Skip to content
MathGrades HS

McGraw-Hill Illustrative Mathematics AGA

McGraw-Hill Education

Judge anthropic/claude-opus-4-7 · Signal Studio judge (claude-opus-4-7) · 2026-05-28

100

% indicator exact match

Gateways 3/3 Meets

Agreement vs gold

Indicator level — gold and the judge as two raters over the rubric criteria.

Exact match

100.0%

16 indicators vs gold

Weighted κ

1.00

ordinal-weighted agreement

MAE

0.00

lower is better

Signed bias

+0.00

no bias

Attribution

Where the judge diverges, and whether it's signal: per-gateway bias localizes the gap, the confusion matrix shows over- vs under-rating, and the noise floor is the judge's self-agreement across passes (a gap below it isn't trustworthy).

gateway-onen=3100.0%bias +0.00
gateway-threen=5100.0%bias +0.00
gateway-twon=8100.0%bias +0.00

Indicator confusion · rows = gold, cols = judge

MeetsPartialDNM
Meets1600
Partial000
DNM000

Diagonal = agreement. Amber = judge rated higher than gold (over-rating).

Gateway rollup

Indicator scores rolled up to EdReports gateway ratings (sequential gating + no-0s cap), gold vs judge.

G1 · Focus & Coherence

18/18 pts

GoldMeets
JudgeMeets
agree

G2 · Rigor & Mathematical Practices

16/16 pts

GoldMeets
JudgeMeets
agree

G3 · Usability

16/16 pts

GoldMeets
JudgeMeets
agree

Gateway-level agreement: exact 100% · κ 1.00 (3 gateways)

Divergences (0)

Indicators where the judge's score differed from gold. Amber = judge under-scored, blue = over-scored.

No divergences

Judge and gold agreed on every scored indicator.

Live read from the Signal Studio spine (core-data).