SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.07207 · 2019

Soft Actor-Critic for Discrete Action Settings

arXiv · PDF · Open in the Atlas

Code that ran

12 of 18 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; 2 honoured the contract we drafted, 1 violated it and 7 have no contract verdict; 2 failures of our instrument; 6 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/1910.07207.json · badge: /api/ran/1910.07207.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
p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch canonical (classifier label)
classifier basis: census
0 ran · 2 no recorded run
cindycia/Atari-SAC-Discrete community (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
keraJLi/rejax community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
ku2482/rltorch community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
EpsilonGreedyPolicy Ran
ran on a synthesized input
keraJLi/rejax/src/rejax/networks.py
code served (permissive licence) · get_code("159ca677b48225e4")
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 torch
import jax
import jax.numpy as jnp
from flax import linen as nn
import distrax

torch.manual_seed(0)

# Create a simple Q-network that takes observations and outputs Q-values
class SimpleQNet(nn.Module):
    num_actions: int = 4
    
    def setup(self):
        self.dense1 = nn.Dense(8)
        self.dense2 = nn.Dense(self.num_actions)
    
    def __call__(self, obs):
        x = nn.relu(self.dense1(obs))
        q_values = self.dense2(x)
        return q_values

# Create a simple observation as a JAX array
obs = jnp.ones((2, 4))  # batch_size=2, obs_dim=4

# Create an RNG key for sampling
rng = jax.random.PRNGKey(0)

# The qnet parameter is a nn.Module class (not an instance)
qnet = SimpleQNet

ARGS = {
    'qnet': qnet
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
distrax, flax, jax, 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
create_dqn_base Ran
ran on a synthesized input
cindycia/Atari-SAC-Discrete/rltorch/network/builder.py
code served (permissive licence) · get_code("c010a6ac8668e20d")
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 Sequential. 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)

str_to_initializer = {'uniform': nn.init.uniform_, 'normal': nn.init.normal_, 'eye': nn.init.eye_, 'xavier_uniform': nn.init.xavier_uniform_, 'xavier': nn.init.xavier_uniform_, 'xavier_normal': nn.init.xavier_normal_, 'kaiming_uniform': nn.init.kaiming_uniform_, 'kaiming': nn.init.kaiming_uniform_, 'kaiming_normal': nn.init.kaiming_normal_, 'he': nn.init.kaiming_normal_, 'orthogonal': nn.init.orthogonal_}

def initialize_weights(initializer):
    def initialize(m):
        if isinstance(m, nn.Linear) or isinstance(m, nn.Conv2d):
            initializer(m.weight)
            if m.bias is not None:
                torch.nn.init.constant_(m.bias, 0)
    return initialize

class Flatten(nn.Module):
    def forward(self, x):
        return x.view(x.size(0), -1)

def create_dqn_base(num_channels, initializer='xavier_uniform'):
    return nn.Sequential(nn.Conv2d(num_channels, 32, kernel_size=8, stride=4, padding=0), nn.ReLU(), nn.Conv2d(32, 64, kernel_size=4, stride=2, padding=0), nn.ReLU(), nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=0), nn.ReLU(), Flatten()).apply(initialize_weights(str_to_initializer[initializer]))

ARGS = {
    'num_channels': 3,
    'initializer': 'xavier_uniform'
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
create_linear_network Ran
ran on a synthesized input
cindycia/Atari-SAC-Discrete/rltorch/network/builder.py
code served (permissive licence) · get_code("95498252faaec791")
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 Sequential. 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_dim': 4,
    'output_dim': 2,
    'hidden_units': [8, 6],
    'hidden_activation': 'relu',
    'output_activation': 'sigmoid',
    'initializer': 'xavier_uniform'
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
evaluate_single Ran
ran on a synthesized input
keraJLi/rejax/src/rejax/evaluate.py
code served (permissive licence) · get_code("098ce6dc4eff278c")
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. 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 jax
import jax.numpy as jnp
import chex
from typing import Any

class MockEnv:
    def reset(self, rng, env_params):
        obs = jnp.ones((4,), dtype=jnp.float32)
        env_state = {"step_count": 0}
        return obs, env_state
    
    def step(self, rng, env_state, action, env_params):
        obs = jnp.ones((4,), dtype=jnp.float32)
        env_state_new = {"step_count": env_state["step_count"] + 1}
        reward = jnp.array([0.1], dtype=jnp.float32)
        done = False
        info = {}
        return obs, env_state_new, reward, done, info

def mock_act(obs, rng):
    return jnp.array(0, dtype=jnp.int32)

class MockEnvParams:
    pass

rng = jax.random.PRNGKey(0)
env = MockEnv()
env_params = MockEnvParams()
max_steps_in_episode = 10

