{"as_of":"2026-08-13T10:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:147c75ff0263afc1273738f668ddea58f5ac3c6af3c17b28afcc72638c700980","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T14:42:06.718882Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2411.15014/citation-record","integrity":"/paper/2411.15014/integrity","json":"/paper/2411.15014/citation-record.json","paper":"/paper/2411.15014"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:42:07.343781Z","title":"⟨ΦΦΦ∗ − ΦΦΦt, −1 N NX i=1 ¯h(θθθi t+1, ΦΦΦt)⟩ # | {z } Term 2 + 2βtE","venue":null,"work_id":"160a8307-94b1-4a82-9aa9-b890b8489c10","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.664846Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:0a30050974824afa07525dfc61b22630521b34929074e53105d8f353555c6a1d","observation_id":"038dc07f-54a5-4eb4-8151-5523b5efc04d","resolution":{"observed_at":"2026-08-12T14:42:07.348596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.404232Z","title":"When the state and action spaces are large, it is com- putationally infeasible to store Qi,πi (s, a) for all state-action pairs","venue":null,"work_id":"d321875e-784e-4bb5-975e-4ed6818dec11","year":1992},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.644122Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:a11a25e27f6d4f2524c0d380251c3cead6784c68c7e461ee1d7a6ecf32dd349a","observation_id":"71d0d850-bf56-4f8a-bf95-56644536c38d","resolution":{"observed_at":"2026-08-12T14:42:07.409378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01540","last_updated":"2016-06-05T17:54:48Z","snapshot_observed_at":"2026-08-12T05:40:07.199512Z","submitted_at":"2016-06-05T17:54:48Z","title":"OpenAI Gym","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.01540","snapshot_observed_at":"2026-08-12T14:42:06.509695Z","title":"Openai gym","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.509695Z"},"links":{"cited_paper":"/paper/1606.01540","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:8a9368f83f09b5c653a7779dca8bd71e85fe0ffb823ca3263a5299263b272252","observation_id":"ceba4d5b-f3d7-43cb-b6da-1bb1f6455a43","resolution":{"observed_at":"2026-08-12T14:42:06.509695Z","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":"2026-08-12T14:42:07.265474Z","title":"(1 + βt−1/αt) (1 + 2βt−1/αt − 2αtKω ) + (12α2 t δ2K 2 + 2L2α3 t /βt−1 + 6K 2δ2α3 t /βt−1) 4β2 t−1L2 N ! + (1 + αt/βt−1) 4β2 t−1L4 N # · E h θθθi t − yi(ΦΦΦt−1) 2i +","venue":null,"work_id":"fe70f43a-3947-4aef-b751-223a8c94cc8a","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.690060Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:be4423ee84a04afd4391606b077103c18902cfe1c9eeb644cb9043f5ed58586c","observation_id":"f8707061-5176-4fc1-969f-f81883379c16","resolution":{"observed_at":"2026-08-12T14:42:07.270994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.389467Z","title":", Edo 2: Get the initial state of the environment; 3: for t = 0, 1, ..., T− 1 do 4: for i = 1,","venue":null,"work_id":"232ba807-7c5b-49da-812e-6d5016449be0","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.649263Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:b443e80b72335e0ac9afc0a14b4847f65fdb810c7639546dc2b9261bed2e5bba","observation_id":"3a1db86c-6920-4cf6-86ac-3b7d9461386c","resolution":{"observed_at":"2026-08-12T14:42:07.394356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.01868","last_updated":"2021-03-23T13:44:57Z","snapshot_observed_at":"2026-08-12T23:05:42.556336Z","submitted_at":"2020-11-03T17:43:39Z","title":"Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.01868","snapshot_observed_at":"2026-08-12T14:42:06.532131Z","title":"Nonlinear two-time-scale stochastic approximation: Convergence and finite-time performance","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.532131Z"},"links":{"cited_paper":"/paper/2011.01868","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:df9df278beb42ed8690e4f8f9e86fc0286490d81e2eff6632003156634794705","observation_id":"fd616239-7398-408b-a104-c93c9faf8145","resolution":{"observed_at":"2026-08-12T14:42:06.532131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.03604","last_updated":"2019-02-28T21:07:51Z","snapshot_observed_at":"2026-08-10T06:38:25.165407Z","submitted_at":"2018-11-08T18:37:03Z","title":"Federated Learning for Mobile Keyboard Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.03604","snapshot_observed_at":"2026-08-12T14:42:06.547663Z","title":"Federated learning for mobile keyboard