Pith. sign in

REVIEW 4 cited by

Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test

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 2401.06465 v1 pith:EDUETONN submitted 2024-01-12 cs.AI cs.LGstat.ME

Anna Hedström , Leander Weber , Sebastian Lapuschkin , Marina MC Höhne This is my paper · ORCID
classification cs.AIcs.LGstat.ME
keywords mprtmodelparameterrandomisationtestcaveatsexplanationfunction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The Model Parameter Randomisation Test (MPRT) is widely acknowledged in the eXplainable Artificial Intelligence (XAI) community for its well-motivated evaluative principle: that the explanation function should be sensitive to changes in the parameters of the model function. However, recent works have identified several methodological caveats for the empirical interpretation of MPRT. To address these caveats, we introduce two adaptations to the original MPRT -- Smooth MPRT and Efficient MPRT, where the former minimises the impact that noise has on the evaluation results through sampling and the latter circumvents the need for biased similarity measurements by re-interpreting the test through the explanation's rise in complexity, after full parameter randomisation. Our experimental results demonstrate that these proposed variants lead to improved metric reliability, thus enabling a more trustworthy application of XAI methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Value bounds and Convergence Analysis for Averages of LRP attributions

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Averaged LRP-beta attributions have Hoeffding convergence bounds independent of weight norms, unlike gradient-based explanations.

  2. Explainable embeddings with Distance Explainer

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Distance Explainer adapts RISE-style random masking to produce attribution maps for pairwise distances in arbitrary embedding spaces, using rank-based mask selection and a two-sided mirror mode.

  3. Complying with the EU AI Act: Innovations in Explainable and User-Centric Hand Gesture Recognition

    cs.HC 2025-02 conditional novelty 4.0 of 10

    A radar gesture recognition system with user-specific VAE thresholding and experience replay calibration reports 11.50% more flagged anomalies and 15.17% better user adaptation, plus a 97.5% characterization rate that...

  4. xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods

    cs.LG 2025-02 reject novelty 2.0 of 10

    A technical report introducing xai_evals, a Python package that wraps existing explainability and metric libraries without adding new methods or validated results.

Pith tools