Pith. sign in

REVIEW 1 cited by

VeriX: Towards Verified Explainability of Deep Neural Networks

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 2212.01051 v5 pith:N4APGQIQ submitted 2022-12-02 cs.LG

Min Wu , Haoze Wu , Clark Barrett This is my paper · ORCID
classification cs.LG
keywords counterfactualsexplainabilityexplanationsverifiedverixaircraftalongautonomous
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present VeriX (Verified eXplainability), a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models. We build such explanations and counterfactuals iteratively using constraint solving techniques and a heuristic based on feature-level sensitivity ranking. We evaluate our method on image recognition benchmarks and a real-world scenario of autonomous aircraft taxiing.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Efficient Contrastive Explanations on Demand

    cs.LG 2024-12 conditional novelty 5.0 of 10

    Parallelized dichotomic search with feature-disjunction pruning computes distance-restricted contrastive explanations for deep neural networks far faster than a sequential baseline, demonstrated on MNIST and GTSRB.

Pith tools