Safety, alignment & interpretability· 2018
RISE: Randomized Input Sampling for Explanation of Black-box Models
On the reading lists
- #69 in Safety, alignment & interpretability (2026 edition)
Why it matters
Model-agnostic randomized masking for saliency.
Condensed from the expert lists' notes.
The record
- First released
- 2018 (from arXiv 1806.07421)
- Citations
- 1,682 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- the grok list only
- Score
- 0.273 · computed rank 673 · consensus 0.24, must-read 0, citations percentile 0.574 (2010s · safety), awards 0, existing lists 0. Method
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.