{"as_of":"2026-08-10T11:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:631eafeff1a0d56956abc187af6d2af9ae98889eb60c915ac1ec04a126488f41","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T15:43:34.601190Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2502.01342/citation-record","integrity":"/paper/2502.01342/integrity","json":"/paper/2502.01342/citation-record.json","paper":"/paper/2502.01342"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T15:43:34.136277Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.136277Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:bd774199e8cfc24f20bb2f81bba11f5d2ffd1b61762e119189a82d6118b47eaf","observation_id":"bda03c52-fe66-46c1-8425-969c8cd55039","resolution":{"observed_at":"2026-08-09T15:43:34.136277Z","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":"2026-08-09T15:43:34.203984Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.203984Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:3d44c510c5ef37c24365675bee4160bf9085f669a6d28e86071324851f165615","observation_id":"ec152f1f-0b91-43e9-a5a4-411432680340","resolution":{"observed_at":"2026-08-09T15:43:34.203984Z","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":"2026-08-09T15:43:35.759073Z","title":"Resetting the optimizer in deep rl: An empirical study","venue":null,"work_id":"bc039992-2395-440f-8c11-6d6f18841b48","year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.291993Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:2d49ace7899e07b6f3a55a1e6c83e9f89a38e1ad4a433075413cab19b8be5b8d","observation_id":"0c99ddcd-a94c-4bb1-bd03-2b8a586fe5bb","resolution":{"observed_at":"2026-08-09T15:43:35.769935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T15:43:35.678155Z","title":"and Adams, R","venue":null,"work_id":"93defccd-7512-4279-a956-aa53862ad331","year":2020},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.319291Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:360c7f5e4bf38a1a807fc222b4ad14311707bf01926fe713097ad82372c438ff","observation_id":"8d72572b-020d-4ed3-957d-29064bbe69f7","resolution":{"observed_at":"2026-08-09T15:43:35.723286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-09T15:43:34.325271Z","title":"L., Kiros, J","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.325271Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:a6ae124323ac978b808559f19305546144998192ff02717febde6cfe1e8b0315","observation_id":"7bd6fc1a-2d56-4534-bd6f-3e68b76b371d","resolution":{"observed_at":"2026-08-09T15:43:34.325271Z","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":"2026-08-09T15:43:35.573353Z","title":"G., Naddaf, Y., Veness, J., and Bowling, M","venue":null,"work_id":"c5a44216-889a-458f-b158-e02eacd50112","year":2013},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.330796Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:b8380d6542ad2f443b085a95175c98cd8377254780b35b38124f4e1a4cdc8754","observation_id":"d7c56c27-278b-4d71-ba1a-6368512f5f36","resolution":{"observed_at":"2026-08-09T15:43:35.599870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T15:43:34.334618Z","title":"A study on the plasticity of neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.334618Z"},"links":{"cited_paper":"/paper/2106.00042","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:23979771506b1e60ca6b1a8fdd62f4f82fc319247b90121e3220287e0eed9c84","observation_id":"d8ec8c1a-06f5-47d4-9303-df0d85a88bb0","resolution":{"observed_at":"2026-08-09T15:43:34.334618Z","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":"2026-08-09T15:43:35.561383Z","title":"Adaptive rational activations to boost deep reinforcement learning","venue":null,"work_id":"16c61a48-0d1e-4ca5-b4f9-6ec4df08edb0","year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.338644Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:0b6c5702a62bf39c46dde46839f94d4719da437b935e5cf978e03e0387ece9d7","observation_id":"631f43bd-c3a5-448e-8745-20b6247e5d11","resolution":{"observed_at":"2026-08-09T15:43:35.565391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.06325","last_updated":"2022-05-05T17:16:00Z","snapshot_observed_at":"2026-07-06T11:38:09.580962Z","submitted_at":"2021-08-13T17:33:47Z","title":"Continual Backprop: Stochastic Gradient Descent with Persistent Randomness","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.06325","snapshot_observed_at":"2026-08-09T15:43:34.341918Z","title":"S., and