SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.10879 · 2021

Discovering Sparse Interpretable Dynamics from Partial Observations

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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 0 have no contract verdict; 1 failure 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/2107.10879.json · badge: /api/ran/2107.10879.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
peterparity/symder canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
get_model_apply Ran
ran; our contract draft was wrong, not the code
peterparity/symder/symder/symder.py
code served (permissive licence) · get_code("f6cad340caf3a795")
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)

# Define encoder_apply: takes params, x, and optionally dxdt
# Returns z (latent) and optionally dzdt_hidden
class SimpleEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 5)
    
    def forward(self, x, dxdt=None):
        z = self.linear(x)
        if dxdt is not None:
            dzdt_hidden = self.linear(dxdt)
            return z, dzdt_hidden
        return z

encoder_module = SimpleEncoder()
encoder_params = dict(encoder_module.named_parameters())

def encoder_apply(params, x, dxdt=None):
    # Simplified encoder that uses params to transform x
    if dxdt is not None:
        z = torch.matmul(x, params['linear.weight'].t()) + params['linear.bias']
        dzdt_hidden = torch.matmul(dxdt, params['linear.weight'].t()) + params['linear.bias']
        return z, dzdt_hidden
    else:
        z = torch.matmul(x, params['linear.weight'].t()) + params['linear.bias']
        return z

# Define symder_apply: takes params, z
# Returns sym_deriv_x and optionally sym_dzdt
class SymModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(5, 4)
    
    def forward(self, z):
        return self.linear(z)

sym_module = SymModel()
sym_params = dict(sym_module.named_parameters())

def symder_apply(params, z):
    # Simplified sym model that takes z and returns derivatives
    sym_deriv_x = torch.matmul(z, params['linear.weight'].t()) + params['linear.bias']
    return sym_deriv_x

# Define hidden_transform: transforms latent z
def hidden_transform(z):
    return z * 0.5

# Prepare params dict with both encoder and sym_model params
params = {
    'encoder': encoder_params,
    'sym_model': sym_params
}

# Test data
x = torch.randn(2, 4)  # batch_size=2, input_dim=4
dxdt = torch.randn(2, 4)

ARGS = {
    'encoder_apply': encoder_apply,
    'symder_apply': symder_apply,
    'encoder_name': 'encoder',
    'sym_model_name': 'sym_model',
    'hidden_transform': hidden_transform,
    'get_dzdt': False
}
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
generate_dataset Not yet run
unverified (harvested, no recorded run)
peterparity/symder/data/lorenz.py
code served (permissive licence) · get_code("27141289006aae18")
How it ran

no invocation recorded.

get_symder_apply Not yet run
unverified (harvested, no recorded run)
peterparity/symder/symder/symder.py
code served (permissive licence) · get_code("5f99e041a0bd1107")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Identifying the governing equations of a nonlinear dynamical system is key to both understanding the physical features of the system and constructing an accurate model of the dynamics that generalizes well beyond the available data. We propose a machine learning framework for discovering these governing equations using only partial observations, combining an encoder for state reconstruction with a sparse symbolic model. Our tests show that this method can successfully reconstruct the full system state and identify the underlying dynamics for a variety of ODE and PDE systems.

For agents

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

get_harvested_code_for_paper("2107.10879")
get_code_for_paper("2107.10879")
have("2107.10879")

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

curl https://syntology.ai/api/ran/2107.10879.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.10879.svg)](https://syntology.ai/paper/2107.10879)

Connect an agent — have() is free.