SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.08415 · 2019

GMAN: A Graph Multi-Attention Network for Traffic Prediction

arXiv · PDF · Open in the Atlas

Code that ran

4 of 10 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 3 have no contract verdict; 1 failure of our instrument; 6 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/1911.08415.json · badge: /api/ran/1911.08415.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
zhengchuanpan/GMAN canonical (classifier label)
classifier basis: census
4 ran · 6 no recorded run
FunctionStatusWhere it lives
alias_draw Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhengchuanpan/GMAN/METR/node2vec/node2vec.py
code served (permissive licence) · get_code("c71ec4f39a2bea7a")
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 int, ndim 0, dtype family int, shape () 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 random seed for reproducibility
np.random.seed(0)

# alias_draw expects:
# J: a sequence/list of indices (used as return values)
# q: an array-like of probabilities (compared with random values)

# Both J and q must have the same length K
# The function uses:
# - len(J) to get K
# - np.floor() and np.random.rand() for sampling
# - indexing into J and q
# - comparison with q[kk]

K = 5
J = [0, 2, 3, 1, 4]  # List of K indices to alias to
q = np.array([0.9, 0.3, 0.7, 0.5, 0.8])  # Array of K probabilities in [0, 1]

ARGS = {
    "J": J,
    "q": q
}
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 int, ndim 0, dtype family int, shape () — shape () 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
dropout Ran
ran on a synthesized input
zhengchuanpan/GMAN/METR/tf_utils.py
code served (permissive licence) · get_code("e4716e5fdd0a9483")
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 EagerTensor, ndim 2, dtype family float, shape (2, 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 tensorflow as tf
import numpy as np

# Create a small tensor (batch=2, dim=4)
x = tf.constant(np.random.randn(2, 4).astype(np.float32))

# Dropout rate (probability of dropping a unit)
drop = 0.5

# Boolean tensor indicating training mode
is_training = tf.constant(True)

ARGS = {
    "x": x,
    "drop": drop,
    "is_training": is_training
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
metric Ran
ran on a synthesized input
zhengchuanpan/GMAN/METR/utils.py
code served (permissive licence) · get_code("1ba47a23adf07065")
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 tuple, ndim 1, 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

# Create small numpy arrays for pred and label
np.random.seed(0)

# Create prediction array with shape (5,)
pred = np.random.randn(5).astype(np.float32)

# Create label array with shape (5,) containing mostly non-zero values
# but some zeros to test the masking logic
label = np.array([1.5, 2.3, 0.0, 4.1, 3.2], dtype=np.float32)

ARGS = {
    'pred': pred,
    'label': label
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
seq2instance Ran
ran on a synthesized input
zhengchuanpan/GMAN/METR/utils.py
code served (permissive licence) · get_code("3fc58cdee460bc5d")
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 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

# The function seq2instance takes:
# - data: a 2D numpy array with shape (num_step, dims)
# - P: an integer representing the number of past steps
# - Q: an integer representing the number of future steps

# Create sample data
num_step = 10
dims = 4
data = np.random.randn(num_step, dims).astype(np.float32)

# Set P and Q such that num_sample = num_step - P - Q + 1 > 0
P = 3
Q = 2

ARGS = {
    "data": data,
    "P": P,
    "Q": Q
}
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 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
alias_setup Not yet run
unverified (harvested, no recorded run)
zhengchuanpan/GMAN/METR/node2vec/node2vec.py
code served (permissive licence) · get_code("0ddb0dd1cf3b67dd")
How it ran

no invocation recorded.

batch_norm Not yet run
unverified (harvested, no recorded run)
zhengchuanpan/GMAN/METR/tf_utils.py
code served (permissive licence) · get_code("8e2329b6f957b2ce")
How it ran

no invocation recorded.

conv2d Not yet run
unverified (harvested, no recorded run)
zhengchuanpan/GMAN/METR/tf_utils.py
code served (permissive licence) · get_code("6122f2f19a4027d8")
How it ran

no invocation recorded.

loadData Not yet run
unverified (harvested, no recorded run)
zhengchuanpan/GMAN/METR/utils.py
code served (permissive licence) · get_code("78c234f574a9d6a2")
How it ran

no invocation recorded.

placeholder Not yet run
unverified (harvested, no recorded run)
zhengchuanpan/GMAN/METR/model.py
code served (permissive licence) · get_code("87a81a456578efcc")
How it ran

no invocation recorded.

placeholder Not yet run
unverified (harvested, no recorded run)
zhengchuanpan/GMAN/PeMS/model.py
code served (permissive licence) · get_code("c11afb5b81b2e8bd")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 5 later) and 5 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
alias_setup 5 other papers
1 dated earlier, 1 the same month, 3 later
1607.00653 (2016-07)
node2vec: Scalable Feature Learning for Networks
1911.02613 (2019-11)
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
2002.04784 (2020-02)
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
and 2 more not named here
alias_draw 4 other papers
1 dated earlier, 3 later
1607.00653 (2016-07)
node2vec: Scalable Feature Learning for Networks
2002.04784 (2020-02)
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
2002.05257 (2020-02)
Shortest path distance approximation using deep learning techniques
and 1 more not named here
loadData 1 other paper
1 later
2412.09972 (2024-12)
Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective
metric 1 other paper
1 later
2412.09972 (2024-12)
Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective
seq2instance 1 other paper
1 later
2412.09972 (2024-12)
Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective

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

Long-term traffic prediction is highly challenging due to the complexity of traffic systems and the constantly changing nature of many impacting factors. In this paper, we focus on the spatio-temporal factors, and propose a graph multi-attention network (GMAN) to predict traffic conditions for time steps ahead at different locations on a road network graph. GMAN adapts an encoder-decoder architecture, where both the encoder and the decoder consist of multiple spatio-temporal attention blocks to model the impact of the spatio-temporal factors on traffic conditions. The encoder encodes the input traffic features and the decoder predicts the output sequence. Between the encoder and the decoder, a transform attention layer is applied to convert the encoded traffic features to generate the sequence representations of future time steps as the input of the decoder. The transform attention mechanism models the direct relationships between historical and future time steps that helps to alleviate the error propagation problem among prediction time steps. Experimental results on two real-world traffic prediction tasks (i.e., traffic volume prediction and traffic speed prediction) demonstrate the superiority of GMAN. In particular, in the 1 hour ahead prediction, GMAN outperforms state-of-the-art methods by up to 4% improvement in MAE measure. The source code is available at https://github.com/zhengchuanpan/GMAN.

For agents

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

get_harvested_code_for_paper("1911.08415")
get_code_for_paper("1911.08415")
have("1911.08415")

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

curl https://syntology.ai/api/ran/1911.08415.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.08415.svg)](https://syntology.ai/paper/1911.08415)

Connect an agent — have() is free.