pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Calibrating Conservatism for Scalable Oversight

cs.AI · 2026-05-27 · unverdicted · novelty 5.0

CCO aggregates scoring functions into a calibrated penalty using conformal decision theory to enforce target violation rates for AI oversight on benchmarks like modified SWE-bench and MACHIAVELLI.

citing papers explorer

Showing 1 of 1 citing paper.

  • Calibrating Conservatism for Scalable Oversight cs.AI · 2026-05-27 · unverdicted · none · ref 2

    CCO aggregates scoring functions into a calibrated penalty using conformal decision theory to enforce target violation rates for AI oversight on benchmarks like modified SWE-bench and MACHIAVELLI.