SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.15055 · NeurIPS · 2020

Object-Centric Learning with Slot Attention

Francesco Locatello, Dirk Weissenborn, Thomas Unterthiner, Aravindh Mahendran, Georg Heigold, Jakob Uszkoreit, Alexey Dosovitskiy, Thomas Kipf

arXiv · PDF · Open in the Atlas

Code that ran

14 of 21 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (7 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 5 failures of our instrument; 7 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/2006.15055.json · badge: /api/ran/2006.15055.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
a-imamshah/savi-pytorch community
Papers with Code archive
5 ran · 2 no recorded run
lucidrains/slot-attention reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 2 no recorded run
HHousen/object-discovery-pytorch community
Papers with Code archive
3 ran · 1 no recorded run
untitled-ai/slot_attention alias (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
adityabingi/Slot-Attention community
Papers with Code archive
1 ran · 0 no recorded run
Michedev/slot-attention-pytorch community
Papers with Code archive
1 ran · 0 no recorded run
google-research/google-research unrelated (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Corrector Ran
ran on a synthesized input · constructed an object; no result was computed
a-imamshah/savi-pytorch/model.py
pointer only (licence: NONE) · get_code("e1aebfe322a32f90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-imamshah/savi-pytorch 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.

SAViParams Ran
ran on a synthesized input · constructed an object; no result was computed
a-imamshah/savi-pytorch/model.py
pointer only (licence: NONE) · get_code("36ddba1f54930ede")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-imamshah/savi-pytorch 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.

SlotAttention Ran
ran on a synthesized input · constructed an object; no result was computed
lucidrains/slot-attention/slot_attention/slot_attention.py
code served (permissive licence) · get_code("8a880cb0b42760d3")
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 an instance of its own class, SlotAttention: the run constructed the object and did not call it, so no result was computed. 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 torch import nn

torch.manual_seed(0)

# Create dummy inputs for SlotAttention.forward()
# Shape: (batch=2, num_tokens=3, dim=4)
inputs = torch.randn(2, 3, 4)

ARGS = {
    'num_slots': 5,
    'dim': 4,
    'iters': 3,
    'eps': 1e-8,
    'hidden_dim': 128,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SlotAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SlotAttention 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
SlotAttention Ran
ran on a synthesized input · constructed an object; no result was computed
HHousen/object-discovery-pytorch/object_discovery/slot_attention_model.py
code served (permissive licence) · get_code("2866aea2f2e12f24")
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 an instance of its own class, SlotAttention: the run constructed the object and did not call it, so no result was computed. 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 torch.nn import functional as F

torch.manual_seed(0)

ARGS = {
    'in_features': 5,
    'num_iterations': 2,
    'num_slots': 3,
    'slot_size': 4,
    'mlp_hidden_size': 8,
    'epsilon': 1e-8,
    'do_input_mlp': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SlotAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SlotAttention 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
SlotAttention Ran
ran on a synthesized input · constructed an object; no result was computed
untitled-ai/slot_attention/slot_attention/model.py
code served (permissive licence) · get_code("6976478c1fa514f0")
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 an instance of its own class, SlotAttention: the run constructed the object and did not call it, so no result was computed. 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 torch import nn

torch.manual_seed(0)

ARGS = {
    'in_features': 16,
    'num_iterations': 3,
    'num_slots': 4,
    'slot_size': 8,
    'mlp_hidden_size': 32,
    'epsilon': 1e-8,
}
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 SlotAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SlotAttention 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
SlotAttention Ran
ran on a synthesized input
adityabingi/Slot-Attention/model.py
code served (permissive licence) · get_code("423454f6dee02cea")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, dtype family float, shape (2, 2, 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 as nn
import torch.nn.functional as F
import torch.distributions as dist

INIT_ARGS = {
    'in_dim': 4,
    'slot_size': 3,
    'num_slots': 2,
    'num_iters': 2,
    'mlp_hdim': 8,
    'epsilon': 1e-08,
    'implicit_grads': False,
}

ARGS = {
    'x': torch.randn(2, 5, 4),
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 3, dtype family float, shape (2, 2, 3) — shape (2, 2, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
SlotAttentionModule Ran
ran on a synthesized input · constructed an object; no result was computed
Michedev/slot-attention-pytorch/slot_attention_pytorch/slot_attention_module.py
code served (permissive licence) · get_code("4032cffa99401bb9")
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 an instance of its own class, SlotAttentionModule: the run constructed the object and did not call it, so no result was computed. 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 math import sqrt

torch.manual_seed(0)

# Define the SlotAttentionModule arguments
num_slots = 4
channels_enc = 5
latent_size = 6
attention_iters = 3
eps = 1e-8
mlp_size = 128

# Create the module instance
module = nn.Module()

# Create input tensor: (batch_size=2, num_positions=3, channels_enc=5)
inputs = torch.randn(2, 3, 5)

ARGS = {
    "num_slots": num_slots,
    "channels_enc": channels_enc,
    "latent_size": latent_size,
    "attention_iters": attention_iters,
    "eps": eps,
    "mlp_size": mlp_size,
}
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 SlotAttentionModule — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SlotAttentionModule 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
SoftPositionEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
a-imamshah/savi-pytorch/model.py
pointer only (licence: NONE) · get_code("b63e60d7d9b40cf2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-imamshah/savi-pytorch 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.

build_grid Ran
ran; our contract draft was wrong, not the code
a-imamshah/savi-pytorch/model.py
pointer only (licence: NONE) · get_code("dc25809a5c10c08d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-imamshah/savi-pytorch 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.

