Paper Citation Record · LEDGER

Reinitializing weights vs units for maintaining plasticity in neural networks

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.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2508.00212 v2

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T10:21:45.248435Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-31T04:05:50.121652Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-06-30T11:04:37.510167Z

Reference resolution

58 of 58 outbound references displayed

verified exact2
verified fuzzy30
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4c578abc-b410-4f3a-80ea-9c07366fbc64 · outbound

This paper cites an unresolved cited work.

Reinitializing weights vs units for maintaining plasticity in neural networks Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:21:45.854603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ea127b4d-640d-4f89-925d-53486d92eac3 · outbound

This paper cites The Impact of Reinitialization on Generalization in Convolutional Neural Networks.

Reinitializing weights vs units for maintaining plasticity in neural networks The Impact of Reinitialization on Generalization in Convolutional Neural Networks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.096030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e412cd1-64f8-4fda-8def-fbbe7f51d3c6 · outbound

This paper cites On warm-starting neural network training.

Reinitializing weights vs units for maintaining plasticity in neural networks On warm-starting neural network training

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.099355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd3461d-6ae6-4437-be91-155fa602cca0 · outbound

This paper cites A better match for drivers and riders: Reinforcement learning at lyft.

Reinitializing weights vs units for maintaining plasticity in neural networks A better match for drivers and riders: Reinforcement learning at lyft

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.841554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 62a6fd46-57f9-4aa9-bf0a-bd35a1dc89b0 · outbound

This paper cites Layer Normalization.

Reinitializing weights vs units for maintaining plasticity in neural networks Layer Normalization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.106051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b18bf3e0-6b4c-45b7-bda0-497f0ea1c9e2 · outbound

This paper cites What is the state of neural network pruning? Proceedings of machine learning and systems, 2: 0 129--146, 2020.

Reinitializing weights vs units for maintaining plasticity in neural networks What is the state of neural network pruning? Proceedings of machine learning and systems, 2: 0 129--146, 2020

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.833846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5a00161e-9de9-4b81-b45c-fff6db929f69 · outbound

This paper cites Dokania, Thalaiyasingam Ajanthan, and Philip H.

Reinitializing weights vs units for maintaining plasticity in neural networks Dokania, Thalaiyasingam Ajanthan, and Philip H

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.825924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e9154600-d5ba-4061-af3f-90ae9c2b388f · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Reinitializing weights vs units for maintaining plasticity in neural networks BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.114488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7800c408-5e63-4930-867d-578cd14409f0 · outbound

This paper cites The interplay of search and gradient descent in semi-stationary learning problems.

Reinitializing weights vs units for maintaining plasticity in neural networks The interplay of search and gradient descent in semi-stationary learning problems

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.818335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3b27e44f-831c-4928-a701-4a6c52aa74ae · outbound

This paper cites Continual Backprop: Stochastic Gradient Descent with Persistent Randomness.

Reinitializing weights vs units for maintaining plasticity in neural networks Continual Backprop: Stochastic Gradient Descent with Persistent Randomness

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.119866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cda5591-b39b-40af-b01a-7642655639df · outbound

This paper cites Loss of plasticity in deep continual learning.

Reinitializing weights vs units for maintaining plasticity in neural networks Loss of plasticity in deep continual learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.122649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e8717b9-fd6d-4781-a3aa-d0b62c9451b6 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Reinitializing weights vs units for maintaining plasticity in neural networks An image is worth 16x16 words: Transformers for image recognition at scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.125179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e19ff38c-6f47-4584-a30f-275982e371a3 · outbound

This paper cites Rupam Mahmood.

Reinitializing weights vs units for maintaining plasticity in neural networks Rupam Mahmood

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.802428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation db43d5a7-2e48-437a-98fd-9d7422251f3f · outbound

This paper cites Rupam Mahmood.

Reinitializing weights vs units for maintaining plasticity in neural networks Rupam Mahmood

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.794721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7732c295-014d-4bdb-ad12-7d24888aaa2a · outbound

This paper cites Rigging the lottery: Making all tickets winners.

