SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.05475 · 2020

Adversarial score matching and improved sampling for image generation

arXiv · PDF · Open in the Atlas

Code that ran

11 of 19 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 5 have no contract verdict; 5 failures of our instrument; 8 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/2009.05475.json · badge: /api/ran/2009.05475.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
AlexiaJM/AdversarialConsistentScoreMatching canonical (classifier label)
classifier basis: census
11 ran · 8 no recorded run
FunctionStatusWhere it lives
D_arch Ran
ran on a synthesized input
AlexiaJM/AdversarialConsistentScoreMatching/models/models_biggan.py
code served (permissive licence) · get_code("732d74a7cda572d3")
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)

# Analyzing the function D_arch:
# - ch: integer, default 64
# - attention: string that gets split by '_' and converted to integers, default '64'
# - ksize: string, default '333333' (appears to be unused in the function body)
# - dilation: string, default '111111' (appears to be unused in the function body)
#
# The function only uses ch and attention parameters in its logic.
# It constructs architecture dictionaries for different image sizes (256, 128, 64, 32, 28)
# The attention parameter is split and parsed to determine attention placement

ARGS = {
    'ch': 64,
    'attention': '64',
    'ksize': '333333',
    'dilation': '111111'
}
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
Normalize Ran
ran; our contract draft was wrong, not the code
AlexiaJM/AdversarialConsistentScoreMatching/models/UNet.py
code served (permissive licence) · get_code("7a5794dd00d68985")
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 GroupNorm. 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)

ARGS = {
    "num_channels": 32
}
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 GroupNorm — a GroupNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GroupNorm 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
adv_loss Ran
ran on a synthesized input
AlexiaJM/AdversarialConsistentScoreMatching/losses/adversarial.py
code served (permissive licence) · get_code("1eb751d5cd076fab")
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 map. 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)

class ConfigStandIn:
    def __init__(self, batch_size):
        self.batch_size = batch_size

ARGS = {
    "loss_type": "GAN",
    "t_config": ConfigStandIn(batch_size=2),
    "device": torch.device("cpu"),
}
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 map — a map output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a map 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
calculate_frechet_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AlexiaJM/AdversarialConsistentScoreMatching/evaluation/fid_score.py
pointer only (licence: MIT); the stored copy get_code serves, from shpda/text-to-image-gen-model-acgan, is pointer only (licence: NONE) · get_code("4cee7c1861294d59")
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 shpda/text-to-image-gen-model-acgan, 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.

dsm_score_evaluation Ran
ran on a synthesized input
AlexiaJM/AdversarialConsistentScoreMatching/losses/dsm.py
code served (permissive licence) · get_code("588d808f7ed634d3")
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)

# Create a minimal args object
class Args:
    def __init__(self):
        self.target = 'gaussian'

# Create a minimal score network
class ScoreNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, labels):
        # x shape: (batch, 4)
        # labels shape: (batch,)
        # Return scores with same shape as input
        return self.linear(x)

# Construct the arguments
args = Args()
scorenet = ScoreNet()
samples = torch.randn(2, 4)  # batch size 2, feature dim 4
sigmas = torch.tensor([0.1, 0.5, 1.0, 2.0])  # 4 different sigma values

ARGS = {
    'args': args,
    'scorenet': scorenet,
    'samples': samples,
    'sigmas': sigmas
}
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
gaussian_filter Ran
ran on a synthesized input
AlexiaJM/AdversarialConsistentScoreMatching/losses/ssim.py
code served (permissive licence) · get_code("ad0128e7c4e3e49b")
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, 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create input tensor: batch of 2, 3 channels, 5x5 spatial dimensions
inpt = torch.randn(2, 3, 5, 5)

# Create 1-D Gaussian kernel
# The kernel needs to be a 4-D tensor for conv2d: (out_channels, in_channels/groups, H, W)
# Since groups=C (3 channels), we need out_channels=3, in_channels=1
# For a 1-D kernel applied horizontally then vertically, shape should be (3, 1, 1, 3)
win = torch.randn(3, 1, 1, 3)

