SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.21845 · 2026

xai-cola: A python library for sparsifying counterfactual explanations

Lin Zhu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 0 have no contract verdict; 1 failure of our instrument; 1 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/2602.21845.json · badge: /api/ran/2602.21845.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
understanding-ml/COLA canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
bootstrap_sw Ran
ran; our contract draft was wrong, not the code
understanding-ml/COLA/xai_cola/ce_generator/discount.py
code served (permissive licence) · get_code("c892efef43f3d504")
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 tuple, 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 numpy as np
import torch
import torch.nn as nn

torch.manual_seed(0)
np.random.seed(0)

# Create a minimal SWD (Sliced Wasserstein Distance) mock class
class MockSWD(nn.Module):
    def __init__(self):
        super().__init__()
    
    def distance(self, x, y, delta):
        # x shape: (n, d), y shape: (m, d)
        # Returns a scalar distance and some auxiliary value
        # Mock implementation: return mean of x minus mean of y, squared
        dist = torch.sum((torch.mean(x, dim=0) - torch.mean(y, dim=0)) ** 2)
        return dist, torch.tensor(0.0)

# Create small sample data
n = 2  # number of samples in x
m = 3  # number of samples in y
d = 4  # dimension

x_data = np.random.randn(n, d).astype(np.float32)
y_data = np.random.randn(m, d).astype(np.float32)

# Create the SWD object
swd = MockSWD()

# Parameters for bootstrap_sw
delta = 0.1  # some threshold parameter
alpha = 0.05  # significance level
r = 2  # power parameter
B = 10  # number of bootstrap samples (kept small for testing)

ARGS = {
    "x": x_data,
    "y": y_data,
    "delta": delta,
    "alpha": alpha,
    "swd": swd,
    "r": r,
    "B": B,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple 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
svm_loss Not yet run
unverified (harvested, no recorded run)
understanding-ml/COLA/xai_cola/ce_sparsifier/utils/pytorch_models.py
code served (permissive licence) · get_code("5256eb726c3b624c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

Counterfactual explanation (CE) is an important domain within post-hoc explainability. However, the explanations generated by most CE generators are often highly redundant. This work introduces an open-source Python library xai-cola, which provides an end-to-end pipeline for sparsifying CEs produced by arbitrary generators, reducing superfluous feature changes while preserving their validity. It offers a documented API that takes as input raw tabular data in pandas DataFrame form, a preprocessing object (for standardization and encoding), and a trained scikit-learn or PyTorch model. On this basis, users can either employ the built-in or externally imported CE generators. The library also implements several sparsification policies and includes visualization routines for analysing and comparing sparsified counterfactuals. xai-cola is released under the MIT license and can be installed from PyPI. Empirical experiments indicate that xai-cola produces sparser counterfactuals across several CE generators, reducing the number of modified features by up to 50% in our setting. The source code is available at https://github.com/understanding-ml/COLA.

For agents

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

get_harvested_code_for_paper("2602.21845")
get_code_for_paper("2602.21845")
have("2602.21845")

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

curl https://syntology.ai/api/ran/2602.21845.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.21845.svg)](https://syntology.ai/paper/2602.21845)

Connect an agent — have() is free.