Pith. sign in

REVIEW

Provably Robust Model-Centric Explanations for Critical Decision-Making

Not yet reviewed by Pith; the record is open.

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 2110.13937 v1 pith:CCJAYBXO submitted 2021-10-26 cs.LG cs.AIcs.RO

Provably Robust Model-Centric Explanations for Critical Decision-Making

classification cs.LG cs.AIcs.RO
keywords explanationsmodel-centriccriticaldata-centricmethodsrobustactionableapplications
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We recommend using a model-centric, Boolean Satisfiability (SAT) formalism to obtain useful explanations of trained model behavior, different and complementary to what can be gleaned from LIME and SHAP, popular data-centric explanation tools in Artificial Intelligence (AI). We compare and contrast these methods, and show that data-centric methods may yield brittle explanations of limited practical utility. The model-centric framework, however, can offer actionable insights into risks of using AI models in practice. For critical applications of AI, split-second decision making is best informed by robust explanations that are invariant to properties of data, the capability offered by model-centric frameworks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.