SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.14668 · 2023

CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows

arXiv · PDF · Open in the Atlas

Code that ran

1 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, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 3 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/2303.14668.json · badge: /api/ran/2303.14668.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
tridungduong16/fairce canonical (classifier label)
classifier basis not recorded on the link
1 ran · 3 no recorded run
FunctionStatusWhere it lives
remove_nans Ran
ran on a synthesized input
tridungduong16/fairce/src/carla/evaluation/process_nans.py
code served (permissive licence) · get_code("9514a2f24fa740e8")
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 3, 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 pandas as pd
import numpy as np

# Create sample dataframes for testing remove_nans
# factuals and counterfactuals must have same shape

# Create factuals dataframe with 5 rows and 4 columns
factuals = pd.DataFrame({
    'feature_1': [1.0, 2.0, 3.0, 4.0, 5.0],
    'feature_2': [10.0, 20.0, 30.0, 40.0, 50.0],
    'feature_3': [100.0, 200.0, 300.0, 400.0, 500.0],
    'feature_4': [1000.0, 2000.0, 3000.0, 4000.0, 5000.0],
})

# Create counterfactuals dataframe with same shape but some NaN values
counterfactuals = pd.DataFrame({
    'feature_1': [1.5, np.nan, 3.5, 4.5, 5.5],
    'feature_2': [15.0, 25.0, 35.0, np.nan, 55.0],
    'feature_3': [150.0, 250.0, 350.0, 450.0, 550.0],
    'feature_4': [1500.0, 2500.0, 3500.0, 4500.0, 5500.0],
})

ARGS = {
    'factuals': factuals,
    'counterfactuals': counterfactuals,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, 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
d1_distance Not yet run
unverified (harvested, no recorded run)
tridungduong16/fairce/src/carla/evaluation/distances.py
code served (permissive licence) · get_code("0aaa962e1866ae50")
How it ran

no invocation recorded.

d2_distance Not yet run
unverified (harvested, no recorded run)
tridungduong16/fairce/src/carla/evaluation/distances.py
code served (permissive licence) · get_code("5a1d4fbcd79868dd")
How it ran

no invocation recorded.

get_distances Not yet run
unverified (harvested, no recorded run)
tridungduong16/fairce/src/carla/evaluation/distances.py
code served (permissive licence) · get_code("dd26c560863fb6ee")
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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 later) and 0 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
d1_distance 1 other paper
1 dated earlier
2203.06768 (2022-03)
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
d2_distance 1 other paper
1 dated earlier
2203.06768 (2022-03)
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
get_distances 1 other paper
1 dated earlier
2203.06768 (2022-03)
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
remove_nans 1 other paper
1 dated earlier
2203.06768 (2022-03)
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse

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 is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired results by altering samples. Although state-of-the-art counterfactual explanation methods are proposed to use variational autoencoder (VAE) to achieve promising improvements, they suffer from two major limitations: 1) the counterfactuals generation is prohibitively slow, which prevents algorithms from being deployed in interactive environments; 2) the counterfactual explanation algorithms produce unstable results due to the randomness in the sampling procedure of variational autoencoder. In this work, to address the above limitations, we design a robust and efficient counterfactual explanation framework, namely CeFlow, which utilizes normalizing flows for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our technique compares favorably to state-of-the-art methods. We release our source at https://github.com/tridungduong16/fairCE.git for reproducing the results.

For agents

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

get_harvested_code_for_paper("2303.14668")
get_code_for_paper("2303.14668")
have("2303.14668")

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

curl https://syntology.ai/api/ran/2303.14668.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.14668.svg)](https://syntology.ai/paper/2303.14668)

Connect an agent — have() is free.