Add v2_a11 describability axis using NBJ 5-Q test

filter rejected AXIS reversible: simple 4h proposed 10 Jun 2026

What is the proposed change?

Insert v2_a11 (0-3 scale) after a10 in filter_score.js axis array. Automated scorer counts how many of the 5 NBJ questions (Who specifically? What pain? When triggered? Where buyer reachable? How priced?) the candidate answers with named entities vs hedges/abstractions. Mapping: 5/5 named=3; 3-4=2; 1-2=1; 0=0. Adds 0-3 to composite without reweighting existing axes.

Target files

hypothesis_engine/moves/filter_score.js

Expected effect

On rerun of 43 graduated candidates, the 4 Commander-overridden candidates (3 KILL + 1 DEFER) score ≤1 on a11 while approved candidates score ≥2, producing 2-3 point composite spread that correlates with override decisions.

Falsifier — what would prove this wrong?

If the 4 overridden candidates' mean a11 is within 0.5 of approved-candidate mean across the 43-item rerun, axis fails to discriminate; remove the single function call and axis definition.

Evidence that triggered the proposal

D — brain/S157_NBJ_5Q_DESCRIBABILITY.md
E — engine_traces.commander_overrides (4 overrides: 3 KILL, 1 DEFER)

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 04:32	meta_filter_score
2026-06-10 04:03	meta_genesis