{"as_of":"2026-08-09T11:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0148584dbb9973f9a08aae67f548e6c8147c26cb4a09b409bb0ec94b389bc341","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T10:21:45.248435Z","state":"measured"},{"denominator":62,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":62,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T04:05:50.121652Z","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":"2026-06-30T11:04:37.510167Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"cited_work":{"arxiv_id":"2508.00212","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.00212","snapshot_observed_at":"2026-06-30T11:04:37.510167Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","venue":null,"work_id":"49d29979-121d-49fa-bb9c-aa6474007480","year":2025},"citing_paper":{"arxiv_id":"2604.27063","last_updated":"2026-04-29T18:01:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-29T18:01:13Z","title":"Learning to Forget: Continual Learning with Adaptive Weight Decay","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-05-07T10:36:32.096050Z"},"links":{"cited_paper":"/paper/2508.00212","citing_paper":"/paper/2604.27063"},"observation_digest":"sha256:487e240d1d847a5a646e05ef29dfdb6abb0fa73d0f0a855cf42268a3bf1d1f10","observation_id":"5791c06e-ad8a-41a1-baca-9a6b7652fb7a","resolution":{"observed_at":"2026-05-12T09:31:26.860362Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"cited_work":{"arxiv_id":"2508.00212","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.00212","snapshot_observed_at":"2026-06-30T11:04:37.510167Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","venue":null,"work_id":"49d29979-121d-49fa-bb9c-aa6474007480","year":2025},"citing_paper":{"arxiv_id":"2605.06834","last_updated":"2026-05-07T18:42:22Z","snapshot_observed_at":"2026-07-31T23:01:48.891332Z","submitted_at":"2026-05-07T18:42:22Z","title":"Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-05-11T00:54:07.569467Z"},"links":{"cited_paper":"/paper/2508.00212","citing_paper":"/paper/2605.06834"},"observation_digest":"sha256:f57d2f7078834d315118fbaf8950953dcb3557a0fac42d81e981d532b6845f58","observation_id":"0b262784-411f-4c3b-9936-b1619af85230","resolution":{"observed_at":"2026-05-11T05:00:56.873138Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"cited_work":{"arxiv_id":"2508.00212","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.00212","snapshot_observed_at":"2026-06-30T11:04:37.510167Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","venue":null,"work_id":"49d29979-121d-49fa-bb9c-aa6474007480","year":2025},"citing_paper":{"arxiv_id":"2606.28347","last_updated":"2026-06-02T17:59:25Z","snapshot_observed_at":"2026-07-07T00:02:29.000757Z","submitted_at":"2026-06-02T17:59:25Z","title":"Agentic Safety is an Epistemic Property, Not a Behavioral One","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-06-30T11:02:47.824120Z"},"links":{"cited_paper":"/paper/2508.00212","citing_paper":"/paper/2606.28347"},"observation_digest":"sha256:c7d506c41138eb7893d2895157340e940fb972c16c8cd88ab0a7938b583ab4b7","observation_id":"f330aa4a-24bd-4d1b-bbc6-8793682b6274","resolution":{"observed_at":"2026-06-30T11:04:37.511527Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.00212","snapshot_observed_at":"2026-07-31T04:05:50.121652Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks.arXiv preprint arXiv:2508.00212,","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":2015,"source":"pdf_text","source_observed_at":"2026-07-31T04:05:50.121652Z"},"links":{"cited_paper":"/paper/2508.00212","citing_paper":"/paper/2607.24996"},"observation_digest":"sha256:c0299efcf08ce658c918772d4993b680a2b166294477e5a853af0f49ce75ba23","observation_id":"9dae1e63-32cb-44b6-88f2-60269538da0d","resolution":{"observed_at":"2026-07-31T04:05:50.121652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2508.00212/citation-record","integrity":"/paper/2508.00212/integrity","json":"/paper/2508.00212/citation-record.json","paper":"/paper/2508.00212"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T10:21:45.851312Z","title":null,"venue":null,"work_id":"924db4d1-ff3f-4df3-a3cd-84f360dfc8cd","year":2023},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.092919Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:c90cd9816fc47e91ce97e92e54086810c7b56c433e40b105caec925ff0e75142","observation_id":"4c578abc-b410-4f3a-80ea-9c07366fbc64","resolution":{"observed_at":"2026-08-06T10:21:45.854603Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.00267","last_updated":"2021-09-01T09:25:57Z","snapshot_observed_at":"2026-07-30T20:14:06.868858Z","submitted_at":"2021-09-01T09:25:57Z","title":"The