SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.10568 · ICLR · 2025

Autoregressive Image Generation with Randomized Parallel Decoding

Huan Wang, Guoqi Li, Haopeng Li, Jinyue Yang

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 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, 0 violated it and 2 have no contract verdict; 9 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/2503.10568.json · badge: /api/ran/2503.10568.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
hp-l33/ARPG canonical (classifier label)
classifier basis not recorded on the link
13 ran · 5 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran; our contract draft was wrong, not the code
hp-l33/ARPG/models/vq_model.py
pointer only (licence: MIT); the stored copy get_code serves, from gogoduan/got-r1, is pointer only (licence: NONE) · get_code("01b5cf639b6bac89")
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 gogoduan/got-r1, 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.

adjust_learning_rate Ran
ran, honoured the contract we drafted
hp-l33/ARPG/train_c2i.py
code served (permissive licence) · get_code("3a774664bfc712ec")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Create a small model to optimize
model = nn.Linear(4, 2)

# Create an optimizer
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Add a parameter group with lr_scale to test that code path
optimizer.add_param_group({'params': [nn.Parameter(torch.randn(3, 4))], 'lr_scale': 0.5})

# Create args dict with all required parameters
ARGS = {
    'optimizer': optimizer,
    'epoch': 5,
    'args': type('Args', (), {
        'warmup_epochs': 2,
        'epochs': 10,
        'lr': 0.1,
        'min_lr': 0.001,
        'lr_schedule': 'cosine'
    })()
}
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 float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
batch_seq_shuffle Ran
ran on a synthesized input
hp-l33/ARPG/models/arpg.py
code served (permissive licence) · get_code("69acd83901569c6a")
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

torch.manual_seed(0)

# Create a small input tensor with shape (batch_size, seq_len, feature_dim)
# Using distinct sizes: batch=2, seq_len=3, feature_dim=4
x = torch.randn(2, 3, 4)

# orders parameter is optional (None by default), but we can provide one
# It should have shape (batch_size, seq_len) with values representing permutation indices
orders = None  # Let the function generate random orders

ARGS = {
    'x': x,
    'orders': orders
}
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 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
build_t2i Ran
ran; our contract draft was wrong, not the code
hp-l33/ARPG/dataset/t2i.py
code served (permissive licence) · get_code("02cb09299c18ee5d")
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 Text2ImgDataset. 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
import json
import numpy as np
import torch
from torchvision import transforms
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory structure with minimal test data
temp_dir = tempfile.mkdtemp()
data_path = os.path.join(temp_dir, "data")
t5_feat_path = os.path.join(temp_dir, "t5_feats")
short_t5_feat_path = os.path.join(temp_dir, "short_t5_feats")

os.makedirs(data_path, exist_ok=True)
os.makedirs(t5_feat_path, exist_ok=True)
os.makedirs(short_t5_feat_path, exist_ok=True)

# Create a minimal JSONL file with image paths
jsonl_file = os.path.join(data_path, "test_data.jsonl")
code_dir_name = "code_001"
code_dir_path_full = os.path.join(t5_feat_path, code_dir_name)
os.makedirs(code_dir_path_full, exist_ok=True)
short_code_dir_path_full = os.path.join(short_t5_feat_path, code_dir_name)
os.makedirs(short_code_dir_path_full, exist_ok=True)

# Create dummy image file
from PIL import Image
dummy_img = Image.new('RGB', (256, 256), color='red')
img_file = os.path.join(temp_dir, "test_image.jpg")
dummy_img.save(img_file)

# Write JSONL data
with open(jsonl_file, 'w') as f:
    json.dump({"image_path": img_file}, f)
    f.write('\n')
    json.dump({"image_path": img_file}, f)
    f.write('\n')

# Create dummy t5 feature files
t5_feat_file_0 = os.path.join(code_dir_path_full, "0.npy")
t5_feat_file_1 = os.path.join(code_dir_path_full, "1.npy")
short_t5_feat_file_0 = os.path.join(short_code_dir_path_full, "0.npy")
short_t5_feat_file_1 = os.path.join(short_code_dir_path_full, "1.npy")

t5_feat_data = np.random.randn(1, 80, 2048).astype(np.float32)
np.save(t5_feat_file_0, t5_feat_data)
np.save(t5_feat_file_1, t5_feat_data)
np.save(short_t5_feat_file_0, t5_feat_data)
np.save(short_t5_feat_file_1, t5_feat_data)

