SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.07574 · CVPR · 2023

Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

Tianyu Pang, Min Lin, Ngai-Man Cheung, Milad Abdollahzadeh, Shuicheng Yan, Yunqing Zhao, Chao Du

arXiv · PDF · Open in the Atlas

Code that ran

20 of 25 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; 2 honoured the contract we drafted, 1 violated it and 10 have no contract verdict; 7 failures of our instrument; 5 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/2304.07574.json · badge: /api/ran/2304.07574.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
yunqing-me/RICK community (classifier label)
classifier basis not recorded on the link
20 ran · 5 no recorded run
FunctionStatusWhere it lives
all_gather Ran
ran on a synthesized input
yunqing-me/RICK/distributed.py
code served (permissive licence) · get_code("ed03ba54397adbe4")
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 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import pickle

torch.manual_seed(0)

# The function all_gather takes one parameter: data
# It should be something that can be pickled and unpickled
# We'll use a simple dictionary containing a tensor and some other data

data = {
    'tensor': torch.randn(2, 4),
    'value': 42,
    'string': 'test'
}

ARGS = {
    'data': data
}
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 list, ndim 1, 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
calculate_activation_statistics Ran
ran on a synthesized input
yunqing-me/RICK/gan_metrics/fid_score.py
code served (permissive licence) · get_code("fa02bf7e7932504d")
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 numpy as np

torch_seed = 0
np.random.seed(torch_seed)

# Create activation statistics as a small numpy array
# Batch size: 2, Feature dimension: 4
# This represents activations from a model's layer (e.g., pool_3 from Inception)
act = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "act": act,
}
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 — 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
compute_pairwise_distances Ran
ran, honoured the contract we drafted
yunqing-me/RICK/gan_metrics/precision_recall.py
code served (permissive licence) · get_code("af985ecf236605b0")
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 (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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create small numpy arrays for testing
# X: shape (2, 4) - 2 samples, 4 dimensions
X = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
], dtype=np.float64)

# Y: shape (3, 4) - 3 samples, 4 dimensions (different from X to show non-square output)
Y = np.array([
    [1.5, 2.5, 3.5, 4.5],
    [5.5, 6.5, 7.5, 8.5],
    [9.0, 10.0, 11.0, 12.0]
], dtype=np.float64)

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
numpy — 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 (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
d_logistic_loss Ran
ran; our contract draft was wrong, not the code
yunqing-me/RICK/train_dynamic_update_prune.py
code served (permissive licence) · get_code("3651db4e5ae8d189")
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 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 predictions from discriminator for real and fake samples
# These are typically logits (unbounded real values)
# Shape: (batch_size,) or (batch_size, 1) - using (batch_size,) for simplicity
real_pred = torch.randn(2)  # batch size 2
fake_pred = torch.randn(2)  # batch size 2

ARGS = {
    'real_pred': real_pred,
    'fake_pred': fake_pred
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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
data_sampler Ran
ran; our contract draft was wrong, not the code
yunqing-me/RICK/train_dynamic_update_prune.py
code served (permissive licence) · get_code("dbb756dcd778f52f")
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 RandomSampler. 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 torch.utils import data

torch.manual_seed(0)

# Create a simple dataset
class SimpleDataset(data.Dataset):
    def __init__(self, size=10):
        self.size = size
        self.data = torch.randn(size, 4)
        self.labels = torch.randint(0, 2, (size,))
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return self.data[idx], self.labels[idx]

