SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.07634 · 2020

SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detection

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 0 have no contract verdict; 3 failures of our instrument; 0 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/2012.07634.json · badge: /api/ran/2012.07634.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
sophos/sorel-20m canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
collect_dataframes Ran
ran; our contract draft was wrong, not the code
sophos/sorel-20m/plot.py
code served (permissive licence) · get_code("10193da1ef835668")
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 dict. 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 pandas as pd
import tempfile
import os

# Create temporary CSV files for testing
temp_dir = tempfile.mkdtemp()

# Create sample CSV files
csv_file_1 = os.path.join(temp_dir, "run_1.csv")
csv_file_2 = os.path.join(temp_dir, "run_2.csv")

df1 = pd.DataFrame({"col1": [1, 2, 3], "col2": [4, 5, 6]})
df2 = pd.DataFrame({"col1": [7, 8, 9], "col2": [10, 11, 12]})

df1.to_csv(csv_file_1, index=False)
df2.to_csv(csv_file_2, index=False)

# Define the argument dictionary
ARGS = {
    "run_id_to_filename_dictionary": {
        "run_1": csv_file_1,
        "run_2": csv_file_2
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
detach_and_copy_array Ran
ran, honoured the contract we drafted
sophos/sorel-20m/evaluate.py
code served (permissive licence) · get_code("9e266df9604ad5a4")
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 ndarray, ndim 1, dtype family float, shape (8,) 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 numpy as np
from copy import deepcopy

torch.manual_seed(0)

# Test case 1: torch.Tensor
tensor_arg = torch.randn(2, 4)

# Test case 2: numpy.ndarray
numpy_arg = np.random.randn(3, 5)

# The function takes a single parameter 'array'
# We'll test with a torch.Tensor as the primary case
ARGS = {
    'array': tensor_arg
}
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 ndarray, ndim 1, dtype family float, shape (8,) — shape (8,) 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_roc_curve Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sophos/sorel-20m/plot.py
code served (permissive licence) · get_code("29e5572fdd11dfde")
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 2, 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 pandas as pd
import numpy as np

# Create a small dataframe with the required columns for the 'malware' key
np.random.seed(0)

# Generate sample data
n_samples = 10
labels = np.random.randint(0, 2, n_samples)
predictions = np.random.rand(n_samples)

# Create dataframe with required columns
result_dataframe = pd.DataFrame({
    'label_malware': labels,
    'pred_malware': predictions
})

ARGS = {
    'result_dataframe': result_dataframe,
    'key': 'malware'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, pandas, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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
get_tprs_at_fpr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sophos/sorel-20m/plot.py
code served (permissive licence) · get_code("d17b01e37fe1ada2")
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 2, 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 pandas as pd
import numpy as np

# Create a small dataframe with the required columns
# The function expects 'label_{key}' and 'pred_{key}' columns
key = 'malware'

# Create synthetic binary labels and predictions
np.random.seed(0)
n_samples = 20
labels = np.random.randint(0, 2, n_samples)
predictions = np.random.rand(n_samples)  # Scores between 0 and 1

result_dataframe = pd.DataFrame({
    f'label_{key}': labels,
    f'pred_{key}': predictions
})

target_fprs = np.array([1e-5, 1e-4, 1e-3, 1e-2, 1e-1])

ARGS = {
    'result_dataframe': result_dataframe,
    'key': key,
    'target_fprs': target_fprs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, pandas, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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 2026-11-22.

Repositories linked to this paper

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

Abstract

In this paper we describe the SOREL-20M (Sophos/ReversingLabs-20 Million) dataset: a large-scale dataset consisting of nearly 20 million files with pre-extracted features and metadata, high-quality labels derived from multiple sources, information about vendor detections of the malware samples at the time of collection, and additional ``tags'' related to each malware sample to serve as additional targets. In addition to features and metadata, we also provide approximately 10 million ``disarmed'' malware samples -- samples with both the optional\_headers.subsystem and file\_header.machine flags set to zero -- that may be used for further exploration of features and detection strategies. We also provide Python code to interact with the data and features, as well as baseline neural network and gradient boosted decision tree models and their results, with full training and evaluation code, to serve as a starting point for further experimentation.

For agents

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

get_harvested_code_for_paper("2012.07634")
get_code_for_paper("2012.07634")
have("2012.07634")

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

curl https://syntology.ai/api/ran/2012.07634.json

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

[![Syntology run record](https://syntology.ai/api/ran/2012.07634.svg)](https://syntology.ai/paper/2012.07634)

Connect an agent — have() is free.