prediction","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.547663Z"},"links":{"cited_paper":"/paper/1811.03604","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:80672faa03445518a39e9d26678d938c8e7781569c8aa09846c23b95de16f691","observation_id":"07f71b43-d9f5-4e2c-9455-3c609b32da0f","resolution":{"observed_at":"2026-08-12T14:42:06.547663Z","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":"2026-08-12T14:42:07.522581Z","title":"Federated learning for resource-constrained IoT devices: Panoramas and state of the art","venue":null,"work_id":"089c47af-a584-4b99-9922-f56ae1d0b273","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.553883Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:9daa6377134c9347d79002358620de8e84313e0e605009ed5e9720644c637b49","observation_id":"b32fa44e-7949-4305-99b9-ac954710a977","resolution":{"observed_at":"2026-08-12T14:42:07.527511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.08003","last_updated":"2025-01-23T23:33:53Z","snapshot_observed_at":"2026-08-13T04:56:00.369912Z","submitted_at":"2024-04-09T04:21:13Z","title":"Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.08003","snapshot_observed_at":"2026-08-12T14:42:06.565017Z","title":"Asynchronous federated reinforcement learning with policy gradient updates: Algorithm design and convergence analysis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.565017Z"},"links":{"cited_paper":"/paper/2404.08003","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:e63dd7147533240eac950a4772ee1f061855feb22921d7332e4c8d87a5a07b2e","observation_id":"f3e1da26-9abc-4a7b-9baa-d46e302e67e8","resolution":{"observed_at":"2026-08-12T14:42:06.565017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.07035","last_updated":"2022-06-21T21:34:58Z","snapshot_observed_at":"2026-08-12T06:50:47.935559Z","submitted_at":"2021-02-14T00:06:54Z","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.07035","snapshot_observed_at":"2026-08-12T14:42:06.576277Z","title":"Model-free representation learning and exploration in low-rank mdps","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.576277Z"},"links":{"cited_paper":"/paper/2102.07035","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:38469b21291954bec33a302a0fd4d1c77c3c073b4faba4a3d3fc8e6f4ba6835e","observation_id":"4a672aa9-75a1-46b1-8b1b-df28aee56911","resolution":{"observed_at":"2026-08-12T14:42:06.576277Z","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":"2026-08-12T14:42:07.492165Z","title":"Federated reinforcement learning for fast personalization","venue":null,"work_id":"1c5d5b3f-eb75-4dbf-870a-2668089d9512","year":2019},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.582400Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:dc6a6531d1b42b87fa261fb507bb0e9755791b4750e6789bd519c11192c2d004","observation_id":"32a20303-1ad8-4726-9920-b54a39269bb4","resolution":{"observed_at":"2026-08-12T14:42:07.496917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.11887","last_updated":"2021-10-24T19:02:03Z","snapshot_observed_at":"2026-07-06T11:41:48.795143Z","submitted_at":"2021-08-26T16:22:49Z","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.11887","snapshot_observed_at":"2026-08-12T14:42:06.587289Z","title":"Federated reinforcement learning: Techniques, applications, and open challenges","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.587289Z"},"links":{"cited_paper":"/paper/2108.11887","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:5e68d847c1ffe5f3c5190ff1322403cfd8496807d2007becf48a49b25486c289","observation_id":"79249f88-028b-44ea-992b-c43695326570","resolution":{"observed_at":"2026-08-12T14:42:06.587289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.16981","last_updated":"2024-10-29T20:37:04Z","snapshot_observed_at":"2026-08-13T08:42:19.528016Z","submitted_at":"2024-08-30T03:03:03Z","title":"The Sample-Communication Complexity Trade-off in Federated Q-Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.16981","snapshot_observed_at":"2026-08-12T14:42:06.592587Z","title":"The sample-communication complexity trade-off in federated q- learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.592587Z"},"links":{"cited_paper":"/paper/2408.16981","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:b64d23b95e53c20f0ca16ce7eaf5d9d8971543bd548e605053adcc07be52c590","observation_id":"a3c50314-475e-4a87-8374-c0265fb7d7eb","resolution":{"observed_at":"2026-08-12T14:42:06.592587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02212","last_updated":"2024-07-01T14:07:58Z","snapshot_observed_at":"2026-08-10T12:46:48.776948Z","submitted_at":"2023-02-04T17:53:55Z","title":"Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.02212","snapshot_observed_at":"2026-08-12T14:42:06.602833Z","title":"Federated