SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.01561 · ICLR · 2025

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

Mingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai Huang

arXiv · PDF · Open in the Atlas

Code that ran

19 of 24 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; 5 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 12 failures of our instrument; 5 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2406.01561.json · badge: /api/ran/2406.01561.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
mingyuanzhou/SiD-LSG canonical (classifier label)
classifier basis: census
16 ran · 3 no recorded run
mingukkang/gigagan canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
mingyuanzhou/sid-lsg canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
parse_tuple Ran
ran, honoured the contract we drafted
mingyuanzhou/SiD-LSG/cocodataset_tool.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("9cd07419f7c926f8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from pdillis/stylegan3-fun, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

compute_clip_score Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mingukkang/gigagan/evaluation/evaluation.py
pointer only (licence: NONE) · get_code("a3aaa665cb2c6e2a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mingukkang/gigagan 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.

compute_distances Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mingyuanzhou/SiD-LSG/metrics/sid_precision_recall.py
code served (permissive licence) · get_code("790b320b90341326")
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 feature tensors
# row_features: used with unsqueeze(0) and cdist, so shape (num_rows, feature_dim)
row_features = torch.randn(2, 4)

# col_features: used with shape[0], unsqueeze(0), cdist, chunk, pad operations
# shape (num_cols, feature_dim)
col_features = torch.randn(3, 4)

# num_gpus: used in range and modulo operations
num_gpus = 1

# rank: used in comparison and indexing operations
rank = 0

# col_batch_size: used in division for batch calculation
col_batch_size = 2

ARGS = {
    "row_features": row_features,
    "col_features": col_features,
    "num_gpus": num_gpus,
    "rank": rank,
    "col_batch_size": col_batch_size,
}
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
encode_prompt Ran
ran; our contract draft was wrong, not the code
mingyuanzhou/SiD-LSG/training/sid_sd_util.py
code served (permissive licence) · get_code("b4e975940805a660")
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, 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
import torch.nn as nn

torch.manual_seed(0)

class MockTextEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.device = torch.device('cpu')
        self.linear = nn.Linear(4, 5)
    
    def forward(self, input_ids, attention_mask=None):
        batch_size = input_ids.shape[0]
        embeddings = self.linear(input_ids.float())
        return (embeddings,)

text_encoder = MockTextEncoder()

input_ids = torch.randint(0, 100, (2, 4))

ARGS = {
    'text_encoder': text_encoder,
    'input_ids': input_ids,
}
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, 5) — shape (2, 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
file_ext Ran
ran; our contract draft was wrong, not the code
mingyuanzhou/SiD-LSG/cocodataset_tool.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("a2b45afa097b55b6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from pdillis/stylegan3-fun, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

find_latest_checkpoint Ran
ran; our contract draft was wrong, not the code
mingyuanzhou/sid-lsg/sid_train.py
code served (permissive licence) · get_code("0021e29612552771")
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 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
import shutil

# Create a temporary directory structure with checkpoint files
temp_dir = tempfile.mkdtemp()

# Create subdirectories
subdir1 = os.path.join(temp_dir, "checkpoints")
subdir2 = os.path.join(temp_dir, "checkpoints", "nested")
os.makedirs(subdir1, exist_ok=True)
os.makedirs(subdir2, exist_ok=True)

# Create some checkpoint files with different numbers
checkpoint_files = [
    os.path.join(subdir1, "training-state-5.pt"),
    os.path.join(subdir1, "training-state-10.pt"),
    os.path.join(subdir2, "training-state-3.pt"),
    os.path.join(subdir2, "training-state-15.pt"),
    os.path.join(temp_dir, "training-state-1.pt"),
    os.path.join(subdir1, "other-file.pt"),
    os.path.join(subdir1, "training-state-invalid.pt"),
]

# Create the files
for filepath in checkpoint_files:
    with open(filepath, 'w') as f:
        f.write("dummy checkpoint")

ARGS = {
    "directory": temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
format_time Ran
ran; our contract draft was wrong, not the code
mingyuanzhou/SiD-LSG/dnnlib/util.py
code served (permissive licence) · get_code("674eca7b9e1b6439")
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 str. 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 typing import Union

# Test with various time values
ARGS = {
    "seconds": 3661.7  # 1 hour, 1 minute, 1.7 seconds - tests rounding and all format branches
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
format_time_brief Ran
ran; our contract draft was wrong, not the code
mingyuanzhou/SiD-LSG/dnnlib/util.py
code served (permissive licence) · get_code("32af001972a0699f")
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 str. 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 typing import Union

# Test with various time values
ARGS = {
    "seconds": 45.7  # A float value that will be rounded to 46 seconds
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_feature_detector_name Ran
ran; our contract draft was wrong, not the code
mingyuanzhou/SiD-LSG/metrics/sid_metric_utils.py
code served (permissive licence) · get_code("c127dc46d6966547")
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 str. 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 os

def get_feature_detector_name(url):
    return os.path.splitext(url.split('/')[-1])[0]

