Add resolver-clause pre-filter gate to genesis output

filter rejected GATE reversible: simple 4h proposed 4 Jun 2026

What is the proposed change?

Insert a new gate `resolver_clause_gate` between genesis emission and v2 filter scoring. Gate parses each hypothesis text for a terminal 'Resolver:' clause that names (a) a public-observable event AND (b) a date or date-window. Implementation: regex pre-pass for the literal token, then a one-shot Haiku 4.5 classifier (cheap) for semantic check. Hypotheses lacking a resolver clause are hard-rejected with kill_reason = 'no_resolver_clause'. Wire into engine pipeline immediately after genesis, before filter_score.

Target files

hypothesis_engine/moves/genesis.js hypothesis_engine/gates/resolver_clause_gate.js

Expected effect

Per S184 forecaster v1 calibration record, ~40-55% of candidate hypotheses graded 'unscoreable - no resolver' by the forecaster grader. Gating at genesis should drop unscoreable rate at grader from baseline to ≤10% while adding ≤5% latency.

Falsifier — what would prove this wrong?

Run gate on the 43 graduated S183 candidates + next 50 fresh genesis outputs. If forecaster grader unscoreable rate does not drop by ≥25 percentage points within first 50 post-gate hypotheses, OR if the gate rejects >70% of all genesis output (over-restrictive), the gate is misdesigned.

Evidence that triggered the proposal

E — S184 forecaster v1 calibration record (commit df3ae7c)
E — engine.db kill_reason traces showing v2_backfill_orphan_S148 concentration (7×)

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