Add v2_a11 describability axis scored via S157 NBJ 5-question rubric

filter rejected AXIS reversible: simple 4h proposed 31 May 2026

What is the proposed change?

Append v2_a11 'describability' to the axis array after v2_a10. Score 0-3 by running the 5-question NBJ rubric from S157 (Q1 can-name, Q2 can-point-to-instance, Q3 can-distinguish-from-near-miss, Q4 has-units-or-cardinality, Q5 can-state-falsifier). Sum yes-answers, map {0-1→0, 2→1, 3→2, 4-5→3}. Wire the axis into the existing weighted composite with weight 1.0 (same as a1-a10). Persist subscore to filter_score boundary_log so argument move can cite it.

Target files

hypothesis_engine/moves/filter_score.js

Expected effect

On the 43 historically-graduated candidates, 847f7e-shape proposals (empty noun phrases) score 0-1 on a11 while ROBUST candidates score 2-3, producing a 2-3 point spread on the composite. Filter-kept rate of 847f7e-shape drops ≥30%.

Falsifier — what would prove this wrong?

Rerun filter_score on the 43 graduated candidates plus the last 30 cycles of filter_rejected items. If a11 score distribution does not separate the human-tagged ROBUST set from the 847f7e-shape set with AUC ≥0.7, axis is misdesigned and must be removed.

Evidence that triggered the proposal

D — brain/S157_NBJ_DESCRIBABILITY_TEST.md
D — brain/V2_FILTER_DESIGN.md
E — kill-reason distribution: 847f7e-shape dominates filter_rejected

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
2026-05-31 04:04	meta_filter_score
2026-05-31 04:03	meta_genesis