Impact of Reinitialization on Generalization in Convolutional Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.00267","snapshot_observed_at":"2026-08-06T10:21:45.096030Z","title":"The impact of reinitialization on generalization in convolutional neural networks, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.096030Z"},"links":{"cited_paper":"/paper/2109.00267","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:db11cccca23f31f7359f186b2a1f70834a2387ce6503a7cfa2a19e3b8304f7dd","observation_id":"ea127b4d-640d-4f89-925d-53486d92eac3","resolution":{"observed_at":"2026-08-06T10:21:45.096030Z","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":"2026-08-06T10:21:45.099355Z","title":"On warm-starting neural network training","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.099355Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:50741f3ecb591f9a297ce0bc48a59ac809be8574a14add3ccbb0c0333ad7ccb9","observation_id":"8e412cd1-64f8-4fda-8def-fbbe7f51d3c6","resolution":{"observed_at":"2026-08-06T10:21:45.099355Z","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":"2026-08-06T10:21:45.838676Z","title":"A better match for drivers and riders: Reinforcement learning at lyft","venue":null,"work_id":"e217bbea-4fa8-4410-9c9e-3e91a06d584b","year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.102213Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:e2acd3e092a1d8e8e0e183c2c6c77661dfcea18793495a03eecc866a6167ccdc","observation_id":"cdd3461d-6ae6-4437-be91-155fa602cca0","resolution":{"observed_at":"2026-08-06T10:21:45.841554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.106051Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.106051Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:2a7eb07abc2fbe927a03e65bb6b6562081300dd023b67dfcc86a083dc770a669","observation_id":"62a6fd46-57f9-4aa9-bf0a-bd35a1dc89b0","resolution":{"observed_at":"2026-08-06T10:21:45.106051Z","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":"2026-08-06T10:21:45.830786Z","title":"What is the state of neural network pruning? Proceedings of machine learning and systems, 2: 0 129--146, 2020","venue":null,"work_id":"6fc8f5ed-7041-48cd-86eb-b94a6ee0e533","year":2020},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.109194Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:3a59308bb900e9c36ede0af104022cb9e3b5cd689df3ce69a27126c4dc8248d5","observation_id":"b18bf3e0-6b4c-45b7-bda0-497f0ea1c9e2","resolution":{"observed_at":"2026-08-06T10:21:45.833846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.823271Z","title":"Dokania, Thalaiyasingam Ajanthan, and Philip H","venue":null,"work_id":"463f51e9-0035-4507-9fec-40c731eb2d18","year":2018},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.112045Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:765869aa9432cee2aea0540149c0cd05a6742c83682ddb74607a433a11a5f8c8","observation_id":"5a00161e-9de9-4b81-b45c-fff6db929f69","resolution":{"observed_at":"2026-08-06T10:21:45.825924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-06T10:21:45.114488Z","title":"BERT: pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.114488Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:c4256d33b803df50a7fead14ccd6a31b8226817363ad56e0f36507e17406e536","observation_id":"e9154600-d5ba-4061-af3f-90ae9c2b388f","resolution":{"observed_at":"2026-08-06T10:21:45.114488Z","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":"2026-08-06T10:21:45.815511Z","title":"The interplay of search and gradient descent in semi-stationary learning