SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.13544 · NeurIPS · 2024

Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?

Julia Vogt, Ričards Marcinkevičs, Moritz Vandenhirtz, Sonia Laguna

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures 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/2401.13544.json · badge: /api/ran/2401.13544.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
sonialagunac/beyond-cbm canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
sonialagunac/Beyond-CBM canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
create_loss Ran
ran; our contract draft was wrong, not the code
sonialagunac/Beyond-CBM/losses.py
pointer only (licence: NONE) · get_code("fdebfb1784d89686")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sonialagunac/Beyond-CBM 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.

generate_random_subset_intervention_mask Ran
ran, honoured the contract we drafted
sonialagunac/beyond-cbm/intervene.py
pointer only (licence: NONE) · get_code("f5b63e7e91bb76e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sonialagunac/beyond-cbm 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.

generate_uncertain_subset_intervention_mask Ran
ran; our contract draft was wrong, not the code
sonialagunac/beyond-cbm/intervene.py
pointer only (licence: NONE) · get_code("b5b3ff2e037d360a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sonialagunac/beyond-cbm 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.

intervene_on_representations Ran
ran; our contract draft was wrong, not the code
sonialagunac/beyond-cbm/intervene.py
pointer only (licence: NONE) · get_code("57ba537bca4d1821")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sonialagunac/beyond-cbm 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.

get_ImageNetCLIP_dataloaders Not yet run
unverified (harvested, no recorded run)
sonialagunac/Beyond-CBM/datasets/CLIP_dataset.py
pointer only (licence: NONE) · get_code("971f1ab2fec29f59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sonialagunac/Beyond-CBM 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. No invocation recorded.

train_test_split_CLIP Not yet run
unverified (harvested, no recorded run)
sonialagunac/Beyond-CBM/datasets/CLIP_dataset.py
pointer only (licence: NONE) · get_code("048ba88a05ec6ddf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sonialagunac/Beyond-CBM 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. 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, 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 6 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

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we introduce a method to perform such concept-based interventions on pretrained neural networks, which are not interpretable by design, only given a small validation set with concept labels. Furthermore, we formalise the notion of intervenability as a measure of the effectiveness of concept-based interventions and leverage this definition to fine-tune black boxes. Empirically, we explore the intervenability of black-box classifiers on synthetic tabular and natural image benchmarks. We focus on backbone architectures of varying complexity, from simple, fully connected neural nets to Stable Diffusion. We demonstrate that the proposed fine-tuning improves intervention effectiveness and often yields better-calibrated predictions. To showcase the practical utility of our techniques, we apply them to deep chest X-ray classifiers and show that fine-tuned black boxes are more intervenable than CBMs. Lastly, we establish that our methods are still effective under vision-languagemodel-based concept annotations, alleviating the need for a human-annotated validation set.

For agents

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

get_harvested_code_for_paper("2401.13544")
get_code_for_paper("2401.13544")
have("2401.13544")

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

curl https://syntology.ai/api/ran/2401.13544.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.13544.svg)](https://syntology.ai/paper/2401.13544)

Connect an agent — have() is free.