conv_transpose_out_shape Ran
ran, honoured the contract we drafted
a-imamshah/savi-pytorch/model.py
pointer only (licence: NONE) · get_code("a841bb8d8f1cb615")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-imamshah/savi-pytorch 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.

gru_cell Ran
ran; our contract draft was wrong, not the code
HHousen/object-discovery-pytorch/object_discovery/slot_attention_model.py
code served (permissive licence) · get_code("4d2babbfd7692155")
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 GRUCell. 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 = {
    "input_size": 4,
    "hidden_size": 3,
    "bias": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GRUCell — a GRUCell output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GRUCell 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
l1norm Ran
ran; our contract draft was wrong, not the code
lucidrains/slot-attention/slot_attention/slot_attention.py
code served (permissive licence) · get_code("fdf3401cb2b8d73a")
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 torch.nn.functional as F

torch.manual_seed(0)

# Create a small tensor for testing
# Using shape (2, 4) - batch size 2, dimension 4
t = torch.randn(2, 4)

# Define ARGS dict with all parameters
ARGS = {
    't': t,
    'dim': -1,
    'eps': 1e-08
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
einops, 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
l1norm Ran
ran; our contract draft was wrong, not the code
lucidrains/slot-attention/slot_attention/slot_attention.py
code served (permissive licence) · get_code("f3e9841706a261f0")
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 (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 torch.nn.functional as F

torch.manual_seed(0)

# The function l1norm takes a tensor t and applies L1 normalization
# Parameters:
# - t: a tensor to normalize
# - dim: dimension along which to normalize (default -1)
# - eps: small epsilon value for numerical stability (default 1e-08)

# Create a small test tensor (batch_size=2, features=4)
t = torch.randn(2, 4)

ARGS = {
    't': t,
    'dim': -1,
    'eps': 1e-08
}
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 (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
linear Ran
ran; our contract draft was wrong, not the code
HHousen/object-discovery-pytorch/object_discovery/slot_attention_model.py
code served (permissive licence) · get_code("e6a98db4b3460c98")
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 Linear. 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 torch import nn

torch.manual_seed(0)

ARGS = {
    'in_features': 4,
    'out_features': 3,
    'bias': True,
    'weight_init': 'xavier',
    'gain': 1.0
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
SAViModel Not yet run
unverified (harvested, no recorded run)
a-imamshah/savi-pytorch/model.py
pointer only (licence: NONE) · get_code("fc3484e23be41e9a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-imamshah/savi-pytorch 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.

SlotAttention Not yet run
unverified (harvested, no recorded run)
google-research/google-research/slot_attention/model.py
code served (permissive licence) · get_code("d27f9166117666a4")
How it ran

no invocation recorded.

assert_shape Not yet run
unverified (harvested, no recorded run)
HHousen/object-discovery-pytorch/object_discovery/slot_attention_model.py
code served (permissive licence) · get_code("79554477c54457b2")
How it ran

no invocation recorded.

assert_shape Not yet run
unverified (harvested, no recorded run)
a-imamshah/savi-pytorch/model.py
pointer only (licence: NONE) · get_code("85fd1318e1fa8108")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-imamshah/savi-pytorch 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.

assert_shape Not yet run
unverified (harvested, no recorded run)
untitled-ai/slot_attention/slot_attention/model.py
code served (permissive licence) · get_code("b59864b89b5b89e0")
How it ran

no invocation recorded.

default Not yet run
unverified (harvested, no recorded run)
lucidrains/slot-attention/slot_attention/slot_attention.py
code served (permissive licence) · get_code("1c5befd817fba622")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

exists Not yet run
unverified (harvested, no recorded run)
lucidrains/slot-attention/slot_attention/slot_attention.py
code served (permissive licence) · get_code("2ad948e611d0af02")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 5 later) and 13 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
brick of this paper's assembly: helper
27 other papers
1 dated earlier, 26 later · 3 only as an assembly brick
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
2010.10241 (2020-10)
BYOL works even without batch statistics
2102.06810 (2021-02)
Understanding self-supervised Learning Dynamics without Contrastive Pairs
and 24 more not named here
default
brick of this paper's assembly: helper
21 other papers
21 later · 1 only as an assembly brick
2110.00218 (2021-10)
On the Importance of Gradients for Detecting Distributional Shifts in the Wild
2309.02612 (2023-09)
Music Source Separation with Band-Split RoPE Transformer
2310.05737 (2023-10)
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
and 18 more not named here
gru_cell
brick of this paper's assembly: helper
3 other papers
3 later · 2 only as an assembly brick
2210.08990 (2022-10)
Improving Object-centric Learning with Query Optimization
2302.08023 (2023-02)
Object-centric Learning with Cyclic Walks between Parts and Whole
2503.15141 (2025-03)
Object-Centric Pretraining via Target Encoder Bootstrapping
linear
brick of this paper's assembly: helper
3 other papers
3 later · 2 only as an assembly brick
2210.08990 (2022-10)
Improving Object-centric Learning with Query Optimization
2302.08023 (2023-02)
Object-centric Learning with Cyclic Walks between Parts and Whole
2503.15141 (2025-03)
Object-Centric Pretraining via Target Encoder Bootstrapping
build_grid
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2210.08990 (2022-10)
Improving Object-centric Learning with Query Optimization

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

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions when trained on unsupervised object discovery and supervised property prediction tasks.

For agents

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

get_harvested_code_for_paper("2006.15055")
get_code_for_paper("2006.15055")
have("2006.15055")

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

curl https://syntology.ai/api/ran/2006.15055.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.15055.svg)](https://syntology.ai/paper/2006.15055)

Connect an agent — have() is free.