Explanation contract is unenforced — set the v2 scoring policy

From the August 2026 harness audit (policy decision needed before the #139 v2 freeze).

Symptom

The response contract requires a short explanation per output, but the requirement is not enforced at scoring time: blank-explanation answers score normally.

Evidence (verified)

• 61 blank-explanation rows accepted on the current board: grok-4.3 = 56, kimi-k2.6 = 4, haiku-4.5 = 1.
• If blanks scored as misses, grok-4.3 would drop 2.574 pts (~7 ranks). No other model moves materially.

Decision for v2

Two coherent options:

1. Score on numbers only (recommended): keep the explanation request in the prompt, publish explanation-compliance as a per-model column, but don't gate the accuracy score on prose compliance. Scoring prose mixes constructs into a numeric-accuracy headline.
2. Enforce as miss, stated up front alongside the parse-failure policy (like Sonnet 5's 56/1,984 unparsed-as-miss under auto).

Either way the v2 methodology must state the policy explicitly; today's behavior is option 1 by accident, undocumented.

Start with the August 2026 harness audit and issue #139's v2 freeze context. Review the current scoring behavior for blank explanations and compare it with the documented parse-failure policy. Done means the v2 methodology explicitly selects and documents one explanation-scoring policy, including how explanation compliance is reported.