feat(reviewer-eval): N-arm matrix, blinded grading, corpus 2->11 for … #4

Job	Run time
Rust Unit Tests (ubuntu-24.04-arm)	1m 26s
Rust Unit Tests (macos-latest)	1m 23s
Rust Unit Tests (ubuntu-latest)	1m 31s
Pure Python Fallback	48m 9s
Python Tests (ubuntu-24.04-arm, py3.14)	32m 47s
Python Tests (windows-latest, py3.14)	59m 25s
Python Tests (ubuntu-24.04-arm, py3.11)	33m 29s
Python Tests (ubuntu-24.04-arm, py3.13)	32m 59s
Python Tests (macos-latest, py3.14)	28m 28s
Python Tests (windows-latest, py3.11)	53m 49s
Python Tests (ubuntu-latest, py3.14)	1h 1m 49s
Python Tests (windows-latest, py3.13)	54m 13s
Rust Unit Tests (windows-latest)	2m 21s
Python Tests (macos-latest, py3.11)	36m 21s
Python Tests (macos-latest, py3.13)	35m 22s
Python Tests (ubuntu-latest, py3.11)	1h 1m 2s
Python Tests (ubuntu-latest, py3.13)	53m 14s
	9h 57m 48s

Provide feedback