problems","venue":null,"work_id":"14602f58-ffb6-459b-a1d5-e605f30178f8","year":2020},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.117366Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:b64216f14424d084a0ed7e3ffc5a46c5aa0b30e2a5f9978ce66f271f3251bcea","observation_id":"7800c408-5e63-4930-867d-578cd14409f0","resolution":{"observed_at":"2026-08-06T10:21:45.818335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.119866Z","title":"Continual B ackprop: Stochastic gradient descent with persistent randomness, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.119866Z"},"links":{"cited_paper":"/paper/2108.06325","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:cafce0b4b458496c394ec6c6ce72fb3b7abdf8bc2637488d1648131cede7fb0f","observation_id":"3b27e44f-831c-4928-a701-4a6c52aa74ae","resolution":{"observed_at":"2026-08-06T10:21:45.119866Z","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":"2026-08-06T10:21:45.122649Z","title":"Loss of plasticity in deep continual learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.122649Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:5204722ee7ca7608f09ab583f9de23e5588a83090be856f79180579ae19fd3d2","observation_id":"8cda5591-b39b-40af-b01a-7642655639df","resolution":{"observed_at":"2026-08-06T10:21:45.122649Z","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":"2026-08-06T10:21:45.125179Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.125179Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:3294b65e2e85ea0e6923408d7b009462d08a11217dcc7f548ed7db6914532f33","observation_id":"2e8717b9-fd6d-4781-a3aa-d0b62c9451b6","resolution":{"observed_at":"2026-08-06T10:21:45.125179Z","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":"2026-08-06T10:21:45.799852Z","title":"Rupam Mahmood","venue":null,"work_id":"f6724b4d-e4ed-47a3-a90c-f3a464310326","year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.128616Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:e44192dca9d52ed6559b5db9f5a02b1ac6eabb753a8cdfc2c62d980ca99661a3","observation_id":"e19ff38c-6f47-4584-a30f-275982e371a3","resolution":{"observed_at":"2026-08-06T10:21:45.802428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.791003Z","title":"Rupam Mahmood","venue":null,"work_id":"9273cd1b-40dc-47a4-b4ab-79e1272cb377","year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.130946Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:16694f5dc64eff19215dd496d87d4acfb830fc304e4d57b429c6cfc766bf407c","observation_id":"db43d5a7-2e48-437a-98fd-9d7422251f3f","resolution":{"observed_at":"2026-08-06T10:21:45.794721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.782352Z","title":"Rigging the lottery: Making all tickets winners","venue":null,"work_id":"18cce8c7-72ee-4cfb-90a9-2a45e1c66c5f","year":2020},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.133435Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:452f0ded31508b967d4d90a5961ed33f99742ac80b03389b699bd15e5352c5ad","observation_id":"7732c295-014d-4bdb-ad12-7d24888aaa2a","resolution":{"observed_at":"2026-08-06T10:21:45.785102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.773665Z","title":"Depgraph: Towards any structural pruning","venue":null,"work_id":"3752ccd3-e4f9-47ba-8acc-e24d6c83d783","year":2023},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.135952Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:91b367c0a8ba1b7f953056a460139300000f1e6ef8e5a66f921a06d4b7f03881","observation_id":"bf0323c0-e8b9-40e8-8cea-3b483583fdde","resolution":{"observed_at":"2026-08-06T10:21:45.776611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.138459Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.138459Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:0e3849c777bba40de8ca364b7e55260b88e18663351280bc2509d58b9dc1d9a2","observation_id":"1c17ebd9-9540-4272-9334-d301726a10bf","resolution":{"observed_at":"2026-08-06T10:21:45.138459Z","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":"2026-08-06T10:21:45.762299Z","title":null,"venue":null,"work_id":"581a87c9-aeae-4609-95dd-dc8159cf8c77","year":1999},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.141020Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:d42f6dda25843e414e4641c5154663dfb68a416ff074bbb674173da0bae55b9c","observation_id":"6d32ec26-21db-4014-bd29-fdf9c948a3a2","resolution":{"observed_at":"2026-08-06T10:21:45.764846Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.143595Z","title":"Understanding