ARGS = {
    "act": mock_act,
    "env": env,
    "env_params": env_params,
    "rng": rng,
    "max_steps_in_episode": max_steps_in_episode,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
chex, jax — 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
initialize_weights Ran
ran on a synthesized input
cindycia/Atari-SAC-Discrete/rltorch/network/builder.py
code served (permissive licence) · get_code("a6efcc2f264c05c0")
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 function. 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)

# The initializer parameter should be a callable that takes a weight tensor
# and initializes it. Let's create a simple initializer function.
def simple_initializer(weight):
    """A simple weight initializer that sets weights to 0.5"""
    torch.nn.init.constant_(weight, 0.5)

# The initialize_weights function returns a function that is used to initialize
# module weights. The returned initialize function expects to be called with
# an nn.Module instance and checks if it's Linear or Conv2d.

ARGS = {
    "initializer": simple_initializer
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
make_atari Ran
ran; our contract draft was wrong, not the code
cindycia/Atari-SAC-Discrete/rltorch/env/atari_wrappers.py
code served (permissive licence) · get_code("4bc698f17fe89d85")
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 MaxAndSkipEnv. 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 gym
import numpy as np

# Create a minimal mock Atari environment that satisfies the requirements
class MockAtariEnv(gym.Env):
    def __init__(self):
        self.observation_space = gym.spaces.Box(
            low=0, high=255, shape=(84, 84), dtype=np.uint8
        )
        self.action_space = gym.spaces.Discrete(4)
        self.spec = type('obj', (object,), {'id': 'PongNoFrameskip-v4'})()
        self._step_count = 0
    
    def get_action_meanings(self):
        return ['NOOP', 'FIRE', 'RIGHT', 'LEFT']
    
    def reset(self, **kwargs):
        self._step_count = 0
        return np.zeros((84, 84), dtype=np.uint8)
    
    def step(self, action):
        self._step_count += 1
        obs = np.zeros((84, 84), dtype=np.uint8)
        reward = 1.0
        done = self._step_count > 100
        info = {}
        return obs, reward, done, info
    
    def seed(self, seed=None):
        np.random.seed(seed)
        return [seed]

# Patch gym.make to return our mock environment
original_gym_make = gym.make

def mock_gym_make(env_id):
    if 'NoFrameskip' in env_id:
        return MockAtariEnv()
    return original_gym_make(env_id)

gym.make = mock_gym_make

# Define arguments for make_atari
ARGS = {
    'env_id': 'PongNoFrameskip-v4'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gym, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MaxAndSkipEnv — a MaxAndSkipEnv output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MaxAndSkipEnv 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
process_action Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from ac-93/soft-actor-critic
pointer only · get_code("e5cbade112f15d84")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

process_observation Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from ac-93/soft-actor-critic
pointer only · get_code("22e993f58f0d200b")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

process_reward Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from ac-93/soft-actor-critic
pointer only · get_code("1deaa4d231ac8f53")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

register_init Ran
ran on a synthesized input
keraJLi/rejax/src/rejax/algos/algorithm.py
code served (permissive licence) · get_code("e62f6ecb2ba1c892")
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 function. 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

def dummy_init_function():
    """A simple function to be registered."""
    pass

def another_function():
    """Another function to register."""
    pass

class DummyModule(nn.Module):
    """Minimal module for testing."""
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# The register_init function takes a single parameter: func
# It should be a callable (function or method)
ARGS = {
    'func': dummy_init_function
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
to_batch Ran
ran; our contract draft was wrong, not the code
cindycia/Atari-SAC-Discrete/rltorch/agent/utils.py
code served (permissive licence) · get_code("3afd917c65b80e08")
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

torch.manual_seed(0)

