SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.08295 · ICML · 2021

Neural Rough Differential Equations for Long Time Series

Patrick Kidger, Terry Lyons, James Morrill, James Foster, Cristopher Salvi

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 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; 2 failures of our instrument; 1 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/2009.08295.json · badge: /api/ran/2009.08295.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
jambo6/neuralRDEs canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
jambo6/neuralCDEs-via-logODEs marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
_NRDECell Ran
ran on a synthesized input · constructed an object; no result was computed
jambo6/neuralRDEs/ncdes/model.py
pointer only (licence: NONE) · get_code("03c0b3b1f931762a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jambo6/neuralRDEs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_NRDECell Ran
ran on a synthesized input · constructed an object; no result was computed
jambo6/neuralCDEs-via-logODEs/ncdes/rdeint.py
pointer only (licence: NONE) · get_code("be6b99ac1c282eca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jambo6/neuralCDEs-via-logODEs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_NRDEFunc Ran
ran on a synthesized input · constructed an object; no result was computed
jambo6/neuralRDEs/ncdes/model.py
pointer only (licence: NONE) · get_code("479e4990b04f81c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jambo6/neuralRDEs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rdeint Ran
ran; our contract draft was wrong, not the code
jambo6/neuralRDEs/ncdes/model.py
pointer only (licence: NONE) · get_code("efd219212fca45f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jambo6/neuralRDEs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rdeint Ran
ran; our contract draft was wrong, not the code
jambo6/neuralCDEs-via-logODEs/ncdes/rdeint.py
pointer only (licence: NONE) · get_code("0905577b4357b699")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jambo6/neuralCDEs-via-logODEs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

NeuralRDE Not yet run
unverified (harvested, no recorded run)
jambo6/neuralRDEs/ncdes/model.py
pointer only (licence: NONE) · get_code("65f51b70e5f7b175")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jambo6/neuralRDEs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. 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 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Neural controlled differential equations (CDEs) are the continuous-time analogue of recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory-efficient continuoustime way to model functions of potentially irregular time series. Existing methods for computing the forward pass of a Neural CDE involve embedding the incoming time series into path space, often via interpolation, and using evaluations of this path to drive the hidden state. Here, we use rough path theory to extend this formulation. Instead of directly embedding into path space, we instead represent the input signal over small time intervals through its log-signature, which are statistics describing how the signal drives a CDE. This is the approach for solving rough differential equations (RDEs), and correspondingly we describe our main contribution as the introduction of Neural RDEs. This extension has a purpose: by generalising the Neural CDE approach to a broader class of driving signals, we demonstrate particular advantages for tackling long time series. In this regime, we demonstrate efficacy on problems of length up to 17k observations and observe significant training speed-ups, improvements in model performance, and reduced memory requirements compared to existing approaches.

For agents

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

get_harvested_code_for_paper("2009.08295")
get_code_for_paper("2009.08295")
have("2009.08295")

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

curl https://syntology.ai/api/ran/2009.08295.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.08295.svg)](https://syntology.ai/paper/2009.08295)

Connect an agent — have() is free.