tem- poral difference learning with linear function approximation under environmental heterogeneity","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.602833Z"},"links":{"cited_paper":"/paper/2302.02212","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:c4994f74b535f2ab4d9229e70438964de039b98fc706612beb8ee1e717b2856f","observation_id":"e59e9cec-68e5-4d4a-bb13-ce7aaf9756d8","resolution":{"observed_at":"2026-08-12T14:42:06.602833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.02903","last_updated":"2018-12-07T04:18:12Z","snapshot_observed_at":"2026-08-08T16:17:30.311416Z","submitted_at":"2018-12-07T04:18:12Z","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.02903","snapshot_observed_at":"2026-08-12T14:42:06.608072Z","title":"Applied federated learning: Improving google keyboard query suggestions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.608072Z"},"links":{"cited_paper":"/paper/1812.02903","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:2d9f6c98ef182999ccebd2aa516fe8b9450941638ae04f2a7362d78d57ff5688","observation_id":"82ce2e8b-5f5d-4461-8498-d0ceeb1a024f","resolution":{"observed_at":"2026-08-12T14:42:06.608072Z","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":"2026-08-12T14:42:07.477434Z","title":"Federated reinforcement learning for generalizable motion planning","venue":null,"work_id":"8f423210-d012-4263-9c2b-ebf9c635f496","year":2023},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.613391Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:06594450da92638da548e42705be11873006cee3793bb4458a3d54169aee70f2","observation_id":"ab6c4bf2-5af5-4e5e-8c3e-2102d4f6fbad","resolution":{"observed_at":"2026-08-12T14:42:07.482601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.15273","last_updated":"2024-04-14T07:17:28Z","snapshot_observed_at":"2026-08-13T04:33:42.594461Z","submitted_at":"2024-01-27T02:43:45Z","title":"Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.15273","snapshot_observed_at":"2026-08-12T14:42:06.618593Z","title":"Finite-time analysis of on-policy heterogeneous federated reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.618593Z"},"links":{"cited_paper":"/paper/2401.15273","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:6390902138c506741099f22e50206ee03b1cb54f9e3598b8233ea5bcb631bb8f","observation_id":"e177451b-2610-44a7-a933-52c490b80dbf","resolution":{"observed_at":"2026-08-12T14:42:06.618593Z","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":"2026-08-12T14:42:07.463162Z","title":null,"venue":null,"work_id":"2ceb0084-7607-49ba-96f9-8c30282b3ea1","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.623676Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:c6115bc2e4d58e665d35b5a412156bd2841d1dff93185948a2f52fe3d1b5555c","observation_id":"e00d9e6d-c828-4a13-a5d9-ff8accf7e0ce","resolution":{"observed_at":"2026-08-12T14:42:07.467718Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.433840Z","title":null,"venue":null,"work_id":"a393a01d-db19-40fd-8918-da8e36577ca6","year":2020},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.633945Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:54b567dfc65135e28702545bede2df1d89978c36d16da496b239f4d58cc39ab1","observation_id":"bae14689-f2d5-4027-abd7-1a2ad05424a9","resolution":{"observed_at":"2026-08-12T14:42:07.438411Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.419235Z","title":"However, it is open in the context of leveraging representation learning in PFedFL","venue":null,"work_id":"1065c9fa-114b-472e-9cf2-0bf07f56787f","year":2021},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.639153Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:638a189bc0507ccd41f66083d0c8a9a0ecf5fc9320f9cd69d318f94ec8bbeee6","observation_id":"37cea18c-ae84-4282-abb7-00d2d7ec8c0f","resolution":{"observed_at":"2026-08-12T14:42:07.423930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.374418Z","title":null,"venue":null,"work_id":"39289230-fb46-4049-bc3a-ebb06da3d157","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.654598Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:a22d13f93c11e1043afd861c35cd9dba5a86e113c03fa72a3885e06298d1ad99","observation_id":"72b6cf77-f908-44e4-b574-61172557b490","resolution":{"observed_at":"2026-08-12T14:42:07.379154Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.358759Z","title":"Hence, Li(ΦΦΦ(si k), θθθi) is convex on ΦΦΦ(si k) under a fixed θi","venue":null,"work_id":"9436bfa8-6c1a-48c6-8a36-a532e1cfbde4","year":2019},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.659538Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:2b91acccdd8460ce00dff198fb83693e5bd930c94117aa103b26fc4f590ac390","observation_id":"446b0021-fc88-4bd0-8c0d-85ba7f1c271d","resolution":{"observed_at":"2026-08-12T14:42:07.363915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.328518Z","title":"NX i=1 ∥θθθi t+1 − yi(ΦΦΦt)∥2 # . (29) Proof. We have Term 2 = 2βtE","venue":null,"work_id":"91e6198e-3501-48af-af4b-f0619c761f39","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.669864Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:3e9810dc88c6300cc0aafed8b239c082ee2f8f2fc9aac36d6f694a226c612683","observation_id":"5abbb615-102e-4475-8bdd-dd7258bc6a0d","resolution":{"observed_at":"2026-08-12T14:42:07.333678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.312748Z","title":"The proof is similar to that of Lemma 3 in Dal Fabbro et al","venue":null,"work_id":"886fea22-19ce-4669-97f8-b1e514fe390a","year":2023},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.674880Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:b54b2c73bbd37b7e88cd2c7056ac09511b06ea05d9b4c1cd7f457c146fd4aabe","observation_id":"696f500d-06f4-48cf-9a25-d971d77573e3","resolution":{"observed_at":"2026-08-12T14:42:07.317741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.297457Z","title":"29 Published as a conference paper at ICLR 2025 Proof","venue":null,"work_id":"31fd6701-880c-498b-8032-6895e92acca2","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.680252Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:5105169e6252ca3127e34e98e3947125dff66f3684ad19ae993c0f16081f5c8b","observation_id":"35dab6f8-e9cc-47ea-9d24-85e61e954513","resolution":{"observed_at":"2026-08-12T14:42:07.302349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.282296Z","title":"* θθθi t − yi(ΦΦΦt−1), KX k=1 g(θθθi t,k−1, ΦΦΦt) +# ≤ E h θθθi t − yi(ΦΦΦt−1) 2i + 6α2 t δ2K 2E h ∥ΦΦΦt − ΦΦΦ∗∥2 i + 6α2 t δ2K 2(1 + B2) + 2α2 t K 2L2B2 + 2αtE","venue":null,"work_id":"39a9442c-f3d5-4439-839f-35cb3325ec49","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.684976Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:fe05a0c1728d72c31d3ae7de8e74a3cecabdf062634397026f6383495f99a9a8","observation_id":"bdf2a534-246b-436f-9b49-4665a4440aaa","resolution":{"observed_at":"2026-08-12T14:42:07.287428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.248537Z","title":"(1 + βt/αt+1) (1 + 2βt/αt+1 − 2αt+1Kω ) + (12α2 t+1δ2K 2 + 2L2α3 t+1/βt + 6K 2δ2α3 t+1/βt) 4β2 t L2 N ! + (1 + αt+1/βt) 4β2 t L4 N # · 1 N E","venue":null,"work_id":"2446fc95-c90d-4eb4-8e36-de3598490e66","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.694669Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:104cf430be83e58c7ece1eaf84ef9a5212a37ecc010cdd32a1d6cabb08d82825","observation_id":"ddd0382f-d770-4115-8031-c91930343c91","resolution":{"observed_at":"2026-08-12T14:42:07.253696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.231938Z","title":"E[∥ΦΦΦt − ΦΦΦ∗∥2] + 1 N E","venue":null,"work_id":"f73dcd8a-1078-42a5-9b82-d74e0896cfde","year":2022},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.699553Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:117b28cd4d09182965082a28821517d6eae298a236c117a4586a4d8479e9fb8b","observation_id":"207b5bae-a917-4a9f-a6c1-e44fcf6f43f6","resolution":{"observed_at":"2026-08-12T14:42:07.237399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.215866Z","title":"PF EDDQN-R EP in Acrobot environment","venue":null,"work_id":"2683ac76-074e-4cda-b450-85c22d65901a","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.704227Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:98901b0c5299fa5b1a9a8f651e69f80c8207e7b44bcfae9c6038d832dfb1d250","observation_id":"16d09803-71ef-42a3-9ad7-86f75f00ddb7","resolution":{"observed_at":"2026-08-12T14:42:07.220936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.199900Z","title":null,"venue":null,"work_id":"d8e8beeb-c224-48a6-b2ac-3a330952a475","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.708860Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:0cea840b1a81c7e7c7f0962e1d95eef88a3d7c8ae0f4609c18117b564d804b01","observation_id":"cfba1b4e-e0a6-4fc1-af64-09323c01044b","resolution":{"observed_at":"2026-08-12T14:42:07.204896Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"0140.0044","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:42:06.857782Z","title":"Figure 