ARGS = {
    "inpt": inpt,
    "win": win,
}
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, 3, 3) — shape (2, 3, 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
get_timestep_embedding Ran
ran on a synthesized input
AlexiaJM/AdversarialConsistentScoreMatching/models/UNet.py
code served (permissive licence) · get_code("925a70f8b592a1dd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (4, 128) 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 math

torch.manual_seed(0)

# The function expects:
# - timesteps: a 1D tensor of integers/floats representing timestep indices
# - embedding_dim: an integer for the embedding dimension

# Looking at the function body:
# - timesteps must be a 1D tensor (len(timesteps.shape) == 1)
# - embedding_dim should be a positive integer
# - The function uses timesteps.shape[0] to get batch size
# - It creates embeddings of shape [batch_size, embedding_dim]

timesteps = torch.tensor([0, 1, 5, 10], dtype=torch.long)

ARGS = {
    "timesteps": timesteps,
    "embedding_dim": 128,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (4, 128) — shape (4, 128) 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
gram_schmidt Ran
ran; our contract draft was wrong, not the code
AlexiaJM/AdversarialConsistentScoreMatching/models/layers_biggan.py
pointer only (licence: MIT); the stored copy get_code serves, from mshahbazi72/cGANTransfer, is pointer only (licence: NONE) · get_code("c41836f3e51fa8f1")
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 mshahbazi72/cGANTransfer, 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.

imread Ran
ran, honoured the contract we drafted
AlexiaJM/AdversarialConsistentScoreMatching/evaluation/fid_score.py
pointer only (licence: MIT); the stored copy get_code serves, from zmtomorrow/mmdgs_neurips, is pointer only (licence: NONE) · get_code("aa4cae054b657ba2")
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 zmtomorrow/mmdgs_neurips, 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.

partialclass Ran
ran; our contract draft was wrong, not the code
AlexiaJM/AdversarialConsistentScoreMatching/models/UNet.py
code served (permissive licence) · get_code("61098cd5c9624563")
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 type. 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 functools
import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple base class to demonstrate partialclass
class SimpleModel(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim):
        super().__init__()
        self.linear1 = nn.Linear(input_dim, hidden_dim)
        self.linear2 = nn.Linear(hidden_dim, output_dim)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Set up arguments for partialclass
# partialclass takes: cls, *args, **kwds
cls_arg = SimpleModel
args_tuple = (4, 8)  # input_dim, hidden_dim as positional args
kwds_dict = {"output_dim": 3}  # output_dim as keyword arg

ARGS = {
    "cls": cls_arg,
    "args": args_tuple,
    "kwds": kwds_dict
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
power_iteration Ran
ran; our contract draft was wrong, not the code
AlexiaJM/AdversarialConsistentScoreMatching/models/layers_biggan.py
code served (permissive licence) · get_code("28d3a35157f2916d")
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.functional as F

torch.manual_seed(0)

# Construct valid arguments for power_iteration
# W: weight matrix that will be multiplied with u and v vectors
# Shape should allow matmul operations: (4, 3) so u (1, 4) @ W (4, 3) = (1, 3)
W = torch.randn(4, 3)

# u_: list of initial vectors
# Each should be a 1D tensor with size matching W's first dimension
u_ = [
    torch.randn(1, 4),
    torch.randn(1, 4),
]

# update: boolean flag
update = True

# eps: small epsilon for numerical stability
eps = 1e-12

ARGS = {
    "W": W,
    "u_": u_,
    "update": update,
    "eps": eps,
}
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
conv1x1 Not yet run
unverified (harvested, no recorded run)
AlexiaJM/AdversarialConsistentScoreMatching/models/layers.py
code served (permissive licence) · get_code("2e78d8e29cc32e5c")
How it ran

no invocation recorded.

get_act Not yet run
unverified (harvested, no recorded run)
AlexiaJM/AdversarialConsistentScoreMatching/models/layers.py
code served (permissive licence) · get_code("8d4b8d16b429680f")
How it ran

no invocation recorded.

get_activations Not yet run
unverified (harvested, no recorded run)
AlexiaJM/AdversarialConsistentScoreMatching/evaluation/fid_score.py
code served (permissive licence) · get_code("ea10a012ef6a93a9")
How it ran

no invocation recorded.

