SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.09387 · 2022

Dual Representation Learning for Out-of-Distribution Detection

arXiv · PDF · Open in the Atlas

Code that ran

12 of 20 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; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 6 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/2206.09387.json · badge: /api/ran/2206.09387.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
lawliet-zzl/drl canonical (classifier label)
classifier basis not recorded on the link
12 ran · 8 no recorded run
FunctionStatusWhere it lives
DPN26 Ran
ran on a synthesized input
lawliet-zzl/drl/code/models/dpn.py
code served (permissive licence) · get_code("5f64843147a6f108")
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 DPN. 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_classes': 10
}
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 DPN — a DPN output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DPN 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
DPN92 Ran
ran on a synthesized input
lawliet-zzl/drl/code/models/dpn.py
code served (permissive licence) · get_code("7773feb89409b320")
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 DPN. 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_classes': 10
}
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 DPN — a DPN output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DPN 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
DenseNet121 Ran
ran; our contract draft was wrong, not the code
lawliet-zzl/drl/code/models/densenet.py
pointer only (licence: MIT); the stored copy get_code serves, from LIONS-EPFL/SAMPa, is pointer only (licence: NONE) · get_code("dfb395bae3d07d76")
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 LIONS-EPFL/SAMPa, 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.

DenseNet169 Ran
ran; our contract draft was wrong, not the code
lawliet-zzl/drl/code/models/densenet.py
pointer only (licence: MIT); the stored copy get_code serves, from LIONS-EPFL/SAMPa, is pointer only (licence: NONE) · get_code("f295fe3c209ecf78")
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 LIONS-EPFL/SAMPa, 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.

DenseNet201 Ran
ran; our contract draft was wrong, not the code
lawliet-zzl/drl/code/models/densenet.py
pointer only (licence: MIT); the stored copy get_code serves, from LIONS-EPFL/SAMPa, is pointer only (licence: NONE) · get_code("6383aee1c940e7a5")
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 LIONS-EPFL/SAMPa, 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.

EfficientNetB0 Ran
ran; our contract draft was wrong, not the code
lawliet-zzl/drl/code/models/efficientnet.py
code served (permissive licence) · get_code("f7b96dbdddb56a68")
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 EfficientNet. 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_classes': 10
}
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 EfficientNet — a EfficientNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EfficientNet 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
drop_connect Ran
ran; our contract draft was wrong, not the code
lawliet-zzl/drl/code/models/efficientnet.py
pointer only (licence: MIT); the stored copy get_code serves, from EnumaCaliber/BRIDGE, is pointer only (licence: NONE) · get_code("4304a326c593f8db")
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 EnumaCaliber/BRIDGE, 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.

getAllOOD Ran
ran on a synthesized input
lawliet-zzl/drl/code/data_loader.py
code served (permissive licence) · get_code("6cfe4ba82c28e7c0")
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.nn as nn
from torchvision import transforms
from PIL import Image
import os
import tempfile

torch.manual_seed(0)

# Create a temporary directory structure for the dataset
temp_dir = tempfile.mkdtemp()
data_dir = os.path.join(temp_dir, 'data')
os.makedirs(data_dir, exist_ok=True)

# Create dummy images
dummy_image = Image.new('RGB', (32, 32), color='red')
dummy_image.save(os.path.join(data_dir, 'img1.jpg'))
dummy_image.save(os.path.join(data_dir, 'img2.jpg'))

# Create list file
list_file_path = os.path.join(temp_dir, 'all_list.txt')
with open(list_file_path, 'w') as f:
    f.write('img1.jpg 0\n')
    f.write('img2.jpg 1\n')

# Define a simple transform
transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
])

ARGS = {
    'root': temp_dir,
    'transform': transform,
    'batch_size': 2,
    'shuffle': False,
    'glist': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
get_mu Ran
ran on a synthesized input
lawliet-zzl/drl/code/model_func.py
code served (permissive licence) · get_code("444f352f6a4b332b")
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 1, dtype family float, shape (5,) 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)

