SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.20722 · 2024

Interpretable Image Classification with Adaptive Prototype-based Vision Transformers

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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; 5 failures of our instrument; 1 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/2410.20722.json · badge: /api/ran/2410.20722.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
Henrymachiyu/ProtoViT canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
create_logger Ran
ran; our contract draft was wrong, not the code
Henrymachiyu/ProtoViT/log.py
code served (permissive licence) · get_code("da0f80d54b852951")
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 os
import tempfile

# Create a temporary file for logging
temp_dir = tempfile.gettempdir()
log_filename = os.path.join(temp_dir, "test_logger.log")

# Ensure the file exists and is empty for this test
with open(log_filename, 'w') as f:
    f.write("")

ARGS = {
    "log_filename": log_filename,
    "display": True,
}
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 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
find_high_activation_crop Ran
ran, honoured the contract we drafted
Henrymachiyu/ProtoViT/helpers.py
code served (permissive licence) · get_code("a578552e64b8de7e")
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 int; 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 a sample activation map
# The function expects a 2D numpy array (height x width)
# Let's create one with some high and low activation values
np.random.seed(0)
activation_map = np.random.rand(8, 6) * 100  # Values between 0-100

# Define ARGS dict with all parameters
ARGS = {
    'activation_map': activation_map,
    'percentile': 95
}
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 int — 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
list_of_distances Ran
ran; our contract draft was wrong, not the code
Henrymachiyu/ProtoViT/helpers.py
code served (permissive licence) · get_code("c9e92d0b7ff929fe")
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 Tensor, ndim 2, dtype family float, shape (2, 3) 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

torch.manual_seed(0)

# X: shape (batch_size, dim) - will be unsqueezed to (batch_size, dim, 1)
X = torch.randn(2, 4)

# Y: shape (num_points, dim) - will be transposed to (dim, num_points) then unsqueezed to (1, dim, num_points)
Y = torch.randn(3, 4)

ARGS = {
    "X": X,
    "Y": Y,
}
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 Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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
preprocess Ran
ran; our contract draft was wrong, not the code
Henrymachiyu/ProtoViT/preprocess.py
code served (permissive licence) · get_code("2f5c8689a7884f62")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) 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

torch.manual_seed(0)

# Create a small tensor with batch size 2, 3 channels, and 4x4 spatial dimensions
x = torch.randn(2, 3, 4, 4)

# Define mean and std for normalization
mean = (0.485, 0.456, 0.406)
std = (0.229, 0.224, 0.225)

ARGS = {
    "x": x,
    "mean": mean,
    "std": std
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 4) 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
preprocess_input_function Ran
ran; our contract draft was wrong, not the code
Henrymachiyu/ProtoViT/preprocess.py
code served (permissive licence) · get_code("d22fdfbc49113693")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 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 torch

torch.manual_seed(0)

# The function preprocess_input_function takes one parameter: x
# Looking at the function body, x is used in preprocess() which:
# - Checks that x.size(1) == 3 (second dimension must be 3, for RGB channels)
# - Creates a tensor of same shape as x
# - Indexes x with [:, i, :, :] for i in range(3)
# This means x must be a 4D tensor with shape (batch, 3, height, width)

# Create a small test tensor: batch_size=2, channels=3, height=4, width=5
x = torch.randn(2, 3, 4, 5)

ARGS = {
    "x": x
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 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
undo_preprocess Ran
ran; our contract draft was wrong, not the code
Henrymachiyu/ProtoViT/preprocess.py
code served (permissive licence) · get_code("efb86a8611f14f72")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) 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

torch.manual_seed(0)

# Create a small batch of preprocessed images (batch_size=2, channels=3, height=4, width=4)
x = torch.randn(2, 3, 4, 4)

mean = (0.485, 0.456, 0.406)
std = (0.229, 0.224, 0.225)

ARGS = {
    "x": x,
    "mean": mean,
    "std": std
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 4) 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
update_prototypes_on_batch Not yet run
unverified (harvested, no recorded run)
Henrymachiyu/ProtoViT/push_greedy.py
code served (permissive licence) · get_code("1b73c64fe6759663")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 3 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
preprocess_input_function 3 other papers
2 dated earlier, 1 later
1606.00915 (2016-06)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
1906.10651 (2019-06)
Interpretable Image Recognition with Hierarchical Prototypes
2503.01087 (2025-03)
Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time
create_logger 2 other papers
2 dated earlier
1606.00915 (2016-06)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
1906.10651 (2019-06)
Interpretable Image Recognition with Hierarchical Prototypes
find_high_activation_crop 2 other papers
2 dated earlier
1606.00915 (2016-06)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
2208.10431 (2022-08)
ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition
list_of_distances 2 other papers
2 dated earlier
1606.00915 (2016-06)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
1906.10651 (2019-06)
Interpretable Image Recognition with Hierarchical Prototypes
preprocess 2 other papers
1 dated earlier, 1 later
1606.00915 (2016-06)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
2605.02167 (2026-05)
Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution
undo_preprocess 2 other papers
1 dated earlier, 1 later
1606.00915 (2016-06)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
2605.02167 (2026-05)
Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution

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 ProtoViT, a method for interpretable image classification combining deep learning and case-based reasoning. This method classifies an image by comparing it to a set of learned prototypes, providing explanations of the form ``this looks like that.'' In our model, a prototype consists of \textit{parts}, which can deform over irregular geometries to create a better comparison between images. Unlike existing models that rely on Convolutional Neural Network (CNN) backbones and spatially rigid prototypes, our model integrates Vision Transformer (ViT) backbones into prototype based models, while offering spatially deformed prototypes that not only accommodate geometric variations of objects but also provide coherent and clear prototypical feature representations with an adaptive number of prototypical parts. Our experiments show that our model can generally achieve higher performance than the existing prototype based models. Our comprehensive analyses ensure that the prototypes are consistent and the interpretations are faithful.

For agents

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

get_harvested_code_for_paper("2410.20722")
get_code_for_paper("2410.20722")
have("2410.20722")

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

curl https://syntology.ai/api/ran/2410.20722.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.20722.svg)](https://syntology.ai/paper/2410.20722)

Connect an agent — have() is free.