ARGS = {
    "state": [1.0, 2.0, 3.0, 4.0],
    "action": 0.5,
    "reward": 1.0,
    "next_state": [2.0, 3.0, 4.0, 5.0],
    "done": 1.0,
    "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 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
update_rms Ran
ran on a synthesized input
keraJLi/rejax/src/rejax/algos/mixins.py
code served (permissive licence) · get_code("ea614117ba22d252")
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 RMSState. 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 jax.numpy as jnp
from jax import tree_util

class RMSState:
    def __init__(self, mean, var, count):
        self.mean = mean
        self.var = var
        self.count = count
    
    def replace(self, mean=None, var=None, count=None):
        return RMSState(
            mean=mean if mean is not None else self.mean,
            var=var if var is not None else self.var,
            count=count if count is not None else self.count
        )

rms_state = RMSState(
    mean=jnp.zeros(4),
    var=jnp.ones(4),
    count=0
)

x = jnp.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
])

ARGS = {
    "rms_state": rms_state,
    "x": x,
    "batched": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RMSState — a RMSState output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RMSState 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
EpsilonGreedyPolicy Not yet run
unverified (harvested, no recorded run)
keraJLi/rejax/src/rejax/algos/iqn.py
code served (permissive licence) · get_code("6fe3b3b62f1d627e")
How it ran

no invocation recorded.

make_atari_game Not yet run
unverified (harvested, no recorded run)
p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch/environments/Atari_Environment.py
code served (permissive licence) · get_code("5518bf3701f7ad8c")
How it ran

no invocation recorded.

make_pytorch_env Not yet run
unverified (harvested, no recorded run)
cindycia/Atari-SAC-Discrete/rltorch/env/atari_wrappers.py
code served (permissive licence) · get_code("20aa2a394b00c4d7")
How it ran

no invocation recorded.

make_pytorch_env Not yet run
unverified (harvested, no recorded run)
ku2482/rltorch/rltorch/env/atari_wrappers.py
code served (permissive licence) · get_code("4710cb8bbbee96dd")
How it ran

no invocation recorded.

wrap_deepmind Not yet run
unverified (harvested, no recorded run)
p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch/environments/Atari_Environment.py
code served (permissive licence) · get_code("f22df3c0c0b99757")
How it ran

no invocation recorded.

wrap_deepmind_pytorch Not yet run
unverified (harvested, no recorded run)
cindycia/Atari-SAC-Discrete/rltorch/env/atari_wrappers.py
code served (permissive licence) · get_code("4d7ad6b7f3100923")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 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 (4 with at least one paper dated earlier, 0 the same month, 2 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
make_atari 6 other papers
1 dated earlier, 5 later
1511.06581 (2015-11)
Dueling Network Architectures for Deep Reinforcement Learning
1911.02140 (2019-11)
Fully Parameterized Quantile Function for Distributional Reinforcement Learning
2002.04839 (2020-02)
LaProp: Separating Momentum and Adaptivity in Adam
and 3 more not named here
to_batch 2 other papers
2 later
2110.02034 (2021-10)
Dropout Q-Functions for Doubly Efficient Reinforcement Learning
2605.21282 (2026-05)
Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
process_action 1 other paper
1 dated earlier
1812.05905 (2018-12)
Soft Actor-Critic Algorithms and Applications
process_observation 1 other paper
1 dated earlier
1812.05905 (2018-12)
Soft Actor-Critic Algorithms and Applications
process_reward 1 other paper
1 dated earlier
1812.05905 (2018-12)
Soft Actor-Critic Algorithms and Applications

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

Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings. Many important settings involve discrete actions, however, and so here we derive an alternative version of the Soft Actor-Critic algorithm that is applicable to discrete action settings. We then show that, even without any hyperparameter tuning, it is competitive with the tuned model-free state-of-the-art on a selection of games from the Atari suite.

For agents

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

get_harvested_code_for_paper("1910.07207")
get_code_for_paper("1910.07207")
have("1910.07207")

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

curl https://syntology.ai/api/ran/1910.07207.json

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

[![Syntology run record](https://syntology.ai/api/ran/1910.07207.svg)](https://syntology.ai/paper/1910.07207)

Connect an agent — have() is free.