{"as_of":"2026-08-08T02:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0eaff35888745ca9081440383009eaca42a1062884768272106c9d1f7849146e","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:07:26.158821Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T04:05:50.160214Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-15T05:19:45.749504Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"cited_work":{"arxiv_id":"2506.00592","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.00592","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mit- igating plasticity loss in continual reinforcement learning by reducing churn","venue":null,"work_id":"562065aa-db59-45c6-afef-7744bf9d7bfa","year":2025},"citing_paper":{"arxiv_id":"2605.12484","last_updated":"2026-05-14T17:49:32Z","snapshot_observed_at":"2026-08-02T06:23:20.104772Z","submitted_at":"2026-05-12T17:58:20Z","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-13T05:00:31.452781Z"},"links":{"cited_paper":"/paper/2506.00592","citing_paper":"/paper/2605.12484"},"observation_digest":"sha256:aa36fc3d00ed8e86c4e2cde6e068fb63c24dc20d3ce965390aaa2794c9e4595b","observation_id":"1296f4cd-21ea-4efc-b362-ee2d8912cd13","resolution":{"observed_at":"2026-05-13T05:07:18.519778Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"cited_work":{"arxiv_id":"2506.00592","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.00592","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mit- igating plasticity loss in continual reinforcement learning by reducing churn","venue":null,"work_id":"562065aa-db59-45c6-afef-7744bf9d7bfa","year":2025},"citing_paper":{"arxiv_id":"2605.12484","last_updated":"2026-05-14T17:49:32Z","snapshot_observed_at":"2026-08-02T06:23:20.104772Z","submitted_at":"2026-05-12T17:58:20Z","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-15T05:19:05.368681Z"},"links":{"cited_paper":"/paper/2506.00592","citing_paper":"/paper/2605.12484"},"observation_digest":"sha256:e33db1dd7cd68b7f845bad2f128a202fc6dc500e1fec8023acc2ae306625f85d","observation_id":"11e621f7-d694-4e05-a863-04a03e4ad03a","resolution":{"observed_at":"2026-05-15T05:19:45.752173Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.00592","snapshot_observed_at":"2026-07-31T04:05:50.160214Z","title":"Mitigating plasticity loss in continual reinforcement learning by reducing churn.arXiv preprint arXiv:2506.00592,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24996","last_updated":"2026-07-27T18:53:00Z","snapshot_observed_at":"2026-08-06T23:30:24.623782Z","submitted_at":"2026-07-27T18:53:00Z","title":"Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning","version":1},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-07-31T04:05:50.160214Z"},"links":{"cited_paper":"/paper/2506.00592","citing_paper":"/paper/2607.24996"},"observation_digest":"sha256:ff5496c8e13d6e054d0aad90661f206929eac6366063f4fb803ad4b8696d39d9","observation_id":"0153ae16-e631-4f4e-af06-b8b37d5699ba","resolution":{"observed_at":"2026-07-31T04:05:50.160214Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.00592/citation-record","integrity":"/paper/2506.00592/integrity","json":"/paper/2506.00592/citation-record.json","paper":"/paper/2506.00592"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:07:26.681386Z","title":null,"venue":null,"work_id":"5e52534a-5978-4698-8bf5-9972b5b31ac5","year":2020},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:26.158821Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:4b80a0bcc3ad49fbcc3312e8e613d2ac02d999b6fec175bbee51e612230ca465","observation_id":"ffcaccea-3f58-4563-841a-8a9cd5a74986","resolution":{"observed_at":"2026-08-07T12:07:26.720173Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.13812","last_updated":"2024-04-09T21:01:56Z","snapshot_observed_at":"2026-07-06T15:46:10.123461Z","submitted_at":"2023-06-23T23:19:21Z","title":"Maintaining Plasticity in Deep Continual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.13812","snapshot_observed_at":"2026-08-07T12:07:24.694086Z","title":"F., Rahman, P., Sutton, R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.694086Z"},"links":{"cited_paper":"/paper/2306.13812","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:28a7c8126dd332c8e971fbd8c44aa7e975b577425402e38a44d62ee314016018","observation_id":"b5fd2619-5719-453a-b739-20d862b81eea","resolution":{"observed_at":"2026-08-07T12:07:24.694086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.17113","last_updated":"2024-12-22T18:01:08Z","snapshot_observed_at":"2026-08-04T04:39:14.357607Z","submitted_at":"2024-12-22T18:01:08Z","title":"Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.17113","snapshot_observed_at":"2026-08-07T12:07:24.760896Z","title":"T., Lupu, A., Goldie, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.760896Z"},"links":{"cited_paper":"/paper/2412.17113","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:408f1eeaa78c69574121c7be779f786942380de6f7bb4b8e777c7b9c95b00f5d","observation_id":"23362e2a-c199-4b18-a865-c8c6fecf0b92","resolution":{"observed_at":"2026-08-07T12:07:24.760896Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00781","last_updated":"2024-04-30T22:52:33Z","snapshot_observed_at":"2026-08-04T23:46:40.606781Z","submitted_at":"2024-03-31T19:57:38Z","title":"Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.00781","snapshot_observed_at":"2026-08-07T12:07:24.841166Z","title":"and