SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04869 · 2021

Discovery of Nonlinear Dynamical Systems using a Runge-Kutta Inspired Dictionary-based Sparse Regression Approach

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 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/2105.04869.json · badge: /api/ran/2105.04869.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
goyalpike/RK4_SinDy canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
FHN_model Ran
ran, violated the contract we drafted
goyalpike/RK4_SinDy/Functions/models.py
code served (permissive licence) · get_code("2f935608225c925d")
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 (2,) 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:
# - x: used as x[0], x[1], and x[0]**3, so needs to be indexable array-like with at least 2 elements
# - t: not used in the function body, but is a parameter that must be provided

# Create minimal valid arguments
x = np.array([0.5, 0.2])  # State vector with 2 components for the FitzHugh-Nagumo model
t = 0.0  # Time parameter (not used in function but required)

ARGS = {
    "x": x,
    "t": t
}
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 (2,) — shape (2,) 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
lorenz_model Ran
ran, violated the contract we drafted
goyalpike/RK4_SinDy/Functions/models.py
code served (permissive licence) · get_code("2d7e629d76ac2f67")
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 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 torch
import numpy as np

torch.manual_seed(0)

# The lorenz_model function takes x (a list/array of 3 state variables) and t (time)
# It returns a list of 3 derivatives
# x should be indexable with [0], [1], [2]
# t is just used as a parameter but not accessed in the function body

# x can be a list or numpy array with 3 elements
x = [1.0, 2.0, 3.0]

# t is a scalar time value
t = 0.0

ARGS = {
    "x": x,
    "t": t
}
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 list, ndim 1, 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
rk4th_onestep Ran
ran; our contract draft was wrong, not the code
goyalpike/RK4_SinDy/Functions/modules.py
code served (permissive licence) · get_code("491becbe60d01e34")
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 as nn

torch.manual_seed(0)

# Define a simple model that takes x and t as inputs
# The function calls model(x, t) multiple times with varying x and t values
class SimpleODEModel(nn.Module):
    def __init__(self, input_dim=4):
        super().__init__()
        self.linear = nn.Linear(input_dim, input_dim)
    
    def forward(self, x, t):
        # x is a tensor, t is a scalar
        # Return a tensor of the same shape as x
        return self.linear(x)

# Create the model
model = SimpleODEModel(input_dim=4)

# Create a small tensor for x: batch size 2, dimension 4
x = torch.randn(2, 4)

# Scalar time parameter
t = 0.0

# Timestep size
timestep = 0.01

ARGS = {
    "model": model,
    "x": x,
    "t": t,
    "timestep": timestep
}
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
rk4th_onestep_SparseId Ran
ran; our contract draft was wrong, not the code
goyalpike/RK4_SinDy/Functions/modules.py
code served (permissive licence) · get_code("0c4d7aa55377d3f9")
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 as nn

torch.manual_seed(0)

# Create a mock library object with transform_torch method
class MockLibrary(nn.Module):
    def __init__(self, output_dim=5):
        super().__init__()
        self.output_dim = output_dim
    
    def transform_torch(self, x):
        # x shape: (batch, state_dim)
        # Returns transformed features of shape (batch, output_dim)
        batch_size = x.shape[0]
        return torch.randn(batch_size, self.output_dim)

# Create a mock LibsCoeffs callable that acts as a coefficient model
class MockLibsCoeffs(nn.Module):
    def __init__(self, state_dim=4, output_dim=5):
        super().__init__()
        self.state_dim = state_dim
        self.output_dim = output_dim
        self.linear = nn.Linear(output_dim, state_dim)
    
    def forward(self, d):
        # d shape: (batch, output_dim)
        # Returns coefficients/derivatives of shape (batch, state_dim)
        return self.linear(d)

# Instantiate the mock objects
library = MockLibrary(output_dim=5)
libs_coeffs = MockLibsCoeffs(state_dim=4, output_dim=5)

# Create input state tensor: (batch_size=2, state_dim=4)
x = torch.randn(2, 4)

# Define arguments
ARGS = {
    'x': x,
    'library': library,
    'LibsCoeffs': libs_coeffs,
    't': 0,
    'timestep': 0.01
}
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
MM_Kinetics Not yet run
unverified (harvested, no recorded run)
goyalpike/RK4_SinDy/Functions/models.py
code served (permissive licence) · get_code("680a2fff15eb02cf")
How it ran

no invocation recorded.

rk4th_onestep_SparseId_control Not yet run
unverified (harvested, no recorded run)
goyalpike/RK4_SinDy/Functions/modules.py
code served (permissive licence) · get_code("f68d7f736aac7f96")
How it ran

no invocation recorded.

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

Discovering dynamical models to describe underlying dynamical behavior is essential to draw decisive conclusions and engineering studies, e.g., optimizing a process. Experimental data availability notwithstanding has increased significantly, but interpretable and explainable models in science and engineering yet remain incomprehensible. In this work, we blend machine learning and dictionary-based learning with numerical analysis tools to discover governing differential equations from noisy and sparsely-sampled measurement data. We utilize the fact that given a dictionary containing huge candidate nonlinear functions, dynamical models can often be described by a few appropriately chosen candidates. As a result, we obtain interpretable and parsimonious models which are prone to generalize better beyond the sampling regime. Additionally, we integrate a numerical integration framework with dictionary learning that yields differential equations without requiring or approximating derivative information at any stage. Hence, it is utterly effective in corrupted and sparsely-sampled data. We discuss its extension to governing equations, containing rational nonlinearities that typically appear in biological networks. Moreover, we generalized the method to governing equations that are subject to parameter variations and externally controlled inputs. We demonstrate the efficiency of the method to discover a number of diverse differential equations using noisy measurements, including a model describing neural dynamics, chaotic Lorenz model, Michaelis-Menten Kinetics, and a parameterized Hopf normal form.

For agents

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

get_harvested_code_for_paper("2105.04869")
get_code_for_paper("2105.04869")
have("2105.04869")

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

curl https://syntology.ai/api/ran/2105.04869.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.04869.svg)](https://syntology.ai/paper/2105.04869)

Connect an agent — have() is free.