SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.10909 · 2023

Graph Neural Rough Differential Equations for Traffic Forecasting

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 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 7 have no contract verdict; 6 failures of our instrument; 4 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/2303.10909.json · badge: /api/ran/2303.10909.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
jeongwhanchoi/STG-NCDE canonical (classifier label)
classifier basis not recorded on the link
13 ran · 4 no recorded run
FunctionStatusWhere it lives
Add_Window_Horizon Ran
ran on a synthesized input
jeongwhanchoi/STG-NCDE/lib/add_window.py
code served (permissive licence) · get_code("be27678f7901f1dc")
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

# Create sample data with shape [B, ...] where B is batch dimension
# Using shape [10, 4] - 10 timesteps, 4 features
data = np.random.randn(10, 4).astype(np.float32)

ARGS = {
    "data": data,
    "window": 3,
    "horizon": 1,
    "single": False
}
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
MAE_torch Ran
ran on a synthesized input
jeongwhanchoi/STG-NCDE/lib/metrics.py
code served (permissive licence) · get_code("2d4043d05780769f")
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 Tensor, ndim 0, dtype family float, 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 torch

torch.manual_seed(0)

# Create small tensors for pred and true
# MAE_torch expects tensors that support:
# - torch.gt() for comparison
# - torch.masked_select() for masking
# - torch.abs() for absolute value
# - torch.mean() for averaging

pred = torch.randn(2, 4)
true = torch.randn(2, 4)

# mask_value is optional, can be None or a numeric value
mask_value = None

ARGS = {
    "pred": pred,
    "true": true,
    "mask_value": mask_value
}
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 Tensor, ndim 0, dtype family float, 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
MSE_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jeongwhanchoi/STG-NCDE/lib/metrics.py
code served (permissive licence) · get_code("bb1134c39c66c490")
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 Tensor, ndim 0, dtype family float, 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 torch

torch.manual_seed(0)

# Create small tensors for pred and true
pred = torch.randn(2, 4)
true = torch.randn(2, 4)

# mask_value is optional, can be None or a numeric value
mask_value = None

ARGS = {
    "pred": pred,
    "true": true,
    "mask_value": mask_value,
}
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 Tensor, ndim 0, dtype family float, 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
RMSE_torch Ran
ran on a synthesized input
jeongwhanchoi/STG-NCDE/lib/metrics.py
code served (permissive licence) · get_code("dadeb499af3778ba")
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 Tensor, ndim 0, dtype family float, 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 torch

torch.manual_seed(0)

# Create small prediction and true value tensors
pred = torch.randn(2, 4)
true = torch.randn(2, 4)

# mask_value is optional; set to None for basic case
mask_value = None

ARGS = {
    "pred": pred,
    "true": true,
    "mask_value": mask_value,
}
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 Tensor, ndim 0, dtype family float, 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
cdeint Ran
ran; our contract draft was wrong, not the code
jeongwhanchoi/STG-NCDE/controldiffeq/cdeint_module.py
code served (permissive licence) · get_code("a4dafc84cbeb2bb5")
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 Tensor, ndim 3, dtype family float, shape (5, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Define a simple func module that takes z and returns vector field
class SimpleFunc(nn.Module):
    def __init__(self, hidden_channels, input_channels):
        super(SimpleFunc, self).__init__()
        self.hidden_channels = hidden_channels
        self.input_channels = input_channels
        # Simple linear layer to map hidden -> (hidden x input)
        self.linear = nn.Linear(hidden_channels, hidden_channels * input_channels)
    
    def forward(self, z):
        # z shape: (..., hidden_channels)
        # Should return (..., hidden_channels, input_channels)
        batch_shape = z.shape[:-1]
        out = self.linear(z)
        # Reshape to (..., hidden_channels, input_channels)
        return out.reshape(*batch_shape, self.hidden_channels, self.input_channels)

# Define dX_dt - a callable that returns control gradients
class ControlGradient(nn.Module):
    def __init__(self, input_channels, batch_shape):
        super(ControlGradient, self).__init__()
        self.input_channels = input_channels
        self.batch_shape = batch_shape
    
    def forward(self, t):
        # t is a scalar tensor
        # Should return tensor of shape (..., input_channels)
        # where ... matches z0's batch dimensions
        return torch.ones(*self.batch_shape, self.input_channels)