dataset = SimpleDataset(size=10)
shuffle = True
distributed = False

ARGS = {
    'dataset': dataset,
    'shuffle': shuffle,
    'distributed': distributed
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RandomSampler — a RandomSampler output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RandomSampler 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
distances2radii Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yunqing-me/RICK/gan_metrics/precision_recall.py
pointer only (licence: MIT); the stored copy get_code serves, from AlexVerine/PrecisionRecallGan, is pointer only (licence: NONE) · get_code("321ebed484cb3298")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from AlexVerine/PrecisionRecallGan, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_kth_value Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yunqing-me/RICK/gan_metrics/precision_recall.py
pointer only (licence: MIT); the stored copy get_code serves, from AlexVerine/PrecisionRecallGan, is pointer only (licence: NONE) · get_code("bcc716018b80b027")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from AlexVerine/PrecisionRecallGan, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_parameter_number Ran
ran on a synthesized input
yunqing-me/RICK/gan_training/utils_model_load.py
code served (permissive licence) · get_code("a6c491bc2737153b")
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 torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 8)
        self.linear2 = nn.Linear(8, 3)
        # Make some parameters non-trainable
        self.linear2.weight.requires_grad = False
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

net = SimpleNet()

ARGS = {
    'net': net,
    'name': 'test_network'
}
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 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
is_url Ran
ran, violated the contract we drafted
yunqing-me/RICK/gan_training/checkpoints.py
code served (permissive licence) · get_code("e39d881796e8d67e")
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 urllib

def is_url(url):
    scheme = urllib.parse.urlparse(url).scheme
    return scheme in ('http', 'https')

ARGS = {
    'url': 'https://example.com'
}
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 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
load_part_model Ran
ran; our contract draft was wrong, not the code
yunqing-me/RICK/gan_training/utils_model_load.py
code served (permissive licence) · get_code("b3be36dffe58c81c")
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 SimpleModel. 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)

class SimpleModel(nn.Module):
    def __init__(self, add_embedding=False, add_fc=False):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
        if add_embedding:
            self.embedding = nn.Embedding(10, 4)
        if add_fc:
            self.fc = nn.Linear(2, 1)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x
    
    def state_dic(self):
        return self.state_dict()

# Create m_fix with some layers including embedding and fc
m_fix = SimpleModel(add_embedding=True, add_fc=True)

# Create m_ini without embedding and fc (but with matching shared layers)
m_ini = SimpleModel(add_embedding=False, add_fc=False)

ARGS = {
    'm_fix': m_fix,
    'm_ini': m_ini
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
load_weights_without_module Ran
ran on a synthesized input
yunqing-me/RICK/gan_training/utils_model_load.py
code served (permissive licence) · get_code("2e7389cbf3256ad6")
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 SimpleModel. 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 collections import OrderedDict

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Create a state dict with 'module' prefix (simulating DataParallel weights)
state_dict_with_module = OrderedDict()
state_dict_with_module['module.linear1.weight'] = torch.randn(3, 4)
state_dict_with_module['module.linear1.bias'] = torch.randn(3)
state_dict_with_module['module.linear2.weight'] = torch.randn(2, 3)
state_dict_with_module['module.linear2.bias'] = torch.randn(2)

ARGS = {
    'model': model,
    'dict': state_dict_with_module,
    'strict': False
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
polynomial_mmd Ran
ran on a synthesized input
yunqing-me/RICK/gan_metrics/kid_score.py
code served (permissive licence) · get_code("7405f2156522f874")
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.metrics.pairwise import polynomial_kernel

np.random.seed(0)

# Create small sample data
codes_g = np.random.randn(4, 5).astype(np.float32)
codes_r = np.random.randn(4, 5).astype(np.float32)

ARGS = {
    'codes_g': codes_g,
    'codes_r': codes_r,
    'degree': 3,
    'gamma': None,
    'coef0': 1,
    'var_at_m': None,
    'ret_var': True,
}
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
reduce_loss_dict Ran
ran on a synthesized input
yunqing-me/RICK/distributed.py
code served (permissive licence) · get_code("5144ad456049f8ce")
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 torch import distributed as dist

torch.manual_seed(0)

# Create a sample loss_dict with tensor values
# The function iterates over keys, stacks values, and performs distributed operations
loss_dict = {
    'loss_classifier': torch.tensor(0.5),
    'loss_box_reg': torch.tensor(0.3),
    'loss_objectness': torch.tensor(0.2),
}