Mahmood, A","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.341918Z"},"links":{"cited_paper":"/paper/2108.06325","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:377909b51e641a9291f996cdf3760b9921c4365d1dbcb0da02e9f36185804559","observation_id":"ba5e11ce-a69d-434d-a3d1-e0573161f456","resolution":{"observed_at":"2026-08-09T15:43:34.341918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.13812","last_updated":"2024-04-09T21:01:56Z","snapshot_observed_at":"2026-08-09T08:28:52.261575Z","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":"2026-08-09T15:43:34.345429Z","title":"F., Rahman, P., Mahmood, A","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.345429Z"},"links":{"cited_paper":"/paper/2306.13812","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:cec851e8fb36ff6d7fa6ff8a1ad150cc250e9e9bcc77c723c03f474e151b4e66","observation_id":"e636f14c-50ac-4ca8-8210-c76517af45c3","resolution":{"observed_at":"2026-08-09T15:43:34.345429Z","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":"2026-08-09T15:43:34.350017Z","title":"F., Lan, Q., Rahman, P., Mahmood, A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.350017Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:ab19fb3faaa8915b0f296503f52800be4229b71d5e308913ea069bb55d18cb39","observation_id":"ac36bb97-ac28-4ce4-a598-ae91e580d4eb","resolution":{"observed_at":"2026-08-09T15:43:34.350017Z","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":"2026-08-09T15:43:34.353187Z","title":"and Mahmood, A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.353187Z"},"links":{"cited_paper":"/paper/2404.00781","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:3010b2b9316a84961165b416ae5ad55d5d79361792152274aa6f91ba83ec746c","observation_id":"719ab7ff-f470-4e6b-9fe1-589468fb6350","resolution":{"observed_at":"2026-08-09T15:43:34.353187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01704","last_updated":"2024-07-01T18:29:29Z","snapshot_observed_at":"2026-08-03T22:09:40.563417Z","submitted_at":"2024-07-01T18:29:29Z","title":"Weight Clipping for Deep Continual and Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01704","snapshot_observed_at":"2026-08-09T15:43:34.356949Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.356949Z"},"links":{"cited_paper":"/paper/2407.01704","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:052971b388f648f14bfbb31ca66bd5561bc3878a7fba2a7e4561fa7e283d6e27","observation_id":"59cbe71f-2a41-4b18-97cc-e65a23ab769e","resolution":{"observed_at":"2026-08-09T15:43:34.356949Z","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":"2026-08-09T15:43:35.542066Z","title":"C., Clopath, C., Busoniu, L., and Pascanu, R","venue":null,"work_id":"6e788000-05fd-45c9-8f0c-4de9ca18c5be","year":2021},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.361125Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:138d0f756896419f515782e8d142b455449862439a499e4f3ae041a88389f115","observation_id":"222fd427-6f10-4c34-a2ae-11423e978b04","resolution":{"observed_at":"2026-08-09T15:43:35.547211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.11818","last_updated":"2022-02-23T23:00:40Z","snapshot_observed_at":"2026-08-07T23:08:05.510879Z","submitted_at":"2022-02-23T23:00:40Z","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.11818","snapshot_observed_at":"2026-08-09T15:43:34.364690Z","title":"and Wagener, N","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.364690Z"},"links":{"cited_paper":"/paper/2202.11818","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:d8dd9a279d66eb0734cd18dee20098d329b1e8a9e0dbfc0a42b5a302dcadde5e","observation_id":"bfddb482-4e1c-4ee8-9666-7e6fecbebe97","resolution":{"observed_at":"2026-08-09T15:43:34.364690Z","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":"2026-08-09T15:43:34.368114Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.368114Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:431579ad61df48d56d7e73cb692422d91fc94332947a43d9c19bfecaad97e598","observation_id":"62f8510a-350b-4516-a144-9a925e2527e1","resolution":{"observed_at":"2026-08-09T15:43:34.368114Z","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":"2026-08-09T15:43:34.371481Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.371481Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:8a9258b92fb88731e8b90f1facb1a15d712e4e8f7d4baffd0adccfb9114a029b","observation_id":"66d0f5c5-de3e-4a4e-a389-32308e446f4a","resolution":{"observed_at":"2026-08-09T15:43:34.371481Z","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":"2026-08-09T15:43:34.374779Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.374779Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:81463dee29fe5b9086df50f1409518ee400a0c13ed64423ebe76d6610589d577","observation_id":"10cdb5e4-a219-4670-96d2-263fe725c82a","resolution":{"observed_at":"2026-08-09T15:43:34.374779Z","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":"2026-08-09T15:43:34.378287Z","title":null,"venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.378287Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:434782ca969476d6460470b509fcef78a2fdf7e7091b6971972c4fe