domains / families / research / experiment-audit

experiment-audit

authentic

Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says \"审计实验\", \"check experiment integrity\", \"audit results\", \"实验诚实度\", or after experiments complete before writing claims.

When to use

• audit experiment integrity
• check for fake ground truth
• detect score normalization fraud
• identify phantom results
• verify insufficient scope
• audit results after experiments complete

When not to use

• wrapping in /loop
• wrapping in /schedule
• wrapping in CronCreate
• re-running verdict on a timer

Skill page

Source