Pith. sign in

Paper Citation Record · LEDGER

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection

As of 19 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2509.21606.

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

pith.paper-citation-record.v1
2509.21606 v3

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:54:59.815140Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

13 of 13 outbound references displayed

  • verified exact0
  • verified fuzzy6
  • unresolved6
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fab52fb0-309a-447e-80cc-3d5a776e4184 · outbound

This paper cites FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformer.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformer

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-15T15:54:59.780237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:54:59.780237Z digest=sha256:16de55e60207e74485bb405017d2c7cf0f884cde66032be1ddb185332bd5d766

Observation 09321b81-d0da-4ba4-a843-caa405793122 · outbound

This paper cites We set the task identity prediction threshold toϵl = 0.95,∀l , based on a hyperparameter search.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection We set the task identity prediction threshold toϵl = 0.95,∀l , based on a hyperparameter search

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:54:59.973325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-15T15:54:59.793119Z digest=sha256:ea63f8a99b74ce9e1a581e595924b7381ee877fd49b62ad1f162707e6fd4990b

Observation cd794cc5-b158-4b93-af37-de8ad36e4405 · outbound

This paper cites an unresolved cited work.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection Unresolved cited work

Reference 8

Resolution
malformed identifier
raw_fallback, observed 2026-08-15T15:54:59.962925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-15T15:54:59.796373Z digest=sha256:765de28d92ae28a2b8a1779afefbe06a73d409558b6b06fc083de9cc97d72ca0

Observation d6b411b7-fb03-46ec-8068-5f81aa5679a8 · outbound

This paper cites A photo of a class.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection A photo of a class

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:54:59.940450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-15T15:54:59.803792Z digest=sha256:68108ba308825c812f1a69e5e8e7d36e7a6f39b9ba00fdedcfe2ea7eddc77d5e

Observation 45f2b17e-1dc1-47aa-a0db-515c10ca4cde · outbound

This paper cites In our implementation, for each dataset we set the sampling dimension of the standard normal vector to five times the feature size.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection In our implementation, for each dataset we set the sampling dimension of the standard normal vector to five times the feature size

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:54:59.929928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-15T15:54:59.807553Z digest=sha256:41d21c6b399658dd8aa9222ee8d495bc67e2d6f6389079688a5a71aa7c10bc9c

Observation 10c1412f-63ec-4a74-b7d5-1a36066e3bd3 · outbound

This paper cites GLFC (Dong et al., 2022.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection GLFC (Dong et al., 2022

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:54:59.918405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-15T15:54:59.811454Z digest=sha256:74ff4e9ec43e73681709eab70df8a14d076ab72b1a2143bfa8146da274ca2a8e

Observation 9c8b2f1e-7c66-4e31-b9ce-ccf74d960f97 · outbound

This paper cites The follow-up studies (Liu et al., 2023; Dai et al., 2023; Li et al., 2024c;a) reduce the size of the replay cache but remain reliant upon old samples.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection The follow-up studies (Liu et al., 2023; Dai et al., 2023; Li et al., 2024c;a) reduce the size of the replay cache but remain reliant upon old samples

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:54:59.907660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-15T15:54:59.815140Z digest=sha256:291b99f4f8f9bd24ad7d219141077449089415238a3ac058700eef89b741558d

Observation 13b87c8e-47df-4d9c-b9b7-90335eba15d7 · outbound

This paper cites Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-15T15:54:59.776424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:54:59.776424Z digest=sha256:9868222ea1a505a0b455e7d9f813bac32ed40d568dd6286b15d766e0a18f22ee

Observation f9f07b14-0e2b-41c1-8060-c3cb5c20d6ae · outbound

This paper cites Recovering Labels from Local Updates in Federated Learning.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection Recovering Labels from Local Updates in Federated Learning

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-15T15:54:59.767855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:54:59.767855Z digest=sha256:07bb44a870d5f715e2522637c82183d056437219bdbe3fc8b64728561a6ee7e9

Observation 073f7bcc-7c39-4687-b9c6-af5f4e0df972 · outbound

This paper cites How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-15T15:54:59.784900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:54:59.784900Z digest=sha256:9e802364cae56174f90c9523f467a945ff719745e06659a1094dd0edc23287b1

Observation f4af513e-d42f-48a1-a84f-59ef67dde270 · outbound

This paper cites For CIFAR100, following the original paper we set the memory size to 2000; to satisfy memory constraints, for DomainNet and ImageNet-R the memory size is limited to.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection For CIFAR100, following the original paper we set the memory size to 2000; to satisfy memory constraints, for DomainNet and ImageNet-R the memory size is limited to

Reference 2022

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:54:59.951290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-15T15:54:59.800274Z digest=sha256:2e3441615c967e92361906d6309baa490a3238e70ebdd99ee9131b4bdb444c9d

Observation 8df439a0-cc18-4140-a48e-31b63eac32e7 · outbound

This paper cites CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-15T15:54:59.789281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:54:59.789281Z digest=sha256:cad18bfee5cef6ffadf36cc4137976ac3d93cfeb6ebd2032b67509117c8954a5

Observation c2c01128-5d10-44b8-8be0-c754cb3386a2 · outbound

This paper cites On the Convergence of FedAvg on Non-IID Data.

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection On the Convergence of FedAvg on Non-IID Data

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-15T15:54:59.772496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:54:59.772496Z digest=sha256:92a3c5ec11289d849f5d0bc67d04f81c43ac15b7940400fa871ef35bb065948e

Pith citing papers

No inbound Pith citation observations are available.