Add v1_a6 acute_pain_not_candy axis to filter_score.js FILTERS array (shadow)

council rejected AXIS reversible: simple 4h proposed 9 Jun 2026

What is the proposed change?

Add a 6th entry to FILTERS at filter_score.js:13-19 — { key: 'acute_pain_not_candy', question: 'Is the named pain a recurring acute event the buyer would queue a vendor demo for, not a nice-to-have they would tolerate forever?' }. Both highSystem and lowSystem prompts already accept arbitrary key sets; expand the schema literal in both to include the 6th key. Compose against composite_rank_score in SHADOW mode only: log to filter_score moves output as { shadow_a6: N } but do NOT include it in the kill-rule or composite computation. After 30 admissions, run a retrospective correlation analysis vs council verdict_action and ICP-survey-style 'would_pay_now' if available. v2.3 design specifies this axis precisely.

Target files

hypothesis_engine/moves/filter_score.js

Expected effect

Across the historical 40 meta_genesis admissions referenced in the corpus, A6 shadow scores will cluster bimodally (acute vs. vitamin) and should correlate r > 0.4 with council STRONG_BUILD/WEAK_BUILD vs KILL/DEFER actions. If correlation is weak, the rubric is mispurposed or the existing five axes already capture this signal.

Falsifier — what would prove this wrong?

Run shadow scoring on 30 historical hypotheses. If A6 distribution is unimodal (all 2s, or all 1s) the axis is collapsing — rubric needs tightening. If A6 correlates r > 0.85 with existing solo_founder_feasible, it's redundant with the existing axes and should be killed. If r < 0.15 with council action, the axis measures noise.

Evidence that triggered the proposal

D — brain/V2_FILTER_DESIGN_v2.3.md — A6 acute_pain_not_candy defined with baseline+boost scoring rubric, documented but never wired
D — hypothesis_engine/migrations/s112_add_v2_filter_columns.js:60 — v2_a6_acute_pain_not_candy schema column exists but is never written by any move
E — hypothesis_engine/moves/filter_score.js:13-19 — FILTERS array has 5 entries; v2 design specifies 10

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
2026-06-12 05:20	meta_council_verdict
2026-06-12 05:00	meta_argument
2026-06-12 04:32	meta_filter_score
2026-06-09 04:05	meta_genesis