ms_ssim Not yet run
unverified (harvested, no recorded run)
AlexiaJM/AdversarialConsistentScoreMatching/losses/ssim.py
code served (permissive licence) · get_code("488d353bf6efcbec")
How it ran

no invocation recorded.

proj Not yet run
unverified (harvested, no recorded run)
AlexiaJM/AdversarialConsistentScoreMatching/models/layers_biggan.py
pointer only (licence: MIT); the stored copy get_code serves, from mshahbazi72/cGANTransfer, is pointer only (licence: NONE) · get_code("4015ab1f3ab9b881")
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 mshahbazi72/cGANTransfer, 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.

run Not yet run
unverified (harvested, no recorded run)
AlexiaJM/AdversarialConsistentScoreMatching/evaluation/inception_score.py
code served (permissive licence) · get_code("1fd21c8226a81691")
How it ran

no invocation recorded.

spectral_norm Not yet run
unverified (harvested, no recorded run)
AlexiaJM/AdversarialConsistentScoreMatching/models/layers.py
code served (permissive licence) · get_code("ae04ffcb2b1c6911")
How it ran

no invocation recorded.

ssim Not yet run
unverified (harvested, no recorded run)
AlexiaJM/AdversarialConsistentScoreMatching/losses/ssim.py
code served (permissive licence) · get_code("823d06885232ea44")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 9 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 9 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
calculate_frechet_distance 74 other papers
18 dated earlier, 56 later
1610.09585 (2016-10)
Conditional Image Synthesis With Auxiliary Classifier GANs
1706.08500 (2017-06)
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
1807.11458 (2018-07)
To learn image super-resolution, use a GAN to learn how to do image degradation first
and 71 more not named here
gram_schmidt 28 other papers
8 dated earlier, 20 later · 5 only as an assembly brick
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
and 25 more not named here
proj 28 other papers
8 dated earlier, 20 later · 5 only as an assembly brick
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
and 25 more not named here
power_iteration 25 other papers
7 dated earlier, 18 later · 5 only as an assembly brick
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
and 22 more not named here
imread 12 other papers
12 later
2106.01954 (2021-06)
Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
2112.05134 (2021-12)
A Shared Representation for Photorealistic Driving Simulators
2201.12220 (2022-01)
Neural Optimal Transport
and 9 more not named here
partialclass 5 other papers
1 dated earlier, 4 later · 1 only as an assembly brick
1906.01618 (2019-06)
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
2205.09853 (2022-05)
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation
2210.05927 (2022-10)
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
and 2 more not named here
conv1x1 2 other papers
2 later
2307.11308 (2023-07)
DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport
2407.04493 (2024-07)
PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation
spectral_norm 2 other papers
2 later
2307.11308 (2023-07)
DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport
2407.04493 (2024-07)
PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation
Normalize 1 other paper
1 later
2205.09853 (2022-05)
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation

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

Denoising Score Matching with Annealed Langevin Sampling (DSM-ALS) has recently found success in generative modeling. The approach works by first training a neural network to estimate the score of a distribution, and then using Langevin dynamics to sample from the data distribution assumed by the score network. Despite the convincing visual quality of samples, this method appears to perform worse than Generative Adversarial Networks (GANs) under the Fréchet Inception Distance, a standard metric for generative models. We show that this apparent gap vanishes when denoising the final Langevin samples using the score network. In addition, we propose two improvements to DSM-ALS: 1) Consistent Annealed Sampling as a more stable alternative to Annealed Langevin Sampling, and 2) a hybrid training formulation, composed of both Denoising Score Matching and adversarial objectives. By combining these two techniques and exploring different network architectures, we elevate score matching methods and obtain results competitive with state-of-the-art image generation on CIFAR-10.

For agents

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

get_harvested_code_for_paper("2009.05475")
get_code_for_paper("2009.05475")
have("2009.05475")

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

curl https://syntology.ai/api/ran/2009.05475.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.05475.svg)](https://syntology.ai/paper/2009.05475)

Connect an agent — have() is free.