ARGS = {
    'loss_dict': loss_dict,
}
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
reduce_sum Ran
ran, honoured the contract we drafted
yunqing-me/RICK/distributed.py
code served (permissive licence) · get_code("3f0a1105ef251d78")
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
import torch.nn as nn
from torch import distributed as dist

torch.manual_seed(0)

# The function takes a single parameter: tensor
# It calls .clone() on it and passes it to dist.all_reduce()
# So we need a torch.Tensor

tensor = torch.randn(2, 4)

ARGS = {
    "tensor": tensor
}
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
resize_and_convert Ran
ran on a synthesized input
yunqing-me/RICK/prepare_data.py
code served (permissive licence) · get_code("3d10a85c0ecf9e1a")
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 bytes. 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.

from PIL import Image
import torch

torch.manual_seed(0)

# Create a small PIL Image object
# The function expects a PIL Image with save() method
img = Image.new('RGB', (100, 80), color='red')

# Define parameters
size = (64, 64)  # target size for resize and center_crop
resample = Image.Resampling.BILINEAR  # resampling filter
quality = 95  # JPEG quality parameter

ARGS = {
    'img': img,
    'size': size,
    'resample': resample,
    'quality': quality
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
resize_multiple Ran
ran; our contract draft was wrong, not the code
yunqing-me/RICK/prepare_data.py
code served (permissive licence) · get_code("f127271d8e059adf")
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 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 torch
from PIL import Image
import numpy as np

# Create a simple PIL Image for testing
# The function expects a PIL Image object
img_array = np.random.randint(0, 256, (256, 256, 3), dtype=np.uint8)
test_img = Image.fromarray(img_array, mode='RGB')

ARGS = {
    'img': test_img,
    'sizes': (128, 256, 512),
    'resample': Image.LANCZOS,
    'quality': 100
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, 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
resize_worker Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yunqing-me/RICK/prepare_data.py
code served (permissive licence) · get_code("45efc707c199b872")
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
from PIL import Image
from io import BytesIO
import tempfile
import os

torch.manual_seed(0)

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

# Create a small test image and save it
test_image = Image.new('RGB', (256, 256), color=(73, 109, 137))
test_image_path = os.path.join(temp_dir, 'test_image.png')
test_image.save(test_image_path)

# Construct arguments for resize_worker
img_file = (0, test_image_path)  # (index, file_path)
sizes = (128, 256, 512)  # tuple of sizes to resize to
resample = Image.LANCZOS  # resampling filter

ARGS = {
    'img_file': img_file,
    'sizes': sizes,
    'resample': resample
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — 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
rotate_mat Ran
ran on a synthesized input
yunqing-me/RICK/non_leaking.py
code served (permissive licence) · get_code("a86cbcaf0967a531")
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 3, dtype family float, shape (2, 3, 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)

# theta should be a 1D tensor of angles
# The function accesses theta.shape[0] to get batch size
# Then applies torch.sin and torch.cos to theta
theta = torch.randn(2)

ARGS = {
    "theta": theta
}
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 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 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
scale_mat Ran
ran on a synthesized input
yunqing-me/RICK/non_leaking.py
code served (permissive licence) · get_code("6817fba628078009")
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 3, dtype family float, shape (2, 3, 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)

# The function scale_mat takes two parameters:
# - s_x: a tensor that will be used as mat[:, 0, 0] = s_x
# - s_y: a tensor that will be used as mat[:, 1, 1] = s_y
# Both need to have shape (batch,) where batch is the batch size

batch_size = 2
s_x = torch.randn(batch_size)
s_y = torch.randn(batch_size)

ARGS = {
    "s_x": s_x,
    "s_y": s_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 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 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
translate_mat Ran
ran on a synthesized input
yunqing-me/RICK/non_leaking.py
code served (permissive licence) · get_code("fdaede2415c5a2eb")
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 3, dtype family float, shape (2, 3, 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)

