2026
BA-FedSHAP: A reproducible toolkit for auditing background-induced attribution drift
SSRN
Preprint on how the choice of background distribution alters federated attribution results, and what that does to an audit.
PublicationsAuthor
Research software
BA-FedSHAP, auditing background-induced attribution drift
- Year
- 23 May 2026
- Role
- Author
Measures how much a federated explanation depends on an arbitrary modelling choice.
Authors: Roy Saurabh
Evidence
Sources
What each document establishes, and where to read it.
Zenodo
BA-FedSHAP, Zenodo software record
Registers BA-FedSHAP as a reproducible auditing toolkit authored by Roy Saurabh.
Related work
Related work
2026
AI in health: how smart technology is breaking new frontiers in medical care
Digital Skills and Jobs Platform, European Commission
A deep-dive for the European Commission's skills platform on where clinical AI is genuinely useful, and what assurance regulated care requires of it.
PolicyAuthor
2026
CSA-Lite, Context-Sliced AI Assurance Lite
A reproducible public-records method for analysing AI risk as a function of deployment context rather than of the model alone.
Research softwareAuthor
2026
LEXON-Bench, Executable AI Regulatory Obligation Reasoning
A benchmark for reasoning over regulatory obligations as executable statements rather than prose.
Research softwareAuthor