13: Worst case personalization error with varying pole length discrepancy across environ- ments","venue":null,"work_id":"628f5100-fabd-415d-8018-b00f6095e535","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.713761Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:6c8b4f69eb59c6a1d8ac0d7819cce4530cf51cc0813cdfd471dd817b34ee1b67","observation_id":"1c7b6026-a0ba-4003-bb92-9f28d5fc1c7e","resolution":{"observed_at":"2026-08-12T14:42:06.870467Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.183882Z","title":null,"venue":null,"work_id":"a78590df-a88c-48e6-bb7b-0c55df095d98","year":2025},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.718882Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:59d265f75102d250cd2a83a6d42b3f8af64cba6815cae5280b3bf357758cecdb","observation_id":"85d23234-0960-488e-a0bb-ed7dd0811986","resolution":{"observed_at":"2026-08-12T14:42:07.188724Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.05148","last_updated":"2022-09-12T11:08:44Z","snapshot_observed_at":"2026-08-08T16:44:51.799401Z","submitted_at":"2022-09-12T11:08:44Z","title":"Personalized Federated Learning with Communication Compression","version":1},"cited_work":{"arxiv_id":"2209.05148","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.05148","snapshot_observed_at":"2026-08-12T14:42:07.151111Z","title":"Personalized Federated Learning with Communication Compression","venue":"cs.LG","work_id":"f6a53270-29d5-4330-a863-10b7579cfafe","year":2022},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.503633Z"},"links":{"cited_paper":"/paper/2209.05148","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:e84886a05d9f662f7d457afe386120a319107d15c4d291d0203079c1ba1286c1","observation_id":"7fa08076-28a6-4478-9b75-51af0140bd62","resolution":{"observed_at":"2026-08-12T14:42:07.156931Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T14:42:07.506522Z","title":"Asynchronous methods for deep reinforcement learning","venue":null,"work_id":"26459ace-96f2-4aed-9628-611a2845bf6c","year":1928},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.570186Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:24942ea911e19aaa7894951dd1bd93d9a690d996c6a095ac133b97b788d199c6","observation_id":"b629bf20-7569-441d-8483-c4e465009569","resolution":{"observed_at":"2026-08-12T14:42:07.512264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.07876","last_updated":"2019-12-14T06:39:54Z","snapshot_observed_at":"2026-08-12T10:36:18.211349Z","submitted_at":"2018-02-22T02:35:32Z","title":"Federated Meta-Learning with Fast Convergence and Efficient Communication","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.07876","snapshot_observed_at":"2026-08-12T14:42:06.515270Z","title":"Federated meta-learning with fast convergence and efficient communication","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.515270Z"},"links":{"cited_paper":"/paper/1802.07876","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:2a8cd284dc97e943e1a5e83b8372fb9099334c571e79d2a2b420020adb14a3eb","observation_id":"002eee82-2db3-490e-8239-7f49a69013a9","resolution":{"observed_at":"2026-08-12T14:42:06.515270Z","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":"2026-08-12T14:42:07.448507Z","title":"Federated reinforcement learning","venue":null,"work_id":"fa23130f-ca4f-4355-ab81-a2c381392695","year":2022},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.628656Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:a722709f163cc851337f7cb634a3cca8b78d4a1727afb253ea20bc66620de76f","observation_id":"f003c5de-0883-452a-9d4e-0ed99ebb4cb6","resolution":{"observed_at":"2026-08-12T14:42:07.453245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11425","last_updated":"2022-01-26T05:25:41Z","snapshot_observed_at":"2026-07-06T07:55:54.995586Z","submitted_at":"2019-05-27T18:01:59Z","title":"Finite-Sample Analysis of Nonlinear Stochastic Approximation with Applications in Reinforcement Learning","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11425","snapshot_observed_at":"2026-08-12T14:42:06.521351Z","title":"Perfor- mance of q-learning with linear function approximation: Stability and finite-time