SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.07532 · 2019

Graph Neural Ordinary Differential Equations

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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, 0 violated it and 5 have no contract verdict; 2 failures of our instrument; 3 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/1911.07532.json · badge: /api/ran/1911.07532.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
caidao22/pnode canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
Zymrael/gde canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
Zymrael/gde/torchgde/utils.py
code served (permissive licence) · get_code("2b440dfe1b5fc91d")
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)

# y_hat: logits/predictions tensor, shape (batch_size, num_classes)
# The function calls torch.max(y_hat, 1)[1] to get predictions
y_hat = torch.randn(2, 4)

# y: ground truth labels tensor, shape (batch_size,)
# The function compares it with preds using ==
y = torch.tensor([0, 2])

ARGS = {
    "y_hat": y_hat,
    "y": y,
}
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
count_parameters Ran
ran, honoured the contract we drafted
caidao22/pnode/examples-pnode/train-Cifar10.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
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) 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 torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
fun Ran
ran on a synthesized input
caidao22/pnode/examples-pnode/ROBER.py
code served (permissive licence) · get_code("10161f75c29a803c")
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 1, dtype family float, shape (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

# This is a stiff ODE system (Robertson problem)
# The function takes a time parameter t and a state vector (3 elements)
# It returns the time derivatives as a numpy array

t = 0.0
state = np.array([1.0, 0.0, 0.0])

ARGS = {
    "t": t,
    "state": state
}
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 1, dtype family float, shape (3,) — shape (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
get_logger Ran
ran; our contract draft was wrong, not the code
caidao22/pnode/examples-pnode/train-Cifar10.py
code served (permissive licence) · get_code("416b44e8cb9fc048")
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) and returned RootLogger. 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 logging
import tempfile
import os

# Create temporary files for the function to read
temp_dir = tempfile.mkdtemp()
logpath = os.path.join(temp_dir, "test.log")
filepath = os.path.join(temp_dir, "main_script.py")
package_file_1 = os.path.join(temp_dir, "package_1.py")
package_file_2 = os.path.join(temp_dir, "package_2.py")

# Write content to the files
with open(filepath, 'w') as f:
    f.write("# Main script content\nprint('hello')\n")

with open(package_file_1, 'w') as f:
    f.write("# Package 1 content\ndef func1(): pass\n")

with open(package_file_2, 'w') as f:
    f.write("# Package 2 content\ndef func2(): pass\n")

ARGS = {
    'logpath': logpath,
    'filepath': filepath,
    'package_files': [package_file_1, package_file_2],
    'displaying': True,
    'saving': True,
    'debug': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger 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
inplace_spectral_norm Ran
ran; our contract draft was wrong, not the code
caidao22/pnode/ffjord-pnode/lib/spectral_norm.py
code served (permissive licence) · get_code("4d3d2e407f692a54")
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 Linear. 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 linear module to apply spectral norm to
module = nn.Linear(in_features=4, out_features=3)

# Define arguments for inplace_spectral_norm function
ARGS = {
    'module': module,
    'name': 'weight',
    'dim': None,
    'eps': 1e-12
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
jac Ran
ran on a synthesized input
caidao22/pnode/examples-pnode/ROBER.py
code served (permissive licence) · get_code("d37932322607e0f6")
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 (3, 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

# The function jac takes two parameters:
# - t: a time parameter (scalar or similar)
# - state: a numpy array of length 3 (used as state[0], state[1], state[2])

# The function uses state as a 1D array with 3 elements for indexing
# It returns a 3x3 numpy array (Jacobian matrix)

t = 0.0  # time parameter, can be any scalar

# state must be a numpy array with at least 3 elements
# The function accesses state[0], state[1], state[2]
state = np.array([1.0, 2.0, 3.0])

ARGS = {
    "t": t,
    "state": state
}
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 (3, 3) — shape (3, 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
lr_schedule Ran
ran on a synthesized input
caidao22/pnode/examples-pnode/models/sqnxt_PETSc.py
code served (permissive licence) · get_code("2003406c1040031b")
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 float, 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 math

def lr_schedule(lr, epoch):
    optim_factor = 0
    if epoch > 250:
        optim_factor = 2
    elif epoch > 150:
        optim_factor = 1
    return lr / math.pow(10, optim_factor)

ARGS = {
    "lr": 0.1,
    "epoch": 100
}
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 float, 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
set_timestamps Ran
ran on a synthesized input
Zymrael/gde/torchgde/data_utils.py
code served (permissive licence) · get_code("ac5619d34e29a26d")
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 list. 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

torch.manual_seed(0)

# The function expects a list of timestamp objects where each element has a .unique() method
# torch.Tensor has a .unique() method, so we'll use small tensors

timestamps = [
    torch.tensor([1, 2, 3, 2, 1]),
    torch.tensor([5, 6, 5, 7]),
    torch.tensor([10, 11, 10])
]

ARGS = {
    "timestamps": timestamps
}
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 list — a list 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
SqNxt_23_1x Not yet run
unverified (harvested, no recorded run)
caidao22/pnode/examples-pnode/models/sqnxt_PETSc.py
code served (permissive licence) · get_code("ed4748e6a32d513c")
How it ran

no invocation recorded.

get_indices Not yet run
unverified (harvested, no recorded run)
Zymrael/gde/torchgde/data_utils.py
code served (permissive licence) · get_code("33ca98e9ddeb9a27")
How it ran

no invocation recorded.

remove_spectral_norm Not yet run
unverified (harvested, no recorded run)
caidao22/pnode/ffjord-pnode/lib/spectral_norm.py
code served (permissive licence) · get_code("d69f23bce39cf751")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 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
count_parameters 180 other papers
14 dated earlier, 1 the same month, 165 later · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
remove_spectral_norm 6 other papers
6 later
2003.00378 (2020-03)
Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
2007.10247 (2020-07)
Learning Joint Spatial-Temporal Transformations for Video Inpainting
2106.08748 (2021-06)
Input Invex Neural Network
and 3 more not named here
get_logger 5 other papers
1 dated earlier, 4 later
1906.02735 (2019-06)
Residual Flows for Invertible Generative Modeling
2002.02798 (2020-02)
How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization
2110.00527 (2021-10)
Consistent Explanations by Contrastive Learning
and 2 more not named here
SqNxt_23_1x 1 other paper
1 dated earlier
1902.10298 (2019-02)
ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
inplace_spectral_norm 1 other paper
1 later
2407.06250 (2024-07)
FairDiff: Fair Segmentation with Point-Image Diffusion
lr_schedule 1 other paper
1 dated earlier
1902.10298 (2019-02)
ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs

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

We introduce the framework of continuous--depth graph neural networks (GNNs). Graph neural ordinary differential equations (GDEs) are formalized as the counterpart to GNNs where the input-output relationship is determined by a continuum of GNN layers, blending discrete topological structures and differential equations. The proposed framework is shown to be compatible with various static and autoregressive GNN models. Results prove general effectiveness of GDEs: in static settings they offer computational advantages by incorporating numerical methods in their forward pass; in dynamic settings, on the other hand, they are shown to improve performance by exploiting the geometry of the underlying dynamics.

For agents

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

get_harvested_code_for_paper("1911.07532")
get_code_for_paper("1911.07532")
have("1911.07532")

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

curl https://syntology.ai/api/ran/1911.07532.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.07532.svg)](https://syntology.ai/paper/1911.07532)

Connect an agent — have() is free.