SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.14741 · NeurIPS · 2025

DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models

Mubarak Shah, Concetto Spampinato, Simone Carnemolla, Matteo Pennisi, Sarinda Samarasinghe, Giovanni Bellitto, Simone Palazzo, Daniela Giordano

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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; 5 failures of our instrument; 3 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/2510.14741.json · badge: /api/ran/2510.14741.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
perceivelab/dexter canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
build_transforms Ran
ran; our contract draft was wrong, not the code
perceivelab/dexter/dexter/classifiers.py
pointer only (licence: NONE) · get_code("24aec0d4a738824d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, perceivelab/dexter 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.

contrastive_loss Ran
ran; our contract draft was wrong, not the code
perceivelab/dexter/dexter/models/modeling_clip.py
pointer only (licence: NONE); the stored copy get_code serves, from microsoft/xpretrain, is pointer only (licence: NOASSERTION) · get_code("4675779aec92d6c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, perceivelab/dexter 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
perceivelab/dexter/dexter/models/resnet.py
pointer only (licence: NONE) · get_code("028f939559c92fc8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, perceivelab/dexter 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
perceivelab/dexter/dexter/models/resnet.py
pointer only (licence: NONE) · get_code("a4355a2ab33ffcc4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, perceivelab/dexter 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.

ensure_output_dir Ran
ran; our contract draft was wrong, not the code
perceivelab/dexter/dexter/utils.py
pointer only (licence: NONE) · get_code("9b2ee4af133c9a09")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, perceivelab/dexter 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.

clip_loss Not yet run
unverified (harvested, no recorded run)
perceivelab/dexter/dexter/models/modeling_clip.py
pointer only (licence: NONE); the stored copy get_code serves, from PeterGriffinJin/InstructG2I, is pointer only (licence: NONE) · get_code("f2ca34eca05d40cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, perceivelab/dexter 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.

resnet18 Not yet run
unverified (harvested, no recorded run)
perceivelab/dexter/dexter/models/resnet.py
pointer only (licence: NONE) · get_code("be3ae0c8dd75192b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, perceivelab/dexter 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.

select_top_features Not yet run
unverified (harvested, no recorded run)
perceivelab/dexter/dexter/utils.py
pointer only (licence: NONE) · get_code("85182be5dfe8a56b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, perceivelab/dexter 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 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
conv1x1 431 other papers
410 dated earlier, 15 later, 5 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
296 dated earlier, 11 later, 4 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 95 other papers
87 dated earlier, 5 later, 2 same year, order not determinable, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
contrastive_loss 27 other papers
24 dated earlier, 3 later · 3 only as an assembly brick
2206.00621 (2022-06)
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training
2209.06430 (2022-09)
CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment
2210.00312 (2022-10)
Multimodal Analogical Reasoning over Knowledge Graphs
and 24 more not named here
clip_loss 16 other papers
14 dated earlier, 2 later · 1 only as an assembly brick
2305.13050 (2023-05)
AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation
2306.02583 (2023-06)
Stable Diffusion is Unstable
2309.16429 (2023-09)
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
and 13 more not named here

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

Understanding and explaining the behavior of machine learning models is essential for building transparent and trustworthy AI systems. We introduce DEX-TER, a data-free framework that employs diffusion models and large language models to generate global, textual explanations of visual classifiers. DEXTER operates by optimizing text prompts to synthesize class-conditional images that strongly activate a target classifier. These synthetic samples are then used to elicit detailed natural language reports that describe class-specific decision patterns and biases. Unlike prior work, DEXTER enables natural language explanation about a classifier's decision process without access to training data or groundtruth labels. We demonstrate DEXTER's flexibility across three tasks-activation maximization, slice discovery and debiasing, and bias explanation-each illustrating its ability to uncover the internal mechanisms of visual classifiers. Quantitative and qualitative evaluations, including a user study, show that DEXTER produces accurate, interpretable outputs. Experiments on ImageNet, Waterbirds, CelebA, and FairFaces confirm that DEXTER outperforms existing approaches in global model explanation and class-level bias reporting. Code is available at https://github.com/perceivelab/dexter.

For agents

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

get_harvested_code_for_paper("2510.14741")
get_code_for_paper("2510.14741")
have("2510.14741")

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

curl https://syntology.ai/api/ran/2510.14741.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.14741.svg)](https://syntology.ai/paper/2510.14741)

Connect an agent — have() is free.