SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.07875 · 2021

S-LIME: Stabilized-LIME for Model Explanation

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 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/2106.07875.json · badge: /api/ran/2106.07875.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
ZhengzeZhou/slime canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
has_arg Ran
ran, violated the contract we drafted
ZhengzeZhou/slime/slime/utils/generic_utils.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from thutzr/glime-general-stable-and-local-lime-explanation, is pointer only (licence: NONE) · get_code("af10c20f7551354a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from thutzr/glime-general-stable-and-local-lime-explanation, 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.

id_generator Ran
ran; our contract draft was wrong, not the code
ZhengzeZhou/slime/slime/explanation.py
code served (permissive licence) · get_code("df74843e3430f8e7")
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 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 string
import numpy as np

def id_generator(size=15, random_state=None):
    """Helper function to generate random div ids. This is useful for embedding
    HTML into ipython notebooks."""
    chars = list(string.ascii_uppercase + string.digits)
    return ''.join(random_state.choice(chars, size, replace=True))

# Create a random state object with a choice method
random_state = np.random.RandomState(42)

ARGS = {
    'size': 15,
    'random_state': random_state
}
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 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
lars_path Not yet run
unverified (harvested, no recorded run)
ZhengzeZhou/slime/slime_lm/_least_angle.py
code served (permissive licence) · get_code("55f865e318165bd3")
How it ran

no invocation recorded.

lars_path_gram Not yet run
unverified (harvested, no recorded run)
ZhengzeZhou/slime/slime_lm/_least_angle.py
code served (permissive licence) · get_code("791e97dcb70d5867")
How it ran

no invocation recorded.

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, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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
has_arg 2 other papers
2 later
2311.15722 (2023-11)
GLIME: General, Stable and Local LIME Explanation
2402.10404 (2024-02)
Explaining generative diffusion models via visual analysis for interpretable decision-making process
id_generator 2 other papers
1 dated earlier, 1 later
1906.10263 (2019-06)
DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems
2311.15722 (2023-11)
GLIME: General, Stable and Local LIME Explanation

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

An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are growing efforts for researchers to develop methods to interpret these black-box models. Post hoc explanations based on perturbations, such as LIME, are widely used approaches to interpret a machine learning model after it has been built. This class of methods has been shown to exhibit large instability, posing serious challenges to the effectiveness of the method itself and harming user trust. In this paper, we propose S-LIME, which utilizes a hypothesis testing framework based on central limit theorem for determining the number of perturbation points needed to guarantee stability of the resulting explanation. Experiments on both simulated and real world data sets are provided to demonstrate the effectiveness of our method.

For agents

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

get_harvested_code_for_paper("2106.07875")
get_code_for_paper("2106.07875")
have("2106.07875")

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

curl https://syntology.ai/api/ran/2106.07875.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.07875.svg)](https://syntology.ai/paper/2106.07875)

Connect an agent — have() is free.