SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.01066 · IJCAI · 2022

Quantifying Health Inequalities Induced by Data and AI Models

Honghan Wu, Aneeta Sylolypavan, Minhong Wang, Sarah Wild

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 6 have no contract verdict; 0 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/2205.01066.json · badge: /api/ran/2205.01066.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
knowlab/DAindex-Framework canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
area_under_curve Ran
ran on a synthesized input
knowlab/DAindex-Framework/daindex/util.py
code served (permissive licence) · get_code("5dd33d7b8a3eefd0")
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 1, 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 numpy as np

# Create sample weighted data
# Shape (n, 3) where columns are: x values, y values, weights
w_data = np.array([
    [0.1, 0.2, 1.0],
    [0.3, 0.4, 1.0],
    [0.5, 0.6, 1.0],
    [0.7, 0.8, 1.0],
    [0.9, 0.95, 1.0]
], dtype=np.float32)

ARGS = {
    "w_data": w_data,
    "decision_boundary": 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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_random_sample Ran
ran on a synthesized input
knowlab/DAindex-Framework/daindex/util.py
code served (permissive licence) · get_code("158b1faa6f61de8f")
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 ndarray, ndim 2, dtype family float, shape (4, 1) 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
import pandas as pd

def dummy_feature_gen(row):
    """Simple feature generator that sums the row values"""
    return row.sum()

# Create a small DataFrame with some sample data
df = pd.DataFrame({
    'feature_a': [1.0, 2.0, 3.0, 4.0],
    'feature_b': [5.0, 6.0, 7.0, 8.0],
    'feature_c': [9.0, 10.0, 11.0, 12.0]
})

ARGS = {
    'df': df,
    'feature': 'feature_a',
    'feature_gen_fun': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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 (4, 1) — shape (4, 1) 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
get_scores Ran
ran on a synthesized input
knowlab/DAindex-Framework/daindex/ml.py
code served (permissive licence) · get_code("1fd27fd4b01f06c1")
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 ndarray, ndim 1, dtype family float, shape (2,) 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
import pandas as pd

class SimpleModel:
    """A minimal probabilistic model with predict_proba method."""
    
    def __init__(self, seed=0):
        np.random.seed(seed)
    
    def predict_proba(self, in_matrix: np.ndarray) -> np.ndarray:
        """
        Returns probabilities for 2 classes.
        Shape: (n_samples, 2) where column 0 is class 0, column 1 is class 1
        """
        n_samples = in_matrix.shape[0]
        probs_class_1 = np.random.rand(n_samples)
        probs_class_0 = 1 - probs_class_1
        return np.column_stack([probs_class_0, probs_class_1])

# Create sample data
np.random.seed(0)
n_rows = 2
n_features = 4

# Create a DataFrame with distinct feature columns
data = {
    'feature_1': np.random.randn(n_rows),
    'feature_2': np.random.randn(n_rows),
    'feature_3': np.random.randn(n_rows),
    'feature_4': np.random.randn(n_rows),
    'target': np.random.randint(0, 2, n_rows)
}
df = pd.DataFrame(data)

# Create multiple models
models = [SimpleModel(seed=i) for i in range(3)]

# Feature list to use
feature_list = ['feature_1', 'feature_2', 'feature_3', 'feature_4']

ARGS = {
    'models': models,
    'df': df,
    'feature_list': feature_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
get_threshold_index Ran
ran on a synthesized input
knowlab/DAindex-Framework/daindex/core.py
code served (permissive licence) · get_code("24105c16220c431c")
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 int, ndim 0, dtype family int, 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 logging

def get_threshold_index(threshold: float, low_bound: float, is_discrete: bool, prev_val_offset: float, step: float, boundary_offset: float) -> int:
    """
    Calculate threshold value index
    """
    threshold_index = int((threshold - low_bound) / step)
    if threshold == low_bound + boundary_offset:
        logging.info(f'adjust boundary {threshold}')
        threshold_index = int((threshold - low_bound - boundary_offset) / step)
    elif is_discrete:
        threshold_index_prev = int((threshold - prev_val_offset - low_bound) / step)
        threshold_index = int(threshold_index_prev + (threshold_index - threshold_index_prev) / 2)
    return threshold_index

ARGS = {
    "threshold": 5.5,
    "low_bound": 0.0,
    "is_discrete": False,
    "prev_val_offset": 1.0,
    "step": 0.5,
    "boundary_offset": 0.2
}
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 int, ndim 0, dtype family int, 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
gridsearch_bandwidth Ran
ran on a synthesized input
knowlab/DAindex-Framework/daindex/core.py
code served (permissive licence) · get_code("afa22693ac638a5f")
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 float64, ndim 0, 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 numpy as np
from sklearn.model_selection import GridSearchCV, KFold
from sklearn.neighbors import KernelDensity

# Create a small numpy array for KDE fitting
# KDE expects 2D array with shape (n_samples, n_features)
np.random.seed(0)
in_matrix = np.random.randn(10, 3)

ARGS = {
    'in_matrix': in_matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
search_for_zero_mass_index Ran
ran on a synthesized input
knowlab/DAindex-Framework/daindex/core.py
code served (permissive licence) · get_code("d96fdb67452197a6")
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 1, 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 numpy as np
from sklearn.neighbors import KernelDensity

# Create training data for the KernelDensity estimator
np.random.seed(0)
train_data = np.random.randn(50, 1) * 2 + 5  # 50 samples, 1 feature, centered around 5

# Fit a KernelDensity estimator
kde = KernelDensity(kernel='gaussian', bandwidth=0.5)
kde.fit(train_data)

# Define arguments
ARGS = {
    'kde': kde,
    'min_v': 0.5,
    'n_samples': 100
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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, ndim 1, 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

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, 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 6 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

AI technologies are being increasingly tested and applied in critical environments including healthcare. Without an effective way to detect and mitigate AI induced inequalities, AI might do more harm than good, potentially leading to the widening of underlying inequalities. This paper proposes a generic allocation-deterioration framework for detecting and quantifying AI induced inequality. Specifically, AI induced inequalities are quantified as the area between two allocation-deterioration curves. To assess the framework's performance, experiments were conducted on ten synthetic datasets (N>33,000) generated from HiRID -a real-world Intensive Care Unit (ICU) dataset, showing its ability to accurately detect and quantify inequality proportionally to controlled inequalities. Extensive analyses were carried out to quantify health inequalities (a) embedded in two real-world ICU datasets; (b) induced by AI models trained for two resource allocation scenarios. Results showed that compared to men, women had up to 33% poorer deterioration in markers of prognosis when admitted to HiRID ICUs. All four AI models assessed were shown to induce significant inequalities (2.45% to 43.2%) for non-White compared to White patients. The models exacerbated data embedded inequalities significantly in 3 out of 8 assessments, one of which was >9 times worse.

For agents

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

get_harvested_code_for_paper("2205.01066")
get_code_for_paper("2205.01066")
have("2205.01066")

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

curl https://syntology.ai/api/ran/2205.01066.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.01066.svg)](https://syntology.ai/paper/2205.01066)

Connect an agent — have() is free.