Add v2_a11 describability axis to filter_score

filter rejected AXIS reversible: simple 4h proposed 11 Jun 2026

What is the proposed change?

Append v2_a11 axis after v2_a10 in the axis array. Score 0-3 using a single judge prompt: 'Can a buyer describe what this offer DOES in one sentence without using AE-internal jargon (foundry, lens, axis, NBJ, substrate)?' 0=requires AE vocabulary; 1=requires domain-expert vocabulary; 2=one clause needs unpacking; 3=fully buyer-readable. Update composite weight vector to include a11 with weight 1.0 (same as a1-a10). Add unit test in filter_score test harness asserting axis is present.

Target files

hypothesis_engine/moves/filter_score.js

Expected effect

On the 43 graduated candidates from S157 NBJ sweep, 847f7e-shape proposals (engine-mirror IP) score 0-1 on a11 while ROBUST candidates score 2-3, producing a 1.5-2.5 point composite spread that increases kill rate on jargon-laden proposals by ≥20%.

Falsifier — what would prove this wrong?

Replay filter_score across the 43 graduated candidates; if a11 score distribution shows <0.5 Spearman correlation with the existing NBJ ROBUST/SHAPE/MIRROR classification, axis is misdesigned and should be removed.

Evidence that triggered the proposal

D — brain/ARCHITECT_MEMORY.md (S157 NBJ sweep, 847f7e-shape category)
E — filter_score kill-reason distribution: 'unclear-what-it-does' as top-3 reason

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	3
composability	3
reversibility	3

Disposition

Rejected by filter_score. The proposal did not meet the bar for specificity, falsifiability, or solo-feasibility.

Evaluation history

When	Move
2026-06-12 04:39	meta_filter_score
2026-06-11 04:03	meta_genesis