SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.13600 · 2022

MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 3 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 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/2205.13600.json · badge: /api/ran/2205.13600.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
facebookresearch/myosuite canonical (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
myo-manipulation/spasticmyoelbow extension (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
FunctionStatusWhere it lives
gaussian_smoothing Ran
ran on a synthesized input
facebookresearch/myosuite/myosuite/envs/heightfields.py
code served (permissive licence) · get_code("ffeb08a58aa54e37")
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 list, ndim 2, 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 numpy as np
import math

# Create a small 2D numpy array for testing
test_array = [
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0],
    [7.0, 8.0, 9.0]
]

ARGS = {
    "array": test_array,
    "sigma": 1.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list 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
inverse_sigmoid Ran
ran, violated the contract we drafted
myo-manipulation/spasticmyoelbow/dev/model_validation_experiment.py
code served (permissive licence) · get_code("a110880086c35bb4")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

# Analyze the function:
# - y: numpy array or scalar, used in arithmetic operations (1-y)/y
# - k: float, default 5.0, used in division
# - x0: float, default 0.5, used in subtraction
# The function computes: x0 - 1/k * log((1-y)/y)
# y should be in range (0, 1) for the log to be valid

# Create valid arguments
y = np.array([0.2, 0.5, 0.8, 0.3])  # Values in (0, 1)
k = 5.0
x0 = 0.5

ARGS = {
    'y': y,
    'k': k,
    'x0': x0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
muscle_spasticity Ran
ran, honoured the contract we drafted
myo-manipulation/spasticmyoelbow/dev/model_validation_experiment.py
code served (permissive licence) · get_code("0cfbee645724de8a")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

class MockSimulator:
    def __init__(self):
        self.dt = 0.02
        self.timeVals = np.array([0.0, 0.02, 0.04, 0.06, 0.08, 0.1])
        
        # Create muscle properties as lists of arrays
        # Each entry is a timestep, last entry is current state
        n_muscles = 4
        self.muscleLen = [
            np.random.rand(n_muscles) for _ in range(len(self.timeVals))
        ]
        self.muscleVel = [
            np.random.rand(n_muscles) * 2 - 1 for _ in range(len(self.timeVals))
        ]
        self.muscleForce = [
            np.random.rand(n_muscles) * 10 for _ in range(len(self.timeVals))
        ]
        self.muscleAct = [
            np.random.rand(n_muscles) * 0.5 for _ in range(len(self.timeVals))
        ]

sim = MockSimulator()

ARGS = {
    'sim': sim,
    'type': 'ml',
    'muscle_dynamics': False,
    'tau': 0.03,
    'g': 1.0,
    'threshold': 0.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
muscle_spasticity Ran
ran; our contract draft was wrong, not the code
myo-manipulation/spasticmyoelbow/dev/new_model_fitting.py
code served (permissive licence) · get_code("18663bc021073324")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

class SimulationMock:
    """Mock simulation object with all attributes accessed in muscle_spasticity"""
    def __init__(self):
        self.dt = 0.01
        self.timeVals = np.linspace(0, 1.0, 101)  # Goes past tau threshold
        
        # Muscle feedback arrays - need history
        num_muscles = 4
        num_timesteps = len(self.timeVals)
        
        self.muscleLen = np.random.rand(num_timesteps, num_muscles) * 0.5 + 0.5
        self.muscleVel = np.random.rand(num_timesteps, num_muscles) * 0.3
        self.muscleForce = np.random.rand(num_timesteps, num_muscles) * 100
        self.muscleAct = np.random.rand(num_timesteps, num_muscles) * 0.8
        
        # Muscle properties
        self.starting_length = np.array([0.4, 0.45, 0.5, 0.55])
        self.stretch_length = np.array([0.1, 0.12, 0.15, 0.18])
        self.max_velocity = np.array([1.0, 1.2, 1.5, 1.8])
        self.max_force = np.array([500, 600, 700, 800])

# Create simulation mock
sim = SimulationMock()

# Parameters for muscle_spasticity
mus_select = np.array([1, 1, 0, 1])  # Select 3 out of 4 muscles
muscle_dynamics = True
tau = 0.1  # Time constant
num_muscles = 4
num_reflex_types = 3  # length, velocity, force