# The function takes two tensors: t_x and t_y
# It expects them to have a batch dimension (shape[0])
# It stacks them together, so they should have the same batch size
# Based on the function logic, t_x and t_y should be 1D tensors with batch elements

batch_size = 2
t_x = torch.randn(batch_size)
t_y = torch.randn(batch_size)

ARGS = {
    't_x': t_x,
    't_y': t_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 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 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
calculate_frechet_distance Not yet run
unverified (harvested, no recorded run)
yunqing-me/RICK/gan_metrics/fid_score.py
code served (permissive licence) · get_code("0def50a351111624")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

d_r1_loss Not yet run
unverified (harvested, no recorded run)
yunqing-me/RICK/train_dynamic_update_prune.py
pointer only (licence: MIT); the stored copy get_code serves, from stevenshaw1999/rssa, is pointer only (licence: NONE) · get_code("1fb99d8f83eb27f3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from stevenshaw1999/rssa, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_activations Not yet run
unverified (harvested, no recorded run)
yunqing-me/RICK/gan_metrics/fid_score.py
pointer only (licence: MIT); the stored copy get_code serves, from ssongwang/mix-domaincontrastivelearning, is pointer only (licence: NONE) · get_code("7b41327814ab3634")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ssongwang/mix-domaincontrastivelearning, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_activations Not yet run
unverified (harvested, no recorded run)
yunqing-me/RICK/gan_metrics/kid_score.py
code served (permissive licence) · get_code("8ab8902f4356f642")
How it ran

no invocation recorded.

polynomial_mmd_averages Not yet run
unverified (harvested, no recorded run)
yunqing-me/RICK/gan_metrics/kid_score.py
code served (permissive licence) · get_code("d24b7925cdc50001")
How it ran

no invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 24 are also present in other papers whose code we hold (24 with at least one paper dated earlier, 0 the same month, 10 later) and 0 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
calculate_frechet_distance 74 other papers
35 dated earlier, 38 later, 1 same year, order not determinable
1610.09585 (2016-10)
Conditional Image Synthesis With Auxiliary Classifier GANs
1706.08500 (2017-06)
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
1807.11458 (2018-07)
To learn image super-resolution, use a GAN to learn how to do image degradation first
and 71 more not named here
reduce_sum 14 other papers
11 dated earlier, 3 later
1910.05852 (2019-10)
Implicit competitive regularization in GANs
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2007.06600 (2020-07)
Closed-Form Factorization of Latent Semantics in GANs
and 11 more not named here
all_gather 13 other papers
11 dated earlier, 2 later
1910.05852 (2019-10)
Implicit competitive regularization in GANs
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2007.06600 (2020-07)
Closed-Form Factorization of Latent Semantics in GANs
and 10 more not named here
data_sampler 13 other papers
13 dated earlier
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2001.04296 (2020-01)
High-Fidelity Synthesis with Disentangled Representation
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
and 10 more not named here
reduce_loss_dict 13 other papers
11 dated earlier, 2 later
1910.05852 (2019-10)
Implicit competitive regularization in GANs
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2007.06600 (2020-07)
Closed-Form Factorization of Latent Semantics in GANs
and 10 more not named here
d_logistic_loss 12 other papers
12 dated earlier
1910.05852 (2019-10)
Implicit competitive regularization in GANs
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2001.04296 (2020-01)
High-Fidelity Synthesis with Disentangled Representation
and 9 more not named here
is_url 12 other papers
9 dated earlier, 3 later
1912.07372 (2019-12)
Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision
2001.05119 (2020-01)
Learning multiview 3D point cloud registration
2003.04618 (2020-03)
Convolutional Occupancy Networks
and 9 more not named here
d_r1_loss 5 other papers
5 dated earlier
1910.05852 (2019-10)
Implicit competitive regularization in GANs
2006.10738 (2020-06)
Differentiable Augmentation for Data-Efficient GAN Training
2112.10762 (2021-12)
StyleSwin: Transformer-based GAN for High-resolution Image Generation
and 2 more not named here
resize_multiple 5 other papers
3 dated earlier, 2 later
2111.15640 (2021-11)
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
2203.14954 (2022-03)
GIRAFFE HD: A High-Resolution 3D-aware Generative Model
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
and 2 more not named here
get_activations 4 other papers
3 dated earlier, 1 later
1907.10830 (2019-07)
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
2006.06676 (2020-06)
Training Generative Adversarial Networks with Limited Data
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
and 1 more not named here
calculate_activation_statistics 3 other papers
3 dated earlier
1907.10830 (2019-07)
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
2006.06676 (2020-06)
Training Generative Adversarial Networks with Limited Data
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
polynomial_mmd 3 other papers
3 dated earlier
2003.05033 (2020-03)
Generalized Energy Based Models
2108.10310 (2021-08)
Ranking Models in Unlabeled New Environments
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
compute_pairwise_distances 2 other papers
1 dated earlier, 1 later
1904.06991 (2019-04)
Improved Precision and Recall Metric for Assessing Generative Models
2412.08480 (2024-12)
InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models
distances2radii 2 other papers
1 dated earlier, 1 later
1904.06991 (2019-04)
Improved Precision and Recall Metric for Assessing Generative Models
2412.08480 (2024-12)
InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models
get_kth_value 2 other papers
1 dated earlier, 1 later
1904.06991 (2019-04)
Improved Precision and Recall Metric for Assessing Generative Models
2412.08480 (2024-12)
InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models
load_part_model 2 other papers
2 dated earlier
1904.01774 (2019-04)
Image Generation From Small Datasets via Batch Statistics Adaptation
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
resize_worker 2 other papers
2 dated earlier
2203.14954 (2022-03)
GIRAFFE HD: A High-Resolution 3D-aware Generative Model
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
get_parameter_number 1 other paper
1 dated earlier
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
load_weights_without_module 1 other paper
1 dated earlier
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
polynomial_mmd_averages 1 other paper
1 dated earlier
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Shown: the 20 functions present in the most other papers. 4 more shared functions are not listed here.

