Add v2_a11 reachability-evidence axis to filter_score

filter rejected AXIS reversible: simple 4h proposed 8 Jun 2026

What is the proposed change?

Current v2_a7 distribution_reachability scores stated intent (does the proposal claim reachability?). Add v2_a11 reachability_evidence scoring 0-3 on whether the proposal names (a) a specific channel/community, (b) a concrete acquisition action Commander can perform within 1 hour, (c) at least one prior datum showing the channel works for similar buyers. Score 0 if none, 3 if all three. Insert after a10 in filter_score.js composite. Re-weight composite so a7+a11 jointly cap at the previous a7 weight (no inflation of distribution dimension).

Target files

hypothesis_engine/moves/filter_score.js hypothesis_engine/moves/filter_axes/v2_a11_reachability_evidence.js

Expected effect

On a backtest over the last 43 graduated candidates, composite spread between top-quartile and bottom-quartile widens by ≥1.5 points; candidates that previously graduated but Commander DEFERed for 'unreachable buyer' score 0-1 on a11.

Falsifier — what would prove this wrong?

Backtest scores on a11 do not correlate (Spearman ρ < 0.25) with Commander reachability-related overrides logged in Corpus E. Axis is then measuring intent-restated, not evidence.

Evidence that triggered the proposal

E — commander_overrides (DEFER reasons cite reachability uncertainty)
D — brain/MANIFESTO_v4_honest_deflated.md (distribution as P0 constraint)

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
2026-06-12 04:27	meta_filter_score
2026-06-08 04:03	meta_genesis