SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.13286 · 2026

Explanatory Interactive Machine Learning for Bias Mitigation in Visual Gender Classification

Markus Schedl, Nathanya Satriani, Djordje Slijepčević, Matthias Zeppelzauer

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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; 7 failures of our instrument; 4 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/2602.13286.json · badge: /api/ran/2602.13286.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
fhstp/xil-gender-classification canonical (classifier label)
classifier basis: census
8 ran · 4 no recorded run
FunctionStatusWhere it lives
analyze_filenames Ran
ran; our contract draft was wrong, not the code
fhstp/xil-gender-classification/explanatory_gender_classification/verify_data.py
pointer only (licence: GPL-3.0) · get_code("d4209c11c90e0be7")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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.

compute_bfp Ran
ran; our contract draft was wrong, not the code
fhstp/xil-gender-classification/explanatory_gender_classification/src/evaluation/bias_metrics.py
pointer only (licence: GPL-3.0) · get_code("ce63b5eb2745b280")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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.

compute_dice_score Ran
ran; our contract draft was wrong, not the code
fhstp/xil-gender-classification/explanatory_gender_classification/src/evaluation/bias_metrics.py
pointer only (licence: GPL-3.0) · get_code("18bf65176d43cb42")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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.

compute_ffp Ran
ran; our contract draft was wrong, not the code
fhstp/xil-gender-classification/explanatory_gender_classification/src/evaluation/bias_metrics.py
pointer only (licence: GPL-3.0) · get_code("b7053f7d0d63c067")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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.

get_gradcam_layer Ran
ran; our contract draft was wrong, not the code
fhstp/xil-gender-classification/explanatory_gender_classification/src/evaluation/explainability.py
pointer only (licence: GPL-3.0) · get_code("7d256999d81b9e01")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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.

get_image_files Ran
ran; our contract draft was wrong, not the code
fhstp/xil-gender-classification/explanatory_gender_classification/verify_data.py
pointer only (licence: GPL-3.0) · get_code("e6e872965a1589c0")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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.

get_mask_files Ran
ran; our contract draft was wrong, not the code
fhstp/xil-gender-classification/explanatory_gender_classification/verify_data.py
pointer only (licence: GPL-3.0) · get_code("ed559698c71c351e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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.

run_command Ran
ran, violated the contract we drafted
fhstp/xil-gender-classification/explanatory_gender_classification/run_example.py
pointer only (licence: GPL-3.0) · get_code("ea63d8659109d801")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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.

apply_caipi_sampling Not yet run
unverified (harvested, no recorded run)
fhstp/xil-gender-classification/explanatory_gender_classification/src/augmentation/caipi.py
pointer only (licence: GPL-3.0) · get_code("5e1fa7ce8706eeee")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

create_bla_model Not yet run
unverified (harvested, no recorded run)
fhstp/xil-gender-classification/explanatory_gender_classification/src/explainability/bla.py
pointer only (licence: GPL-3.0) · get_code("3beb9c05c97874b6")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

create_gradcam_explainer Not yet run
unverified (harvested, no recorded run)
fhstp/xil-gender-classification/explanatory_gender_classification/src/explainability/gradcam.py
pointer only (licence: GPL-3.0) · get_code("38e33b18347377ef")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

rrr_loss_function Not yet run
unverified (harvested, no recorded run)
fhstp/xil-gender-classification/explanatory_gender_classification/src/models/rrr_model.py
pointer only (licence: GPL-3.0) · get_code("4daba99bcd26a744")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, fhstp/xil-gender-classification, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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

Explanatory interactive learning (XIL) enables users to guide model training in machine learning (ML) by providing feedback on the model's explanations, thereby helping it to focus on features that are relevant to the prediction from the user's perspective. In this study, we explore the capability of this learning paradigm to mitigate bias and spurious correlations in visual classifiers, specifically in scenarios prone to data bias, such as gender classification. We investigate two methodologically different state-of-the-art XIL strategies, i.e., CAIPI and Right for the Right Reasons (RRR), as well as a novel hybrid approach that combines both strategies. The results are evaluated quantitatively by comparing segmentation masks with explanations generated using Gradient-weighted Class Activation Mapping (GradCAM) and Bounded Logit Attention (BLA). Experimental results demonstrate the effectiveness of these methods in (i) guiding ML models to focus on relevant image features, particularly when CAIPI is used, and (ii) reducing model bias (i.e., balancing the misclassification rates between male and female predictions). Our analysis further supports the potential of XIL methods to improve fairness in gender classifiers. Overall, the increased transparency and fairness obtained by XIL leads to slight performance decreases with an exception being CAIPI, which shows potential to even improve classification accuracy.

For agents

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

get_harvested_code_for_paper("2602.13286")
get_code_for_paper("2602.13286")
have("2602.13286")

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

curl https://syntology.ai/api/ran/2602.13286.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.13286.svg)](https://syntology.ai/paper/2602.13286)

Connect an agent — have() is free.