SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.08408 · 2022

Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 1 honoured the contract we drafted, 3 violated it and 0 have no contract verdict; 0 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/2202.08408.json · badge: /api/ran/2202.08408.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
grand-lab/mtgode canonical (classifier label)
classifier basis: plan_row
4 ran · 0 no recorded run
trustagi-lab/mtgode canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
asym_adj Ran
ran, violated the contract we drafted
grand-lab/mtgode/util.py
code served (permissive licence) · get_code("b2bde59f87bab41d")
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 matrix, ndim 2, dtype family float, shape (4, 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
import scipy.sparse as sp

# Create a small sparse adjacency matrix
# Using a 4x4 matrix with some connections
rows = np.array([0, 1, 2, 3, 0, 2])
cols = np.array([1, 2, 3, 0, 3, 1])
data = np.array([1, 1, 1, 1, 1, 1])
adj_sparse = sp.coo_matrix((data, (rows, cols)), shape=(4, 4))

# Convert to a dense numpy array for testing
adj = adj_sparse.toarray().astype(np.float32)

ARGS = {
    "adj": adj
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type matrix, ndim 2, dtype family float, shape (4, 4) — shape (4, 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
normal_std Ran
ran, honoured the contract we drafted
grand-lab/mtgode/util.py
code served (permissive licence) · get_code("1ef18a710e2babf6")
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 float64, ndim 0, 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

def normal_std(x):
    return x.std() * np.sqrt((len(x) - 1.0) / len(x))

# The function takes a single parameter 'x' which needs:
# - .std() method (numpy array or similar)
# - len() support
# - numeric operations (* and numpy.sqrt)

x = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

ARGS = {
    "x": x
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
str_to_bool Ran
ran, violated the contract we drafted
grand-lab/mtgode/run_multi_step.py
pointer only (licence: MIT); the stored copy get_code serves, from sjtu-dmtai/lift, is pointer only (licence: NONE) · get_code("ece7c69991e1b54f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sjtu-dmtai/lift, and GitHub detected no licence in that repository 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.

sym_adj Ran
ran, violated the contract we drafted
grand-lab/mtgode/util.py
code served (permissive licence) · get_code("9a7928795f74526c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned matrix, ndim 2, dtype family float, shape (5, 5) 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
import scipy.sparse as sp

# Create a small adjacency matrix for a graph with 5 nodes
# This represents a simple undirected graph
adj_dense = np.array([
    [0, 1, 1, 0, 0],
    [1, 0, 1, 1, 0],
    [1, 1, 0, 1, 1],
    [0, 1, 1, 0, 1],
    [0, 0, 1, 1, 0]
], dtype=np.float32)

# Convert to sparse matrix (the function expects this format or will convert it)
adj_sparse = sp.csr_matrix(adj_dense)

ARGS = {
    'adj': adj_sparse
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type matrix, ndim 2, dtype family float, shape (5, 5) — shape (5, 5) 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
evaluate Not yet run
unverified (harvested, no recorded run)
trustagi-lab/mtgode/run_single_step.py
code served (permissive licence) · get_code("0320dc4eae4b7df0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
asym_adj 6 other papers
2 dated earlier, 4 later
1906.00121 (2019-06)
Graph WaveNet for Deep Spatial-Temporal Graph Modeling
2104.14917 (2021-04)
Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution
2401.03138 (2024-01)
TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling
and 3 more not named here
str_to_bool 4 other papers
1 dated earlier, 3 later
2005.11650 (2020-05)
Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
2401.03138 (2024-01)
TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling
2401.17548 (2024-01)
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
and 1 more not named here
sym_adj 4 other papers
2 dated earlier, 2 later
1906.00121 (2019-06)
Graph WaveNet for Deep Spatial-Temporal Graph Modeling
2104.14917 (2021-04)
Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution
2403.02600 (2024-03)
TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
and 1 more not named here
normal_std 2 other papers
2 dated earlier
1703.07015 (2017-03)
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
2104.14917 (2021-04)
Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

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

Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction. While recent methods demonstrate good forecasting abilities, they have three fundamental limitations. (i) Discrete neural architectures: Interlacing individually parameterized spatial and temporal blocks to encode rich underlying patterns leads to discontinuous latent state trajectories and higher forecasting numerical errors. (ii) High complexity: Discrete approaches complicate models with dedicated designs and redundant parameters, leading to higher computational and memory overheads. (iii) Reliance on graph priors: Relying on predefined static graph structures limits their effectiveness and practicability in real-world applications. In this paper, we address all the above limitations by proposing a continuous model to forecast $\textbf{M}$ultivariate $\textbf{T}$ime series with dynamic $\textbf{G}$raph neural $\textbf{O}$rdinary $\textbf{D}$ifferential $\textbf{E}$quations ($\texttt{MTGODE}$). Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing, allowing deeper graph propagation and fine-grained temporal information aggregation to characterize stable and precise latent spatial-temporal dynamics. Our experiments demonstrate the superiorities of $\texttt{MTGODE}$ from various perspectives on five time series benchmark datasets.

For agents

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

get_harvested_code_for_paper("2202.08408")
get_code_for_paper("2202.08408")
have("2202.08408")

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

curl https://syntology.ai/api/ran/2202.08408.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.08408.svg)](https://syntology.ai/paper/2202.08408)

Connect an agent — have() is free.