SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.12379 · 2020

Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 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/2005.12379.json · badge: /api/ran/2005.12379.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
sumonbis/ML-Fairness canonical (classifier label)
classifier basis: classifier_2025
2 ran · 3 no recorded run
FunctionStatusWhere it lives
custom_preprocessing Ran
ran; our contract draft was wrong, not the code
sumonbis/ML-Fairness/src/models/adult/model1.py
code served (permissive licence) · get_code("0be461860002672e")
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 DataFrame. 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 pandas as pd
import numpy as np

# Create a small DataFrame with the columns that the function expects
df = pd.DataFrame({
    'sex': ['Female', 'Male', 'Female', 'Male'],
    'race': ['White', 'Black', 'Asian', 'White']
})

ARGS = {
    'df': df
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
get_model_performance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sumonbis/ML-Fairness/src/utils/ml_fairness.py
code served (permissive licence) · get_code("26b8db924559d0fc")
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 tuple. 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 numpy as np
from sklearn.metrics import confusion_matrix, accuracy_score, f1_score, roc_curve, auc

# Create small test data for binary classification
n_samples = 10

# X_test: feature matrix
X_test = np.array([
    [0.1, 0.2, 0.3, 0.4],
    [0.5, 0.6, 0.7, 0.8],
    [0.2, 0.3, 0.4, 0.5],
    [0.6, 0.7, 0.8, 0.9],
    [0.3, 0.4, 0.5, 0.6],
    [0.7, 0.8, 0.9, 1.0],
    [0.4, 0.5, 0.6, 0.7],
    [0.8, 0.9, 1.0, 0.1],
    [0.5, 0.6, 0.7, 0.8],
    [0.9, 1.0, 0.1, 0.2]
])

# y_true: true binary labels
y_true = np.array([0, 1, 0, 1, 0, 1, 0, 1, 0, 1])

# y_pred: predicted binary labels
y_pred = np.array([0, 1, 0, 1, 0, 0, 0, 1, 1, 1])

# probs: predicted probabilities (for binary classification, typically probability of class 1)
probs = np.array([0.2, 0.8, 0.3, 0.9, 0.1, 0.4, 0.2, 0.7, 0.6, 0.85])

ARGS = {
    'X_test': X_test,
    'y_true': y_true,
    'y_pred': y_pred,
    'probs': probs
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
fair_metrics Not yet run
unverified (harvested, no recorded run)
sumonbis/ML-Fairness/src/utils/ml_fairness.py
code served (permissive licence) · get_code("013a8435b59884df")
How it ran

no invocation recorded.

format_probs Not yet run
unverified (harvested, no recorded run)
sumonbis/ML-Fairness/src/models/adult/model1.py
code served (permissive licence) · get_code("f88f5bc7b8330d33")
How it ran

no invocation recorded.

get_fair_metrics_and_plot Not yet run
unverified (harvested, no recorded run)
sumonbis/ML-Fairness/src/utils/ml_fairness.py
code served (permissive licence) · get_code("35f02c03216dc245")
How it ran

no invocation 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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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.

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

Machine learning models are increasingly being used in important decision-making software such as approving bank loans, recommending criminal sentencing, hiring employees, and so on. It is important to ensure the fairness of these models so that no discrimination is made based on protected attribute (e.g., race, sex, age) while decision making. Algorithms have been developed to measure unfairness and mitigate them to a certain extent. In this paper, we have focused on the empirical evaluation of fairness and mitigations on real-world machine learning models. We have created a benchmark of 40 top-rated models from Kaggle used for 5 different tasks, and then using a comprehensive set of fairness metrics, evaluated their fairness. Then, we have applied 7 mitigation techniques on these models and analyzed the fairness, mitigation results, and impacts on performance. We have found that some model optimization techniques result in inducing unfairness in the models. On the other hand, although there are some fairness control mechanisms in machine learning libraries, they are not documented. The mitigation algorithm also exhibit common patterns such as mitigation in the post-processing is often costly (in terms of performance) and mitigation in the pre-processing stage is preferred in most cases. We have also presented different trade-off choices of fairness mitigation decisions. Our study suggests future research directions to reduce the gap between theoretical fairness aware algorithms and the software engineering methods to leverage them in practice.

For agents

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

get_harvested_code_for_paper("2005.12379")
get_code_for_paper("2005.12379")
have("2005.12379")

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

curl https://syntology.ai/api/ran/2005.12379.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.12379.svg)](https://syntology.ai/paper/2005.12379)

Connect an agent — have() is free.