09dc6c007","observation_id":"366522af-9930-4cdd-a890-19e69fedd7a1","resolution":{"observed_at":"2026-08-09T15:43:34.378287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-09T15:43:34.388820Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.388820Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:1e417e1e74bdb6034ff3aa84175dd66d9bf30df47aab037e510e24f5bae0f425","observation_id":"6586a4b5-e16b-4411-8645-6e639211726b","resolution":{"observed_at":"2026-08-09T15:43:34.388820Z","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":"2026-08-09T15:43:34.415899Z","title":"A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.415899Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:d68aec8190e73544ba8746ceecc5e9adac7d083e3daac7671f5032f241884af2","observation_id":"8903ee2d-0243-449a-b18a-94b7ff1c3433","resolution":{"observed_at":"2026-08-09T15:43:34.415899Z","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":"2026-08-09T15:43:34.428389Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.428389Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:31ec1fdb648f3cf1cb8756db981315e3334bd8ea192acadbe895808afe42447f","observation_id":"1e93845d-3d0f-4310-8d25-3ff43c0dea94","resolution":{"observed_at":"2026-08-09T15:43:34.428389Z","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":"2026-08-09T15:43:34.456010Z","title":"and Hertz, J","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.456010Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:94b32cae68634553ad872468a341189153dab97e5f665ae0cf534b3672c0042d","observation_id":"7cb8e0ff-9ee3-49ef-9214-9bcc5248f581","resolution":{"observed_at":"2026-08-09T15:43:34.456010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.14498","last_updated":"2021-10-25T03:10:12Z","snapshot_observed_at":"2026-08-07T21:48:38.523798Z","submitted_at":"2020-10-27T17:55:16Z","title":"Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.14498","snapshot_observed_at":"2026-08-09T15:43:34.479997Z","title":"Implicit under-parameterization inhibits data-efficient deep reinforcement learning","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.479997Z"},"links":{"cited_paper":"/paper/2010.14498","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:1f5e5bd9526c620809d39f26d14383d0273c9baec5bf0f2d34ad8574a19422f0","observation_id":"2b7e8b45-47b3-4ba0-9f99-2c2a4f6f78fa","resolution":{"observed_at":"2026-08-09T15:43:34.479997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.11958","last_updated":"2024-10-24T23:03:41Z","snapshot_observed_at":"2026-08-10T07:10:46.104947Z","submitted_at":"2023-08-23T06:57:05Z","title":"Maintaining Plasticity in Continual Learning via Regenerative Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.11958","snapshot_observed_at":"2026-08-09T15:43:34.502240Z","title":"Maintaining plasticity via regenerative regularization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.502240Z"},"links":{"cited_paper":"/paper/2308.11958","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:786138d7909f50175510d2103a39ac2da7edd20506748618730eebb16433c5f0","observation_id":"aaedbe56-acc7-4844-8859-809c19d6ee50","resolution":{"observed_at":"2026-08-09T15:43:34.502240Z","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":"2026-08-09T15:43:34.527031Z","title":"and Yang, X","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.527031Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:60ba08e49b6faee995619ed13c7eee2d62392a44fae9d09f5188fd0197516b60","observation_id":"648494b9-1e34-41f3-b007-5f13585065b6","resolution":{"observed_at":"2026-08-09T15:43:34.527031Z","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":"2026-08-09T15:43:35.327766Z","title":"Plastic: Improving input and label plasticity for sample efficient reinforcement learning","venue":null,"work_id":"fef418b0-a49c-41d8-a5bf-a8ff22774dde","year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.531116Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:a3fed1568e21cb6495f313c374df22a81e30a3517c252c982f4bef8069d07ec3","observation_id":"9a96f114-a7d1-4536-a531-64b4dd06cb46","resolution":{"observed_at":"2026-08-09T15:43:35.447039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T15:43:35.163089Z","title":"Slow and steady wins the race: Maintaining plasticity with hare and tortoise