# Create args class
class Args:
    def __init__(self):
        self.data_path = data_path
        self.t5_feat_path = t5_feat_path
        self.short_t5_feat_path = short_t5_feat_path
        self.image_size = 256
        self.downsample_size = 8

args = Args()

# Create a simple transform
transform = transforms.Compose([
    transforms.Resize((256, 256)),
    transforms.ToTensor(),
])

ARGS = {
    "args": args,
    "transform": transform,
}
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 Text2ImgDataset — a Text2ImgDataset 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
build_t2i_code Ran
ran; our contract draft was wrong, not the code
hp-l33/ARPG/dataset/t2i.py
code served (permissive licence) · get_code("ff9ed4675cb307aa")
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 Text2ImgDatasetCode. 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 torch.utils.data import Dataset

torch.manual_seed(0)

class Args:
    def __init__(self):
        self.batch_size = 2
        self.num_workers = 0
        self.dataset_path = None
        self.text_encoder = None
        self.image_encoder = None
        self.vocab_size = 100
        self.max_length = 16
        self.image_size = 32
        self.num_classes = 10
        self.shuffle = True
        self.pin_memory = False

ARGS = {
    "args": Args()
}
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 Text2ImgDatasetCode — a Text2ImgDatasetCode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Text2ImgDatasetCode 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
build_t2i_image Ran
ran; our contract draft was wrong, not the code
hp-l33/ARPG/dataset/t2i.py
code served (permissive licence) · get_code("090d7b6b1260114e")
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 Text2ImgDatasetImg. 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
import json
import tempfile
from PIL import Image
import torch
from torchvision import transforms

torch.manual_seed(0)

# Create temporary directories with test data
temp_dir = tempfile.mkdtemp()
lst_dir = os.path.join(temp_dir, 'lists')
face_lst_dir = os.path.join(temp_dir, 'face_lists')
img_dir = os.path.join(temp_dir, 'images')

os.makedirs(lst_dir)
os.makedirs(face_lst_dir)
os.makedirs(img_dir)

# Create dummy images
for i in range(2):
    img = Image.new('RGB', (4, 3), color=(i*50, i*100, i*150))
    img_path = os.path.join(img_dir, f'image_{i}.jpg')
    img.save(img_path)

# Create JSONL files with image paths
lst_file = os.path.join(lst_dir, 'dataset.jsonl')
with open(lst_file, 'w') as f:
    for i in range(2):
        img_path = os.path.join(img_dir, f'image_{i}.jpg')
        data = {'image_path': img_path}
        f.write(json.dumps(data) + '\n')

# Create face JSONL file
face_lst_file = os.path.join(face_lst_dir, 'faces_face.jsonl')
with open(face_lst_file, 'w') as f:
    for i in range(2):
        img_path = os.path.join(img_dir, f'image_{i}.jpg')
        data = {'image_path': img_path}
        f.write(json.dumps(data) + '\n')

# Create a simple transform
transform = transforms.Compose([
    transforms.Resize((4, 3)),
    transforms.ToTensor()
])

# Create args object with required attributes
class Args:
    def __init__(self, data_path, data_face_path):
        self.data_path = data_path
        self.data_face_path = data_face_path

args = Args(lst_dir, face_lst_dir)

ARGS = {
    'args': args,
    'transform': transform
}
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 Text2ImgDatasetImg — a Text2ImgDatasetImg 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
center_crop_arr Ran
ran; our contract draft was wrong, not the code
hp-l33/ARPG/dataset/augmentation.py
code served (permissive licence) · get_code("1712a07966b542ee")
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 numpy as np
from PIL import Image

# Create a small test image
width, height = 256, 256
pil_image = Image.new('RGB', (width, height), color='red')

# Define arguments
ARGS = {
    'pil_image': pil_image,
    'image_size': 64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — 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
compute_entropy_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hp-l33/ARPG/models/vq_model.py
pointer only (licence: MIT); the stored copy get_code serves, from gogoduan/got-r1, is pointer only (licence: NONE) · get_code("774c95b77d7621f3")
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 gogoduan/got-r1, 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.

creat_optimizer Ran
ran; our contract draft was wrong, not the code
hp-l33/ARPG/train_c2i.py
code served (permissive licence) · get_code("ba65976c1d96a7cb")
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 AdamW. 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 logging

torch.manual_seed(0)

