SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.01401 · 2024

An Information Theoretic Approach to Machine Unlearning

arXiv · PDF · Open in the Atlas

Code that ran

14 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 5 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 8 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2402.01401.json · badge: /api/ran/2402.01401.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
jwf40/zeroshot-unlearning-at-scale canonical (classifier label)
classifier basis: census
12 ran · 0 no recorded run
jwf40/information-theoretic-unlearning canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
JSDiv Ran
ran; our contract draft was wrong, not the code
jwf40/zeroshot-unlearning-at-scale/src/metrics.py
pointer only (licence: NONE) · get_code("65e6e724245e6071")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

UnLearningScore Ran
ran, honoured the contract we drafted
jwf40/zeroshot-unlearning-at-scale/src/metrics.py
pointer only (licence: NONE) · get_code("e982685418b19915")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

UnlearnerLoss Ran
ran; our contract draft was wrong, not the code
jwf40/information-theoretic-unlearning/src/unlearn.py
pointer only (licence: NONE) · get_code("35a220c6eeea45d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/information-theoretic-unlearning 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.

attention Ran
ran, honoured the contract we drafted
jwf40/zeroshot-unlearning-at-scale/src/gkt.py
pointer only (licence: NONE) · get_code("b817aa66879a905d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

attention_diff Ran
ran, honoured the contract we drafted
jwf40/zeroshot-unlearning-at-scale/src/gkt.py
pointer only (licence: NONE) · get_code("fa2c8ba3cdf9f1d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

build_retain_forget_sets Ran
ran; our contract draft was wrong, not the code
jwf40/zeroshot-unlearning-at-scale/src/forget_full_class_strategies.py
pointer only (licence: NONE) · get_code("1142b442d4f39943")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

build_retain_forget_sets Ran
ran on a synthesized input
jwf40/zeroshot-unlearning-at-scale/src/forget_subclass_strategies.py
pointer only (licence: NONE) · get_code("ccc32fcda24fa317")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

divergence Ran
ran; our contract draft was wrong, not the code
jwf40/zeroshot-unlearning-at-scale/src/gkt.py
pointer only (licence: NONE) · get_code("391f84dc0ccdbf82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

entropy Ran
ran; our contract draft was wrong, not the code
jwf40/zeroshot-unlearning-at-scale/src/metrics.py
pointer only (licence: NONE) · get_code("4a12bd3434683bbc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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_classwise_ds Ran
ran; our contract draft was wrong, not the code
jwf40/zeroshot-unlearning-at-scale/src/forget_full_class_strategies.py
pointer only (licence: NONE) · get_code("ea3bbc7bfbf7ad33")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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_classwise_ds Ran
ran; our contract draft was wrong, not the code
jwf40/zeroshot-unlearning-at-scale/src/forget_subclass_strategies.py
pointer only (licence: NONE) · get_code("93763b90cbaa67db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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_gf_loader Ran
ran; our contract draft was wrong, not the code
jwf40/zeroshot-unlearning-at-scale/src/forget_random_strategies.py
pointer only (licence: NONE) · get_code("01df4dbd4f3784f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

guided_eval Ran
ran, honoured the contract we drafted
jwf40/zeroshot-unlearning-at-scale/src/forget_random_strategies.py
pointer only (licence: NONE) · get_code("ddad3b26002d7f99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/zeroshot-unlearning-at-scale 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.

unlearning_step Ran
ran, honoured the contract we drafted
jwf40/information-theoretic-unlearning/src/unlearn.py
pointer only (licence: NONE) · get_code("7920183b7b2256da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/information-theoretic-unlearning 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.

fit_one_unlearning_cycle Not yet run
unverified (harvested, no recorded run)
jwf40/information-theoretic-unlearning/src/unlearn.py
pointer only (licence: NONE) · get_code("015561a0364e1ddb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jwf40/information-theoretic-unlearning 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 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 2 later) and 4 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
entropy 4 other papers
4 dated earlier
2201.05629 (2022-01)
Zero-Shot Machine Unlearning
2205.08096 (2022-05)
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
2308.07707 (2023-08)
Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening
and 1 more not named here
attention 3 other papers
3 dated earlier
1905.09768 (2019-05)
Zero-shot Knowledge Transfer via Adversarial Belief Matching
2201.05629 (2022-01)
Zero-Shot Machine Unlearning
2210.08196 (2022-10)
Deep Regression Unlearning
attention_diff 3 other papers
3 dated earlier
1905.09768 (2019-05)
Zero-shot Knowledge Transfer via Adversarial Belief Matching
2201.05629 (2022-01)
Zero-Shot Machine Unlearning
2210.08196 (2022-10)
Deep Regression Unlearning
JSDiv 2 other papers
2 dated earlier
2205.08096 (2022-05)
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
2308.07707 (2023-08)
Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening
UnLearningScore 2 other papers
2 dated earlier
2205.08096 (2022-05)
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
2308.07707 (2023-08)
Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening
fit_one_unlearning_cycle 2 other papers
1 dated earlier, 1 later
2205.08096 (2022-05)
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
2403.01267 (2024-03)
Dissecting Language Models: Machine Unlearning via Selective Pruning
unlearning_step 2 other papers
1 dated earlier, 1 later
2205.08096 (2022-05)
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
2403.01267 (2024-03)
Dissecting Language Models: Machine Unlearning via Selective Pruning
UnlearnerLoss 1 other paper
1 dated earlier
2205.08096 (2022-05)
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
build_retain_forget_sets 1 other paper
1 dated earlier
2308.07707 (2023-08)
Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening
divergence 1 other paper
1 dated earlier
2201.05629 (2022-01)
Zero-Shot Machine Unlearning
get_classwise_ds 1 other paper
1 dated earlier
2308.07707 (2023-08)
Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening

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

To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models is increasingly important. The key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance. In this work, we address the zero-shot unlearning scenario, whereby an unlearning algorithm must be able to remove data given only a trained model and the data to be forgotten. We explore unlearning from an information theoretic perspective, connecting the influence of a sample to the information gain a model receives by observing it. From this, we derive a simple but principled zero-shot unlearning method based on the geometry of the model. Our approach takes the form of minimising the gradient of a learned function with respect to a small neighbourhood around a target forget point. This induces a smoothing effect, causing forgetting by moving the boundary of the classifier. We explore the intuition behind why this approach can jointly unlearn forget samples while preserving general model performance through a series of low-dimensional experiments. We perform extensive empirical evaluation of our method over a range of contemporary benchmarks, verifying that our method is competitive with state-of-the-art performance under the strict constraints of zero-shot unlearning. Code for the project can be found at https://github.com/jwf40/Information-Theoretic-Unlearning

For agents

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

get_harvested_code_for_paper("2402.01401")
get_code_for_paper("2402.01401")
have("2402.01401")

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

curl https://syntology.ai/api/ran/2402.01401.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.01401.svg)](https://syntology.ai/paper/2402.01401)

Connect an agent — have() is free.