SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.08685 · ICML · 2020

Leveraging Frequency Analysis for Deep Fake Image Recognition

Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, Thorsten Holz

arXiv · PDF · Open in the Atlas

Code that ran

12 of 12 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; 1 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; 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/2003.08685.json · badge: /api/ran/2003.08685.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
RUB-SysSec/GANDCTAnalysis canonical (classifier label)
classifier basis: census
12 ran · 0 no recorded run
FunctionStatusWhere it lives
blur Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
RUB-SysSec/GANDCTAnalysis/create_perturbed_imagedata.py
code served (permissive licence) · get_code("dc1f37b3667e76c4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (4, 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 cv2
import numpy as np

# The function blur() takes an image parameter
# It expects a numpy array that cv2.GaussianBlur can process
# cv2.GaussianBlur expects a 2D or 3D numpy array (grayscale or color image)

# Create a small test image (4x3 grayscale)
image = np.random.randint(0, 256, size=(4, 3), dtype=np.uint8)

ARGS = {
    "image": image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (4, 3) — shape (4, 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
convert_images Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/prepare_dataset.py
code served (permissive licence) · get_code("6106b4cc51e62441")
How it ran

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

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define load_function: takes an image identifier and returns a tensor
def load_function(image_id):
    # Returns a small tensor representing an image (e.g., 3x4x4 for 3-channel 4x4 image)
    return torch.randn(3, 4, 4)

# Define transformation_function: applies some transformation to the image
def transformation_function(image):
    # Simple transformation: add a small constant
    return image + 0.1

# Define absolute_function: takes absolute value
def absolute_function(image):
    return torch.abs(image)

# Define normalize_function: normalizes the image
def normalize_function(image):
    # Simple normalization: scale to [0, 1]
    return (image - image.min()) / (image.max() - image.min() + 1e-8)

# Create sample input: (image_identifier, label)
sample_image_id = "image_001"
sample_label = 5

inputs = (sample_image_id, sample_label)

# Define ARGS dict with all parameters
ARGS = {
    'inputs': inputs,
    'load_function': load_function,
    'transformation_function': transformation_function,
    'absolute_function': absolute_function,
    'normalize_function': normalize_function
}
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
crop_image Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/crop_celeba.py
code served (permissive licence) · get_code("de3819ddb7821c62")
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 os
import tempfile
import numpy as np
from PIL import Image

# Create temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
output_dir = tempfile.mkdtemp()
image_dir = tempfile.mkdtemp()

# Create a valid test image (256x256 RGB)
test_image = np.random.randint(0, 256, (256, 256, 3), dtype=np.uint8)
test_image_path = os.path.join(image_dir, "test_image.png")
Image.fromarray(test_image).save(test_image_path)

# The function expects: (i, directory, file_path, output)
# where i is an index, directory is the folder containing images,
# file_path is the filename, and output is where to save results

ARGS = {
    'stupid': (
        0,                           # i: index
        image_dir,                   # directory: path to image folder
        "test_image.png",            # file_path: filename
        output_dir                   # output: output directory path
    )
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — 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
dct2 Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/src/image.py
code served (permissive licence) · get_code("4bf75d4114551e1d")
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 EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 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 tensorflow as tf
import numpy as np

# Create a small batched array with distinct dimensions
# Shape: (batch=2, height=4, width=3, channels=5)
batched_array = tf.constant(
    np.random.randn(2, 4, 3, 5).astype(np.float32),
    dtype=tf.float32
)

# Create a small non-batched array
# Shape: (height=4, width=3, channels=5)
non_batched_array = tf.constant(
    np.random.randn(4, 3, 5).astype(np.float32),
    dtype=tf.float32
)

ARGS = {
    "array": batched_array,
    "batched": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 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
dct2 Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/src/image_np.py
code served (permissive licence) · get_code("fb2dbd27277ccd27")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from scipy import fftpack

# Create a small 2D array for DCT input
# Using distinct dimensions (4x3) to make shapes unambiguous
array = np.random.randn(4, 3).astype(np.float64)

ARGS = {
    'array': array
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 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
deserialize_data Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/src/dataset.py
code served (permissive licence) · get_code("ea00a1a5e9e3ba3f")
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 tensorflow as tf
import numpy as np