Mahmood, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.841166Z"},"links":{"cited_paper":"/paper/2404.00781","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:f7255456566a7a34bdadbe5edffaea0445d6e45aa970da218036587cbf31497d","observation_id":"db57ee08-4494-48de-9065-11345ab9a021","resolution":{"observed_at":"2026-08-07T12:07:24.841166Z","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":"2026-08-07T12:07:27.924843Z","title":null,"venue":null,"work_id":"c3595518-e966-49c1-bdc4-f067cc892156","year":2024},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.878499Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:adb8d9946f3ebfacd12211ee6cc46a7cf3cd253267dd0ecf0570e595b7abaee7","observation_id":"48e55a01-91f5-41f9-ab6d-9dd2ebb39426","resolution":{"observed_at":"2026-08-07T12:07:28.016634Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:07:27.733374Z","title":"Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T","venue":null,"work_id":"76eedea4-3fd6-49e6-85e0-a6922b69115d","year":2007},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.311840Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:1a9e970b720fef94b8d333a666c8fe2d306f81f1a8e1129ce09c48435393c39c","observation_id":"1c4802a7-b563-4996-b8b4-12d37db6f373","resolution":{"observed_at":"2026-08-07T12:07:27.833015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18762","last_updated":"2024-02-29T00:02:33Z","snapshot_observed_at":"2026-08-07T07:57:33.036330Z","submitted_at":"2024-02-29T00:02:33Z","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18762","snapshot_observed_at":"2026-08-07T12:07:25.099245Z","title":"V ., Pas- canu, R., Martens, J., and Dabney, W","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.099245Z"},"links":{"cited_paper":"/paper/2402.18762","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:9ae4292715c9a5f240a080a59a3d2b352c72ca6b1d6e2cf212f0d8dc5b7d40ec","observation_id":"d5a79819-a857-405e-9ff8-3747ae614d44","resolution":{"observed_at":"2026-08-07T12:07:25.099245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07418","last_updated":"2024-05-19T19:04:31Z","snapshot_observed_at":"2026-08-05T20:04:39.463011Z","submitted_at":"2023-10-11T12:05:34Z","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.07418","snapshot_observed_at":"2026-08-07T12:07:25.165280Z","title":"Revisiting plasticity in visual reinforcement learning: Data, modules and training stages.arXiv preprint, arXiv:2310.07418,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.165280Z"},"links":{"cited_paper":"/paper/2310.07418","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:f0c785538d76f932d206827bdf1fea2fd35098a16517764931a0430fc3367363","observation_id":"fbe77174-476f-4664-a2db-db10933858d9","resolution":{"observed_at":"2026-08-07T12:07:25.165280Z","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":"2026-08-07T12:07:25.392028Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.392028Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:2d837f4543954198ca4d6884c49b7c62d7d434a8390579623c32c2e9251cfc18","observation_id":"ed7c0b0f-544b-4b8a-bc29-ae11cb31f517","resolution":{"observed_at":"2026-08-07T12:07:25.392028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.00690","last_updated":"2018-01-02T15:48:14Z","snapshot_observed_at":"2026-08-01T20:24:08.300098Z","submitted_at":"2018-01-02T15:48:14Z","title":"DeepMind Control Suite","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.00690","snapshot_observed_at":"2026-08-07T12:07:25.491932Z","title":"P., and Riedmiller, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.491932Z"},"links":{"cited_paper":"/paper/1801.00690","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:97bcd1082f0ea13247f2d6b73d1b7cb8358491f9ee80379c5b0f2a59242df904","observation_id":"16b43741-5e71-4deb-b037-c7410b7eb4ad","resolution":{"observed_at":"2026-08-07T12:07:25.491932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.02648","last_updated":"2018-12-06T16:36:20Z","snapshot_observed_at":"2026-07-06T07:19:38.028327Z","submitted_at":"2018-12-06T16:36:20Z","title":"Deep Reinforcement Learning and the Deadly Triad","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.02648","snapshot_observed_at":"2026-08-07T12:07:25.603506Z","title":"Deep reinforcement learning and the deadly triad.arXiv