EURE
EURE measures whether a corpus segment produces high entropy while also carrying strong unique-token behavior and low repetition pressure.
Open EURE detail
LDI
LDI measures whether the vocabulary engine is broad, sustained, and disciplined without using entropy in the formula.
Open LDI detail
RACS
RACS measures how much complexity remains after accounting for repetition pressure, vocabulary strength, and lexical narrowness.
Open RACS detail
How To Use These Metrics
Read EURE, LDI, and RACS as separate lenses. Agreement across the three indexes strengthens a public-safe finding; disagreement is useful too, because it shows which behavior changes when entropy, vocabulary discipline, or repetition control is emphasized.
What This Page Proves / Does Not Prove
This page supports an aggregate measurement claim: PRM evidence can be read through distinct metric families instead of one blended score. It does not publish source text, expose private mappings, or claim universal artistic ranking. Scores are strongest-inside-the-tested-pool values, not absolute perfection.
PRM uses standard external measures alongside PRM-specific composite indexes. Standard measures include established entropy, lexical diversity, and repetition-related metrics. Composite indexes such as EURE, LDI, and RACS combine selected metric families to make aggregate behavior easier to review. Composite scores are interpretive review tools, not replacements for the underlying measurements.
Reference Comparison Boundary
Reference comparisons are baseline coordinates for interpreting metric behavior. They are not presented as artistic rankings or claims of superiority over other writers.