SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.03496 · 2019

Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks

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, 0 violated it and 4 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-21; 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/1909.03496.json · badge: /api/ran/1909.03496.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
saikat107/Devign community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
epicosy/devign reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
evaluate_loss Ran
ran on a synthesized input
saikat107/Devign/trainer.py
code served (permissive licence) · get_code("0422695bfb48e57f")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Define a minimal model that works with the function's usage
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, graph, cuda=False):
        # The function passes a graph and cuda flag
        # We'll just return logits for classification
        return self.linear(graph)

# Define a minimal loss function
loss_fn = nn.CrossEntropyLoss()

# Define a data iterator that yields (graph, targets) tuples
class DataIterator:
    def __init__(self):
        self.call_count = 0
    
    def __call__(self):
        # Return a small graph tensor and targets
        # graph: (batch_size=2, features=4)
        # targets: (batch_size=2,) with class indices 0-2
        graph = torch.randn(2, 4)
        targets = torch.randint(0, 3, (2,))
        return graph, targets

data_iterator = DataIterator()

# Create the model
model = MinimalModel()

# Define ARGS
ARGS = {
    'model': model,
    'loss_function': loss_fn,
    'num_batches': 2,
    'data_iter': data_iterator,
    'cuda': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — 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
evaluate_metrics Ran
ran on a synthesized input
saikat107/Devign/trainer.py
code served (permissive licence) · get_code("7930b76c6c087f9f")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Create a simple model that accepts a graph and cuda parameter
class SimpleGraphModel(nn.Module):
    def __init__(self, num_classes=3):
        super().__init__()
        self.linear = nn.Linear(4, num_classes)
    
    def forward(self, graph, cuda=False):
        # graph is a dummy tensor, just process it
        return self.linear(graph)

# Create loss function
loss_function = nn.CrossEntropyLoss()

# Create model
model = SimpleGraphModel(num_classes=3)

# Create a data iterator function that yields batches
batch_count = 0
def data_iter():
    global batch_count
    batch_count += 1
    # Return a graph tensor (2, 4) and targets tensor (2,) with class indices
    graph = torch.randn(2, 4)
    targets = torch.tensor([0, 1], dtype=torch.long)
    return graph, targets

# Number of batches to evaluate
num_batches = 2

ARGS = {
    "model": model,
    "loss_function": loss_function,
    "num_batches": num_batches,
    "data_iter": data_iter
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — 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
graph_indexing Ran
ran; our contract draft was wrong, not the code
epicosy/devign/src/prepare/cpg_generator.py
code served (permissive licence) · get_code("a3a01919b1db43eb")
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 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 torch
import numpy as np

# The function expects a graph dict with a 'file' key
# The 'file' value should be a path ending in .c with a numeric identifier
# Example: "/path/to/123.c" -> idx = 123

graph = {
    'file': '/path/to/42.c',
    'functions': [],
    'other_data': 'some_value'
}

ARGS = {
    'graph': graph
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 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
initialize_batch Ran
ran on a synthesized input
saikat107/Devign/utils.py
code served (permissive licence) · get_code("e27b3bbdae6eca62")
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 numpy as np

# Create a simple list of entries
entries = ['entry_0', 'entry_1', 'entry_2', 'entry_3', 'entry_4', 'entry_5']

# Define batch size
batch_size = 2

# Define shuffle parameter
shuffle = False

# Construct the ARGS dictionary
ARGS = {
    'entries': entries,
    'batch_size': batch_size,
    'shuffle': shuffle
}
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 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
tally_param Ran
ran on a synthesized input
saikat107/Devign/utils.py
code served (permissive licence) · get_code("5427b39c21c3a6b1")
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 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, 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 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
funcs_to_graphs Not yet run
unverified (harvested, no recorded run)
epicosy/devign/src/prepare/cpg_generator.py
code served (permissive licence) · get_code("d51f0d19c0d96758")
How it ran

no invocation recorded.

joern_parse Not yet run
unverified (harvested, no recorded run)
epicosy/devign/src/prepare/cpg_generator.py
code served (permissive licence) · get_code("b0ca691a6d4e7496")
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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.

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Vulnerability identification is crucial to protect the software systems from attacks for cyber security. It is especially important to localize the vulnerable functions among the source code to facilitate the fix. However, it is a challenging and tedious process, and also requires specialized security expertise. Inspired by the work on manually-defined patterns of vulnerabilities from various code representation graphs and the recent advance on graph neural networks, we propose Devign, a general graph neural network based model for graph-level classification through learning on a rich set of code semantic representations. It includes a novel Conv module to efficiently extract useful features in the learned rich node representations for graph-level classification. The model is trained over manually labeled datasets built on 4 diversified large-scale open-source C projects that incorporate high complexity and variety of real source code instead of synthesis code used in previous works. The results of the extensive evaluation on the datasets demonstrate that Devign outperforms the state of the arts significantly with an average of 10.51% higher accuracy and 8.68\% F1 score, increases averagely 4.66% accuracy and 6.37% F1 by the Conv module.

For agents

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

get_harvested_code_for_paper("1909.03496")
get_code_for_paper("1909.03496")
have("1909.03496")

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

curl https://syntology.ai/api/ran/1909.03496.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.03496.svg)](https://syntology.ai/paper/1909.03496)

Connect an agent — have() is free.