works on
ai agents 1evaluation methodology 1failure analysis 1research automation 1shadow evaluation 1

From the 1 of 12 linked papers with an AI index.

most citedTowards a Science of AI Agent Reliability

2 citations · 2 across the 5 of their papers we have counts for

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2025

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Stephan Rabanser, Ali Shahin Shamsabadi, Olive Franzese +3

Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify…