SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.13802 · ECCV · 2024

ZigMa: A DiT-style Zigzag Mamba Diffusion Model

Pingchuan Ma, Vincent Hu, Ming Gui, Stefan Baumann, Olga Grebenkova, Johannes Fischer, Björn Compvis

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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, 2 violated it and 0 have no contract verdict; 10 failures of our instrument; 1 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/2403.13802.json · badge: /api/ran/2403.13802.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
CompVis/zigma canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
center_crop_arr Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/datasets/video_utils.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
crop Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/datasets/video_utils.py
code served (permissive licence) · get_code("b6159b54fe35ce26")
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 4, dtype family float, shape (2, 3, 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 torch

torch.manual_seed(0)

# Create a small 4D video clip tensor with shape (T, C, H, W)
# T=2 (temporal), C=3 (channels), H=8 (height), W=6 (width)
clip = torch.randn(2, 3, 8, 6)

# Define crop parameters
i = 1  # starting row index
j = 2  # starting column index
h = 4  # crop height
w = 3  # crop width

ARGS = {
    'clip': clip,
    'i': i,
    'j': j,
    'h': h,
    'w': w
}
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 4, dtype family float, shape (2, 3, 4, 3) — shape (2, 3, 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
dict_collation_fn Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/datasets/wds_dataloader.py
code served (permissive licence) · get_code("fffa4c66b7275f88")
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

torch.manual_seed(0)

# Create sample data with different types
samples = [
    {
        'tensor_field': torch.randn(4),
        'scalar_int': 5,
        'scalar_float': 3.14,
        'ndarray_field': np.random.randn(3),
        'list_field': [1, 2, 3]
    },
    {
        'tensor_field': torch.randn(4),
        'scalar_int': 7,
        'scalar_float': 2.71,
        'ndarray_field': np.random.randn(3),
        'list_field': [4, 5, 6]
    }
]

ARGS = {
    'samples': samples,
    'combine_tensors': True,
    'combine_scalars': True
}
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
exists Ran
ran, violated the contract we drafted
CompVis/zigma/model_zigma.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

expand_t_like_x Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/transport/path.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from poppuppy/secant-expectation, is pointer only (licence: NONE) · get_code("6de57ffd4ee7fee7")
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 poppuppy/secant-expectation, 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.

generate_run_id Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/wandb_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from leaplabthu/attention-mediators, is pointer only (licence: NONE) · get_code("661fd94e23de34b1")
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 leaplabthu/attention-mediators, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_max_ckpt_from_dir Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/wandb_utils.py
code served (permissive licence) · get_code("0ed422d461596968")
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
import tempfile
import shutil

# Create a temporary directory structure with checkpoint files
temp_dir = tempfile.mkdtemp()
checkpoints_dir = os.path.join(temp_dir, 'checkpoints')
os.makedirs(checkpoints_dir, exist_ok=True)

# Create some dummy checkpoint files with numeric names
checkpoint_files = ['100.pt', '50.pt', '200.pt', '75.pt']
for filename in checkpoint_files:
    filepath = os.path.join(checkpoints_dir, filename)
    with open(filepath, 'w') as f:
        f.write('dummy checkpoint')

ARGS = {
    'dir_path': temp_dir
}
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
has_text Ran
ran, violated the contract we drafted
CompVis/zigma/train_acc.py
code served (permissive licence) · get_code("7a53c711fb94458d")
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
import torch.nn as nn

class MockArgs:
    def __init__(self, data_name):
        self.data = MockData(data_name)

class MockData:
    def __init__(self, name):
        self.name = name

ARGS = {
    'args': MockArgs('celebamm_dataset')
}
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
modulate Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/model_zigma.py
code served (permissive licence) · get_code("03310bba324ae4fb")
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)

# Create small tensors for the modulate function
# x: input tensor with shape (batch_size, feature_dim)
x = torch.randn(2, 4)

# shift: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
shift = torch.randn(2)

# scale: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
scale = torch.randn(2)

ARGS = {
    "x": x,
    "shift": shift,
    "scale": scale,
}
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
namespace_to_dict Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/wandb_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from leaplabthu/attention-mediators, is pointer only (licence: NONE) · get_code("06a3ad042b36b928")
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 leaplabthu/attention-mediators, 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.

out2img Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/train_acc.py
code served (permissive licence) · get_code("50a84404aceceeb8")
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, 4) 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

torch.manual_seed(0)

# Create a small tensor that will be clamped and converted to uint8
# Shape: (2, 4) - batch of 2, 4 features
samples = torch.randn(2, 4)

ARGS = {
    "samples": samples
}
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, 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
t2i_modulate Ran
ran, honoured the contract we drafted
CompVis/zigma/model_zigma.py
code served (permissive licence) · get_code("a5e3d9618aac5205")
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
import numpy as np

torch.manual_seed(0)

# Create small tensors for the function parameters
x = torch.randn(2, 4)  # batch size 2, dimension 4
shift = torch.randn(2, 4)  # same shape as x
scale = torch.randn(2, 4)  # same shape as x

ARGS = {
    "x": x,
    "shift": shift,
    "scale": scale,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
update_note Ran
ran; our contract draft was wrong, not the code
CompVis/zigma/train_acc.py
code served (permissive licence) · get_code("887e16a203fee3e4")
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 torch
from unittest.mock import Mock

torch.manual_seed(0)

# Create a mock args object with nested config objects
class ConfigObj:
    def __init__(self, **kwargs):
        for key, value in kwargs.items():
            setattr(self, key, value)

args = ConfigObj(
    note='test_note',
    data=ConfigObj(
        name='cifar10',
        batch_size=32
    ),
    model=ConfigObj(
        name='resnet18'
    ),
    optim=ConfigObj(
        wd=0.0001
    )
)

# Create a mock accelerator object
accelerator = Mock()
accelerator.state = Mock()
accelerator.state.num_processes = 4

# SLURM job ID
slurm_job_id = '12345'

ARGS = {
    'args': args,
    'accelerator': accelerator,
    'slurm_job_id': slurm_job_id
}
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 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
resize Not yet run
unverified (harvested, no recorded run)
CompVis/zigma/datasets/video_utils.py
code served (permissive licence) · get_code("f1f9c7dfbe0b3105")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 2 the same month, 9 later) and 4 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
exists 486 other papers
309 dated earlier, 19 the same month, 147 later, 9 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
modulate 101 other papers
21 dated earlier, 2 the same month, 77 later, 1 undated · 29 only as an assembly brick
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2203.10897 (2022-03)
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
and 98 more not named here
center_crop_arr 37 other papers
4 dated earlier, 33 later
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
crop 5 other papers
1 dated earlier, 4 later
2402.16050 (2024-02)
Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
2411.12951 (2024-11)
On the Consistency of Video Large Language Models in Temporal Comprehension
2412.07720 (2024-12)
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
and 2 more not named here
expand_t_like_x 5 other papers
1 dated earlier, 4 later
2401.08740 (2024-01)
SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
2408.05710 (2024-08)
Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
2409.18128 (2024-09)
FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
and 2 more not named here
t2i_modulate 5 other papers
1 dated earlier, 4 later
2310.00426 (2023-10)
PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
2405.14979 (2024-05)
CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
2405.17403 (2024-05)
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
and 2 more not named here
resize 4 other papers
1 dated earlier, 3 later
2402.16050 (2024-02)
Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
2411.12951 (2024-11)
On the Consistency of Video Large Language Models in Temporal Comprehension
2412.07720 (2024-12)
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
and 1 more not named here
generate_run_id 2 other papers
1 dated earlier, 1 later
2401.08740 (2024-01)
SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
2408.05710 (2024-08)
Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
namespace_to_dict 2 other papers
1 dated earlier, 1 later
2401.08740 (2024-01)
SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
2408.05710 (2024-08)
Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
dict_collation_fn 1 other paper
1 dated earlier
2312.00330 (2023-12)
StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

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

The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called Mamba to extend its applicability to visual data generation. Firstly, we identify a critical oversight in most current Mamba-based vision methods, namely the lack of consideration for spatial continuity in the scan scheme of Mamba. Secondly, building upon this insight, we introduce Zigzag Mamba, a simple, plug-andplay, minimal-parameter burden, DiT style solution, which outperforms Mamba-based baselines and demonstrates improved speed and memory utilization compared to transformer-based baselines, also this heterogeneous layerwise scan enables zero memory and speed burden when we consider more scan paths. Lastly, we integrate Zigzag Mamba with the Stochastic Interpolant framework to investigate the scalability of the model on large-resolution visual datasets, such as FacesHQ 1024 × 1024 and UCF101, MultiModal-CelebA-HQ, and MS COCO 256 × 256.

For agents

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

get_harvested_code_for_paper("2403.13802")
get_code_for_paper("2403.13802")
have("2403.13802")

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

curl https://syntology.ai/api/ran/2403.13802.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.13802.svg)](https://syntology.ai/paper/2403.13802)

Connect an agent — have() is free.