SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.02604 · 2020

BARK: Open Behavior Benchmarking in Multi-Agent Environments

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 3 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2003.02604.json · badge: /api/ran/2003.02604.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
bark-simulator/bark canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
deserialize_benchmark_config Ran
ran on a synthesized input
bark-simulator/bark/bark/benchmark/benchmark_runner_mp.py
code served (permissive licence) · get_code("9eb70f020b27eabe")
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 pickle
import torch
import numpy as np

torch.manual_seed(0)

# The function deserialize_benchmark_config simply calls pickle.loads on the input
# So we need to create a pickled object that can be deserialized

# Create a simple benchmark config dictionary
benchmark_config = {
    "model_name": "test_model",
    "batch_size": 32,
    "learning_rate": 0.001,
    "num_epochs": 10,
    "layers": [64, 128, 256],
    "dropout": 0.5
}

# Serialize it using pickle
serialized_config = pickle.dumps(benchmark_config)

ARGS = {
    "bc": serialized_config
}
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
return_execution_time Ran
ran on a synthesized input
bark-simulator/bark/bark/runtime/commons/commons.py
code served (permissive licence) · get_code("2cbc7b7a886e6b50")
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
import time

def return_execution_time(func):

    def wrapper(*args, **kwargs):
        time_before_step = time.time()
        func(*args, **kwargs)
        step_duration = time.time() - time_before_step
        return step_duration
    return wrapper


# Define a simple test function to be decorated
def sample_function(x, y):
    """A simple function that does some computation"""
    total = x + y
    for _ in range(1000):
        total = total * 1.0001
    return total


# Setup ARGS dictionary
ARGS = {
    "func": sample_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
serialize_benchmark_config Ran
ran on a synthesized input
bark-simulator/bark/bark/benchmark/benchmark_runner_mp.py
code served (permissive licence) · get_code("4ce488f0946799a8")
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 bytes. 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 pickle
import torch
import numpy as np

torch.manual_seed(0)

# The function serialize_benchmark_config takes a benchmark config object
# and pickles it. We need to create a valid config object that can be pickled.
# Since the function just calls pickle.dumps on it, any picklable object works.

# Create a simple benchmark config as a dict
benchmark_config = {
    "model_name": "test_model",
    "batch_size": 32,
    "learning_rate": 0.001,
    "num_epochs": 10,
    "dataset": "test_dataset",
    "metrics": ["accuracy", "loss"],
    "seed": 42,
    "tensor_param": torch.randn(2, 4),
    "numpy_param": np.array([1, 2, 3, 4]),
}

ARGS = {
    "bc": benchmark_config
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
serialize_scenario Not yet run
unverified (harvested, no recorded run)
bark-simulator/bark/bark/benchmark/benchmark_runner_mp.py
code served (permissive licence) · get_code("5057a516509b52b5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Predicting and planning interactive behaviors in complex traffic situations presents a challenging task. Especially in scenarios involving multiple traffic participants that interact densely, autonomous vehicles still struggle to interpret situations and to eventually achieve their own mission goal. As driving tests are costly and challenging scenarios are hard to find and reproduce, simulation is widely used to develop, test, and benchmark behavior models. However, most simulations rely on datasets and simplistic behavior models for traffic participants and do not cover the full variety of real-world, interactive human behaviors. In this work, we introduce BARK, an open-source behavior benchmarking environment designed to mitigate the shortcomings stated above. In BARK, behavior models are (re-)used for planning, prediction, and simulation. A range of models is currently available, such as Monte-Carlo Tree Search and Reinforcement Learning-based behavior models. We use a public dataset and sampling-based scenario generation to show the inter-exchangeability of behavior models in BARK. We evaluate how well the models used cope with interactions and how robust they are towards exchanging behavior models. Our evaluation shows that BARK provides a suitable framework for a systematic development of behavior models.

For agents

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

get_harvested_code_for_paper("2003.02604")
get_code_for_paper("2003.02604")
have("2003.02604")

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

curl https://syntology.ai/api/ran/2003.02604.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.02604.svg)](https://syntology.ai/paper/2003.02604)

Connect an agent — have() is free.