networks","venue":null,"work_id":"deeb04a3-d7b3-4fb1-93fb-ef9727d21f60","year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.538552Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:d888590e40c6c8e77ca7c2fc249f6d1c24db525ea9967f62ee3adc37d7462b42","observation_id":"cfc5c816-3ef6-438a-8a13-e129b1e4b6a0","resolution":{"observed_at":"2026-08-09T15:43:35.230950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T15:43:35.151509Z","title":null,"venue":null,"work_id":"3edb10fc-a84b-45f0-985a-815683f692e4","year":2023},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.542484Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:530ca0a0095380a935660810e558d050ef1c38028793c163864d19f3445355c3","observation_id":"6654c213-8e89-4234-a689-0a8424b323bc","resolution":{"observed_at":"2026-08-09T15:43:35.155913Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20634","last_updated":"2024-10-27T23:38:06Z","snapshot_observed_at":"2026-08-07T10:53:37.661864Z","submitted_at":"2024-10-27T23:38:06Z","title":"Plastic Learning with Deep Fourier Features","version":1},"cited_work":{"arxiv_id":"2410.20634","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.20634","snapshot_observed_at":"2026-08-09T15:43:34.691133Z","title":"Plastic Learning with Deep Fourier Features","venue":"cs.LG","work_id":"f95c5542-4bb8-4243-a052-8a6261754d85","year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.545987Z"},"links":{"cited_paper":"/paper/2410.20634","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:14eff3be777c0fae09b799acfd3872319293201823517382ca3ce884c0256d4d","observation_id":"92a6d55c-6656-4f48-a72a-2d752f79babb","resolution":{"observed_at":"2026-08-09T15:43:34.734995Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T15:43:35.138627Z","title":"Drop-activation: implicit parameter reduction and harmonious regularization","venue":null,"work_id":"616aeca4-8d94-4e51-8449-3711ee5638ad","year":2021},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.549795Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:9c5708c83fb70d7a16a4dc4ad984dc171e127f453a7378c49e1d01e3af08953b","observation_id":"937f3492-6cea-4029-9357-d2a6bf3fe198","resolution":{"observed_at":"2026-08-09T15:43:35.143619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.09560","last_updated":"2022-05-04T14:50:26Z","snapshot_observed_at":"2026-08-03T20:56:03.618011Z","submitted_at":"2022-04-20T15:55:15Z","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.09560","snapshot_observed_at":"2026-08-09T15:43:34.553252Z","title":"Understanding and preventing capacity loss in reinforcement learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.553252Z"},"links":{"cited_paper":"/paper/2204.09560","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:1a8866608fcd94f3d07110306970b75cee18d14735f29f329463cd3ac9c0e4aa","observation_id":"846107ef-1787-448e-8112-22a7695d7451","resolution":{"observed_at":"2026-08-09T15:43:34.553252Z","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":"2026-08-09T15:43:34.556961Z","title":"A., Pascanu, R., and Dabney, W","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.556961Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:8d8b8321f76bb6347372bd63ee9478a2e5cf36f29ee107e901631e6fb2d71ece","observation_id":"1d0f5d35-c676-4ad9-913e-773c99db71d2","resolution":{"observed_at":"2026-08-09T15:43:34.556961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18762","last_updated":"2024-02-29T00:02:33Z","snapshot_observed_at":"2026-08-10T04:15:31.920517Z","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":"2026-08-09T15:43:34.560214Z","title":"Disentangling the causes of plasticity loss in neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.560214Z"},"links":{"cited_paper":"/paper/2402.18762","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:1f152bbb381befe3a8fe61ec84beb9c51445d732130476820321c4499368c98b","observation_id":"b063ca0c-b9a7-47ba-bce0-65a0ca1973ba","resolution":{"observed_at":"2026-08-09T15:43:34.560214Z","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":"2026-08-09T15:43:34.564384Z","title":"Revisiting plasticity in visual reinforcement learning: Data, modules and training stages","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.564384Z"},"links":{"cited_paper":"/paper/2310.07418","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:38803686596ae0114555f38d2b610d4c9cb65d2bcabe1b5ed2ea4b0b0fb4e9f6","observation_id":"17acfa86-37af-40d2-b9ad-bcc2a8607746","resolution":{"observed_at":"2026-08-09T15:43:34.564384Z","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":"2026-08-09T15:43:35.084482Z","title":"I., Farajtabar, M., and Ghasemzadeh, H","venue":null,"work_id":"997e3166-0de2-498f-95f3-af54c7a0eb99","year":2020},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.567846Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:b9653c8fcdd00334dc473d9f06bd730ca6035b735277b11079beef4723e731ac","observation_id":"18633f36-50bc-4c57-a909-adda9781c79e","resolution":{"observed_at":"2026-08-09T15:43:35.124008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T15:43:34.571180Z","title":"A., Veness, J., Bellemare, M","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.571180Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:238fdeef046f1104ec446a1d3c0d93085e8094147cd044babcdc2578b7cccbd6","observation_id":"15d38b12-ee4f-433f-8bd2-7d9ae83c612c","resolution":{"observed_at":"2026-08-09T15:43:34.571180Z","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":"2026-08-09T15:43:34.574162Z","title":"The