SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04580 · ICCV · 2021

Towards Discovery and Attribution of Open-world GAN Generated Images

Saksham Suri, Sharath Girish

arXiv · PDF · Open in the Atlas

Code that ran

15 of 16 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; 3 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 10 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/2105.04580.json · badge: /api/ran/2105.04580.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
Sharath-girish/openworld-gan canonical (classifier label)
classifier basis: census
15 ran · 1 no recorded run
FunctionStatusWhere it lives
blur_jpeg_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Sharath-girish/openworld-gan/transforms.py
code served (permissive licence) · get_code("564f45fee3b447f8")
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 Compose. 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 numpy as np
from PIL import Image
import cv2

torch.manual_seed(0)

# The function blur_jpeg_transform takes one parameter: resize_dims
# Looking at the function body, resize_dims is used in:
# - transforms.CenterCrop(resize_dims)
# - transforms.Lambda(lambda img: custom_resize(img, resize_dims))
# Both of these expect a tuple of (height, width) or an int
# CenterCrop and resize accept tuple[int, int] or int

# Create a small test image to verify the pipeline works
test_image = Image.new('RGB', (8, 8), color='red')

ARGS = {
    'resize_dims': (4, 4)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy, scipy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
data_augment Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/transforms.py
code served (permissive licence) · get_code("edd4d9dc63592d37")
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 Image. 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 PIL import Image

# Create a small test image (height=4, width=3, channels=3)
# Using uint8 dtype as expected by the function
test_img = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)
test_pil_img = Image.fromarray(test_img)

ARGS = {
    'img': test_pil_img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
deep_update Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/config.py
code served (permissive licence) · get_code("4fb209b49087100a")
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 dict. 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
from collections.abc import Mapping, MutableMapping

torch.manual_seed(0)

# Create a base dictionary to update
d = {
    "learning_rate": 0.001,
    "batch_size": 32,
    "model": {
        "hidden_dim": 128,
        "num_layers": 2
    }
}

# Create an update dictionary with nested mappings
u = {
    "batch_size": 64,
    "model": {
        "num_layers": 3,
        "dropout": 0.5
    },
    "optimizer": {
        "name": "adam",
        "params": {
            "betas": (0.9, 0.999)
        }
    }
}

# Create a factory function for creating new MutableMapping instances
def create_map():
    return {}

ARGS = {
    "d": d,
    "u": u,
    "create_map": create_map
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
default_loader Ran
ran, honoured the contract we drafted
Sharath-girish/openworld-gan/datasets.py
code served (permissive licence) · get_code("c22099ee6d7856ba")
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 Image. 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 tempfile
import os
from PIL import Image

# Create a temporary directory and a valid test image
temp_dir = tempfile.mkdtemp()
test_image_path = os.path.join(temp_dir, "test_image.png")

# Create a small RGB image and save it
img = Image.new('RGB', (4, 3), color=(255, 0, 0))
img.save(test_image_path)

ARGS = {
    "path": test_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
default_transform Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/transforms.py
code served (permissive licence) · get_code("1ea9bdb8a1949c6a")
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 Compose. 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 torchvision.transforms as transforms

torch.manual_seed(0)

ARGS = {
    "resize_dims": (224, 224)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
get_hashperm Ran
ran, honoured the contract we drafted
Sharath-girish/openworld-gan/ood_detection.py
code served (permissive licence) · get_code("c5da6ea2b1410b04")
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, 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)

N = 2
n_feats = 4
device = 'cpu'

ARGS = {
    'N': N,
    'n_feats': n_feats,
    'device': device
}
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, 4) — shape (2, 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
get_means Ran
ran, violated the contract we drafted
Sharath-girish/openworld-gan/merge.py
code served (permissive licence) · get_code("69b2b3610e7431ba")
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 list, 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 numpy as np

# Create sample data
# X: feature matrix with shape (6, 4) - 6 samples, 4 features
X = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [1.5, 2.5, 3.5, 4.5],
    [5.0, 6.0, 7.0, 8.0],
    [5.5, 6.5, 7.5, 8.5],
    [9.0, 10.0, 11.0, 12.0],
    [9.5, 10.5, 11.5, 12.5]
], dtype=np.float32)

# labels: class assignments for each sample (3 unique classes: 0, 1, 2)
labels = np.array([0, 0, 1, 1, 2, 2], dtype=np.int32)

ARGS = {
    "X": X,
    "labels": labels
}
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 list, ndim 2, dtype family float — a list 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_network Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/networks.py
code served (permissive licence) · get_code("11582436ae076f3a")
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 type. 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
from torchvision import models

torch.manual_seed(0)

# The function get_network takes a single parameter 'name'
# It looks up the name in network_mapping and returns the corresponding class
# Valid names are 'multiclassnet' and 'mobilenetv2'

ARGS = {
    'name': 'multiclassnet'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
get_pairwise_distances Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/clustering.py
code served (permissive licence) · get_code("de40e954cfc6291e")
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)

# Create small tensors for X and Y
# X: (2, 4) - 2 samples, 4 dimensions
# Y: (3, 4) - 3 samples, 4 dimensions (distinct sizes for probing)
X = torch.randn(2, 4)
Y = torch.randn(3, 4)

