evidence boundary
unknowntheoretical
An evidence atom is an inspectable support unit. It is not a finding by itself; it supports or challenges a finding through review.
frontiers / frontier
Evidence atom
back to sourcesevidence boundary
unknownAn evidence atom is an inspectable support unit. It is not a finding by itself; it supports or challenges a finding through review.
finding binding
boundBehavioral safety evaluations (refusal-based testing on harmful content categories) show strong surface-level safety but do not assess deeper deception, sandbagging, or scheming capabilities.
inspect finding →
source binding
source-boundvs_0ed2b819f71baff6
inspect source →
review context
unverified1 reviewable changes and 0 evaluation records target this atom or its bound objects.
Evidence statement
Behavioral safety evaluations (refusal-based testing on harmful content categories) show strong surface-level safety but do not assess deeper deception, sandbagging, or scheming capabilities.
extraction method
manual_curation
support relation
unknown
condition refs
vcnd_3ae0127ecf633b64
Caveats
events
vev_f495bad59887515cfinding.assertedManual finding added to frontier state
reviewer:will-blair · 2026-05-29
reviewable changes
vpr_162253ea3f0f4c69finding.addManual finding added to frontier state
applied · reviewer:will-blair · 2026-05-29
evaluations
No evaluation rows are attached.