Add v2_a11 falsifier_concreteness axis to filter_score

filter rejected AXIS reversible: simple 4h proposed 15 Jun 2026

What is the proposed change?

Add an 11th composite axis scoring each hypothesis 0-3 on whether the 'falsifier' field names a measurable observation runnable in <8h of solo work. 0 = vague/missing ('we'd see if it didn't work'); 1 = named metric, no threshold; 2 = named metric + threshold; 3 = named metric + threshold + concrete data source. Insert axis call after the existing a10 block in filter_score.js, register in the axis weights map, and surface in argument-move prompt as a per-axis subscore. No schema migration: reuses existing composite_score column.

Target files

hypothesis_engine/moves/filter_score.js

Expected effect

Hypotheses written without a runnable falsifier (the 847f7e-shape pattern Commander has flagged) drop ~2 points in composite, pushing them below the kept-threshold ~60% of the time. ROBUST candidates retain composite within 0.5 of current.

Falsifier — what would prove this wrong?

Re-score last 90 days of council_verdict='kept' and 'rejected' hypotheses with the new axis. If axis score distribution does not separate kept from rejected with delta >= 0.8 mean, axis is misdesigned and should be reverted.

Evidence that triggered the proposal

D — S157_NBJ_SWEEP / S161_LAYER_4_LENS_SET_SYNTHESIZED.md (falsifier-quality lens)
E — filter_score.js v2_a1..v2_a10 axis registry

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

Evaluation history

When	Move
2026-06-15 04:04	meta_filter_score
2026-06-15 04:03	meta_genesis