Explainable AI by BAPC -- Before and After correction Parameter Comparison

Florian Sobieczky; Manuela Gei{\ss}

Explainable AI by BAPC -- Before and After correction Parameter Comparison

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 2103.07155 v2 pith:UYZ76U2Y submitted 2021-03-12 stat.ML cs.LG

Florian Sobieczky , Manuela Gei{ss} This is my paper · ORCID

classification stat.MLcs.LG

keywords modelaccuracyai-modelbasesurrogatecriteriaexplanationsfidelity

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

A local surrogate for an AI-model correcting a simpler 'base' model is introduced representing an analytical method to yield explanations of AI-predictions. The approach is studied here in the context of the base model being linear regression. The AI-model approximates the residual error of the linear model and the explanations are formulated in terms of the change of the interpretable base model's parameters. Criteria are formulated for the precise relation between lost accuracy of the surrogate, the accuracy of the AI-model, and the surrogate fidelity. It is shown that, assuming a certain maximal amount of noise in the observed data, these criteria induce neighborhoods of the instances to be explained which have an ideal size in terms of maximal accuracy and fidelity.

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

Surrogate Modeling for Explainable Predictive Time Series Corrections
stat.ML 2024-12 conditional novelty 4.0 of 10

A before-and-after parameter comparison makes black-box corrections to time series forecasts explainable, with integrated-gradient scores attributing the correction to base-model parameters.

Pith tools