SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.09818 · ICML · 2022

Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification

Peter Bevan, Amir Atapour-Abarghouei

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 2 honoured the contract we drafted, 0 violated it and 1 has 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/2109.09818.json · badge: /api/ran/2109.09818.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
pbevan1/Skin-Deep-Unlearning canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
auc_lst Ran
ran on a synthesized input
pbevan1/Skin-Deep-Unlearning/misc_code/df_random_seeds.py
code served (permissive licence) · get_code("78475b0c01c38b23")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 temporary directory structure for pickle files
temp_dir = tempfile.mkdtemp()
results_dir = os.path.join(temp_dir, 'results', 'logs')

# Create mock pickle data
# Each pickle file contains a list of tuples (one per dataset)
# Each tuple contains: (fpr, tpr, auc, threshold, specificity)
test_nos = [1, 2]
dset_lst = ['dataset_a', 'dataset_b']

# Create the directory structure and pickle files
for test_num in test_nos:
    test_dir = os.path.join(results_dir, str(test_num))
    os.makedirs(test_dir, exist_ok=True)
    
    # Create mock ROC data: list of tuples per dataset
    # Each tuple: (fpr, tpr, auc, threshold, specificity)
    roc_data = [
        ([0.0, 0.5, 1.0], [0.0, 0.8, 1.0], 0.85, 0.5, 0.92),
        ([0.0, 0.4, 1.0], [0.0, 0.75, 1.0], 0.78, 0.6, 0.88),
    ]
    
    pkl_path = os.path.join(test_dir, f'log_Test{test_num}_roc_plt_lst.pkl')
    with open(pkl_path, 'wb') as f:
        pickle.dump(roc_data, f)

# Monkey-patch the file path to use our temp directory
import sys
original_open = open

def patched_open(path, *args, **kwargs):
    if '../results/logs/' in path:
        # Replace relative path with our temp directory path
        new_path = path.replace('../results/logs/', results_dir + '/')
        return original_open(new_path, *args, **kwargs)
    return original_open(path, *args, **kwargs)

import builtins
builtins.open = patched_open

ARGS = {
    'test_nos': [1, 2],
    'dset_lst': ['dataset_a', 'dataset_b']
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
get_mean_std Ran
ran, honoured the contract we drafted
pbevan1/Skin-Deep-Unlearning/preprocessing.py
pointer only (licence: MIT); the stored copy get_code serves, from pbevan1/detecting-melanoma-fairly, is pointer only (licence: NONE) · get_code("ba8470699bf72aa4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pbevan1/detecting-melanoma-fairly, and GitHub detected no licence in that repository 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_size_ISIC Ran
ran; our contract draft was wrong, not the code
pbevan1/Skin-Deep-Unlearning/preprocessing.py
pointer only (licence: MIT); the stored copy get_code serves, from pbevan1/detecting-melanoma-fairly, is pointer only (licence: NONE) · get_code("1e48325cf21a28e8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pbevan1/detecting-melanoma-fairly, and GitHub detected no licence in that repository 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_size_from_raw Ran
ran; our contract draft was wrong, not the code
pbevan1/Skin-Deep-Unlearning/preprocessing.py
pointer only (licence: MIT); the stored copy get_code serves, from pbevan1/detecting-melanoma-fairly, is pointer only (licence: NONE) · get_code("e6d83a666e60e46d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pbevan1/detecting-melanoma-fairly, and GitHub detected no licence in that repository 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.

grad_reverse Ran
ran, honoured the contract we drafted
pbevan1/Skin-Deep-Unlearning/models.py
pointer only (licence: MIT); the stored copy get_code serves, from feidfoe/learning-not-to-learn, is pointer only (licence: NONE) · get_code("8a26ee1d7d102851")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from feidfoe/learning-not-to-learn, and GitHub detected no licence in that repository 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 later) and 1 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
grad_reverse 9 other papers
5 dated earlier, 1 the same month, 3 later
1711.05139 (2017-11)
XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings
1802.06901 (2018-02)
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
1812.10352 (2018-12)
Learning Not to Learn: Training Deep Neural Networks with Biased Data
and 6 more not named here
get_mean_std 1 other paper
1 later
2202.02832 (2022-02)
Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification
get_size_ISIC 1 other paper
1 later
2202.02832 (2022-02)
Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification
get_size_from_raw 1 other paper
1 later
2202.02832 (2022-02)
Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification

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

Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma from skin lesion images, but prediction irregularities due to biases seen within the training data are an issue that should be addressed before widespread deployment is possible. In this work, we robustly remove bias and spurious variation from an automated melanoma classification pipeline using two leading bias 'unlearning' techniques. We show that the biases introduced by surgical markings and rulers presented in previous studies can be reasonably mitigated using these bias removal methods. We also demonstrate the generalisation benefits of 'unlearning' spurious variation relating to the imaging instrument used to capture lesion images. Our experimental results provide evidence that the effects of each of the aforementioned biases are notably reduced, with different debiasing techniques excelling at different tasks.

For agents

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

get_harvested_code_for_paper("2109.09818")
get_code_for_paper("2109.09818")
have("2109.09818")

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

curl https://syntology.ai/api/ran/2109.09818.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.09818.svg)](https://syntology.ai/paper/2109.09818)

Connect an agent — have() is free.