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

ProgressiveGAN StyleGAN-V2 Church ↦ Sailboat FFHQ ↦ AFHQ-Cat Church ↦ Sailboat FFHQ ↦ AFHQ-Cat Pretraining on large source dataset (e.g., LSUN-Church, FFHQ…) Adaptation on few-shot target samples (e.g., Sailboat, AFHQ-Cat…) G s G t SailBoat (10-shot) initialize LSUN-Church (126 K) Resulting generator Transfer Learning for FSIG TGAN AdAM Ours EWC AFHQ-Cat (10-shot) SailBoat (10-shot) Resulting generator (a) (c) G s (b) Figure 1. In FSIG, transfer of incompatible knowledge would cause significant degradation of the realisticness of synthetic samples, and existing SOTA methods fail to address this issue. (a) Prior knowledge of the source GAN generator Gs is selected, preserved, and transferred to learn the target generator Gt, given very limited target domain training samples (see 10-shot in (b)). In this work, we consider challenging setups where the target domain could be semantically distant from the source domain, e.g., (i) Church Ñ Sailboat (ii) FFHQ Ñ AFHQ-Cat. (c) Synthetic images from Gs, TGAN [65]; and SOTA methods: EWC [41] and AdAM [75]. Images in each column are from the same noise input. Critically, existing FSIG methods focus on knowledge preservation, while failing to prevent the transfer of knowledge that is incompatible with the target domain. This gives rise to unrealistic samples generated by Gt, e.g., "Trees/Buildings on the Sea" (Red frames), or "Cats with Glasses" (Green frames). In contrast, our method (row-5 in (c)) based on knowledge truncation can effectively prevent the transfer of incompatible knowledge. See our detailed analysis in Sec. 4. Best viewed in color with zooming in.

For agents

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

get_harvested_code_for_paper("2304.07574")
get_code_for_paper("2304.07574")
have("2304.07574")

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

curl https://syntology.ai/api/ran/2304.07574.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.07574.svg)](https://syntology.ai/paper/2304.07574)

Connect an agent — have() is free.