# Set up dimensions
batch_size = 2
hidden_channels = 4
input_channels = 3

# Create initial state z0
z0 = torch.randn(batch_size, hidden_channels)

# Create the func module
func = SimpleFunc(hidden_channels, input_channels)

# Create the control gradient callable
batch_shape = (batch_size,)
dX_dt = ControlGradient(input_channels, batch_shape)

# Create time points to integrate over
t = torch.linspace(0, 1, 5)

# Build ARGS dictionary
ARGS = {
    'dX_dt': dX_dt,
    'z0': z0,
    'func': func,
    't': t,
    'adjoint': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchdiffeq — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (5, 2, 4) — shape (5, 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
get_logger Ran
ran; our contract draft was wrong, not the code
jeongwhanchoi/STG-NCDE/lib/logger.py
code served (permissive licence) · get_code("996764623af1eab9")
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 Logger. 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 os
import logging
import tempfile

# Create a temporary directory for the logger to use
temp_dir = tempfile.mkdtemp()

ARGS = {
    'root': temp_dir,
    'name': 'test_logger',
    'debug': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
init_lr_scheduler Ran
ran; our contract draft was wrong, not the code
jeongwhanchoi/STG-NCDE/lib/TrainInits.py
code served (permissive licence) · get_code("e246ed362e86604f")
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 MultiStepLR. 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)

# Create a simple optimizer
model = nn.Linear(4, 3)
optim = torch.optim.SGD(model.parameters(), lr=0.1)

# Create a config object with the required attributes
class OptConfig:
    def __init__(self):
        self.lr_decay_steps = [10, 20, 30]
        self.lr_scheduler_rate = 0.1

opt = OptConfig()

ARGS = {
    "optim": optim,
    "opt": opt
}
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 MultiStepLR — a MultiStepLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiStepLR 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
init_optim Ran
ran; our contract draft was wrong, not the code
jeongwhanchoi/STG-NCDE/lib/TrainInits.py
code served (permissive licence) · get_code("ffe6b5e6a255061f")
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 Adam. 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

class OptConfig:
    def __init__(self):
        self.lr_init = 0.001

model = SimpleModel()
opt = OptConfig()

ARGS = {
    'model': model,
    'opt': opt
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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
load_st_dataset Ran
ran on a synthesized input
jeongwhanchoi/STG-NCDE/lib/load_dataset.py
code served (permissive licence) · get_code("691381e2874098e4")
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 ndarray, ndim 3, dtype family float, shape (100, 50, 1) 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 os
import tempfile

# Create a temporary directory and mock NPZ files for testing
temp_dir = tempfile.mkdtemp()

# Create mock PEMS04 data
pems04_path = os.path.join(temp_dir, 'PEMS04.npz')
mock_data_4d = np.random.rand(100, 50, 3)  # time x nodes x features
np.savez(pems04_path, data=mock_data_4d)

# Monkey-patch os.path.join to redirect data paths to our temp directory
_original_join = os.path.join
def patched_join(path, *paths):
    result = _original_join(path, *paths)
    if 'PEMS04' in result:
        return pems04_path
    return result

os.path.join = patched_join

# Test with one of the valid dataset options
ARGS = {
    'dataset': 'PEMSD4'
}
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 ndarray, ndim 3, dtype family float, shape (100, 50, 1) — shape (100, 50, 1) 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
minmax_by_column Ran
ran on a synthesized input
jeongwhanchoi/STG-NCDE/lib/normalization.py
code served (permissive licence) · get_code("0ef827883d7bf3e6")
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 ndarray, ndim 2, dtype family float, shape (4, 3) 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

# Create a small 2D numpy array with distinct dimensions (4 rows, 3 columns)
# to test the minmax normalization by column
data = np.array([
    [1.0, 10.0, 100.0],
    [2.0, 20.0, 200.0],
    [3.0, 30.0, 300.0],
    [4.0, 40.0, 400.0]
], dtype=np.float32)

ARGS = {
    "data": data
}
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 ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 3) 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
one_hot_by_column Ran
ran on a synthesized input
jeongwhanchoi/STG-NCDE/lib/normalization.py
code served (permissive licence) · get_code("132385707ec527a2")
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 ndarray, ndim 2, dtype family float, shape (2, 9) 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

# Construct a small 2D numpy array with integer values for one-hot encoding
# The function expects a 2D array where each column will be one-hot encoded
# Using shape (2, 4) - 2 rows, 4 columns with distinct values
data = np.array([
    [0, 1, 2, 0],
    [1, 2, 1, 2]
], dtype=np.int64)

ARGS = {
    "data": data
}
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 ndarray, ndim 2, dtype family float, shape (2, 9) — shape (2, 9) 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
split_data_by_days Ran
ran on a synthesized input
jeongwhanchoi/STG-NCDE/lib/dataloader.py
code served (permissive licence) · get_code("8266f31f7ee7c353")
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 torch
import numpy as np

torch.manual_seed(0)