# Create a simple logger
logger = logging.getLogger("test_logger")
logger.setLevel(logging.INFO)
handler = logging.StreamHandler()
logger.addHandler(handler)

# Create a simple model with parameters of different dimensions
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        # 2D parameter (will be in decay_params)
        self.linear1 = nn.Linear(4, 3)
        # 1D parameter (will be in nodecay_params)
        self.bias_only = nn.Parameter(torch.randn(2))
        # Another 2D parameter (will be in decay_params)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Ensure all parameters require gradients
for param in model.parameters():
    param.requires_grad = True

weight_decay = 0.01
learning_rate = 0.001
betas = (0.9, 0.999)

ARGS = {
    "model": model,
    "weight_decay": weight_decay,
    "learning_rate": learning_rate,
    "betas": betas,
    "logger": logger,
}
Setup block drafted by
a language model, Claude Haiku 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 AdamW — a AdamW output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AdamW 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
create_deepspeed_config Ran
ran on a synthesized input
hp-l33/ARPG/utils/deepspeed.py
code served (permissive licence) · get_code("a2c47fee1f9960c8")
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
import numpy as np
from dataclasses import dataclass

torch.manual_seed(0)

@dataclass
class Args:
    global_batch_size: int = 32
    gradient_accumulation_steps: int = 4
    lr: float = 0.001
    weight_decay: float = 0.01
    beta1: float = 0.9
    beta2: float = 0.999
    mixed_precision: str = 'fp16'
    clip_grad: float = 1.0
    zero_stage: int = 2

ARGS = {
    'args': Args(
        global_batch_size=32,
        gradient_accumulation_steps=4,
        lr=0.001,
        weight_decay=0.01,
        beta1=0.9,
        beta2=0.999,
        mixed_precision='fp16',
        clip_grad=1.0,
        zero_stage=2
    )
}
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 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
create_npz_from_sample_folder Ran
ran; our contract draft was wrong, not the code
hp-l33/ARPG/sample_c2i_ddp.py
code served (permissive licence) · get_code("7b21a01ae77703a3")
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 tempfile
import os
from PIL import Image
import numpy as np

# Create a temporary directory with sample PNG files
temp_dir = tempfile.mkdtemp()

# Create a few small sample PNG images (3 samples instead of 50000 for testing)
num_samples = 3
image_height = 32
image_width = 32

for i in range(num_samples):
    # Create a small RGB image array
    img_array = np.random.randint(0, 256, (image_height, image_width, 3), dtype=np.uint8)
    img = Image.fromarray(img_array, mode='RGB')
    img.save(f'{temp_dir}/{i:06d}.png')

ARGS = {
    'sample_dir': temp_dir,
    'num': num_samples,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy, tqdm — 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
find_multiple Ran
ran, honoured the contract we drafted
hp-l33/ARPG/models/arpg.py
code served (permissive licence) · get_code("f6ff7671338c9c92")
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 numpy as np

torch.manual_seed(0)

# Analyze the function: find_multiple(n: int, k: int)
# The function takes two integers and returns an integer
# It checks if n is divisible by k, and if not, rounds n up to the next multiple of k

ARGS = {
    "n": 10,
    "k": 3
}
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 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
nonlinearity Ran
ran; our contract draft was wrong, not the code
hp-l33/ARPG/models/vq_model.py
code served (permissive licence) · get_code("3137073275f8c21a")
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 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)

# The function takes a single parameter 'x' which is used with:
# - multiplication operator (*)
# - torch.sigmoid() function
# This means x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 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 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
build_coco Not yet run
unverified (harvested, no recorded run)
hp-l33/ARPG/dataset/coco.py
pointer only (licence: MIT); the stored copy get_code serves, from ThisisBillhe/ZipAR, is pointer only (licence: NONE) · get_code("a5dc3fcd09ebc843")
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 ThisisBillhe/ZipAR, 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.

build_imagenet_code Not yet run
unverified (harvested, no recorded run)
hp-l33/ARPG/dataset/imagenet.py
code served (permissive licence) · get_code("c5aec8b86d5fb5f7")
How it ran

no invocation recorded.

