SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.06648 · NeurIPS · 2022

OmniPrint: A Configurable Printed Character Synthesizer

Isabelle Guyon, A Configurable, Haozhe Sun, Wei-Wei Tu #+

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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 3 have no contract verdict; 2 failures of our instrument; 2 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/2201.06648.json · badge: /api/ran/2201.06648.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
SunHaozhe/transferlearning canonical (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
sunhaozhe/omniprint canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
SunHaozhe/transferlearning/code/DeepDG/alg/modelopera.py
code served (permissive licence) · get_code("e31d1f2fae01ad6e")
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. 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, 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 SimpleNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def predict(self, x):
        return self.linear(x)

network = SimpleNetwork()

loader = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
]

ARGS = {
    "network": network,
    "loader": loader,
}
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
factor2magnitude Ran
ran, honoured the contract we drafted
sunhaozhe/omniprint/omniprint/data_generator.py
code served (permissive licence) · get_code("bdd7955dce858142")
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 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.

ARGS = {
    'factor': 0.5
}
Setup block drafted by
a language model, Claude Sonnet 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 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
get_data_loader Ran
ran on a synthesized input
SunHaozhe/transferlearning/code/DeepDA/data_loader.py
code served (permissive licence) · get_code("95c4b2cf2eaa5127")
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 DataLoader. 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.utils.data

torch.manual_seed(0)

# Create a simple dataset
class SimpleDataset(torch.utils.data.Dataset):
    def __init__(self, num_samples=10, feature_dim=4):
        self.num_samples = num_samples
        self.feature_dim = feature_dim
    
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        x = torch.randn(self.feature_dim)
        y = torch.randint(0, 2, (1,))
        return x, y

dataset = SimpleDataset(num_samples=10, feature_dim=4)

ARGS = {
    'dataset': dataset,
    'batch_size': 2,
    'shuffle': True,
    'drop_last': False,
    'num_workers': 0,
    'infinite_data_loader': 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 DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
image_enhancement Ran
ran; our contract draft was wrong, not the code
sunhaozhe/omniprint/omniprint/data_generator.py
code served (permissive licence) · get_code("a4039b6c26958010")
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 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
from PIL import Image

# Create a small PIL Image
img = Image.new('RGB', (8, 6), color=(128, 128, 128))

# Create a label dictionary
label = {}

# Create args dictionary with various enhancement parameters
args = {
    'brightness': [0.8, 1.2],  # range for random uniform
    'contrast': 1.1,  # single value
    'color_enhance': [0.9, 1.1],  # range for random uniform
    'sharpness': [1.0]  # single value in list
}

ARGS = {
    'img': img,
    'label': label,
    'args': args
}
Setup block drafted by
a language model, Claude Sonnet 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 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
load_data Ran
ran on a synthesized input
SunHaozhe/transferlearning/code/DeepDA/data_loader.py
code served (permissive licence) · get_code("07ef759d2a42d6c8")
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 torch
import torch.nn as nn
from torchvision import datasets, transforms
import tempfile
import os
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a temporary directory with fake image data
temp_dir = tempfile.mkdtemp()
train_dir = os.path.join(temp_dir, 'train')
os.makedirs(train_dir, exist_ok=True)

# Create subdirectories for classes
class_dir = os.path.join(train_dir, 'class0')
os.makedirs(class_dir, exist_ok=True)

# Create a few dummy images
for i in range(3):
    img_array = np.random.randint(0, 255, (224, 224, 3), dtype=np.uint8)
    img = Image.fromarray(img_array)
    img.save(os.path.join(class_dir, f'image_{i}.jpg'))

ARGS = {
    'data_folder': train_dir,
    'batch_size': 2,
    'train': True,
    'num_workers': 0,
}
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, 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
plain_color Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sunhaozhe/omniprint/omniprint/background_generator.py
code served (permissive licence) · get_code("a50b0f7b5b620e04")
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 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.

ARGS = {
    'height': 100,
    'width': 150,
    'color': (255, 128, 64)
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
PIL — 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
plain_white Ran
ran, honoured the contract we drafted
sunhaozhe/omniprint/omniprint/background_generator.py
code served (permissive licence) · get_code("65fc77213d3ff17a")
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 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.

ARGS = {
    'height': 100,
    'width': 150
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
PIL — 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
str2bool Ran
ran, violated the contract we drafted
SunHaozhe/transferlearning/code/DeepDA/utils.py
code served (permissive licence) · get_code("1c31f800b71774a1")
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

def str2bool(v):
    if isinstance(v, bool):
        return v
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise ValueError('Boolean value expected.')

ARGS = {
    'v': 'true'
}
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
CORAL Not yet run
unverified (harvested, no recorded run)
SunHaozhe/transferlearning/code/DeepDA/loss_funcs/coral.py
code served (permissive licence) · get_code("0a0126c7e10b7de1")
How it ran

no invocation recorded.

get_backbone Not yet run
unverified (harvested, no recorded run)
SunHaozhe/transferlearning/code/DeepDA/backbones.py
code served (permissive licence) · get_code("46b83ab54c34fbc1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 6 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
str2bool 5 other papers
1 dated earlier, 4 later
2010.16262 (2020-10)
Experimental design for MRI by greedy policy search
2207.12020 (2022-07)
Domain-invariant Feature Exploration for Domain Generalization
2305.02164 (2023-05)
Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
and 2 more not named here
CORAL 1 other paper
1 later
2207.12020 (2022-07)
Domain-invariant Feature Exploration for Domain Generalization
accuracy 1 other paper
1 later
aaai_28994 (2024 (year only))
Mixup-Induced Domain Extrapolation for Domain Generalization
get_backbone 1 other paper
1 later
2207.12020 (2022-07)
Domain-invariant Feature Exploration for Domain Generalization

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce OmniPrint, a synthetic data generator of isolated printed characters, geared toward machine learning research. It draws inspiration from famous datasets such as MNIST, SVHN and Omniglot, but offers the capability of generating a wide variety of printed characters from various languages, fonts and styles, with customized distortions. We include 935 fonts from 27 scripts and many types of distortions. As a proof of concept, we show various use cases, including an example of meta-learning dataset designed for the upcoming MetaDL NeurIPS 2021 competition. OmniPrint is available at https://github.com/SunHaozhe/OmniPrint. Figure 1: Examples of characters generated by OmniPrint. 35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks.

For agents

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

get_harvested_code_for_paper("2201.06648")
get_code_for_paper("2201.06648")
have("2201.06648")

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

curl https://syntology.ai/api/ran/2201.06648.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.06648.svg)](https://syntology.ai/paper/2201.06648)

Connect an agent — have() is free.