SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.07326 · ICLR · 2021

CPR: Classifier-Projection Regularization for Continual Learning

Sungmin Cha, Hsiang Hsu, Taebaek Hwang, Flavio Calmon, Taesup Moon, 𝜽 𝟑

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2006.07326.json · badge: /api/ran/2006.07326.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
csm9493/CPR_CL marked official in Papers with Code
Papers with Code archive
3 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Appr Ran
ran on a synthesized input · constructed an object; no result was computed
csm9493/CPR_CL/approaches/ags_cl_cpr.py
pointer only (licence: NONE) · get_code("cb9317a345f54a2a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csm9493/CPR_CL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CPR Ran
ran on a synthesized input
csm9493/CPR_CL/approaches/ags_cl_cpr.py
pointer only (licence: NONE) · get_code("fcb6a94c25b8785b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csm9493/CPR_CL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_model Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sahagobinda/GPM
pointer only · get_code("ebd151f2b9fc07af")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gs_cal Ran
ran; our contract draft was wrong, not the code
csm9493/CPR_CL/approaches/ags_cl_cpr.py
pointer only (licence: NONE) · get_code("c5f89c0918a00536")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csm9493/CPR_CL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

freeze_model Not yet run
unverified (harvested, no recorded run)
csm9493/CPR_CL/approaches/ags_cl_cpr.py
pointer only (licence: NONE) · get_code("26c79efcdfaa6774")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csm9493/CPR_CL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

set_model_ Not yet run
unverified (harvested, no recorded run)
csm9493/CPR_CL/approaches/ags_cl_cpr.py
pointer only (licence: NONE) · get_code("d445207730f05972")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csm9493/CPR_CL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_model
brick of this paper's assembly: helper
7 other papers
1 dated earlier, 6 later · 2 only as an assembly brick
2003.09553 (2020-03)
Adversarial Continual Learning
2010.01528 (2020-10)
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
2103.09762 (2021-03)
Gradient Projection Memory for Continual Learning
and 4 more not named here
freeze_model
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2207.06543 (2022-07)
CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One
set_model_
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2207.06543 (2022-07)
CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a general, yet simple patch that can be applied to existing regularizationbased continual learning methods called classifier-projection regularization (CPR). Inspired by both recent results on neural networks with wide local minima and information theory, CPR adds an additional regularization term that maximizes the entropy of a classifier's output probability. We demonstrate that this additional term can be interpreted as a projection of the conditional probability given by a classifier's output to the uniform distribution. By applying the Pythagorean theorem for KL divergence, we then prove that this projection may (in theory) improve the performance of continual learning methods. In our extensive experimental results, we apply CPR to several state-of-the-art regularization-based continual learning methods and benchmark performance on popular image recognition datasets. Our results demonstrate that CPR indeed promotes a wide local minima and significantly improves both accuracy and plasticity while simultaneously mitigating the catastrophic forgetting of baseline continual learning methods. The codes and scripts for this work are available at https://github.com/csm9493/CPR_CL.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.07326")
get_code_for_paper("2006.07326")
have("2006.07326")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.07326.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.07326.svg)](https://syntology.ai/paper/2006.07326)

Connect an agent — have() is free.