# Gains for each reflex type
gains = np.array([0.5, 0.3, 0.2])  # One gain per reflex type

# Thresholds for each muscle and reflex type: shape (3, 4)
thresholds = np.array([
    [0.45, 0.48, 0.51, 0.54],  # length thresholds
    [0.1, 0.15, 0.2, 0.25],    # velocity thresholds
    [50, 60, 70, 80]            # force thresholds
])

ARGS = {
    'sim': sim,
    'mus_select': mus_select,
    'muscle_dynamics': muscle_dynamics,
    'tau': tau,
    'gains': gains,
    'thresholds': thresholds
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
muscle_spasticity Ran
ran, honoured the contract we drafted
myo-manipulation/spasticmyoelbow/dev/test_spasticity_model.py
code served (permissive licence) · get_code("77c384b08c049d5f")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

class MockSimulator:
    def __init__(self):
        self.dt = 0.02
        self.timeVals = np.array([0.0, 0.02, 0.04, 0.06, 0.08, 0.10])
        num_muscles = 4
        num_steps = len(self.timeVals)
        self.muscleLen = np.random.rand(num_steps, num_muscles)
        self.muscleVel = np.random.rand(num_steps, num_muscles)
        self.muscleAct = np.random.rand(num_steps, num_muscles) * 0.5

sim = MockSimulator()

ARGS = {
    'sim': sim,
    'type': 'ml',
    'muscle_dynamics': False,
    'tau': 0.03,
    'g': 2.0,
    'b': 1.0,
    'threshold': 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
sigmoid Ran
ran, honoured the contract we drafted
myo-manipulation/spasticmyoelbow/dev/model_validation_experiment.py
code served (permissive licence) · get_code("8716af66856e8e15")
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 ndarray, 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 numpy as np

def sigmoid(x, k=5.0, x0=0.5):
    return 1.0 / (1.0 + np.exp(-k * (x - x0)))

# Construct arguments for sigmoid function
x = np.array([[0.1, 0.3, 0.5, 0.7],
              [0.2, 0.4, 0.6, 0.8]])

k = 5.0
x0 = 0.5

ARGS = {
    'x': x,
    'k': k,
    'x0': x0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, 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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Embodied agents in continuous control domains have had limited exposure to tasks allowing to explore musculoskeletal properties that enable agile and nimble behaviors in biological beings. The sophistication behind neuro-musculoskeletal control can pose new challenges for the motor learning community. At the same time, agents solving complex neural control problems allow impact in fields such as neuro-rehabilitation, as well as collaborative-robotics. Human biomechanics underlies complex multi-joint-multi-actuator musculoskeletal systems. The sensory-motor system relies on a range of sensory-contact rich and proprioceptive inputs that define and condition muscle actuation required to exhibit intelligent behaviors in the physical world. Current frameworks for musculoskeletal control do not support physiological sophistication of the musculoskeletal systems along with physical world interaction capabilities. In addition, they are neither embedded in complex and skillful motor tasks nor are computationally effective and scalable to study large-scale learning paradigms. Here, we present MyoSuite -- a suite of physiologically accurate biomechanical models of elbow, wrist, and hand, with physical contact capabilities, which allow learning of complex and skillful contact-rich real-world tasks. We provide diverse motor-control challenges: from simple postural control to skilled hand-object interactions such as turning a key, twirling a pen, rotating two balls in one hand, etc. By supporting physiological alterations in musculoskeletal geometry (tendon transfer), assistive devices (exoskeleton assistance), and muscle contraction dynamics (muscle fatigue, sarcopenia), we present real-life tasks with temporal changes, thereby exposing realistic non-stationary conditions in our tasks which most continuous control benchmarks lack.

For agents

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

get_harvested_code_for_paper("2205.13600")
get_code_for_paper("2205.13600")
have("2205.13600")

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

curl https://syntology.ai/api/ran/2205.13600.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.13600.svg)](https://syntology.ai/paper/2205.13600)

Connect an agent — have() is free.