analysis","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.521351Z"},"links":{"cited_paper":"/paper/1905.11425","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:9dd8c2681b236810b1b08c26b0b8e6a60b6ba6b9dc8235e9bc35c004eb41051d","observation_id":"7e609893-30bb-41a1-8138-b0da64aa5543","resolution":{"observed_at":"2026-08-12T14:42:06.521351Z","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":"2026-08-12T14:42:07.537281Z","title":"Exploiting shared repre- sentations for personalized federated learning","venue":null,"work_id":"246f9d35-f152-41ed-a443-c81a5cffdf3a","year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.526914Z"},"links":{"citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:44e8c2c50cf03f42f57eb4307a949daa6b8d3d32e864561e599426a34ab765a8","observation_id":"28c2266c-5516-403d-aba8-d84d932dafae","resolution":{"observed_at":"2026-08-12T14:42:07.542119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.01627","last_updated":"2021-04-04T15:19:19Z","snapshot_observed_at":"2026-08-11T16:53:33.268215Z","submitted_at":"2021-04-04T15:19:19Z","title":"Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.01627","snapshot_observed_at":"2026-08-12T14:42:06.537436Z","title":"Finite-time convergence rates of nonlinear two-time-scale stochastic approximation under markovian noise","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.537436Z"},"links":{"cited_paper":"/paper/2104.01627","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:29e7cc82cd5c72f49b2a64d4222b1af41aa4b66b615ca4ce74f552a55c271e89","observation_id":"36f5ea1a-2805-4d61-8769-fc821194a6c3","resolution":{"observed_at":"2026-08-12T14:42:06.537436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07948","last_updated":"2020-10-23T03:04:01Z","snapshot_observed_at":"2026-08-08T19:27:05.920106Z","submitted_at":"2020-02-19T01:08:46Z","title":"Personalized Federated Learning: A Meta-Learning Approach","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07948","snapshot_observed_at":"2026-08-12T14:42:06.542443Z","title":"Personalized federated learning: A meta- learning approach","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.542443Z"},"links":{"cited_paper":"/paper/2002.07948","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:9d1cbd4f812d362e44029233e34d8261f0a42bbfad46d8e538c9fa7a4244eca2","observation_id":"866f3c36-2592-4d73-ba50-792967565713","resolution":{"observed_at":"2026-08-12T14:42:06.542443Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15454","last_updated":"2023-10-24T01:59:28Z","snapshot_observed_at":"2026-08-13T05:42:35.975192Z","submitted_at":"2023-10-24T01:59:28Z","title":"Private Learning with Public Features","version":1},"cited_work":{"arxiv_id":"2310.15454","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.15454","snapshot_observed_at":"2026-08-12T14:42:07.015900Z","title":"Private Learning with Public Features","venue":"cs.LG","work_id":"3f781016-754c-43ad-9906-556e5d7bc77c","year":2023},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.559832Z"},"links":{"cited_paper":"/paper/2310.15454","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:297751a6e7cea5a9cd19d06309b796de3d7ad1830a5a4bf9400c7a96a4fd6fe3","observation_id":"8d8d1e64-7df7-4439-a032-c072af0c3c7a","resolution":{"observed_at":"2026-08-12T14:42:07.021393Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.00818","last_updated":"2019-12-02T14:29:00Z","snapshot_observed_at":"2026-08-12T16:18:55.704115Z","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":"2026-08-12T14:42:06.497266Z","title":"Fed- erated learning with personalization layers","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.497266Z"},"links":{"cited_paper":"/paper/1912.00818","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:a7b2f885b3004e3e36027fd59d2d5f1e8cd13651ec5e502393af7b236847453b","observation_id":"d633920a-3126-46cc-85fd-c8a45e64c57c","resolution":{"observed_at":"2026-08-12T14:42:06.497266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-12T14:42:06.597861Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-12T14:42:06.597861Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2411.15014"},"observation_digest":"sha256:4cb710578c93fc5c47614507373ffdb488a7b1e54a9876cc722bd73314d15e89","observation_id":"e3667d99-aeb2-435b-9898-6659f46973b0","resolution":{"observed_at":"2026-08-12T14:42:06.597861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.15014","last_updated":"2025-07-16T21:34:45Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T23:05:05.810651Z","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":3,"verified_fuzzy":19},"total_outbound_references":43},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2411.15014."}