"2024-04-09T16:23:01Z","title":"pfl-research: simulation framework for accelerating research in Private Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.06430","snapshot_observed_at":"2026-08-07T15:21:58.248378Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T15:21:58.248378Z"},"links":{"cited_paper":"/paper/2404.06430","citing_paper":"/paper/2505.15579"},"observation_digest":"sha256:59a4b4003cf0fb98f03fb40b03e625654c89b97607f16ee2a199b443695b6396","observation_id":"3dec3547-3c63-411c-8cdb-dee20fece73f","resolution":{"observed_at":"2026-08-07T15:21:58.248378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.15579","last_updated":"2025-05-21T14:30:59Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T15:12:18.349218Z","submitted_at":"2025-05-21T14:30:59Z","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":6},"total_outbound_references":15},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2505.15579."}