the difficulty of training deep feedforward neural networks","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.143595Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:5424f2f3e47c8cddc0efe8d3f73ffa716554c2db0407fc30e3aca768db974d6a","observation_id":"c74bd31d-7483-45e7-80f5-53a6fefbdc30","resolution":{"observed_at":"2026-08-06T10:21:45.143595Z","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":"2026-08-06T10:21:45.750640Z","title":"Deep learning, volume 1","venue":null,"work_id":"9c4ca2c1-51be-4565-b11b-3f72855c8cc4","year":2016},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.146224Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:c476a9156bda50177ae238dcc4db17508f85e3ee6c367c5e899f920a0ee59d5e","observation_id":"8e80cff2-f52f-4e62-ab1b-c432dd781be2","resolution":{"observed_at":"2026-08-06T10:21:45.753256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6211","last_updated":"2015-03-04T01:43:31Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T06:31:41Z","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6211","snapshot_observed_at":"2026-08-06T10:21:45.148655Z","title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.148655Z"},"links":{"cited_paper":"/paper/1312.6211","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:2c18dccca42269585956e5f4d07d4b51d36fde8c023801bba305bbafea716dfb","observation_id":"02e0f028-d303-4736-8852-5314c461eb5c","resolution":{"observed_at":"2026-08-06T10:21:45.148655Z","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":"2026-08-06T10:21:45.742841Z","title":"Taylor, Mykola Pechenizkiy, and Decebal Constantin Mocanu","venue":null,"work_id":"80bfa414-aa1f-4202-b9e0-76b5bf19a0c0","year":2023},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.151514Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:db37d4101b749abbd22f58dd11db3d6405dd1c030bf248cb2b6b20689b2568d2","observation_id":"0e59d9b3-f432-4ea8-8beb-1dd262e097a6","resolution":{"observed_at":"2026-08-06T10:21:45.745572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.154076Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.154076Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:e53a26a3bb73523a5d5e42cb7bbda45a89f60ed4e94c46391f6fbeb8e3ffd4aa","observation_id":"2d3c7edc-9e26-4c09-8b8c-9e62d59dd397","resolution":{"observed_at":"2026-08-06T10:21:45.154076Z","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":"2026-08-06T10:21:45.730973Z","title":"Gvfs in the real world: making predictions online for water treatment","venue":null,"work_id":"b26368e1-a6c0-43e1-aa55-eacd6cf6086b","year":2023},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.156545Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:43e707e32360e6df9004a432f52a91ee1e504683ce06dbf60ba6b5b4515af81c","observation_id":"fe0352eb-22ea-402d-b2b3-b620923c6a57","resolution":{"observed_at":"2026-08-06T10:21:45.733748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.723252Z","title":null,"venue":null,"work_id":"42c368b9-32cf-4f2e-a6ac-9e63050b1512","year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.159165Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:84c18d3c06216fc640e1aedfe36ecc9ce7e21cd58035f0c4ec22825c179f0adc","observation_id":"503091b5-bf0a-4bc3-84bb-06b5d9bf0c29","resolution":{"observed_at":"2026-08-06T10:21:45.725911Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.714304Z","title":"Spine dynamics in the brain, mental disorders and artificial neural networks","venue":null,"work_id":"1b775f9e-349b-41cc-9245-3778e1504a76","year":2021},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.162369Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:59266f89a7c24eff93a2ccd57c7ec8c175f29f0f4cc784a1a3a9124753f67337","observation_id":"66b033b3-1922-4de0-9a0d-74250b533f57","resolution":{"observed_at":"2026-08-06T10:21:45.717974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.706414Z","title":"Learning multiple layers of features from tiny images, 