primacy bias in deep reinforcement learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.574162Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:4f995a7593a9f03ce8ca1054163cfb6f39bf3438e8a90a7f581067f160349b27","observation_id":"39769f41-db12-4199-8337-f482059cfbba","resolution":{"observed_at":"2026-08-09T15:43:34.574162Z","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":"2026-08-09T15:43:35.000298Z","title":"Deep reinforcement learning with plasticity injection","venue":null,"work_id":"f99f7076-f5e8-4053-af94-c2ba1533ef00","year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.577927Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:3842a8ee5e8b60195ef1c3977e69436898470fca61769de994f29b76acf04977","observation_id":"45daac46-112a-4ee2-b8cc-2f27a9e49a47","resolution":{"observed_at":"2026-08-09T15:43:35.034555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04484","last_updated":"2024-06-06T20:12:55Z","snapshot_observed_at":"2026-07-06T18:26:50.515452Z","submitted_at":"2024-06-06T20:12:55Z","title":"Step Out and Seek Around: On Warm-Start Training with Incremental Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04484","snapshot_observed_at":"2026-08-09T15:43:34.581763Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.581763Z"},"links":{"cited_paper":"/paper/2406.04484","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:d30841cf64ad7dbeb8aaa90bf29dcf1d8c5ebc5032369c127e4ebfbbf961d266","observation_id":"cf5c8228-353b-44f2-aaf2-d37ce479591b","resolution":{"observed_at":"2026-08-09T15:43:34.581763Z","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":"2026-08-09T15:43:34.919722Z","title":"Dash: Warm-starting neural network training in stationary settings without loss of plasticity","venue":null,"work_id":"8116a695-c188-45ce-be24-502c3e84a506","year":2024},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.585678Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:2b9c271f8d77aaac8e513b6cd3e8340d6e02a569db457fbe33b2751660796f94","observation_id":"8df2e2bc-bb18-4f6c-ad70-fd28208d02d4","resolution":{"observed_at":"2026-08-09T15:43:34.953570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-09T15:43:34.589492Z","title":"and Zisserman, A","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.589492Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:847a75e84d057c33a11873b6d73c904f95dd8eaffbc05ec06b19ee869790d419","observation_id":"26f930c8-cc32-4008-919b-f87c1d51278a","resolution":{"observed_at":"2026-08-09T15:43:34.589492Z","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":"2026-08-09T15:43:34.593859Z","title":"S., and Evci, U","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.593859Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:d9ef4258d5e175fdfc457fe08e0838f3f2cd8994f4341744acb7d527374a784e","observation_id":"7b34efb7-7839-4a2c-b064-c147a618f7ca","resolution":{"observed_at":"2026-08-09T15:43:34.593859Z","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":"2026-08-09T15:43:34.597556Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.597556Z"},"links":{"citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:df7d1e9574f1bf139f9061a17f340a40cce74c875cc34dbd578ff8edbd654ea1","observation_id":"bab6d2ae-07bf-4af4-b538-26570b20029f","resolution":{"observed_at":"2026-08-09T15:43:34.597556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1505.00853","last_updated":"2015-11-27T06:58:14Z","snapshot_observed_at":"2026-07-06T04:16:54.272660Z","submitted_at":"2015-05-05T01:16:39Z","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.00853","snapshot_observed_at":"2026-08-09T15:43:34.601190Z","title":"Empirical evaluation of rectified activations in convolutional network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-09T15:43:34.601190Z"},"links":{"cited_paper":"/paper/1505.00853","citing_paper":"/paper/2502.01342"},"observation_digest":"sha256:1f593aaa305e0957106c9e0ac5faf8d0110877b97f945b654c8d338b985ec4c5","observation_id":"e7d003db-12f5-4269-9ea6-68ae736aa269","resolution":{"observed_at":"2026-08-09T15:43:34.601190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.01342","last_updated":"2025-06-15T08:12:44Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T04:16:28.444262Z","submitted_at":"2025-02-03T13:34:53Z","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":33,"verified_exact":1,"verified_fuzzy":11},"total_outbound_references":45},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2502.01342."}