SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11168 · ICML · 2024

Trust Regions for Explanations via Black-Box Probabilistic Certification

Karthikeyan Ramamurthy, Dennis Wei, Amit Dhurandhar, Swagatam Haldar

arXiv · PDF · Open in the Atlas

Code that ran

4 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, 3 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; 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/2402.11168.json · badge: /api/ran/2402.11168.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
trusted-ai/aix360 canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
Trusted-AI/AIX360 canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
bb Ran
ran, violated the contract we drafted
trusted-ai/aix360/aix360/algorithms/ecertify/ExpCertifyBB.py
code served (permissive licence) · get_code("f437c40c8921cd8c")
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 float64, 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 numpy as np

# The function bb takes parameter x and:
# 1. Creates an array of ones with length equal to len(x)
# 2. Calls dot product between alpha and x
# This means x should be a 1D array-like object that supports len() and dot product

x = np.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
e Ran
ran, violated the contract we drafted
trusted-ai/aix360/aix360/algorithms/ecertify/ExpCertifyBB.py
code served (permissive licence) · get_code("15ff4533de1a6af8")
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 float64, 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 numpy as np

# The function e(x) expects x to be array-like that supports:
# - len(x) to get the length
# - dot product with a numpy array of the same length
# This means x should be a 1D array or array-like of numeric values

x = np.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
f Ran
ran, violated the contract we drafted
trusted-ai/aix360/aix360/algorithms/ecertify/ExpCertifyBB.py
code served (permissive licence) · get_code("6a51d68741d2ae12")
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 float64, 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 numpy as np

# The function f takes a single parameter x
# Looking at the function body:
# - x is passed to bb(x) and e(x)
# - bb(x) does alpha.dot(x) where alpha = np.ones(len(x))
# - e(x) does beta.dot(x) where beta = 0.75 * np.ones(len(x))
# - Both operations require x to be array-like with a length
# - The dot product suggests x should be a 1D array or vector

# Create a small numpy array as input
x = np.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
onehot_encoding Ran
ran; our contract draft was wrong, not the code
Trusted-AI/AIX360/aix360/algorithms/cofrnet/utils.py
code served (permissive licence) · get_code("d269f5f6d592112e")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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)

# Create a label tensor with class indices
# Using batch size 2, with 4 classes total
label = torch.tensor([0, 2], dtype=torch.long)

# Number of classes
n_classes = 4

ARGS = {
    "label": label,
    "n_classes": n_classes,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
generate_connections Not yet run
unverified (harvested, no recorded run)
Trusted-AI/AIX360/aix360/algorithms/cofrnet/utils.py
code served (permissive licence) · get_code("6be0ec7a3027f695")
How it ran

no invocation recorded.

process_data Not yet run
unverified (harvested, no recorded run)
Trusted-AI/AIX360/aix360/algorithms/cofrnet/utils.py
code served (permissive licence) · get_code("d81355b81c3d33f8")
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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 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
generate_connections 1 other paper
1 dated earlier
1909.03012 (2019-09)
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
onehot_encoding 1 other paper
1 dated earlier
1909.03012 (2019-09)
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
process_data 1 other paper
1 dated earlier
1909.03012 (2019-09)
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

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

Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic) explanation certification. We ask the question: Given a black box model with only query access, an explanation for an example and a quality metric (viz. fidelity, stability), can we find the largest hypercube (i.e., ℓ ∞ ball) centered at the example such that when the explanation is applied to all examples within the hypercube, (with high probability) a quality criterion is met (viz. fidelity greater than some value)? Being able to efficiently find such a trust region has multiple benefits: i) insight into model behavior in a region, with a guarantee; ii) ascertained stability of the explanation; iii) explanation reuse, which can save time, energy and money by not having to find explanations for every example; and iv) a possible meta-metric to compare explanation methods. Our contributions include formalizing this problem, proposing solutions, providing theoretical guarantees for these solutions that are computable, and experimentally showing their efficacy on synthetic and real data.

For agents

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

get_harvested_code_for_paper("2402.11168")
get_code_for_paper("2402.11168")
have("2402.11168")

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

curl https://syntology.ai/api/ran/2402.11168.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.11168.svg)](https://syntology.ai/paper/2402.11168)

Connect an agent — have() is free.