Reinitializing weights vs units for maintaining plasticity in neural networks Rigging the lottery: Making all tickets winners

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.785102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bf0323c0-e8b9-40e8-8cea-3b483583fdde · outbound

This paper cites Depgraph: Towards any structural pruning.

Reinitializing weights vs units for maintaining plasticity in neural networks Depgraph: Towards any structural pruning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.776611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1c17ebd9-9540-4272-9334-d301726a10bf · outbound

This paper cites The lottery ticket hypothesis: Finding sparse, trainable neural networks.

Reinitializing weights vs units for maintaining plasticity in neural networks The lottery ticket hypothesis: Finding sparse, trainable neural networks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.138459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d32ec26-21db-4014-bd29-fdf9c948a3a2 · outbound

This paper cites an unresolved cited work.

Reinitializing weights vs units for maintaining plasticity in neural networks Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:21:45.764846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c74bd31d-7483-45e7-80f5-53a6fefbdc30 · outbound

This paper cites Understanding the difficulty of training deep feedforward neural networks.

Reinitializing weights vs units for maintaining plasticity in neural networks Understanding the difficulty of training deep feedforward neural networks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.143595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e80cff2-f52f-4e62-ab1b-c432dd781be2 · outbound

This paper cites Deep learning, volume 1.

Reinitializing weights vs units for maintaining plasticity in neural networks Deep learning, volume 1

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.753256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 02e0f028-d303-4736-8852-5314c461eb5c · outbound

This paper cites An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks.

Reinitializing weights vs units for maintaining plasticity in neural networks An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.148655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e59d9b3-f432-4ea8-8beb-1dd262e097a6 · outbound

This paper cites Taylor, Mykola Pechenizkiy, and Decebal Constantin Mocanu.

Reinitializing weights vs units for maintaining plasticity in neural networks Taylor, Mykola Pechenizkiy, and Decebal Constantin Mocanu

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.745572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2d3c7edc-9e26-4c09-8b8c-9e62d59dd397 · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.

Reinitializing weights vs units for maintaining plasticity in neural networks Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.154076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe0352eb-22ea-402d-b2b3-b620923c6a57 · outbound

This paper cites Gvfs in the real world: making predictions online for water treatment.

Reinitializing weights vs units for maintaining plasticity in neural networks Gvfs in the real world: making predictions online for water treatment

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.733748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 503091b5-bf0a-4bc3-84bb-06b5d9bf0c29 · outbound

This paper cites an unresolved cited work.

Reinitializing weights vs units for maintaining plasticity in neural networks Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:21:45.725911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 66b033b3-1922-4de0-9a0d-74250b533f57 · outbound

This paper cites Spine dynamics in the brain, mental disorders and artificial neural networks.

Reinitializing weights vs units for maintaining plasticity in neural networks Spine dynamics in the brain, mental disorders and artificial neural networks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.717974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a3217b8-f182-44c0-8412-662800cd3f94 · outbound

This paper cites Learning multiple layers of features from tiny images, 2009.

Reinitializing weights vs units for maintaining plasticity in neural networks Learning multiple layers of features from tiny images, 2009

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.709527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a452aa75-0ca3-4e74-85f1-e04310a3171e · outbound

This paper cites Implicit under-parameterization inhibits data-efficient deep reinforcement learning.

Reinitializing weights vs units for maintaining plasticity in neural networks Implicit under-parameterization inhibits data-efficient deep reinforcement learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.701298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6e10ade9-dd40-4177-b652-4983357ea552 · outbound

This paper cites Maintaining plasticity in continual learning via regenerative regularization.

Reinitializing weights vs units for maintaining plasticity in neural networks Maintaining plasticity in continual learning via regenerative regularization

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.694070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 82462293-120b-4dd6-ad1c-315c05e329d2 · outbound

This paper cites Plastic: Improving input and label plasticity for sample efficient reinforcement learning.

Reinitializing weights vs units for maintaining plasticity in neural networks Plastic: Improving input and label plasticity for sample efficient reinforcement learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.686714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 33c6cdf5-9be9-4604-b2d3-9adcf5ba6042 · outbound

This paper cites Slow and steady wins the race: Maintaining plasticity with hare and tortoise networks.