ARGS = {
    'url': 'https://example.com/path/to/model_weights.pth'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
is_valid_metric Ran
ran, violated the contract we drafted
mingyuanzhou/SiD-LSG/metrics/sid_metric_main.py
code served (permissive licence) · get_code("147acc22e758c8e5")
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

torch.manual_seed(0)

# The function is_valid_metric checks if a metric is in the _metric_dict
# To make this function executable, we need to:
# 1. Populate the _metric_dict with some metrics
# 2. Pass a metric string that exists in _metric_dict

_metric_dict = {
    "accuracy": lambda x, y: (x == y).float().mean(),
    "loss": lambda x, y: ((x - y) ** 2).mean(),
    "f1_score": lambda x, y: 0.95
}

# Valid metric to pass to is_valid_metric
metric_value = "accuracy"

ARGS = {
    "metric": metric_value
}
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
maybe_min Ran
ran, honoured the contract we drafted
mingyuanzhou/SiD-LSG/cocodataset_tool.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("dd1dc700e87f36cc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from pdillis/stylegan3-fun, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

parse_int_list Ran
ran, honoured the contract we drafted
mingyuanzhou/SiD-LSG/sid_metrics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from newbeeer/stf, is pointer only (licence: NONE) · get_code("cacd4f6ec202d9b4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from newbeeer/stf, 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.

parse_tuple Ran
ran, honoured the contract we drafted
mingyuanzhou/SiD-LSG/dataset_tool.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from xfetus/fetal-ultrasound-edm2, is pointer only (licence: NONE) · get_code("07b21b35ecb4815c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from xfetus/fetal-ultrasound-edm2, 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.

register_metric Ran
ran; our contract draft was wrong, not the code
mingyuanzhou/SiD-LSG/metrics/sid_metric_main.py
code served (permissive licence) · get_code("e574c21e7f007b61")
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 function. 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)

# The function register_metric takes one parameter: fn
# It checks that fn is callable, then stores it in a dict
# So we need to provide a callable function

def example_metric_fn():
    """A simple callable function to use as a metric."""
    return 42

ARGS = {
    "fn": example_metric_fn
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
safe_load Ran
ran; our contract draft was wrong, not the code
mingyuanzhou/SiD-LSG/metrics/sid_metric_utils.py
code served (permissive licence) · get_code("2ff552e801a5c835")
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
import dill
import tempfile
import os

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

# Create a temporary file and save a model to it using dill
temp_dir = tempfile.gettempdir()
test_file = os.path.join(temp_dir, "test_model.pkl")

model = SimpleModel()
with open(test_file, 'wb') as f:
    dill.dump(model, f)

# Define arguments for safe_load function
ARGS = {
    'file_path': test_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
dill, 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
setup_snapshot_image_grid Ran
ran on a synthesized input
mingyuanzhou/SiD-LSG/training/sid_training_loop.py
code served (permissive licence) · get_code("4eb9bd36235b00bf")
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
import torch

class MockTrainingSet:
    def __init__(self, resolution, num_samples=10):
        self.resolution = resolution
        self.num_samples = num_samples
    
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        # Return (image, context) tuple
        image = np.random.rand(3, self.resolution, self.resolution).astype(np.float32)
        context = {"idx": idx, "label": idx % 5}
        return (image, context)

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

training_set = MockTrainingSet(resolution=256, num_samples=10)

ARGS = {
    "training_set": training_set,
    "random_seed": 0,
}
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
split_list Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mingyuanzhou/SiD-LSG/training/sid_training_loop.py
code served (permissive licence) · get_code("baad057101faa00e")
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 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 torch
import numpy as np
from itertools import islice

torch.manual_seed(0)

# Test case 1: Split with integer size
lst_1 = [1, 2, 3, 4, 5, 6, 7, 8, 9]
split_sizes_1 = 3

# Test case 2: Split with list of sizes
lst_2 = ['a', 'b', 'c', 'd', 'e', 'f']
split_sizes_2 = [2, 3, 1]

# Test case 3: Split with tensor elements and list of sizes
lst_3 = [torch.randn(2, 4) for _ in range(5)]
split_sizes_3 = [2, 2, 1]

# Use the first test case for ARGS
ARGS = {
    'lst': lst_1,
    'split_sizes': split_sizes_1
}
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 list, ndim 2, dtype family int — 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
tensor2pil Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mingukkang/gigagan/evaluation/evaluation.py
pointer only (licence: NONE) · get_code("11687d1d3ed1d3db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mingukkang/gigagan 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.

tokenize_captions Ran
ran, honoured the contract we drafted
mingyuanzhou/SiD-LSG/training/sid_sd_util.py
code served (permissive licence) · get_code("a7ee9e9cfc473967")
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 int, shape (2, 16) 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 MockTokenizer:
    def __init__(self):
        self.model_max_length = 16
    
    def __call__(self, captions, truncation=False, padding=None, max_length=None, return_tensors=None):
        # Return a mock tokenizer output with input_ids
        batch_size = len(captions)
        seq_length = max_length if max_length else 16
        input_ids = torch.randint(0, 1000, (batch_size, seq_length))
        
        class TokenizerOutput:
            def __init__(self, ids):
                self.input_ids = ids
        
        return TokenizerOutput(input_ids)

tokenizer = MockTokenizer()
examples = ["a dog running in the park", "a cat sleeping on a mat"]

