SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.14925 · 2020

MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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 4 have no contract verdict; 2 failures of our instrument; 4 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/2010.14925.json · badge: /api/ran/2010.14925.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
MedMNIST/MedMNIST canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
zhenyx19/medmnist community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
blupblupblup/near-ood-doppler-signatures community (classifier label)
classifier basis not recorded on the link
0 ran · 4 no recorded run
FunctionStatusWhere it lives
ResNet18 Ran
ran on a synthesized input
zhenyx19/medmnist/medmnist/models.py
code served (permissive licence) · get_code("0dab80778783602c")
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 ResNet. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_channels": 1,
    "num_classes": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
ResNet50 Ran
ran on a synthesized input
zhenyx19/medmnist/medmnist/models.py
code served (permissive licence) · get_code("2f6d81eee664f861")
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 ResNet. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_channels": 1,
    "num_classes": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
getACC Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MedMNIST/MedMNIST/medmnist/evaluator.py
code served (permissive licence) · get_code("6a63099a0deb619e")
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 float, 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

# Test case 1: binary-class task with 1D y_score
y_true_binary = np.array([0, 1, 1, 0, 1])
y_score_binary = np.array([0.2, 0.8, 0.9, 0.3, 0.7])
task_binary = 'binary-class'

# Test case 2: multi-label, binary-class task with 2D arrays
y_true_multilabel = np.array([[0, 1, 0],
                               [1, 0, 1],
                               [0, 0, 1],
                               [1, 1, 0]])
y_score_multilabel = np.array([[0.2, 0.8, 0.3],
                                [0.9, 0.1, 0.7],
                                [0.1, 0.2, 0.9],
                                [0.8, 0.7, 0.2]])
task_multilabel = 'multi-label, binary-class'

# Test case 3: multi-class task
y_true_multiclass = np.array([0, 1, 2, 1, 0])
y_score_multiclass = np.array([[0.7, 0.2, 0.1],
                                [0.1, 0.8, 0.1],
                                [0.1, 0.1, 0.8],
                                [0.2, 0.6, 0.2],
                                [0.8, 0.1, 0.1]])
task_multiclass = 'multi-class'

# Use binary-class as the default test case
ARGS = {
    'y_true': y_true_binary,
    'y_score': y_score_binary,
    'task': task_binary,
    'threshold': 0.5
}
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 float, 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
getACC Ran
ran on a synthesized input
zhenyx19/medmnist/medmnist/evaluator.py
code served (permissive licence) · get_code("14ad4a09179bc8c9")
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 float, 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

# Test case 1: multi-label, binary-class task
y_true_multilabel = np.array([
    [1, 0, 1],
    [0, 1, 0],
    [1, 1, 0]
])
y_score_multilabel = np.array([
    [0.8, 0.2, 0.6],
    [0.3, 0.7, 0.4],
    [0.9, 0.6, 0.1]
])

# Test case 2: binary-class task
y_true_binary = np.array([1, 0, 1, 0])
y_score_binary = np.array([
    [0.2, 0.8],
    [0.7, 0.3],
    [0.1, 0.9],
    [0.6, 0.4]
])

# Test case 3: multi-class task
y_true_multiclass = np.array([0, 1, 2, 1])
y_score_multiclass = np.array([
    [0.7, 0.2, 0.1],
    [0.1, 0.8, 0.1],
    [0.2, 0.1, 0.7],
    [0.3, 0.5, 0.2]
])

ARGS = {
    'y_true': y_true_multilabel,
    'y_score': y_score_multilabel,
    'task': 'multi-label, binary-class',
    'threshold': 0.5
}
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 float, 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
getAUC Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MedMNIST/MedMNIST/medmnist/evaluator.py
code served (permissive licence) · get_code("c046f776e3213c4a")
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 float, 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 torch
import numpy as np
from sklearn.metrics import roc_auc_score

torch.manual_seed(0)

# Test case 1: multi-label, binary-class task
# y_true shape: (n_samples, n_labels)
# y_score shape: (n_samples, n_labels)
y_true_multilabel = np.array([[0, 1], [1, 0], [1, 1], [0, 0]])
y_score_multilabel = np.array([[0.1, 0.9], [0.8, 0.2], [0.7, 0.8], [0.3, 0.4]])

# Test case 2: binary-class task
# y_true shape: (n_samples,)
# y_score shape: (n_samples, 2) or (n_samples,)
y_true_binary = np.array([0, 1, 1, 0])
y_score_binary_2d = np.array([[0.2, 0.8], [0.3, 0.7], [0.1, 0.9], [0.6, 0.4]])

# Test case 3: multi-class task
# y_true shape: (n_samples,)
# y_score shape: (n_samples, n_classes)
y_true_multiclass = np.array([0, 1, 2, 0])
y_score_multiclass = np.array([[0.7, 0.2, 0.1], [0.1, 0.8, 0.1], [0.1, 0.2, 0.7], [0.8, 0.1, 0.1]])

ARGS = {
    "y_true": y_true_multilabel,
    "y_score": y_score_multilabel,
    "task": "multi-label, binary-class"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
getAUC Ran
ran on a synthesized input
zhenyx19/medmnist/medmnist/evaluator.py
code served (permissive licence) · get_code("01680b1f5aae44d4")
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 float, 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

# Test case 1: binary-class task
y_true_binary = np.array([0, 1, 1, 0, 1])
y_score_binary = np.array([
    [0.1, 0.9],
    [0.2, 0.8],
    [0.3, 0.7],
    [0.6, 0.4],
    [0.1, 0.9]
])

ARGS = {
    'y_true': y_true_binary,
    'y_score': y_score_binary,
    'task': 'binary-class'
}
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 float, 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
deep_msvdd Not yet run
unverified (harvested, no recorded run)
blupblupblup/near-ood-doppler-signatures/deep_msvdd.py
code served (permissive licence) · get_code("5effdf9e89a5bb8c")
How it ran

no invocation recorded.

deep_rpo_ssl Not yet run
unverified (harvested, no recorded run)
blupblupblup/near-ood-doppler-signatures/deep_rpo.py
code served (permissive licence) · get_code("59dbedad98df5e34")
How it ran

no invocation recorded.

deep_svdd_ssl Not yet run
unverified (harvested, no recorded run)
blupblupblup/near-ood-doppler-signatures/deep_svdd.py
code served (permissive licence) · get_code("2b2046a8f4b6fe68")
How it ran

no invocation recorded.

shallow_pca Not yet run
unverified (harvested, no recorded run)
blupblupblup/near-ood-doppler-signatures/shallow_pca.py
code served (permissive licence) · get_code("87a216a4d9ea4421")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

We present MedMNIST, a collection of 10 pre-processed medical open datasets. MedMNIST is standardized to perform classification tasks on lightweight 28x28 images, which requires no background knowledge. Covering the primary data modalities in medical image analysis, it is diverse on data scale (from 100 to 100,000) and tasks (binary/multi-class, ordinal regression and multi-label). MedMNIST could be used for educational purpose, rapid prototyping, multi-modal machine learning or AutoML in medical image analysis. Moreover, MedMNIST Classification Decathlon is designed to benchmark AutoML algorithms on all 10 datasets; We have compared several baseline methods, including open-source or commercial AutoML tools. The datasets, evaluation code and baseline methods for MedMNIST are publicly available at https://medmnist.github.io/.

For agents

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

get_harvested_code_for_paper("2010.14925")
get_code_for_paper("2010.14925")
have("2010.14925")

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

curl https://syntology.ai/api/ran/2010.14925.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.14925.svg)](https://syntology.ai/paper/2010.14925)

Connect an agent — have() is free.