Reinitializing weights vs units for maintaining plasticity in neural networks Slow and steady wins the race: Maintaining plasticity with hare and tortoise networks

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.677960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 10889e72-1624-4875-b87d-730575acaf2f · outbound

This paper cites Learning Continually by Spectral Regularization.

Reinitializing weights vs units for maintaining plasticity in neural networks Learning Continually by Spectral Regularization

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.177682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bf80d93-8bda-45c8-b285-08696bbda4f3 · outbound

This paper cites Decoupled weight decay regularization.

Reinitializing weights vs units for maintaining plasticity in neural networks Decoupled weight decay regularization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.180511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20d9396a-6aaf-4230-a521-5ad9e9a3fbad · outbound

This paper cites Understanding and preventing capacity loss in reinforcement learning.

Reinitializing weights vs units for maintaining plasticity in neural networks Understanding and preventing capacity loss in reinforcement learning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.665944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5d1d9a21-b238-4c08-9f1f-4d0a26c5d1d9 · outbound

This paper cites Understanding plasticity in neural networks.

Reinitializing weights vs units for maintaining plasticity in neural networks Understanding plasticity in neural networks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.186100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cfc317f-fa84-4864-946b-742968a055fd · outbound

This paper cites Normalization and effective learning rates in reinforcement learning.

Reinitializing weights vs units for maintaining plasticity in neural networks Normalization and effective learning rates in reinforcement learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.188704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd23a209-dfce-4265-98dd-66788f93280d · outbound

This paper cites Representation search through generate and test.

Reinitializing weights vs units for maintaining plasticity in neural networks Representation search through generate and test

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.653656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a1810806-83f8-4d57-bc18-9034436c0a49 · outbound

This paper cites Torchvision: Pytorch's computer vision library.

Reinitializing weights vs units for maintaining plasticity in neural networks Torchvision: Pytorch's computer vision library

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.644668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a87ad04e-f103-4d56-8cee-8fec0f3ffffc · outbound

This paper cites Catastrophic interference in connectionist networks: The sequential learning problem.

Reinitializing weights vs units for maintaining plasticity in neural networks Catastrophic interference in connectionist networks: The sequential learning problem

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.637401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4d1b5066-4901-4da7-a689-eafccd89b4e1 · outbound

This paper cites Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science.

Reinitializing weights vs units for maintaining plasticity in neural networks Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.630232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d846b25d-e5a4-48d2-a81d-7d9a326af4f0 · outbound

This paper cites The primacy bias in deep reinforcement learning.

Reinitializing weights vs units for maintaining plasticity in neural networks The primacy bias in deep reinforcement learning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.202642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01f39a88-bd60-4faf-9074-49032dff16e2 · outbound

This paper cites Deep reinforcement learning with plasticity injection.

Reinitializing weights vs units for maintaining plasticity in neural networks Deep reinforcement learning with plasticity injection

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.618700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 36c5372f-0bad-48a7-9ea5-d1f17a43b967 · outbound

This paper cites GPT-4 Technical Report.

Reinitializing weights vs units for maintaining plasticity in neural networks GPT-4 Technical Report

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.207698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3a73095-a7cc-4b9f-b589-a2aa685807d4 · outbound

This paper cites Toward generate-and-test algorithms for continual feature discovery.

Reinitializing weights vs units for maintaining plasticity in neural networks Toward generate-and-test algorithms for continual feature discovery

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.611443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c1032d12-2b57-4813-bb51-6a391ebb60b6 · outbound

This paper cites i C a RL : Incremental classifier and representation learning.

Reinitializing weights vs units for maintaining plasticity in neural networks i C a RL : Incremental classifier and representation learning

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.602880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c4a401d-db25-48b2-ad6d-5c44e8157cb9 · outbound

This paper cites The dormant neuron phenomenon in deep reinforcement learning.