# Build a minimal neural network that outputs num_classes dimensions
class SimpleNet(nn.Module):
    def __init__(self, num_classes):
        super().__init__()
        self.linear = nn.Linear(3, num_classes)
    
    def forward(self, x):
        return self.linear(x)

num_classes = 5
net = SimpleNet(num_classes)

# Create a minimal testloader as a list of (inputs, targets) tuples
# Each input is a batch of 2 samples with 3 features
# Each target is a batch of 2 class labels
testloader = [
    (torch.randn(2, 3), torch.tensor([0, 1])),
    (torch.randn(2, 3), torch.tensor([2, 3])),
]

ARGS = {
    "testloader": testloader,
    "net": net,
    "num_classes": num_classes,
}
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 1, dtype family float, shape (5,) — shape (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
swish Ran
ran; our contract draft was wrong, not the code
lawliet-zzl/drl/code/models/efficientnet.py
pointer only (licence: MIT); the stored copy get_code serves, from EnumaCaliber/BRIDGE, is pointer only (licence: NONE) · get_code("8737c82de631cffc")
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 EnumaCaliber/BRIDGE, 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.

train_DRL Ran
ran on a synthesized input
lawliet-zzl/drl/code/main_DRL.py
code served (permissive licence) · get_code("87718beb1d43a53b")
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. 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 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

torch.manual_seed(0)

# Create a small discriminator network
class NetD(nn.Module):
    def __init__(self):
        super(NetD, self).__init__()
        self.fc = nn.Linear(4, 8)
    
    def forward(self, x):
        return self.fc(x)

# Create a small classifier network
class NetC(nn.Module):
    def __init__(self):
        super(NetC, self).__init__()
        self.fc = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.fc(x)

# Create a custom criterion that accepts outputs_C, outputs_D, and targets
class CustomCriterion(nn.Module):
    def __init__(self):
        super(CustomCriterion, self).__init__()
        self.ce_loss = nn.CrossEntropyLoss()
    
    def forward(self, outputs_C, outputs_D, targets):
        # Simple combination of losses
        loss_c = self.ce_loss(outputs_C, targets)
        return loss_c

# Create a small trainloader with 2 batches of size 2
trainloader = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
    (torch.randn(2, 4), torch.randint(0, 3, (2,)))
]

# Instantiate networks and criterion
net_D = NetD()
net_C = NetC()
criterion = CustomCriterion()

# Create optimizer
optimizer = torch.optim.SGD(net_C.parameters(), lr=0.01)

epoch = 1

ARGS = {
    'trainloader': trainloader,
    'net_D': net_D,
    'net_C': net_C,
    'criterion': criterion,
    'optimizer': optimizer,
    'epoch': epoch
}
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, 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
train_pretrained Ran
ran on a synthesized input
lawliet-zzl/drl/code/main_DRL.py
code served (permissive licence) · get_code("bf5929484b8bce78")
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. 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 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

torch.manual_seed(0)

# Create a small neural network
class SmallNet(nn.Module):
    def __init__(self):
        super(SmallNet, self).__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, 3)
    
    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

net = SmallNet()

# Create a small trainloader (list of (inputs, targets) tuples)
trainloader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 0])),
]

# Create criterion and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.01)

epoch = 1

ARGS = {
    "trainloader": trainloader,
    "net": net,
    "criterion": criterion,
    "optimizer": optimizer,
    "epoch": epoch
}
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, 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
auroc Not yet run
unverified (harvested, no recorded run)
lawliet-zzl/drl/code/OOD_Metric.py
code served (permissive licence) · get_code("647ffb2c86d7808f")
How it ran

no invocation recorded.

auroc_XY Not yet run
unverified (harvested, no recorded run)
lawliet-zzl/drl/code/OOD_Metric.py
code served (permissive licence) · get_code("c048fb086170daf9")
How it ran

no invocation recorded.

