feat(evals): add budget-matched Elite evaluation substrate - #52

Merged

ernestprovo23 merged 8 commits into

mainfrom

feat/h1-budget-matched-eval

Jul 18, 2026

Commits on Jul 17, 2026

docs: plan H1 budget-matched evaluation
ernestprovo23
committed
5440bdf
feat(evals): add versioned study planning contracts
ernestprovo23
committed
35b6969
feat(evals): add budget caps and strict replay
ernestprovo23
committed
27cf1a4
feat(evals): add failure-inclusive runner and blinding
ernestprovo23
committed
9690195
feat(evals): add failure-inclusive scoring reports
ernestprovo23
committed
a632185
feat(evals): expose offline evaluation workflow
ernestprovo23
committed
f1c61ef
fix(evals): enforce artifact integrity boundaries
ernestprovo23
committed
4365c28

Commits on Jul 18, 2026

Merge main into feat/h1-budget-matched-eval
ernestprovo23
committed
b84bc9b