SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.02152 · 2020

PaRoT: A Practical Framework for Robust Deep Neural Network Training

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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; 0 failures of our instrument; 3 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/2001.02152.json · badge: /api/ran/2001.02152.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
fiveai/parot canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
depends_on_any Ran
ran on a synthesized input
fiveai/parot/parot/utils/graph.py
code served (permissive licence) · get_code("f54fd0894a4cb336")
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 bool, 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 tensorflow as tf

# Create a simple computation graph with dependencies
with tf.Graph().as_default():
    # Create base tensors
    x1 = tf.constant([1.0, 2.0, 3.0, 4.0], name='x1')
    x2 = tf.constant([5.0, 6.0, 7.0, 8.0], name='x2')
    
    # Create dependent tensors
    y = tf.add(x1, x2, name='y')
    z = tf.multiply(y, 2.0, name='z')
    
    # Create another independent branch
    w = tf.constant([9.0, 10.0, 11.0, 12.0], name='w')
    
    ARGS = {
        'z': z,
        'xs': [x1, x2]
    }
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
gridify Ran
ran on a synthesized input
fiveai/parot/parot/utils/util.py
code served (permissive licence) · get_code("a3d36ccea8f2fb8a")
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 SymbolicTensor. 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 tensorflow as tf
import math

# Create a small test tensor with shape (H, W, C, CO)
# Using distinct dimensions: H=4, W=3, C=6, CO=2
H, W, C, CO = 4, 3, 6, 2
input_tensor = tf.random.normal((H, W, C, CO))

# Define ARGS dict with all parameters
ARGS = {
    "input": input_tensor,
    "pad": 2,
    "I": None,
    "J": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
isin Ran
ran on a synthesized input
fiveai/parot/parot/utils/graph.py
code served (permissive licence) · get_code("6e89c26e38e57ef1")
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 bool, 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)

# The function isin(z, xs) checks if z is identical (same object) to any object in xs
# It uses:
# - z: any object to check identity against
# - xs: an iterable of objects to compare against using 'is'

# Create some distinct objects
obj1 = torch.tensor([1, 2, 3, 4])
obj2 = torch.tensor([5, 6, 7, 8])
obj3 = torch.tensor([9, 10, 11, 12])

# z will be one of the objects in xs (so isin returns True)
z = obj1

# xs is a list containing the same object references
xs = [obj1, obj2, obj3]

ARGS = {
    "z": z,
    "xs": xs
}
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 bool, 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
depends_on Not yet run
unverified (harvested, no recorded run)
fiveai/parot/parot/utils/graph.py
code served (permissive licence) · get_code("826a29965f63b0c5")
How it ran

no invocation recorded.

linterp Not yet run
unverified (harvested, no recorded run)
fiveai/parot/parot/utils/util.py
code served (permissive licence) · get_code("f3e0e7df4af01b26")
How it ran

no invocation recorded.

to_log_heatmap Not yet run
unverified (harvested, no recorded run)
fiveai/parot/parot/utils/util.py
code served (permissive licence) · get_code("269295415fb81712")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Deep Neural Networks (DNNs) are finding important applications in safety-critical systems such as Autonomous Vehicles (AVs), where perceiving the environment correctly and robustly is necessary for safe operation. Raising unique challenges for assurance due to their black-box nature, DNNs pose a fundamental problem for regulatory acceptance of these types of systems. Robust training --- training to minimize excessive sensitivity to small changes in input --- has emerged as one promising technique to address this challenge. However, existing robust training tools are inconvenient to use or apply to existing codebases and models: they typically only support a small subset of model elements and require users to extensively rewrite the training code. In this paper we introduce a novel framework, PaRoT, developed on the popular TensorFlow platform, that greatly reduces the barrier to entry. Our framework enables robust training to be performed on arbitrary DNNs without any rewrites to the model. We demonstrate that our framework's performance is comparable to prior art, and exemplify its ease of use on off-the-shelf, trained models and its testing capabilities on a real-world industrial application: a traffic light detection network.

For agents

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

get_harvested_code_for_paper("2001.02152")
get_code_for_paper("2001.02152")
have("2001.02152")

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

curl https://syntology.ai/api/ran/2001.02152.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.02152.svg)](https://syntology.ai/paper/2001.02152)

Connect an agent — have() is free.