ARGS = {
    'X': X,
    'Y': Y,
    'metric': 'euclidean'
}
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
has_file_allowed_extension Ran
ran, violated the contract we drafted
Sharath-girish/openworld-gan/datasets.py
code served (permissive licence) · get_code("70ee124084db90b2")
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 bool, 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

ARGS = {
    "filename": "document.pdf",
    "extensions": (".pdf", ".txt", ".doc")
}
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 bool, 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
kmeans_gpu Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/clustering.py
code served (permissive licence) · get_code("f8a13f0f143a2d1d")
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. 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 numpy as np

torch.manual_seed(0)
np.random.seed(0)

# Create small synthetic data
# data shape: (num_samples, num_features)
data = torch.randn(6, 4)

# Number of clusters
k = 2

# Device (CPU only)
device = 'cpu'

# Optional: pre-initialized centroids (None means kmeans_init will be called)
centroids = None

# Max iterations
max_iter = 3

ARGS = {
    'data': data,
    'k': k,
    'device': device,
    'max_iter': max_iter,
    'centroids': centroids
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
kmeans_init Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/clustering.py
code served (permissive licence) · get_code("842a033bdf67b205")
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 (3, 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
import numpy as np
import sys

torch.manual_seed(0)
np.random.seed(0)

# Create small test data: 6 samples, 4 features
data = torch.randn(6, 4)

# Parameters for kmeans_init
k = 3  # number of clusters
device = 'cpu'  # CPU only

ARGS = {
    'data': data,
    'k': k,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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 (3, 4) — shape (3, 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
knn_gpu Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/merge.py
code served (permissive licence) · get_code("70fdb12e24d64495")
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 (6, 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 torch
import numpy as np

torch.manual_seed(0)

# Create small test data
# X should be a numpy array of shape (n_samples, n_features)
# Let's use 6 samples with 4 features
X = np.random.randn(6, 4).astype(np.float32)

# k is the number of nearest neighbors to find
k = 2

# device is where to run the computation
device = 'cpu'

ARGS = {
    'X': X,
    'k': k,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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 (6, 2) — shape (6, 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
pil_loader Ran
ran, honoured the contract we drafted
Sharath-girish/openworld-gan/datasets.py
code served (permissive licence) · get_code("f321f54723433661")
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) and returned Image. 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 numpy as np
from PIL import Image
import io
import os
import tempfile

# Create a temporary directory for test files
temp_dir = tempfile.mkdtemp()

# Create a simple RGB image and save it to a temporary file
img = Image.new('RGB', (10, 10), color=(73, 109, 137))
test_image_path = os.path.join(temp_dir, 'test_image.jpg')
img.save(test_image_path)

ARGS = {
    'path': test_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
quantiles Ran
ran; our contract draft was wrong, not the code
Sharath-girish/openworld-gan/ood_detection.py
code served (permissive licence) · get_code("f07bc59b09e88c87")
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 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

torch.manual_seed(0)

# Create a small tensor for x parameter
x = torch.randn(4)

# Create a fraction value for frac parameter
frac = 0.25

ARGS = {
    "x": x,
    "frac": frac
}
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 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
get_hash Not yet run
unverified (harvested, no recorded run)
Sharath-girish/openworld-gan/ood_detection.py
code served (permissive licence) · get_code("a631d17bc1b9daee")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 3 later) and 13 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
pil_loader 66 other papers
12 dated earlier, 1 the same month, 53 later
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
and 63 more not named here
has_file_allowed_extension 4 other papers
2 dated earlier, 2 later
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
2003.14297 (2020-03)
Generative Latent Implicit Conditional Optimization when Learning from Small Sample
2306.02031 (2023-06)
DOS: Diverse Outlier Sampling for Out-of-Distribution Detection
and 1 more not named here
deep_update 2 other papers
2 later
2203.02094 (2022-03)
LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models
2408.09153 (2024-08)
Are CLIP features all you need for Universal Synthetic Image Origin 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

With the recent progress in Generative Adversarial Networks (GANs), it is imperative for media and visual forensics to develop detectors which can identify and attribute images to the model generating them. Existing works have shown to attribute images to their corresponding GAN sources with high accuracy. However, these works are limited to a closed set scenario, failing to generalize to GANs unseen during train time and are therefore, not scalable with a steady influx of new GANs. We present an iterative algorithm for discovering images generated from previously unseen GANs by exploiting the fact that all GANs leave distinct fingerprints on their generated images. Our algorithm consists of multiple components including network training, out-of-distribution detection, clustering, merge and refine steps. Through extensive experiments, we show that our algorithm discovers unseen GANs with high accuracy and also generalizes to GANs trained on unseen real datasets. We additionally apply our algorithm to attribution and discovery of GANs in an online fashion as well as to the more standard task of real/fake detection. Our experiments demonstrate the effectiveness of our approach to discover new GANs and can be used in an open-world setup.

For agents

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

get_harvested_code_for_paper("2105.04580")
get_code_for_paper("2105.04580")
have("2105.04580")

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

curl https://syntology.ai/api/ran/2105.04580.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.04580.svg)](https://syntology.ai/paper/2105.04580)

Connect an agent — have() is free.