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

CONDITIONAL 1

representative citing papers

Safety from Honesty in a Disinterested AI Predictor

cs.AI · 2026-06-28 · conditional · novelty 7.0

Under consequence-invariant posterior training and sparsity of coordinated harm patterns, the training mass on dangerous guarded Predictors is bounded by C_bad times R_shell.

citing papers explorer

Showing 1 of 1 citing paper.

  • Safety from Honesty in a Disinterested AI Predictor cs.AI · 2026-06-28 · conditional · none · ref 15

    Under consequence-invariant posterior training and sparsity of coordinated harm patterns, the training mass on dangerous guarded Predictors is bounded by C_bad times R_shell.