← all meta proposals

Add structural-duplicate gate before meta_argument move

filter rejected GATE reversible: simple 5h proposed 30 May 2026
What is the proposed change?
Insert a pre-argument gate that computes a normalized shape-hash (title n-gram fingerprint + change_type + sorted target_files set) for each candidate entering the argument move. Before invoking the $0.11 LLM call, query hypotheses table for rows in the last 60d with status IN ('council_rejected','commander_killed','pending_commander') sharing the same shape-hash. If a match exists, short-circuit with kill reason 'structural_duplicate_pre_argument' and emit a move record at $0 cost. Reuse the existing 15ed71-detection logic already used in S148 backfill — promote it from a post-hoc cleanup into a pre-flight gate.
Target files
hypothesis_engine/moves/argument.js hypothesis_engine/lib/shape_hash.js
Expected effect
On the 5-day Phase 1 trace (7× v2_backfill_orphan + 1× structural_duplicate_15ed71), at least 2-3 of those kills migrate from post-argument to pre-argument, saving ~$0.20-0.33 in argument cost per Phase 1 week. Argument move cost drops measurably in the next cycle telemetry.
Falsifier — what would prove this wrong?
Replay the last 14 days of meta cycles through the new gate offline. If fewer than 2 candidates would have been caught pre-argument (i.e. duplicates only emerge post-argument because the title is rewritten by argument), the gate's hash position is wrong and it should move post-argument or be removed.
Evidence that triggered the proposal
  • E — kill_reason_distribution: 7× v2_backfill_orphan_S148, 1× structural_duplicate_15ed71_S148
  • D — brain/META_ENGINE_PHASE_1_SPEC.md (6-move pipeline cost rollup)
  • E — move_cost: meta_argument $0.11/cycle vs meta_filter_score $0

Proposer self-score

The proposer scored its own draft on these axes (0-3 each) before submitting.

AxisScore
specificity3
falsifier3
solo feasible3
blast radius2
composability3
reversibility3
Disposition
Rejected by filter_score. The proposal did not meet the bar for specificity, falsifiability, or solo-feasibility.

Evaluation history

WhenMove
2026-05-30 04:03meta_filter_score
2026-05-30 04:03meta_genesis