2009","venue":null,"work_id":"9ee0f2f7-6a7d-478d-b22c-ba8740128992","year":2009},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.164688Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:3f9abfeba6d2d94a821a608a691ed3cb58fa4c4f872ae61561d76f168ddc8416","observation_id":"1a3217b8-f182-44c0-8412-662800cd3f94","resolution":{"observed_at":"2026-08-06T10:21:45.709527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.698567Z","title":"Implicit under-parameterization inhibits data-efficient deep reinforcement learning","venue":null,"work_id":"9b20bad4-f8a9-4651-a3fa-c1b44c564473","year":2021},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.167321Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:4e17ef18b3eb08b3b85111e4c0999b258a20fc4ba5a57a2ca359585de848ab45","observation_id":"a452aa75-0ca3-4e74-85f1-e04310a3171e","resolution":{"observed_at":"2026-08-06T10:21:45.701298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.691396Z","title":"Maintaining plasticity in continual learning via regenerative regularization","venue":null,"work_id":"5d83a54a-7423-41dc-8ef0-3157b65f96fc","year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.169938Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:5e912bfd23b551cf1e6f30cf636d96a8de029726f6d5c30ec5342f2e3b8f7708","observation_id":"6e10ade9-dd40-4177-b652-4983357ea552","resolution":{"observed_at":"2026-08-06T10:21:45.694070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.683157Z","title":"Plastic: Improving input and label plasticity for sample efficient reinforcement learning","venue":null,"work_id":"553815bd-913d-4b0a-802c-f839bda3a14a","year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.172363Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:3584055cd39558fd7ad21322de482f108be7e55ee747246e4fd5fb69c8c4d058","observation_id":"82462293-120b-4dd6-ad1c-315c05e329d2","resolution":{"observed_at":"2026-08-06T10:21:45.686714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.674871Z","title":"Slow and steady wins the race: Maintaining plasticity with hare and tortoise networks","venue":null,"work_id":"82a39024-c628-411e-9ba5-a82d2926b3b9","year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.175202Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:7da739f6894fb57966e8867b40e205da6d69a40a4c355a1fb59b61e2eb287109","observation_id":"33c6cdf5-9be9-4604-b2d3-9adcf5ba6042","resolution":{"observed_at":"2026-08-06T10:21:45.677960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06811","last_updated":"2024-10-27T23:45:38Z","snapshot_observed_at":"2026-07-06T18:28:33.795339Z","submitted_at":"2024-06-10T21:34:43Z","title":"Learning Continually by Spectral Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06811","snapshot_observed_at":"2026-08-06T10:21:45.177682Z","title":"Learning continually by spectral regularization, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.177682Z"},"links":{"cited_paper":"/paper/2406.06811","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:a706e436fd8681d2c6d82e936bd1e99ac07b9c4d865fae57128ebbe66ab9931a","observation_id":"10889e72-1624-4875-b87d-730575acaf2f","resolution":{"observed_at":"2026-08-06T10:21:45.177682Z","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":"2026-08-06T10:21:45.180511Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.180511Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:e1c4920489118bdb39a4adebe959fbe6b19d06356944c5a5052e60077b7464e5","observation_id":"4bf80d93-8bda-45c8-b285-08696bbda4f3","resolution":{"observed_at":"2026-08-06T10:21:45.180511Z","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":"2026-08-06T10:21:45.662902Z","title":"Understanding and preventing capacity loss in reinforcement learning","venue":null,"work_id":"8c27c4e5-0ec4-4c98-bfa4-bd54b3f53a5f","year":2022},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.182940Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:b01942f17701f91dc0d696b44bb96f9cfb1ada51171116b19fccc2347e661a6e","observation_id":"20d9396a-6aaf-4230-a521-5ad9e9a3fbad","resolution":{"observed_at":"2026-08-06T10:21:45.665944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.186100Z","title":"Understanding plasticity in neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.186100Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:67cf8be69f1a442649419bb67203a2cbe960eac9ea4a3d1f82bcdf16ccdf5680","observation_id":"5d1d9a21-b238-4c08-9f1f-4d0a26c5d1d9","resolution":{"observed_at":"2026-08-06T10:21:45.186100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01800","last_updated":"2024-07-01T20:58:01Z","snapshot_observed_at":"2026-08-04T16:00:17.686427Z","submitted_at":"2024-07-01T20:58:01Z","title":"Normalization and effective learning rates in reinforcement learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01800","snapshot_observed_at":"2026-08-06T10:21:45.188704Z","title":"Normalization and effective learning rates in reinforcement learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.188704Z"},"links":{"cited_paper":"/paper/2407.01800","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:6956abfca886ee60b503829181e87dd8c311a7b62f5cd92f71ed8776fba87769","observation_id":"4cfc317f-fa84-4864-946b-742968a055fd","resolution":{"observed_at":"2026-08-06T10:21:45.188704Z","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":"2026-08-06T10:21:45.650921Z","title":"Representation search through generate and test","venue":null,"work_id":"d1a23e73-5df3-4559-b1ce-7d32f533509e","year":2013},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.191476Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:b0ae9143d9959791648e460df721525292df646def5821e90a265a1d2f1048c8","observation_id":"cd23a209-dfce-4265-98dd-66788f93280d","resolution":{"observed_at":"2026-08-06T10:21:45.653656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.642025Z","title":"Torchvision: Pytorch's computer vision library","venue":null,"work_id":"aeb1846c-c129-4d76-867a-d20f2ef25a6b","year":2016},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.194536Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:0d56856e0bbf8927e5a17b7aab1b6ac6222b532789da3840543d6ac1323ae487","observation_id":"a1810806-83f8-4d57-bc18-9034436c0a49","resolution":{"observed_at":"2026-08-06T10:21:45.644668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.634611Z","title":"Catastrophic interference in connectionist networks: The sequential learning problem","venue":null,"work_id":"a6434471-ca4c-41cc-91de-caa71cd28727","year":1989},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.197027Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:18828bfae9c6be2ccbb3646f5d272cf4392806791d23d9c3ed83fbd63566a5b2","observation_id":"a87ad04e-f103-4d56-8cee-8fec0f3ffffc","resolution":{"observed_at":"2026-08-06T10:21:45.637401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.627336Z","title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science","venue":null,"work_id":"2bda0b5b-d59f-448a-b8b8-ef9989292d50","year":2018},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.200231Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:a4dd7387eb970904f9c181a054e38040acdf76a1bbc334277bc68459c2461680","observation_id":"4d1b5066-4901-4da7-a689-eafccd89b4e1","resolution":{"observed_at":"2026-08-06T10:21:45.630232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.202642Z","title":"The primacy bias in deep reinforcement learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.202642Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:943b4dad66bf3370e2587b0b685d602ac0182bdf159856102f1ac77e232cdcb4","observation_id":"d846b25d-e5a4-48d2-a81d-7d9a326af4f0","resolution":{"observed_at":"2026-08-06T10:21:45.202642Z","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":"2026-08-06T10:21:45.615972Z","title":"Deep reinforcement learning with plasticity injection","venue":null,"work_id":"a3cce0ea-8d66-4d01-b49e-a8c48e392545","year":2023},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.205116Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:efc924fba6df3f75301f810a0a75d3a52771468c6cf0478e505d7946a54f0cb0","observation_id":"01f39a88-bd60-4faf-9074-49032dff16e2","resolution":{"observed_at":"2026-08-06T10:21:45.618700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T10:21:45.207698Z","title":"GPT -4 technical report, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.207698Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:7bdde050ea4f25ffe95254e1fc31592067b35522a82df2dd9d376f88b602052c","observation_id":"36c5372f-0bad-48a7-9ea5-d1f17a43b967","resolution":{"observed_at":"2026-08-06T10:21:45.207698Z","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":"2026-08-06T10:21:45.608372Z","title":"Toward generate-and-test algorithms for continual feature discovery","venue":null,"work_id":"94ad7f8a-4446-4d26-9279-517618af92aa","year":2021},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.210210Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:454d0e86df89cd95e60ac736eff548c08783381406b3ef9e11c8d0412c6a373e","observation_id":"b3a73095-a7cc-4b9f-b589-a2aa685807d4","resolution":{"observed_at":"2026-08-06T10:21:45.611443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.599399Z","title":"i C a RL : Incremental classifier and representation learning","venue":null,"work_id":"e7a59e20-ae3b-4378-a93e-d1c8454a2a36","year":2001},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.212611Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:c3e9f0cdfa3c33bd8e508e73058d15b725d88a6b129260d6ea2243296508aa5b","observation_id":"c1032d12-2b57-4813-bb51-6a391ebb60b6","resolution":{"observed_at":"2026-08-06T10:21:45.602880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.591365Z","title":"The dormant neuron phenomenon in deep reinforcement learning","venue":null,"work_id":"38b53b31-399f-4a32-95ab-f7508c96ae94","year":2023},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.215043Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:bf4ae4e0655e0cfeb1b82614d6854e30c7d3e363eda81b1fabbe022940334fa7","observation_id":"0c4a401d-db25-48b2-ad6d-5c44e8157cb9","resolution":{"observed_at":"2026-08-06T10:21:45.594104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19206","last_updated":"2025-03-28T02:10:05Z","snapshot_observed_at":"2026-08-07T16:39:47.680195Z","submitted_at":"2025-03-24T23:11:56Z","title":"Overtrained Language Models Are Harder to Fine-Tune","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19206","snapshot_observed_at":"2026-08-06T10:21:45.218106Z","title":"Overtrained language models are harder to fine-tune, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.218106Z"},"links":{"cited_paper":"/paper/2503.19206","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:4630d9e0512c5819bab568c5bc69de2a1216513d0eaab5980bebc36a18145512","observation_id":"91a537ed-3b3d-4a52-8761-96514c953cfc","resolution":{"observed_at":"2026-08-06T10:21:45.218106Z","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":"2026-08-06T10:21:45.582443Z","title":"Sutton and Shibhansh Dohare","venue":null,"work_id":"f45318e4-7717-4b61-9e76-81176a3e9892","year":2022},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.221527Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:f9f19aaac1a90ab815c78e8921c73ba30c62e1445450b40869ed22ca61a48926","observation_id":"e01a76e8-edc5-4ea8-aff6-852174a1d24a","resolution":{"observed_at":"2026-08-06T10:21:45.585328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T10:21:45.466425Z","title":"Knowledge evolution in neural networks","venue":null,"work_id":"9332ef99-7273-4c63-9ef6-d46e20f5dbf6","year":2021},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.223861Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:9731040e8cc1ce289ff209b5725601db37ba18a374d54a074f07a4b627ff871a","observation_id":"a6789748-d0bf-4f29-88e3-e56113c425f1","resolution":{"observed_at":"2026-08-06T10:21:45.469888Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.226330Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.226330Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:f610c7a2fead91b8ab88521a2bad73206573eb7cfa420a45fc37724448a9156b","observation_id":"53d57cd9-205e-4bd2-a316-68a824ccf2da","resolution":{"observed_at":"2026-08-06T10:21:45.226330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.21147","last_updated":"2025-02-28T15:28:12Z","snapshot_observed_at":"2026-08-09T08:48:09.229992Z","submitted_at":"2025-02-28T15:28:12Z","title":"Same accuracy, twice as fast: continuous training surpasses retraining from