SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.05012 · 2019

Making AI Forget You: Data Deletion in Machine Learning

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 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/1907.05012.json · badge: /api/ran/1907.05012.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
thupchnsky/mufc extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
clustering_loss Ran
ran, honoured the contract we drafted
thupchnsky/mufc/utils.py
code served (permissive licence) · get_code("1edf05df1902dd99")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float64, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create small data and centroids arrays
# data: (n, d) where n=5 samples, d=3 dimensions
# centroids: (k, d) where k=2 clusters, d=3 dimensions
data = np.random.randn(5, 3)
centroids = np.random.randn(2, 3)

ARGS = {
    'data': data,
    'centroids': centroids
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_dataset Ran
ran; our contract draft was wrong, not the code
thupchnsky/mufc/utils.py
code served (permissive licence) · get_code("00c55dc0b22e77ee")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pickle
import tempfile
import os

# Create a temporary pickle file with a dataset dictionary
dataset_content = {
    'train': {
        'data': [[1, 2, 3], [4, 5, 6]],
        'labels': [0, 1]
    },
    'test': {
        'data': [[7, 8, 9]],
        'labels': [1]
    },
    'metadata': {
        'num_classes': 2,
        'feature_dim': 3
    }
}

# Create a temporary file and write the pickle data
temp_file = tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pkl')
pickle.dump(dataset_content, temp_file)
temp_file.close()

ARGS = {
    'filepath': temp_file.name
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sample_points_in_bin Ran
ran; our contract draft was wrong, not the code
thupchnsky/mufc/utils.py
code served (permissive licence) · get_code("c16a71bb4f15abdc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 2, dtype family float, shape (10, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

np.random.seed(0)

bin_mid = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
total_points = 10
quant_eps = 0.5

ARGS = {
    'bin_mid': bin_mid,
    'total_points': total_points,
    'quant_eps': quant_eps
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (10, 5) — shape (10, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
clustering_loss 1 other paper
1 later
2210.16424 (2022-10)
Machine Unlearning of Federated Clusters
load_dataset 1 other paper
1 later
2210.16424 (2022-10)
Machine Unlearning of Federated Clusters
sample_points_in_bin 1 other paper
1 later
2210.16424 (2022-10)
Machine Unlearning of Federated Clusters

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

Intense recent discussions have focused on how to provide individuals with control over when their data can and cannot be used --- the EU's Right To Be Forgotten regulation is an example of this effort. In this paper we initiate a framework studying what to do when it is no longer permissible to deploy models derivative from specific user data. In particular, we formulate the problem of efficiently deleting individual data points from trained machine learning models. For many standard ML models, the only way to completely remove an individual's data is to retrain the whole model from scratch on the remaining data, which is often not computationally practical. We investigate algorithmic principles that enable efficient data deletion in ML. For the specific setting of k-means clustering, we propose two provably efficient deletion algorithms which achieve an average of over 100X improvement in deletion efficiency across 6 datasets, while producing clusters of comparable statistical quality to a canonical k-means++ baseline.

For agents

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

get_harvested_code_for_paper("1907.05012")
get_code_for_paper("1907.05012")
have("1907.05012")

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

curl https://syntology.ai/api/ran/1907.05012.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.05012.svg)](https://syntology.ai/paper/1907.05012)

Connect an agent — have() is free.