build_openimage Not yet run
unverified (harvested, no recorded run)
hp-l33/ARPG/dataset/openimage.py
pointer only (licence: MIT); the stored copy get_code serves, from ThisisBillhe/ZipAR, is pointer only (licence: NONE) · get_code("0a65aaf586d4f90b")
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 ThisisBillhe/ZipAR, 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.

precompute_freqs_cis Not yet run
unverified (harvested, no recorded run)
hp-l33/ARPG/models/arpg.py
pointer only (licence: MIT); the stored copy get_code serves, from ThisisBillhe/ZipAR, is pointer only (licence: NONE) · get_code("0f0ff4e443413018")
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 ThisisBillhe/ZipAR, 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.

random_crop_arr Not yet run
unverified (harvested, no recorded run)
hp-l33/ARPG/dataset/augmentation.py
pointer only (licence: MIT); the stored copy get_code serves, from ThisisBillhe/ZipAR, is pointer only (licence: NONE) · get_code("980fb099f82d8b84")
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 ThisisBillhe/ZipAR, 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.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 15 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 5 the same month, 9 later) and 3 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
nonlinearity 156 other papers
124 dated earlier, 4 the same month, 28 later · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
center_crop_arr 37 other papers
27 dated earlier, 2 the same month, 6 later, 2 same year, order not determinable
2211.17091 (2022-11)
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2311.09257 (2023-11)
UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs
and 34 more not named here
create_npz_from_sample_folder 23 other papers
19 dated earlier, 4 later
2401.08740 (2024-01)
SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
2402.14167 (2024-02)
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
2403.09176 (2024-03)
Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts
and 20 more not named here
find_multiple 13 other papers
8 dated earlier, 2 the same month, 2 later, 1 undated · 2 only as an assembly brick
2406.06525 (2024-06)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
2409.13689 (2024-09)
Temporally Aligned Audio for Video with Autoregression
2410.02705 (2024-10)
ControlAR: Controllable Image Generation with Autoregressive Models
and 10 more not named here
compute_entropy_loss 10 other papers
3 dated earlier, 2 the same month, 5 later · 2 only as an assembly brick
2408.12245 (2024-08)
Scalable Autoregressive Image Generation with Mamba
2411.15867 (2024-11)
PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs
2502.20313 (2025-02)
FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
and 7 more not named here
Normalize 9 other papers
3 dated earlier, 2 the same month, 4 later · 3 only as an assembly brick
2408.12245 (2024-08)
Scalable Autoregressive Image Generation with Mamba
2411.15867 (2024-11)
PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs
2502.20313 (2025-02)
FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
and 6 more not named here
precompute_freqs_cis 7 other papers
4 dated earlier, 2 later, 1 undated
2406.06525 (2024-06)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
2410.02705 (2024-10)
ControlAR: Controllable Image Generation with Autoregressive Models
2411.15867 (2024-11)
PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs
and 4 more not named here
build_openimage 4 other papers
4 dated earlier
2406.06525 (2024-06)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
2412.03069 (2024-12)
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
2412.04062 (2024-12)
ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality
and 1 more not named here
creat_optimizer 4 other papers
4 dated earlier
2410.09347 (2024-10)
Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary
2501.15420 (2025-01)
Visual Generation Without Guidance
and 1 more not named here
random_crop_arr 4 other papers
3 dated earlier, 1 later
2406.06525 (2024-06)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
2412.03069 (2024-12)
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
2412.04062 (2024-12)
ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality
and 1 more not named here
adjust_learning_rate 3 other papers
1 dated earlier, 2 later
2502.17437 (2025-02)
Fractal Generative Models
2605.27102 (2026-05)
JLT: Clean-Latent Prediction in Latent Diffusion Transformers
2607.17849 (2026-07)
AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning
build_coco 3 other papers
3 dated earlier
2406.06525 (2024-06)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
2412.03069 (2024-12)
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
2412.04062 (2024-12)
ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality
build_t2i 1 other paper
1 dated earlier
2406.06525 (2024-06)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
build_t2i_code 1 other paper
1 dated earlier
2406.06525 (2024-06)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
build_t2i_image 1 other paper
1 dated earlier
2406.06525 (2024-06)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

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.

For agents

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

get_harvested_code_for_paper("2503.10568")
get_code_for_paper("2503.10568")
have("2503.10568")

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

curl https://syntology.ai/api/ran/2503.10568.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.10568.svg)](https://syntology.ai/paper/2503.10568)

Connect an agent — have() is free.