scratch","version":1},"cited_work":{"arxiv_id":"2502.21147","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.21147","snapshot_observed_at":"2026-08-06T10:21:45.271468Z","title":"Same accuracy, twice as fast: continuous training surpasses retraining from scratch","venue":"cs.LG","work_id":"db343132-f110-423c-8255-2d7fded2c4b1","year":2025},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.228697Z"},"links":{"cited_paper":"/paper/2502.21147","citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:29b32ca74d2624e8d0c19c5f87265c38d4318580b341cdc42036c7da7d1ce942","observation_id":"f5334d0e-f61c-4188-b892-26e23efbae53","resolution":{"observed_at":"2026-08-06T10:21:45.276608Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.570294Z","title":"I Can't Believe It's Not Better! - Understanding Deep Learning Through Empirical Falsification","venue":null,"work_id":"3937c8b6-1e83-4ff8-9626-fffe968bb250","year":2022},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.231372Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:43aa668464442970ddcfcd1e3131f66590b2f3a6a4d8024d567ed61f504da962","observation_id":"081029a2-e636-4791-9c07-a3e8668ea3f3","resolution":{"observed_at":"2026-08-06T10:21:45.573410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.560616Z","title":"Continual learning through synaptic intelligence","venue":null,"work_id":"a188baf0-e9bd-42ae-956a-7542c5b3dad7","year":2017},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.233753Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:aedd021710b121dd1770d52eb2f47b3a241d034d96133aa23a5e4ac323e1e070","observation_id":"178d0201-e36e-48c0-a025-586c8ce87758","resolution":{"observed_at":"2026-08-06T10:21:45.565049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.552295Z","title":"Fortuitous forgetting in connectionist networks","venue":null,"work_id":"253d4b1d-e7f8-438e-8f6d-b73d1397102c","year":2022},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.236849Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:92607e02d020de32b24148f0a843eccf47b9f3ced369a34251a7c23ce6a80602","observation_id":"e29b39b8-aec7-494b-a31a-99e106e5d324","resolution":{"observed_at":"2026-08-06T10:21:45.555371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T10:21:45.239441Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.239441Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:d04625d0df4b1079abe9ef27ff5e46aa63b1b2aa8fec042413d05f9b3ffe3d16","observation_id":"7c4a46ef-04ef-4ea9-8d19-a5317a14fec3","resolution":{"observed_at":"2026-08-06T10:21:45.239441Z","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":"2026-08-06T10:21:45.242537Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.242537Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:b0c9dafc61ddc612860ee1f24b1fb65d6ce795879dbed57813143b4d6941f762","observation_id":"80d1d688-4636-4b34-a642-ee2667518d26","resolution":{"observed_at":"2026-08-06T10:21:45.242537Z","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":"2026-08-06T10:21:45.245779Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.245779Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:b9ef9a44dd3c22a333ce3154c58f3b1ffd6e1d5c38d4699b4c60175a14b349c2","observation_id":"19c2f0b2-58ea-434a-95a4-55fbff7691f5","resolution":{"observed_at":"2026-08-06T10:21:45.245779Z","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":"2026-08-06T10:21:45.248435Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-06T10:21:45.248435Z"},"links":{"citing_paper":"/paper/2508.00212"},"observation_digest":"sha256:bc707cd445bdd20cb7afab0452130907567f7fc34715e008f6079b9fc09f35c3","observation_id":"cfad34af-c72f-47b5-8d88-250c1bc2beb3","resolution":{"observed_at":"2026-08-06T10:21:45.248435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.00212","last_updated":"2025-08-20T01:53:57Z","latest_version":2,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-06T20:14:56.864316Z","submitted_at":"2025-07-31T23:25:19Z","title":"Reinitializing weights vs units for maintaining plasticity in neural networks"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":2,"verified_fuzzy":30},"total_outbound_references":58},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 4 inbound Pith citation observations for arXiv:2508.00212."}