Add v2_a11 cross-engine convergence axis to filter_score

filter rejected AXIS reversible: simple 8h proposed 24 Jun 2026

What is the proposed change?

Add axis v2_a11 'cross_engine_convergence' scored 0-3. Open opportunity_engine's opportunity.db read-only at filter_score time; for each hypothesis_engine candidate, fuzzy-match (embedding cosine >0.6) against opportunity_engine FACTOR_BACKLOG entries (the external_buyer_signal corpus from S209). 0 = no match, 1 = one weak match (cosine 0.6-0.7), 2 = one strong match (>0.7), 3 = multiple strong matches. Equal-weight with existing v2_a1..v2_a10 axes in composite. Insert axis definition + scorer call after existing axis block in filter_score.js.

Target files

hypothesis_engine/moves/filter_score.js

Expected effect

Among the 43 graduated candidates, median v2_a11 score is >=1; among killed candidates, median is 0. Composite score spread between graduated and killed widens by >=0.5 points after adding the axis. At least 1 historically-killed candidate would have passed filter with the new axis included.

Falsifier — what would prove this wrong?

Median v2_a11 score is within 0.2 between graduated and killed candidates on the 43-candidate replay — cross-engine signal does not discriminate and axis is pure noise; remove it.

Evidence that triggered the proposal

D — Layer 4 cross-engine convergence specified in S161 build sequence but not surfaced into filter_score
D — brain/S209 close: external_buyer_signal / FACTOR_BACKLOG explicitly named as the ranking signal

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	2
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
2026-06-24 04:05	meta_filter_score
2026-06-24 04:03	meta_genesis