Pith. sign in

REVIEW 5 cited by

Getting a CLUE: A Method for Explaining Uncertainty Estimates

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.06848 v2 pith:DQZCCDVL submitted 2020-06-11 stat.ML cs.LG

Javier Antorán , Umang Bhatt , Tameem Adel , Adrian Weller , José Miguel Hernández-Lobato This is my paper · ORCID
classification stat.MLcs.LG
keywords uncertaintyclueinputmethodcounterfactualestimatesexperimentsexplanations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems. However, there is little work at the intersection of these two areas. We address this gap by proposing a novel method for interpreting uncertainty estimates from differentiable probabilistic models, like Bayesian Neural Networks (BNNs). Our method, Counterfactual Latent Uncertainty Explanations (CLUE), indicates how to change an input, while keeping it on the data manifold, such that a BNN becomes more confident about the input's prediction. We validate CLUE through 1) a novel framework for evaluating counterfactual explanations of uncertainty, 2) a series of ablation experiments, and 3) a user study. Our experiments show that CLUE outperforms baselines and enables practitioners to better understand which input patterns are responsible for predictive uncertainty.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. An Explainable Gaussian Process Auto-encoder for Tabular Data

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A Gaussian-process autoencoder with a latent-space density estimator generates counterfactual examples for tabular data, with competitive or better scores on several evaluation metrics.

  2. Do you see what I see? An Ambiguous Optical Illusion Dataset exposing limitations of Explainable AI

    cs.CV 2025-05 reject novelty 6.0 of 10

    Ambivision is a new dataset of AI-generated animal optical illusions, and the paper claims that adding gaze and eye annotations as visible image features improves classification while exposing limits of pixel-based ex...

  3. Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

    cs.LG 2026-07 conditional novelty 5.0 of 10

    An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.

  4. Uncertainty Awareness and Trust in Explainable AI- On Trust Calibration using Local and Global Explanations

    cs.AI 2025-09 conditional novelty 4.0 of 10

    People who saw uncertainty visualizations trusted a more certain model more, but the study does not demonstrate that this explanation calibrates trust better than numeric accuracy.

  5. Tabular Diffusion Counterfactual Explanations

    cs.LG 2025-08 conditional novelty 4.0 of 10

    TDCE guides a tabular diffusion reverse process with Gumbel-softmax classifier gradients to produce counterfactual explanations, achieving high validity on four benchmarks.

Pith tools