SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.08090 · NeurIPS · 2024

Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees

Ambuj Singh, Sean Jaffe, Alexander Davydov, Deniz Lapsekili, Francesco Bullo

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 (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 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/2402.08090.json · badge: /api/ran/2402.08090.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
seanjaffe1/extended-linearized-contracting-dynamics canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
FunctionStatusWhere it lives
ELCD Ran
ran on a synthesized input · constructed an object; no result was computed
seanjaffe1/extended-linearized-contracting-dynamics/models/elcd.py
code served (permissive licence) · get_code("2c90eabfcaa148ae")
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, ELCD: 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

torch.manual_seed(0)

# Dimension parameter
d = 4

# Create x_eq tensor: shape (1, d)
x_eq = torch.randn(1, d)

# Hidden dimension for the networks
hidden_dim = 10

# Train x_eq flag
train_x_eq = False

ARGS = {
    'd': d,
    'x_eq': x_eq,
    'hidden_dim': hidden_dim,
    'train_x_eq': train_x_eq,
}
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 ELCD — 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 ELCD 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
batch_jacobian Ran
ran; our contract draft was wrong, not the code
seanjaffe1/extended-linearized-contracting-dynamics/models/elcd.py
code served (permissive licence) · get_code("0238ff2b3f78a2ad")
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 3, dtype family float, shape (2, 3, 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 numpy as np

torch.manual_seed(0)

# Create small tensors for batch_jacobian
# outputs: batch_size=2, output_dim=3
# inputs: batch_size=2, input_dim=4
# These need to have requires_grad=True for autograd to work

batch_size = 2
input_dim = 4
output_dim = 3

# Create inputs with requires_grad
inputs = torch.randn(batch_size, input_dim, requires_grad=True)

# Create outputs by applying a simple linear transformation
# This ensures outputs depend on inputs for meaningful jacobian computation
linear_transform = torch.randn(output_dim, input_dim)
outputs = torch.matmul(inputs, linear_transform.t())
outputs.requires_grad_(True)

ARGS = {
    "outputs": outputs,
    "inputs": inputs,
    "create_graph": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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, 3, 4) — shape (2, 3, 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
calculate_jacobian Ran
ran; our contract draft was wrong, not the code
seanjaffe1/extended-linearized-contracting-dynamics/models/elcd.py
code served (permissive licence) · get_code("b2152523eee0eca4")
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 (4, 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

torch.manual_seed(0)

# Create a simple function that maps inputs to outputs
# We'll use a small neural network as the function
inputs = torch.randn(3, requires_grad=True)  # 3-dimensional input vector
outputs = torch.randn(4, requires_grad=True)  # 4-dimensional output vector

# Actually, we need outputs to be a function of inputs for the jacobian to make sense
# Let's create a proper setup where outputs depend on inputs
inputs = torch.randn(3, requires_grad=True)
# Create outputs as a function of inputs (e.g., through a simple linear transformation)
weight = torch.randn(4, 3)
outputs = torch.matmul(weight, inputs)

ARGS = {
    "outputs": outputs,
    "inputs": inputs,
    "create_graph": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (4, 3) — shape (4, 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: none by the harness; any seed is in the setup block
get_jacobian_eflow Not yet run
unverified (harvested, no recorded run)
seanjaffe1/extended-linearized-contracting-dynamics/models/elcd.py
code served (permissive licence) · get_code("43e2ecc75ecef6bd")
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

Global stability and robustness guarantees in learned dynamical systems are essential to ensure well-behavedness of the systems in the face of uncertainty. We present Extended Linearized Contracting Dynamics (ELCD), the first neural network-based dynamical system with global contractivity guarantees in arbitrary metrics. The key feature of ELCD is a parametrization of the extended linearization of the nonlinear vector field. In its most basic form, ELCD is guaranteed to be (i) globally exponentially stable, (ii) equilibrium contracting, and (iii) globally contracting with respect to some metric. To allow for contraction with respect to more general metrics in the data space, we train diffeomorphisms between the data space and a latent space and enforce contractivity in the latent space, which ensures global contractivity in the data space. We demonstrate the performance of ELCD on the high dimensional LASA, multi-link pendulum, and Rosenbrock datasets.

For agents

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

get_harvested_code_for_paper("2402.08090")
get_code_for_paper("2402.08090")
have("2402.08090")

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

curl https://syntology.ai/api/ran/2402.08090.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.08090.svg)](https://syntology.ai/paper/2402.08090)

Connect an agent — have() is free.