preprint, arXiv:1812.02648,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.603506Z"},"links":{"cited_paper":"/paper/1812.02648","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:14f71d903c4ef7c3678238c5b483db33725af6300f5b6a3939165fe5cd8d0eda","observation_id":"0b56d979-6340-4f05-80d1-27ccb30156dc","resolution":{"observed_at":"2026-08-07T12:07:25.603506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01364","last_updated":"2024-02-07T07:14:39Z","snapshot_observed_at":"2026-08-04T18:35:41.659861Z","submitted_at":"2024-02-02T12:34:09Z","title":"Continual Learning for Large Language Models: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01364","snapshot_observed_at":"2026-08-07T12:07:25.660754Z","title":"Continual learning for large language models: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.660754Z"},"links":{"cited_paper":"/paper/2402.01364","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:4dc4dc07136b7fdfd9386e502ff9f04712c2a4117b64bdef224d6f2a0c4b246d","observation_id":"456c8a55-bdc7-4a0e-aca0-dcc8c5803e59","resolution":{"observed_at":"2026-08-07T12:07:25.660754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.03176","last_updated":"2019-06-07T00:36:50Z","snapshot_observed_at":"2026-07-06T07:37:51.655095Z","submitted_at":"2019-03-07T20:34:36Z","title":"MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.03176","snapshot_observed_at":"2026-08-07T12:07:25.752483Z","title":"and Tian, T","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.752483Z"},"links":{"cited_paper":"/paper/1903.03176","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:16ef119a1d67ed536a3ac3534a7c3a51b8a77a6a824a956f5d3543223e130909","observation_id":"4d8cfb7f-872f-499e-a4b3-67211ff87b2d","resolution":{"observed_at":"2026-08-07T12:07:25.752483Z","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":"2026-08-07T12:07:27.509776Z","title":"Experimental Details A.1","venue":null,"work_id":"47c6c669-567b-4022-92b5-f4ebb1194cea","year":2024},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.843649Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:04f687a9118f8a403c250e0d5c60d32cb61986c32fed832135814c05210470aa","observation_id":"a7bb5d2b-2af0-440f-9716-0454207ceab0","resolution":{"observed_at":"2026-08-07T12:07:27.584006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:07:27.304129Z","title":"Therefore, we useσ= 0.02for MountainCar-v0","venue":null,"work_id":"34acb7a5-4051-4448-93ea-8d31da9f44c2","year":2024},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.940013Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:9307cc24f58d8bfde95363da4891c4f4a4568f798a1915cd6b22c6944563b569","observation_id":"9706fc3c-9988-4285-a5b3-3964fe89aa71","resolution":{"observed_at":"2026-08-07T12:07:27.419347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:07:27.115425Z","title":"The values of conventional hyperparameters are taken from the recommended values inCleanRL","venue":null,"work_id":"49f6affd-67fa-4e52-800d-089bd3aa34d4","year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.979456Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:e5e6d08abd6fb2bfb1907c0dd7d9ef4bdab7b2b405ab685713a527b497fcd55d","observation_id":"5ef0ff6e-5ef5-4654-a8e1-83b8d66dd2d6","resolution":{"observed_at":"2026-08-07T12:07:27.232688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:07:26.940182Z","title":"The values of conventional hyperpa- rameters are taken from the recommended values in (Young & Tian, 2019)","venue":null,"work_id":"9fcc49be-7c13-4b49-bbee-aa47d9cafaa3","year":2019},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:26.046554Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:bdaf41d2f4822204727df0dc870ab71e27d47c18f4e59c60057be9faa0734c45","observation_id":"4f1d25d3-7542-4daa-9e50-6e8bc22be371","resolution":{"observed_at":"2026-08-07T12:07:27.029517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:07:26.791645Z","title":null,"venue":null,"work_id":"0a8c76f3-52de-42ff-b909-de19619a757e","year":2024},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:26.112993Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:8976b351de58fd8d94c637cff28a76cc75ee518d61ba387e6dbcf8a417b4ccce","observation_id":"9c52f6e0-8f13-4e70-9bf1-6672d71ced88","resolution":{"observed_at":"2026-08-07T12:07:26.880531Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:07:25.216383Z","title":"URL http://www.amazon.com/exec/obidos/ redirect?tag=citeulike07-20&path= ASIN/1449319793","venue":null,"work_id":null,"year":1928},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.216383Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:c416f49be86abf4079219e2f07ccb13a21ee3b01d5c2f169be4ae7eda08727b1","observation_id":"5a6f8cff-d641-494b-80b6-54bb3dc2d75a","resolution":{"observed_at":"2026-08-07T12:07:25.216383Z","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":"2026-08-07T12:07:24.948826Z","title":"Kumar, A., Agarwal, R., Ghosh, D., and