SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.05086 · 2020

Boundary thickness and robustness in learning models

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; 0 honoured the contract we drafted, 1 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/2007.05086.json · badge: /api/ran/2007.05086.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
nsfzyzz/boundary_thickness canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_thickness Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nsfzyzz/boundary_thickness/measure_thickness.py
code served (permissive licence) · get_code("6b1d369b876a5225")
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 list, 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 takes input and outputs logits
class SimpleModel(nn.Module):
    def __init__(self, num_classes=5):
        super(SimpleModel, self).__init__()
        self.fc = nn.Linear(4, num_classes)
    
    def forward(self, x):
        return self.fc(x)

# Create a simple PGD attack class
class SimplePGDAttack:
    def __call__(self, images, labels):
        # Return perturbed images (just add small noise for testing)
        return images + torch.randn_like(images) * 0.1

# Create a simple data loader (list of batches)
train_loader = [
    (torch.randn(2, 4), torch.randint(0, 5, (2,))),
    (torch.randn(2, 4), torch.randint(0, 5, (2,))),
]

# Create model
model = SimpleModel(num_classes=5)

# Create PGD attack
pgd_attack = SimplePGDAttack()

# Create args namespace
class Args:
    def __init__(self):
        self.num_measurements = 2
        self.num_points = 5
        self.class_pair = False
        self.alpha = 0.2
        self.beta = 0.8

args = Args()

ARGS = {
    'train_loader': train_loader,
    'model': model,
    'PGD_attack': pgd_attack,
    'num_classes': 5,
    'args': args
}
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 list, ndim 1, dtype family float — a list 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
check_result Ran
ran, violated the contract we drafted
nsfzyzz/boundary_thickness/Reproduce_thickness_measurement_experiment.py
code served (permissive licence) · get_code("ae0d40b7ea4676e3")
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 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 os
import tempfile

# Create temporary files to test the function
temp_dir = tempfile.mkdtemp()
test_file_1 = os.path.join(temp_dir, "result_1.txt")
test_file_2 = os.path.join(temp_dir, "result_2.txt")

# Create the files so they exist
with open(test_file_1, 'w') as f:
    f.write("test")
with open(test_file_2, 'w') as f:
    f.write("test")

ARGS = {
    "result_names": [test_file_1, test_file_2]
}
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 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
return_command Ran
ran; our contract draft was wrong, not the code
nsfzyzz/boundary_thickness/Reproduce_thickness_measurement_experiment.py
code served (permissive licence) · get_code("60577d977542fee8")
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 str. 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)

# Analyzing the function:
# - FILE_NAME: string, used in format() as {0}.py
# - LOG_NAME: string, used in format() as {4}
# - PREFIX_NAME: string, used in format() as {2}
# - IND: used in format() as {1}, {5} - appears to be an integer or string identifier
# - ADV_PARAMS: string (optional), used in format() as {3}

ARGS = {
    'FILE_NAME': 'train_model',
    'LOG_NAME': 'thickness_experiment',
    'PREFIX_NAME': 'model_v1',
    'IND': 42,
    'ADV_PARAMS': '--learning-rate 0.001 --batch-size 32'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
return_results Ran
ran; our contract draft was wrong, not the code
nsfzyzz/boundary_thickness/Reproduce_thickness_measurement_experiment.py
code served (permissive licence) · get_code("6f43cced85743e21")
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 list, 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 os

torch.manual_seed(0)

RESULT_DIR = './results/thickness_model_zoo/'
PREFIX_NAME = 'model_results'
IND = 0

ARGS = {
    'RESULT_DIR': RESULT_DIR,
    'PREFIX_NAME': PREFIX_NAME,
    'IND': IND
}
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 list, ndim 1, dtype family float — a list 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

Robustness of machine learning models to various adversarial and non-adversarial corruptions continues to be of interest. In this paper, we introduce the notion of the boundary thickness of a classifier, and we describe its connection with and usefulness for model robustness. Thick decision boundaries lead to improved performance, while thin decision boundaries lead to overfitting (e.g., measured by the robust generalization gap between training and testing) and lower robustness. We show that a thicker boundary helps improve robustness against adversarial examples (e.g., improving the robust test accuracy of adversarial training) as well as so-called out-of-distribution (OOD) transforms, and we show that many commonly-used regularization and data augmentation procedures can increase boundary thickness. On the theoretical side, we establish that maximizing boundary thickness during training is akin to the so-called mixup training. Using these observations, we show that noise-augmentation on mixup training further increases boundary thickness, thereby combating vulnerability to various forms of adversarial attacks and OOD transforms. We can also show that the performance improvement in several lines of recent work happens in conjunction with a thicker boundary.

For agents

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

get_harvested_code_for_paper("2007.05086")
get_code_for_paper("2007.05086")
have("2007.05086")

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

curl https://syntology.ai/api/ran/2007.05086.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.05086.svg)](https://syntology.ai/paper/2007.05086)

Connect an agent — have() is free.