SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.06643 · 2020

Smoothed Geometry for Robust Attribution

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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 1 has no contract verdict; 1 failure of our instrument; 2 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/2006.06643.json · badge: /api/ran/2006.06643.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
zifanw/smoothed_geometry canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
lr_schedule Ran
ran, honoured the contract we drafted
zifanw/smoothed_geometry/models/keras_model.py
pointer only (licence: MIT); the stored copy get_code serves, from Jeongyun-Lee-0423/Classification, is pointer only (licence: NONE) · get_code("67e18e3fdd805d03")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Jeongyun-Lee-0423/Classification, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

resnet_layer Ran
ran; our contract draft was wrong, not the code
zifanw/smoothed_geometry/models/keras_model.py
code served (permissive licence) · get_code("7c10248ed4cd4926")
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 KerasTensor. 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
from tensorflow import keras
from keras.layers import Input

# Create a small input tensor
# Using Keras functional API to create the input
input_tensor = Input(shape=(4, 4, 3))

ARGS = {
    'inputs': input_tensor,
    'num_filters': 16,
    'kernel_size': 3,
    'strides': 1,
    'activation': 'relu',
    'batch_normalization': True,
    'conv_first': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type KerasTensor — a KerasTensor 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
resnet_v1 Ran
ran on a synthesized input
zifanw/smoothed_geometry/models/keras_model.py
code served (permissive licence) · get_code("9f3315577c74cf33")
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 Functional. 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 keras
import numpy as np

ARGS = {
    'input_shape': (32, 32, 3),
    'depth': 20,
    'num_classes': 10,
    'activation': 'relu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
BetaLoss Not yet run
unverified (harvested, no recorded run)
zifanw/smoothed_geometry/robust/smooth_space.py
code served (permissive licence) · get_code("e8cce4587fde5f47")
How it ran

no invocation recorded.

compute_W Not yet run
unverified (harvested, no recorded run)
zifanw/smoothed_geometry/robust/smooth_space.py
code served (permissive licence) · get_code("f9c81687f57290ac")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
lr_schedule 7 other papers
7 dated earlier
1511.06807 (2015-11)
Adding Gradient Noise Improves Learning for Very Deep Networks
1603.05027 (2016-03)
Identity Mappings in Deep Residual Networks
1807.06521 (2018-07)
CBAM: Convolutional Block Attention Module
and 4 more not named here
resnet_layer 5 other papers
4 dated earlier, 1 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1807.06521 (2018-07)
CBAM: Convolutional Block Attention Module
1905.10626 (2019-05)
Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness
and 2 more not named here

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

Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs. This lack of robustness is especially problematic in high-stakes applications where adversarially-manipulated explanations could impair safety and trustworthiness. Building on a geometric understanding of these attacks presented in recent work, we identify Lipschitz continuity conditions on models' gradient that lead to robust gradient-based attributions, and observe that smoothness may also be related to the ability of an attack to transfer across multiple attribution methods. To mitigate these attacks in practice, we propose an inexpensive regularization method that promotes these conditions in DNNs, as well as a stochastic smoothing technique that does not require re-training. Our experiments on a range of image models demonstrate that both of these mitigations consistently improve attribution robustness, and confirm the role that smooth geometry plays in these attacks on real, large-scale models.

For agents

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

get_harvested_code_for_paper("2006.06643")
get_code_for_paper("2006.06643")
have("2006.06643")

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

curl https://syntology.ai/api/ran/2006.06643.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.06643.svg)](https://syntology.ai/paper/2006.06643)

Connect an agent — have() is free.