# Construct a small time-series data tensor
# Shape: [B, T] where B is batch size and T is time steps
# We need enough time steps to cover test_days + val_days + some training data
# With interval=60 (hourly), T = 24 time steps per day
# Let's create data for 10 days: 10 * 24 = 240 time steps
B = 2  # batch size
T = 240  # 10 days worth of hourly data (24 * 10)
data = torch.randn(T, 4)  # [T, feature_dim] - time series data

# Parameters for splitting
val_days = 2
test_days = 1
interval = 60

ARGS = {
    "data": data,
    "val_days": val_days,
    "test_days": test_days,
    "interval": interval
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
split_data_by_ratio Ran
ran; our contract draft was wrong, not the code
jeongwhanchoi/STG-NCDE/lib/dataloader.py
code served (permissive licence) · get_code("f06b9dde37d1edca")
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 torch
import numpy as np

torch.manual_seed(0)

# The function expects:
# - data: an array-like object with a .shape[0] attribute and supports indexing/slicing
# - val_ratio: a float between 0 and 1
# - test_ratio: a float between 0 and 1

# Create a small numpy array as the data
data = np.random.randn(10, 4)

# Define validation and test ratios
val_ratio = 0.2
test_ratio = 0.1

ARGS = {
    "data": data,
    "val_ratio": val_ratio,
    "test_ratio": test_ratio,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
cdeint_gde Not yet run
unverified (harvested, no recorded run)
jeongwhanchoi/STG-NCDE/controldiffeq/cdeint_module.py
code served (permissive licence) · get_code("d11447048d8aee41")
How it ran

no invocation recorded.

cdeint_gde_dev Not yet run
unverified (harvested, no recorded run)
jeongwhanchoi/STG-NCDE/controldiffeq/cdeint_module.py
code served (permissive licence) · get_code("f79327f4cedd197d")
How it ran

no invocation recorded.

init_device Not yet run
unverified (harvested, no recorded run)
jeongwhanchoi/STG-NCDE/lib/TrainInits.py
code served (permissive licence) · get_code("d7187fc207b2d503")
How it ran

no invocation recorded.

make_model Not yet run
unverified (harvested, no recorded run)
jeongwhanchoi/STG-NCDE/model/Make_model.py
code served (permissive licence) · get_code("7747ed35840050f5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 12 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 7 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
MSE_torch 2 other papers
1 dated earlier, 1 later
2203.15737 (2022-03)
Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version
2405.17898 (2024-05)
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
cdeint 2 other papers
1 dated earlier, 1 later
2005.08926 (2020-05)
Neural Controlled Differential Equations for Irregular Time Series
2402.14989 (2024-02)
Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
split_data_by_ratio 2 other papers
1 dated earlier, 1 later
2208.04360 (2022-08)
SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022
2405.17898 (2024-05)
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
Add_Window_Horizon 1 other paper
1 dated earlier
2203.15737 (2022-03)
Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version
MAE_torch 1 other paper
1 dated earlier
2203.15737 (2022-03)
Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version
RMSE_torch 1 other paper
1 dated earlier
2203.15737 (2022-03)
Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version
get_logger 1 other paper
1 later
2405.17898 (2024-05)
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
init_device 1 other paper
1 later
2405.17898 (2024-05)
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
init_lr_scheduler 1 other paper
1 later
2405.17898 (2024-05)
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
init_optim 1 other paper
1 later
2405.17898 (2024-05)
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
minmax_by_column 1 other paper
1 dated earlier
2203.15737 (2022-03)
Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version
one_hot_by_column 1 other paper
1 dated earlier
2203.15737 (2022-03)
Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version

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

Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present the method of spatio-temporal graph neural rough differential equation (STG-NRDE). Neural rough differential equations (NRDEs) are a breakthrough concept for processing time-series data. Their main concept is to use the log-signature transform to convert a time-series sample into a relatively shorter series of feature vectors. We extend the concept and design two NRDEs: one for the temporal processing and the other for the spatial processing. After that, we combine them into a single framework. We conduct experiments with 6 benchmark datasets and 27 baselines. STG-NRDE shows the best accuracy in all cases, outperforming all those 27 baselines by non-trivial margins.

For agents

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

get_harvested_code_for_paper("2303.10909")
get_code_for_paper("2303.10909")
have("2303.10909")

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

curl https://syntology.ai/api/ran/2303.10909.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.10909.svg)](https://syntology.ai/paper/2303.10909)

Connect an agent — have() is free.