Paper Citation Record · LEDGER

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation

As of 16 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:1908.02984.

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

pith.paper-citation-record.v1
1908.02984 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T14:35:24.500978Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

37 of 37 outbound references displayed

verified exact0
verified fuzzy31
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0a3630f3-40fb-4711-9f3e-3fb0b5a05b30 · outbound

This paper cites Available at tiny-imagenet.herokuapp.com.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Available at tiny-imagenet.herokuapp.com

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.467057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6f0fd379-de7d-4b3d-8e4a-86e07554dc24 · outbound

This paper cites Memory aware synapses: Learning what (not) to forget.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Memory aware synapses: Learning what (not) to forget

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.448671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d2d72dac-84ad-4eec-aed9-31a6340c5776 · outbound

This paper cites Expert gate: Lifelong learning with a network of experts.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Expert gate: Lifelong learning with a network of experts

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.426401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 09b48e4a-6f89-43c6-86b1-9692bdf3b326 · outbound

This paper cites Weight uncertainty in neural network.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Weight uncertainty in neural network

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T14:35:24.309450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1361d27-13bc-4393-9c85-0e71f4885079 · outbound

This paper cites Streaming varia- tional bayes.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Streaming varia- tional bayes

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.389992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9611cd44-bd8e-4651-ba1b-7978fd8b1c0d · outbound

This paper cites Riemannian walk for incremen- tal learning: Understanding forgetting and intransigence.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Riemannian walk for incremen- tal learning: Understanding forgetting and intransigence

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.368077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2b97c140-a857-4008-a07b-598e10406fe9 · outbound

This paper cites PathNet: Evolution Channels Gradient Descent in Super Neural Networks.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation PathNet: Evolution Channels Gradient Descent in Super Neural Networks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T14:35:24.331804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc28c27a-7592-4723-a4d5-0323139bb587 · outbound

This paper cites Catastrophic forgetting in connectionist networks.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Catastrophic forgetting in connectionist networks

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.349503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 55982127-1ff0-42b0-b77b-ea7cc8c6ef3e · outbound

This paper cites Online variational bayesian learning.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Online variational bayesian learning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.331773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 50cd277a-51d4-4fb8-af32-fddbdea51f3e · outbound

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

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T14:35:24.347856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a36b2b8c-8fea-48ba-a4ff-49471b518632 · outbound

This paper cites Generative adversarial nets.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Generative adversarial nets

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T14:35:24.354024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fd5e4a1-43d1-4344-9f17-225661c61a73 · outbound

This paper cites Overcoming catastrophic inter- ference using conceptor-aided backpropagation.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Overcoming catastrophic inter- ference using conceptor-aided backpropagation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.288439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4a147a2f-eb60-4bab-83da-f71c6da806b8 · outbound

This paper cites Over- coming catastrophic forgetting via model adaptation.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Over- coming catastrophic forgetting via model adaptation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.264267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 27e6bf48-4176-40ca-8984-9212967451d5 · outbound

This paper cites Less-forgetful learning for domain expansion in deep neu- ral networks.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Less-forgetful learning for domain expansion in deep neu- ral networks

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.246405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 561fef74-0e39-4014-b4ae-0fe38eb9112a · outbound

This paper cites Fearnet: Brain- inspired model for incremental learning.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Fearnet: Brain- inspired model for incremental learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.225569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation def231fb-9c8d-416b-bc6a-7cd341ed8c1f · outbound

This paper cites Stochastic estimation of the maximum of a regression function.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Stochastic estimation of the maximum of a regression function

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.194485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation daf72c28-6100-45f1-a079-5763530e61b0 · outbound

This paper cites Overcoming catastrophic forgetting in neu- ral networks.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Overcoming catastrophic forgetting in neu- ral networks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.171366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d2d6a6a1-9744-430d-b4bb-514e76230dfb · outbound

This paper cites The CIFAR-10 and CIFAR-100 datasets.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation The CIFAR-10 and CIFAR-100 datasets

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.153068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d41ad11c-0c06-4e30-8494-46c2044a05bf · outbound

This paper cites an unresolved cited work.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-14T14:35:25.132807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e7cde388-6c07-4251-bd09-3dfe464fbfa5 · outbound

This paper cites Lifelong learning with dynamically expandable net- works.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Lifelong learning with dynamically expandable net- works

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.107106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ed58ecad-ae35-4523-a02b-f475a98469f6 · outbound

This paper cites Overcoming catastrophic forgetting by incremental moment matching.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Overcoming catastrophic forgetting by incremental moment matching

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.079928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cef78b81-5604-4144-93df-54da34d575ed · outbound

This paper cites Dual-memory deep learning architectures for lifelong learning of everyday human behaviors.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Dual-memory deep learning architectures for lifelong learning of everyday human behaviors

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.057941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c984c0eb-2099-43a2-a90e-76988f784c68 · outbound

This paper cites Learning without forgetting.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Learning without forgetting

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.036298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a6891d69-290d-4a01-a857-835e5b07a9e3 · outbound

This paper cites Gradient episodic memory for contin- ual learning.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Gradient episodic memory for contin- ual learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:25.015234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0d7e6ca9-af5a-406b-88b2-57dff0d53b73 · outbound

This paper cites Packnet: Adding mul- tiple tasks to a single network by iterative pruning.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Packnet: Adding mul- tiple tasks to a single network by iterative pruning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.993347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7d011f99-dd1b-4212-9f5e-5d7eeda449dc · outbound

This paper cites Catastrophic inter- ference in connectionist networks: The sequential learning problem.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Catastrophic inter- ference in connectionist networks: The sequential learning problem

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.974093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cf6ef8db-a987-4061-8813-54f20099b640 · outbound

This paper cites Variational continual learning.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Variational continual learning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.956878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c3084a97-b852-4d7b-8c3d-6a025e572e49 · outbound

This paper cites icarl: Incremental classiﬁer and representation learning.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation icarl: Incremental classiﬁer and representation learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.935987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dda79d15-cc2b-4591-9183-0689e02b56f9 · outbound

This paper cites A stochastic approxima- tion method.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation A stochastic approxima- tion method

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.767344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f2aa5137-1d45-4abf-a307-474bdeb888f2 · outbound

This paper cites Progressive Neural Networks.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Progressive Neural Networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-14T14:35:24.463066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3021a22-c8b9-4112-8542-2b7a3af7b4d8 · outbound

This paper cites Online model selection based on the varia- tional bayes.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Online model selection based on the varia- tional bayes

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.748817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e842defb-b77d-4a10-bd0c-5a519b84c253 · outbound

This paper cites Progress compress: A scalable framework for continual learning.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Progress compress: A scalable framework for continual learning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.729991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c2d7a7e1-6dcc-43f4-ae25-2d3823e25006 · outbound

This paper cites Overcoming catastrophic forgetting with hard attention to the task.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Overcoming catastrophic forgetting with hard attention to the task

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.703938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7d89f852-8d54-43fb-a668-527dc9dccd58 · outbound

This paper cites Continual learning with deep generative replay.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Continual learning with deep generative replay

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.683849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation deb0b2d5-efb5-4e2f-ac20-e91c3d230934 · outbound

This paper cites Memory-based parameter adaptation.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Memory-based parameter adaptation

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.662080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 022f72ce-65f9-47c6-b756-153ca716ab85 · outbound

This paper cites Compete to com- pute.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Compete to com- pute

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.643861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 98c3f44a-ba72-4b66-b302-ab33e0cc4f49 · outbound

This paper cites Contin- ual learning through synaptic intelligence.

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation Contin- ual learning through synaptic intelligence

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:35:24.620715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

No inbound Pith citation observations are available.