SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.00121 · 2019

Graph WaveNet for Deep Spatial-Temporal Graph Modeling

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 3 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/1906.00121.json · badge: /api/ran/1906.00121.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
sshleifer/Graph-WaveNet extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
simonvino/graphwavenet_brain_connectivity community (classifier label)
classifier basis: plan_row
1 ran · 1 no recorded run
JiahuiSun/Exp-Graph-WaveNet reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
asym_adj Ran
ran, violated the contract we drafted
sshleifer/Graph-WaveNet/util.py
code served (permissive licence) · get_code("901bedf723a6f00d")
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 (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 adjacency matrix (4x4)
# This represents a directed graph with 4 nodes
adj_dense = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [0, 1, 0, 1],
    [1, 0, 0, 0]
], dtype=np.float32)

# Convert to sparse matrix format (coo_matrix is used in the function)
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 (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
calculate_normalized_laplacian Ran
ran; our contract draft was wrong, not the code
sshleifer/Graph-WaveNet/util.py
code served (permissive licence) · get_code("e7b2e6a60daa42ca")
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 csr_matrix. 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 numpy as np
import scipy.sparse as sp

# Create a small adjacency matrix for a graph
# Using a 5x5 matrix to represent a simple graph with 5 nodes
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)
adj = sp.csr_matrix(adj_dense)

ARGS = {
    'adj': adj
}
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 csr_matrix — a csr_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a csr_matrix 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_train_val_test Ran
ran; our contract draft was wrong, not the code
simonvino/graphwavenet_brain_connectivity/generate_samples.py
code served (permissive licence) · get_code("c6093e02db929cdb")
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 tuple. 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 numpy as np
import os
import tempfile
import shutil

# Create temporary directories for input and output
temp_base = tempfile.mkdtemp()
input_dir = os.path.join(temp_base, "input")
output_dir = os.path.join(temp_base, "output")
os.makedirs(output_dir, exist_ok=True)

# Setup parameters
NSess = 2
NSub = 2
NROIs = 5
input_horizon = 10
output_horizon = 10

# Create the directory structure and data files
# input_dir/session_{nSess}/input_filename{nSub}.txt
for nSess in range(1, NSess + 1):
    session_dir = os.path.join(input_dir, f"session_{nSess}")
    os.makedirs(session_dir, exist_ok=True)
    
    for nSub in range(1, NSub + 1):
        # Create synthetic fMRI timecourse data
        # Expected dimension: ROIs x Samples
        num_samples = 100
        num_rois = 8
        
        # Generate random timecourse data
        np.random.seed(nSess * 10 + nSub)
        timeseries = np.random.randn(num_rois, num_samples).astype('float32')
        
        # Save to file
        filename = os.path.join(session_dir, f"subject_{nSub}.txt")
        np.savetxt(filename, timeseries, delimiter=',')

ARGS = {
    "input_dir": input_dir,
    "input_filename": "subject_",
    "output_dir": output_dir,
    "NSess": NSess,
    "NSub": NSub,
    "input_horizon": input_horizon,
    "output_horizon": output_horizon,
    "scaling": "n",
    "save_data": True,
    "train_prop": 0.8,
    "test_prop": 0.1,
    "NROIs": NROIs,
    "perturbations": None
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
seq_gen Ran
ran; our contract draft was wrong, not the code
JiahuiSun/Exp-Graph-WaveNet/generate_training_data.py
code served (permissive licence) · get_code("3028268c1774ed96")
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 ndarray, ndim 4, dtype family float, shape (18, 12, 5, 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

# Set parameters
n_day = 2
n_route = 5
day_slot = 20
n_frame = 12
C_0 = 2
offset = 1

# Calculate total time steps needed in data_seq
# We need enough data to cover (n_day + offset) * day_slot + n_frame - 1
total_time_steps = (n_day + offset) * day_slot + n_frame

# Create data_seq with shape [total_time_steps, n_route, C_0]
data_seq = np.random.randn(total_time_steps, n_route, C_0)

ARGS = {
    'n_day': n_day,
    'data_seq': data_seq,
    'offset': offset,
    'n_frame': n_frame,
    'n_route': n_route,
    'day_slot': day_slot,
    'C_0': C_0
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 4, dtype family float, shape (18, 12, 5, 2) — shape (18, 12, 5, 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
sym_adj Ran
ran, violated the contract we drafted
sshleifer/Graph-WaveNet/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
generate_graph_seq2seq_io_data Not yet run
unverified (harvested, no recorded run)
JiahuiSun/Exp-Graph-WaveNet/generate_training_data.py
code served (permissive licence) · get_code("fc148af599e95656")
How it ran

no invocation recorded.

generate_graph_seq2seq_io_data Not yet run
unverified (harvested, no recorded run)
simonvino/graphwavenet_brain_connectivity/old_stuff/generate_training_data.py
code served (permissive licence) · get_code("1175f39f2d567546")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
asym_adj 6 other papers
6 later
2104.14917 (2021-04)
Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution
2202.08408 (2022-02)
Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
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
calculate_normalized_laplacian 5 other papers
1 dated earlier, 4 later
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
2308.10436 (2023-08)
Approximately Equivariant Graph Networks
2312.11198 (2023-12)
Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-time Dynamics
and 2 more not named here
sym_adj 4 other papers
4 later
2104.14917 (2021-04)
Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution
2202.08408 (2022-02)
Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
2403.02600 (2024-03)
TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
and 1 more not named here
generate_train_val_test 2 other papers
1 dated earlier, 1 later
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
2010.07143 (2020-10)
A Graph Neural Network Framework for Causal Inference in Brain Networks

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

Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.

For agents

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

get_harvested_code_for_paper("1906.00121")
get_code_for_paper("1906.00121")
have("1906.00121")

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

curl https://syntology.ai/api/ran/1906.00121.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.00121.svg)](https://syntology.ai/paper/1906.00121)

Connect an agent — have() is free.