Equation 4 · Part 3 · The Safeguards Behind a Claude Refusal, and What They're Actually Trading Off
Symbol p_esc
What this part means
sc is one of the signed contributions combined to compute the quantity on the left.
Its job in the formula
sc is one of the signed contributions combined to compute the quantity on the left.
Full expression→Symbol p_esc→Article meaning
The passage around this formula
…it flags to a slower, more capable classifier that reviews the input and output together [ 1 ] . If is the near-free cost of the first pass and the much larger cost of the second, and is the fraction of traffic the probe escalates, the expected added cost per request is . Because is small on ordinary traffic, the average cost collapses toward even though did not get any cheaper — which is the…
Learn the underlying idea
A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.
Open the illustrated subscripts: which member of a family? guide →
See this notation across published equations →
Sources cited in the surrounding passage
- [4] Constitutional Classifiers: Defending Against Universal Jailbreaks across Thousands of Hours of Red Teaming ↗
- [1] Next-Generation Constitutional Classifiers: More Efficient Protection Against Universal Jailbreaks ↗
These citations provide research context; check each source for the exact claim it supports.