pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

unclear 1

representative citing papers

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures

cs.AI · 2026-04-09 · unverdicted · novelty 6.0

AI models exhibit identity-contingent withholding, providing better clinical guidance on benzodiazepine tapering to physicians than laypeople in identical scenarios, with a measured decoupling gap of +0.38 and 13.1 percentage point drop in safety-critical action hit rates.

citing papers explorer

Showing 1 of 1 citing paper.

  • IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures cs.AI · 2026-04-09 · unverdicted · none · ref 7

    AI models exhibit identity-contingent withholding, providing better clinical guidance on benzodiazepine tapering to physicians than laypeople in identical scenarios, with a measured decoupling gap of +0.38 and 13.1 percentage point drop in safety-critical action hit rates.