Add v2_a11 describability axis scored via NBJ 5-question test

council rejected AXIS reversible: simple 4h proposed 21 Jun 2026

What is the proposed change?

Insert v2_a11 axis after v2_a10. Score 0-3 by asking judge to answer the S157 NBJ 5 questions (inputs/outputs/exceptions/criteria/non-AI-verb) about the proposal. 3 = all 5 answered crisply; 0 = ≥3 unanswerable. Add axis to composite sum and to filter_kept gate threshold (raise gate by +2 to preserve current pass rate).

Target files

hypothesis_engine/moves/filter_score.js

Expected effect

On 43 graduated candidates from S157, 847f7e-shape proposals (the 14 NBJ-failed ones) score ≤1 on a11; ROBUST candidates score 2-3. Composite spread widens 2-3 points and matches S157 sweep classification.

Falsifier — what would prove this wrong?

Re-score the 43 graduated candidates; if Spearman correlation between a11 and S157 NBJ classification is <0.5, axis is misdesigned.

Evidence that triggered the proposal

D — brain/S157_NBJ_DESCRIBABILITY_TEST.md
D — brain/META_ENGINE_S158_ROUND2_SYNTHESIS.md (P3 survivor)

Proposer self-score

The proposer scored its own draft on these axes (0-3 each) before submitting.

Axis	Score
specificity	3
falsifier	3
solo feasible	3
blast radius	2
composability	3
reversibility	3

Disposition

Rejected at the council verdict. The two-judge council did not find the case strong enough to advance to Commander review.

Evaluation history

When	Move
2026-06-21 04:12	meta_council_verdict
2026-06-21 04:09	meta_argument
2026-06-21 04:03	meta_filter_score
2026-06-21 04:03	meta_genesis