# Create a minimal valid TFRecord example
def create_tfrecord_example(image_data, label, shape):
    """Create a serialized TFRecord example."""
    feature = {
        'image': tf.train.Feature(float_list=tf.train.FloatList(value=image_data.flatten())),
        'label': tf.train.Feature(int64_list=tf.train.Int64List(value=[label])),
        'shape': tf.train.Feature(int64_list=tf.train.Int64List(value=shape)),
    }
    example_proto = tf.train.Example(features=tf.train.Features(feature=feature))
    return example_proto.SerializeToString()

# Create sample data
image_shape = [128, 128, 1]
sample_image = np.random.randn(128, 128, 1).astype(np.float32)
sample_label = 5
actual_shape = [128, 128, 1]

# Create raw_record (serialized TFRecord)
raw_record = create_tfrecord_example(sample_image, sample_label, actual_shape)

ARGS = {
    'raw_record': raw_record,
    'raw': True,
    'shape': [128, 128, 1],
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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
fft2d Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/src/image_np.py
code served (permissive licence) · get_code("0bee49f8f05fe911")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from scipy import fftpack

# Create a small 2D array for FFT
array = np.random.randn(4, 3).astype(np.complex128)

ARGS = {
    "array": array
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 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
image_paths Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/src/dataset.py
code served (permissive licence) · get_code("6688920fab4c673d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
from pathlib import Path

# Create a temporary directory with some image files
temp_dir = tempfile.TemporaryDirectory()
temp_path = temp_dir.name

# Create some dummy image files with different extensions
Path(temp_path, "image1.jpeg").touch()
Path(temp_path, "image2.jpeg").touch()
Path(temp_path, "image3.jpg").touch()
Path(temp_path, "image4.png").touch()

ARGS = {
    "dir_path": temp_path
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
jpeg Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/create_perturbed_imagedata.py
code served (permissive licence) · get_code("814f39fb6ae264ea")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (4, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import cv2
import numpy as np

# Create a small valid image (BGR format, as expected by cv2)
# Using a 4x3 image (height x width x channels) to have distinct dimensions
image = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

ARGS = {
    'image': image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_image Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/src/image.py
code served (permissive licence) · get_code("8c156c4355abbec4")
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 EagerTensor, ndim 3, dtype family float, shape (10, 8, 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 tensorflow as tf
import tempfile
import os
from PIL import Image
import numpy as np

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
img_array = np.random.randint(0, 256, (10, 8, 3), dtype=np.uint8)
img = Image.fromarray(img_array, mode='RGB')
temp_image_path = os.path.join(temp_dir, 'test_image.png')
img.save(temp_image_path)

ARGS = {
    'path': temp_image_path,
    'grayscale': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, shape (10, 8, 3) — shape (10, 8, 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
noise Ran
ran, honoured the contract we drafted
RUB-SysSec/GANDCTAnalysis/create_perturbed_imagedata.py
code served (permissive licence) · get_code("98ee32fa8f79db2a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small test image as a uint8 numpy array
# Using shape (4, 3) for distinctness
test_image = np.random.randint(0, 256, size=(4, 3), dtype=np.uint8)

ARGS = {
    "image": test_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (4, 3) — shape (4, 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
serialize_data Ran
ran on a synthesized input
RUB-SysSec/GANDCTAnalysis/src/dataset.py
code served (permissive licence) · get_code("676fc31eed31fb44")
How it ran

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

import numpy as np

# Construct the data tuple needed for serialize_data
# The function expects (image, label) where:
# - image is a numpy array that will be flattened and converted to float list
# - label is an integer that will be converted to int64

image = np.random.rand(4, 3).astype(np.float32)  # 4x3 image array
label = 1  # integer label

data = (image, label)

ARGS = {
    'data': data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 10 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
blur 1 other paper
1 later
2402.19091 (2024-02)
Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection
noise 1 other paper
1 later
2402.19091 (2024-02)
Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection

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

Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements have been largely made possible by Generative Adversarial Networks (GANs). While deep fake images have been thoroughly investigated in the image domain-a classical approach from the area of image forensics-an analysis in the frequency domain has been missing so far. In this paper, we address this shortcoming and our results reveal that in frequency space, GAN-generated images exhibit severe artifacts that can be easily identified. We perform a comprehensive analysis, showing that these artifacts are consistent across different neural network architectures, data sets, and resolutions. In a further investigation, we demonstrate that these artifacts are caused by upsampling operations found in all current GAN architectures, indicating a structural and fundamental problem in the way images are generated via GANs. Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("2003.08685")
get_code_for_paper("2003.08685")
have("2003.08685")

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

curl https://syntology.ai/api/ran/2003.08685.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.08685.svg)](https://syntology.ai/paper/2003.08685)

Connect an agent — have() is free.