Reinitializing weights vs units for maintaining plasticity in neural networks The dormant neuron phenomenon in deep reinforcement learning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.594104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 91a537ed-3b3d-4a52-8761-96514c953cfc · outbound

This paper cites Overtrained Language Models Are Harder to Fine-Tune.

Reinitializing weights vs units for maintaining plasticity in neural networks Overtrained Language Models Are Harder to Fine-Tune

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.218106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e01a76e8-edc5-4ea8-aff6-852174a1d24a · outbound

This paper cites Sutton and Shibhansh Dohare.

Reinitializing weights vs units for maintaining plasticity in neural networks Sutton and Shibhansh Dohare

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.585328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a6789748-d0bf-4f29-88e3-e56113c425f1 · outbound

This paper cites Knowledge evolution in neural networks.

Reinitializing weights vs units for maintaining plasticity in neural networks Knowledge evolution in neural networks

Reference 49

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-06T10:21:45.469888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 53d57cd9-205e-4bd2-a316-68a824ccf2da · outbound

This paper cites Attention is all you need.

Reinitializing weights vs units for maintaining plasticity in neural networks Attention is all you need

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.226330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5334d0e-f61c-4188-b892-26e23efbae53 · outbound

This paper cites Same accuracy, twice as fast: continuous training surpasses retraining from scratch.

Reinitializing weights vs units for maintaining plasticity in neural networks Same accuracy, twice as fast: continuous training surpasses retraining from scratch

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-06T10:21:45.276608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 081029a2-e636-4791-9c07-a3e8668ea3f3 · outbound

This paper cites I Can't Believe It's Not Better! - Understanding Deep Learning Through Empirical Falsification.

Reinitializing weights vs units for maintaining plasticity in neural networks I Can't Believe It's Not Better! - Understanding Deep Learning Through Empirical Falsification

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.573410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 178d0201-e36e-48c0-a025-586c8ce87758 · outbound

This paper cites Continual learning through synaptic intelligence.

Reinitializing weights vs units for maintaining plasticity in neural networks Continual learning through synaptic intelligence

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.565049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e29b39b8-aec7-494b-a31a-99e106e5d324 · outbound

This paper cites Fortuitous forgetting in connectionist networks.

Reinitializing weights vs units for maintaining plasticity in neural networks Fortuitous forgetting in connectionist networks

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:21:45.555371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7c4a46ef-04ef-4ea9-8d19-a5317a14fec3 · outbound

This paper cites write newline.

Reinitializing weights vs units for maintaining plasticity in neural networks write newline

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.239441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80d1d688-4636-4b34-a642-ee2667518d26 · outbound

This paper cites @esa (Ref.

Reinitializing weights vs units for maintaining plasticity in neural networks @esa (Ref

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.242537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19c2f0b2-58ea-434a-95a4-55fbff7691f5 · outbound

This paper cites an unresolved cited work.

Reinitializing weights vs units for maintaining plasticity in neural networks Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.245779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfad34af-c72f-47b5-8d88-250c1bc2beb3 · outbound

This paper cites an unresolved cited work.

Reinitializing weights vs units for maintaining plasticity in neural networks Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T10:21:45.248435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5791c06e-ad8a-41a1-baca-9a6b7652fb7a · inbound

Learning to Forget: Continual Learning with Adaptive Weight Decay cites this paper.

Learning to Forget: Continual Learning with Adaptive Weight Decay Reinitializing weights vs units for maintaining plasticity in neural networks

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:31:26.860362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0b262784-411f-4c3b-9936-b1619af85230 · inbound

Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks cites this paper.

Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks Reinitializing weights vs units for maintaining plasticity in neural networks

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:00:56.873138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f330aa4a-24bd-4d1b-bbc6-8793682b6274 · inbound

Agentic Safety is an Epistemic Property, Not a Behavioral One cites this paper.

Agentic Safety is an Epistemic Property, Not a Behavioral One Reinitializing weights vs units for maintaining plasticity in neural networks

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T11:04:37.511527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9dae1e63-32cb-44b6-88f2-60269538da0d · inbound

Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning cites this paper.

Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning Reinitializing weights vs units for maintaining plasticity in neural networks

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-07-31T04:05:50.121652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.