Add v2_a11 source_family_independence axis to filter_score

filter rejected AXIS reversible: simple 6h proposed 22 Jun 2026

What is the proposed change?

Add v2_a11 (0-3) measuring how many independent source families back a proposal's evidence array. Define families as: {job_postings, awarded_contracts, g2_complaints, regulatory_filings, support_forum_logs, sec_filings, paid_telemetry}. Tag each corpus item with a `source_family` field at ingest. Axis returns: 0 if all evidence from one family; 1 if two families but ≥80% mass on one; 2 if two families balanced; 3 if ≥3 families. Insert after current a10 in composite calculator; weight 1.0 in shadow mode for 2 weeks before activating.

Target files

hypothesis_engine/moves/filter_score.js

Expected effect

Proposals leaning solely on PUBLIC text-visible sources (the Codex #7 shared-bias class) score 0-1; cross-family proposals score 2-3, producing 1-2 point composite spread that correlates with Gate 1 PROCEED outcomes on the S204 instrument.

Falsifier — what would prove this wrong?

Re-score 43 graduated S203/S204-era candidates. If a11 distribution shows zero correlation (|r|<0.15) with Gate 1 PROCEED/STOP classification once the instrument lands, the axis is misdesigned (or `source_family` tagging is wrong) and gets removed.

Evidence that triggered the proposal

D — S204 Codex council finding #7: two PUBLIC text-visible sources cannot validate whole thesis
E — S204 spec v1 REJECT: same-proxy-both-sides breaks Gate 1 calibration

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
2026-06-22 04:03	meta_filter_score
2026-06-22 04:03	meta_genesis