build_model Not yet run
unverified (harvested, no recorded run)
lawliet-zzl/drl/code/model_func.py
code served (permissive licence) · get_code("95c820c65911f5ea")
How it ran

no invocation recorded.

getCIFAR10 Not yet run
unverified (harvested, no recorded run)
lawliet-zzl/drl/code/data_loader.py
code served (permissive licence) · get_code("75c46c0650d96502")
How it ran

no invocation recorded.

getCIFAR100 Not yet run
unverified (harvested, no recorded run)
lawliet-zzl/drl/code/data_loader.py
code served (permissive licence) · get_code("c3c76761ed08bd70")
How it ran

no invocation recorded.

getCoupled Not yet run
unverified (harvested, no recorded run)
lawliet-zzl/drl/code/main_DRL.py
code served (permissive licence) · get_code("852857c5a8b391fd")
How it ran

no invocation recorded.

init_setting Not yet run
unverified (harvested, no recorded run)
lawliet-zzl/drl/code/model_func.py
code served (permissive licence) · get_code("40cc6d19b3002c5c")
How it ran

no invocation recorded.

tpr95 Not yet run
unverified (harvested, no recorded run)
lawliet-zzl/drl/code/OOD_Metric.py
code served (permissive licence) · get_code("d9455f51710ae474")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 6 later) and 9 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
swish 32 other papers
7 dated earlier, 25 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2002.11318 (2020-02)
Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks
2106.01440 (2021-06)
Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models
and 29 more not named here
drop_connect 29 other papers
8 dated earlier, 21 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
2002.09564 (2020-02)
Towards Robust and Reproducible Active Learning Using Neural Networks
and 26 more not named here
DenseNet121 11 other papers
4 dated earlier, 7 later
2006.15815 (2020-06)
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
2105.13937 (2021-05)
Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
and 8 more not named here
DenseNet169 9 other papers
3 dated earlier, 6 later
2006.15815 (2020-06)
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
2201.13329 (2022-01)
Can Adversarial Training Be Manipulated By Non-Robust Features?
and 6 more not named here
DenseNet201 9 other papers
3 dated earlier, 6 later
2006.15815 (2020-06)
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
2201.13329 (2022-01)
Can Adversarial Training Be Manipulated By Non-Robust Features?
and 6 more not named here
EfficientNetB0 3 other papers
1 dated earlier, 2 later
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
2305.15316 (2023-05)
Training on Thin Air: Improve Image Classification with Generated Data
2312.12606 (2023-12)
Optimizing Neural Networks with Gradient Lexicase Selection
DPN26 1 other paper
1 dated earlier
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
DPN92 1 other paper
1 dated earlier
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
auroc 1 other paper
1 dated earlier
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
auroc_XY 1 other paper
1 dated earlier
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
tpr95 1 other paper
1 dated earlier
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators

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

To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions differing from that of in-distribution samples could be assigned with unexpected high-confidence predictions because they could obtain minimum strongly label-related information. To distinguish in- and out-of-distribution samples, Dual Representation Learning (DRL) makes out-of-distribution samples harder to have high-confidence predictions by exploring both strongly and weakly label-related information from in-distribution samples. For a pretrained network exploring strongly label-related information to learn label-discriminative representations, DRL trains its auxiliary network exploring the remaining weakly label-related information to learn distribution-discriminative representations. Specifically, for a label-discriminative representation, DRL constructs its complementary distribution-discriminative representation by integrating diverse representations less similar to the label-discriminative representation. Accordingly, DRL combines label- and distribution-discriminative representations to detect out-of-distribution samples. Experiments show that DRL outperforms the state-of-the-art methods for out-of-distribution detection.

For agents

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

get_harvested_code_for_paper("2206.09387")
get_code_for_paper("2206.09387")
have("2206.09387")

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

curl https://syntology.ai/api/ran/2206.09387.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.09387.svg)](https://syntology.ai/paper/2206.09387)

Connect an agent — have() is free.