Levine, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.948826Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:70379f4280f917ee643aeb1f48468436289510431aea1e94f911fe6d6f72b600","observation_id":"3d7a8ee3-9fff-4ca4-a75a-0cfaa8c849e6","resolution":{"observed_at":"2026-08-07T12:07:24.948826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.00730","last_updated":"2022-10-20T19:29:24Z","snapshot_observed_at":"2026-07-06T13:16:32.021229Z","submitted_at":"2022-06-01T19:44:18Z","title":"The Phenomenon of Policy Churn","version":3},"cited_work":{"arxiv_id":"2206.00730","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.00730","snapshot_observed_at":"2026-08-07T12:07:26.364941Z","title":"The Phenomenon of Policy Churn","venue":"cs.LG","work_id":"cd033d22-1532-4705-9a7e-7a034be92c5e","year":2022},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.364666Z"},"links":{"cited_paper":"/paper/2206.00730","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:f639a3408d1908a53f4051ea97c1af05ff3acbefb5570d7c8655bdfc58b333c8","observation_id":"253ee046-0a55-4926-aabd-4d8766f4e933","resolution":{"observed_at":"2026-08-07T12:07:26.446753Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.00042","last_updated":"2023-10-14T11:58:06Z","snapshot_observed_at":"2026-07-06T11:14:31.306862Z","submitted_at":"2021-05-31T18:21:06Z","title":"A study on the plasticity of neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.00042","snapshot_observed_at":"2026-08-07T12:07:24.494023Z","title":"L., Pascanu, R., and Clopath, C","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.494023Z"},"links":{"cited_paper":"/paper/2106.00042","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:3c37a3a9c9792ec44296b6a2d14475e7c858e042819bf9a5f3cc3f82b8a8886a","observation_id":"c49b059f-2ede-4824-b1ea-b1fc61245a3d","resolution":{"observed_at":"2026-08-07T12:07:24.494023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01540","last_updated":"2016-06-05T17:54:48Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2026-08-07T12:07:24.549328Z","title":"Openai gym","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.549328Z"},"links":{"cited_paper":"/paper/1606.01540","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:fc6404694a39654ae9574096d4963d0851ee85c97aade2c0d1570c30640629e8","observation_id":"9bb40a89-7900-44ad-a453-fde6ae77c769","resolution":{"observed_at":"2026-08-07T12:07:24.549328Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04345","last_updated":"2025-06-26T16:08:44Z","snapshot_observed_at":"2026-07-06T15:51:58.017259Z","submitted_at":"2023-07-10T05:06:41Z","title":"Continual Learning as Computationally Constrained Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04345","snapshot_observed_at":"2026-08-07T12:07:25.020778Z","title":"J., Liu, Y ., and Van Roy, B","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:25.020778Z"},"links":{"cited_paper":"/paper/2307.04345","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:c9ba0e3be4520d6f4273e9d94251faf0106dd287100521453ae1a583def75516","observation_id":"f76e2d38-6922-4e82-b427-0bb18df945f4","resolution":{"observed_at":"2026-08-07T12:07:25.020778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.08894","last_updated":"2019-03-21T09:42:41Z","snapshot_observed_at":"2026-08-04T21:37:15.275989Z","submitted_at":"2019-03-21T09:42:41Z","title":"Towards Characterizing Divergence in Deep Q-Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.08894","snapshot_observed_at":"2026-08-07T12:07:24.428368Z","title":"Towards charac- terizing divergence in deep q-learning.arXiv preprint, arXiv:1903.08894,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.428368Z"},"links":{"cited_paper":"/paper/1903.08894","citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:e0bf22a237b217f74d4e916d7137341b014a5db97f8f8c3280f47aeb2eb69957","observation_id":"97b49dac-aa77-4af6-b424-75d914f9fa9e","resolution":{"observed_at":"2026-08-07T12:07:24.428368Z","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":"2026-08-07T12:07:28.106512Z","title":"Lever- aging procedural generation to benchmark reinforcement learning","venue":null,"work_id":"c656f36b-cedc-4804-8490-38ff659033b9","year":null},"citing_paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T12:07:24.600466Z"},"links":{"citing_paper":"/paper/2506.00592"},"observation_digest":"sha256:227efcd311863aa041614d1700ae9663a07109945ee19fe0490b3a18d0238c47","observation_id":"85313622-e286-4119-bcbd-195fa7782460","resolution":{"observed_at":"2026-08-07T12:07:28.195071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.00592","last_updated":"2025-05-31T14:58:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T21:20:18.341329Z","submitted_at":"2025-05-31T14:58:22Z","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":6},"total_outbound_references":26},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 3 inbound Pith citation observations for arXiv:2506.00592."}