Add commodity-wedge shadow check at argument.js entry point (Survivor E)

filter rejected GATE reversible: simple 6h proposed 21 May 2026

What is the proposed change?

At the entry point of argument.js, before any argument move dispatches, add a synchronous 5-axis binary check: (1) core product is a thin wrapper on a single commodity API, (2) API provider could ship this feature in <6 months, (3) margin structure depends on a single provider's pricing decisions, (4) moat relies on UI/UX alone with no data lock-in or network effects, (5) primary distribution channel is owned by a potential incumbent. Each axis scores 0 (pass) or 1 (fail). If total ≥3, write shadow verdict {hypothesis_id, axes_failed: [...], score, timestamp} to meta_engine/data/shadow_gate_verdicts/commodity_wedge_{hypothesis_id}.json. Do NOT block argument execution — shadow mode only. Emit log line: '[SHADOW] commodity_wedge_score=N for {hypothesis_id}'. Scoring uses the hypothesis description text; no additional LLM call — keyword/heuristic match only to keep latency near zero.

Target files

hypothesis_engine/moves/argument.js

Expected effect

Flag rate in first 30 days should fall between 5-15% of argument runs. Flagged hypotheses should show lower graduation rates than unflagged over a 60-day observation window. If the commander-killed AI control / ClaimGate / AI Tool Verification for Agencies hypotheses are run through the check retroactively, all 3 should score ≥3 (flagged).

Falsifier — what would prove this wrong?

If shadow flag rate exceeds 20% in first 30 days, the threshold (≥3 of 5) is too permissive and must be raised to ≥4. If no flagged hypothesis is killed for commodity/incumbent reasons in council or commander review within 60 days, the gate is not correlating with actual kill decisions and axis definitions need revision.

Evidence that triggered the proposal

Corpus D: brain/META_ENGINE_S158_ROUND2_SYNTHESIS.md — Survivor E: commodity-wedge shadow check approved COMMIT_WITH_REVISION, specified as 5-axis binary gate at argument.js entry point
Corpus E: kill distribution last 7d — v2_backfill_orphan_S148 accounts for 7 kills and commander KILLed 3 incumbents; commodity-wedge pattern not intercepted before argument runs consumed $0.45 in red_team_kill calls
Corpus E: cost rollup — red_team_kill n=40 at $0.45/7d; shadow gate operating at near-zero latency (heuristic only) could flag commodity-wedge candidates before argument compute is spent

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	3
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
2026-05-21 04:17	meta_filter_score
2026-05-21 04:15	meta_genesis