ARGS = {
    "tokenizer": tokenizer,
    "examples": examples
}
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 int, shape (2, 16) — shape (2, 16) 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
ask_yes_no Not yet run
unverified (harvested, no recorded run)
mingyuanzhou/SiD-LSG/dnnlib/util.py
code served (permissive licence) · get_code("9d31d2c4cd16bb2d")
How it ran

no invocation recorded.

compute_fid_and_clip Not yet run
unverified (harvested, no recorded run)
mingyuanzhou/SiD-LSG/metrics/sid_fid_and_clip.py
code served (permissive licence) · get_code("4df77172213d4bd0")
How it ran

no invocation recorded.

compute_pr Not yet run
unverified (harvested, no recorded run)
mingyuanzhou/SiD-LSG/metrics/sid_precision_recall.py
code served (permissive licence) · get_code("e687131b851cf012")
How it ran

no invocation recorded.

sid_sd_sampler Not yet run
unverified (harvested, no recorded run)
mingyuanzhou/sid-lsg/training/sid_sd_util.py
code served (permissive licence) · get_code("8c9557ae76612b77")
How it ran

no invocation recorded.

upcast_vae Not yet run
unverified (harvested, no recorded run)
mingyuanzhou/sid-lsg/training/sid_sd_util.py
code served (permissive licence) · get_code("abdafc09a34957ba")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 13 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 6 the same month, 10 later) and 11 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
format_time 73 other papers
37 dated earlier, 3 the same month, 32 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 70 more not named here
ask_yes_no 69 other papers
37 dated earlier, 3 the same month, 28 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 66 more not named here
format_time_brief 68 other papers
33 dated earlier, 3 the same month, 31 later, 1 undated
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 65 more not named here
parse_int_list 37 other papers
20 dated earlier, 2 the same month, 15 later
2206.00364 (2022-06)
Elucidating the Design Space of Diffusion-Based Generative Models
2302.00670 (2023-02)
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
2302.04265 (2023-02)
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
and 34 more not named here
file_ext 35 other papers
22 dated earlier, 1 the same month, 12 later
2106.07023 (2021-06)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2111.13792 (2021-11)
LAFITE: Towards Language-Free Training for Text-to-Image Generation
and 32 more not named here
maybe_min 35 other papers
22 dated earlier, 1 the same month, 12 later
2106.07023 (2021-06)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2111.13792 (2021-11)
LAFITE: Towards Language-Free Training for Text-to-Image Generation
and 32 more not named here
parse_tuple 20 other papers
11 dated earlier, 9 later
2303.10137 (2023-03)
A Recipe for Watermarking Diffusion Models
2306.06991 (2023-06)
Fast Diffusion Model
2308.15321 (2023-08)
Elucidating the Exposure Bias in Diffusion Models
and 17 more not named here
parse_tuple 7 other papers
4 dated earlier, 3 later
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 4 more not named here
get_feature_detector_name 2 other papers
1 dated earlier, 1 later
2404.04057 (2024-04)
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
2509.24526 (2025-09)
CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Models
compute_distances 1 other paper
1 dated earlier
2404.04057 (2024-04)
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
is_valid_metric 1 other paper
1 dated earlier
2404.04057 (2024-04)
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
register_metric 1 other paper
1 dated earlier
2404.04057 (2024-04)
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
tensor2pil 1 other paper
1 later
2511.01307 (2025-11)
Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models

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

Google DeepMind, and 3 Atlassian distinguished older gentleman in a vintage study, surrounded by books and dim lighting [...] saharian landscape at sunset , 4k ultra realism, BY Anton Gorlin, trending on artstation, [...] chinese red blouse, in the style of dreamy and romantic compositions, floral explosions. [...] futuristic simple multilayered architecture, habitation cabin in the trees, dramatic soft light [...] poster art for the collection of the asian woman, dynamic anime [...], mysterious realism, [...] A fantasy-themed portrait of a female elf with golden hair and violet eyes, her attire [...] very beautiful girl in [...], white short top, charismatic personality, professional photo, [...] steampunk atmosphere, a stunning girl with a mecha musume aesthetic, adorned in [...] (Pirate ship sailing into a bioluminescence sea with a galaxy in the sky), epic, 4k, ultra. tshirt design, colourful, no background, yoda with sun glasses, dancing at a festival [...] 8k.

For agents

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

get_harvested_code_for_paper("2406.01561")
get_code_for_paper("2406.01561")
have("2406.01561")

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

curl https://syntology.ai/api/ran/2406.01561.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.01561.svg)](https://syntology.ai/paper/2406.01561)

Connect an agent — have() is free.