← Back to Updates · v1 plan (May 11)

SUPREME EDGE ENHANCEMENT v2

Amended Master Plan — Thin-Sample Universe Expansion + Infrastructure Gates + COT-Corrected COMMODITY

RESEARCH SURFACE — NOT FINANCIAL ADVICE. Supersedes the 2026-05-11 v1 plan after Opus 4.7 session caught COT timing-leakage, COMMODITY n-drop, and 5 P0.5 infra gaps the v1 missed.

Generated 2026-05-13 02:45 UTC · Branch main · Supersedes v1 plan · Triggered by external-model second-opinion (DeepSeek V4-Pro / Loker 480B / GPT-OSS 120B) + internal code audit + per-class forensic + supreme-plan delta review

TL;DR — what changed since v1 (May 11)

The thin-sample emission-expansion strategy (new in v2)

v1 treated thin sample as a "wait for n to grow naturally" problem. That's slow and assumes the emission pipeline is already firing. For three of our six asset classes, emission is the bottleneck, not data-fetch.

ClassData-fetch universe (config.py)Production-emission universe (gates)Closed-pick n todayBottleneck
CRYPTObroad (Binance liquid set)broad post-quan_engine cap7,800not emission-bound
EQUITYbroadbroad447not emission-bound
FOREXbroadsizing_allowed=false per PR #9091,357intentionally capped until PF≥0.8
ETF50+ symbolssame as data-fetch107just past charter floor
COMMODITY24 symbolsrestricted to HG=F + PL=F per PR #535178 raw / 27 post-filteremission gate too narrow for the data we have
BOND14 symbolsbond_* strategies emit 0 picks/run; BOND_ELITE_FLOOR was 40, now 320 real bond_* / 21 legacy ZN=Fcuration gate + forward-gate + active_picks integration all dam the stream
FUTURES16 symbolssilent-dead after kills with no replacements0no strategies emitting

Recommended emission-expansion plan (thin-sample classes)

COMMODITY — temporarily widen emission allowlist while sample accumulates

Current PR #535 emission allowlist = HG=F + PL=F only. This restriction was correct for the production sizing path (the killed sub-classes had real losses), but it leaves the walk-forward at n=27 (HG=F=27 / PL=F=0). v1's "STABLE_EDGE" verdict was on the broader 178-row historical sample.

Proposal: add a COMMODITY_SHADOW_UNIVERSE tier that permits emission for {PA=F palladium, BZ=F brent, GC=F gold} at 0% sizing for the next 60 days. Picks accumulate in active_picks.json for tracking but cannot be sized for capital. After 60 days, re-evaluate per-symbol via the mutate-before-kill protocol (docs/MUTATION_THREE_AXIS_PROTOCOL.md) using only the new shadow-period data.

Acceptance: COMMODITY walk-forward n ≥ 100 within 90 days post-COT-lag-patch with PF maintained ≥ 1.5 on the broader universe. If a shadow symbol's WR < 40% on its own n ≥ 25, remove from shadow.

P1 universe-expansion

BOND — 3-layer cluster + Connors RSI2 wire on existing universe

BOND_SYMBOLS already has 14 liquid ETFs (TLT/IEF/SHY/LQD/HYG/JNK/EMB/TLH/MUB/TIP/AGG/BND/BNDX/GOVT). The bottleneck is gates, not symbols.

Layer 1 (SHIPPED): vars.BOND_ELITE_FLOOR=32. Should unblock 7/7 raw signals being rejected at curation.

Layer 2 (open): FORWARD_GATE_OVERRIDES["bond"] = 10 in alpha_engine/forward_validator.py. Currently every bond_* strategy fails the global FORWARD_GATE_MIN_TRADES=50 with 0 closed picks. Per-class override defensible because bond ETFs have lower idiosyncratic vol — 10 trades carry ~the weight of 50 crypto trades.

Layer 3 (open): merge non_crypto_agent/data/bond_picks.jsonalpha_engine/data/active_picks.json in the bond-agent workflow. Today bond picks are stats-only via orphan_emitter_bond; they never reach the live sizing path.

Plus Connors RSI2 wire on TLT/IEF/LQD (~120 trades/yr) + credit-spread bond_credit_spread_mean_reversion (env-enabled via PR #545; LQD-HYG pair).

Acceptance: /audit BOND n rises from 21 toward 50+ within 60 days; PF maintains ≥ 1.5 on the new picks (legacy ZN=F pool can stay at 0.66, it'll wash out as real picks accumulate).

P0 3-layer fix cluster

FUTURES — reactivate killed strategies via mutation, not new symbols

FUTURES_SYMBOLS has 16 liquid contracts (ES/NQ/YM/RTY equity index + ZN/ZT/ZB rates + GC/SI/HG metals + 6E/6B/6J/6A/6C FX). Universe is fine; strategies are dead.

Proposal: per the v1 plan + memory, FUTURES was silent-dead after 2 strategies got killed with no replacements. Apply mutate-before-kill (docs/MUTATION_THREE_AXIS_PROTOCOL.md) to the killed pair on the SHORT direction axis (FOREX taught us SHORT-only mutations recover 30-40% of dead strategy classes — updates/2026-05-06-forex-mutation-decisions.md).

If mutation produces a SHORT-axis variant with WR ≥ 50% on n ≥ 20 paper, promote to SHADOW with 0% sizing for 60 days.

P2 mutation-replay

ETF — already past charter floor; minor PF push

ETF is at PF 1.34 / WR 56.1% / n=107. Crossed n≥100 charter floor this session. Universe is 50+ symbols; data-fetch isn't bound.

Proposal: apply v1's P1-C floor reductions (Trust -20%, Score -15%, Smart Picks gate 85→70, min-hold ≥ 4h). Target PF 1.5 (T2 PF floor) within 30 days. ETF was the only class with surfaced signal in the research orchestrator's P5 verdicts.

P1 gate-loosen

5 P0.5 Infrastructure gates (new in v2 — binding for every class)

External-model review (DeepSeek V4-Pro + Loker 480B + GPT-OSS 120B) converged: infrastructure gates every asset-class promotion, not just CRYPTO/FOREX. The v1 5-plan synthesis missed these. They are now top priority.

#ItemWhy money-ready needs itWhere it lives
P0.5-1Explicit position sizingCurrently sizing_allowed=true is meaningless without vol-targeting + max-allocation-per-name. One high-conviction coin can torch the book.alpha_engine/position_sizer.py (new) wired into scanner.py + quality_gates.py
P0.5-2Slippage + execution cost modelNo cost model = backtest PF is a fantasy. HG=F futures fills could destroy COMMODITY PF 3.94 once realistic spreads/impact deducted.per-class bps deduction in outcome_resolver.py + reflected in walk_forward_validate
P0.5-3Drift circuit-breakerCRYPTO −31.12pp backtest-live gap is currently charted but not acted on. Need: if realized_wr_30d < backtest_wr - 2σ, auto-flip sizing_allowed=false.alpha_engine/drift_circuit_breaker.py (new) called from same place PR #909's FOREX sizing-cap fired
P0.5-4Concentration / correlation controlsCOMMODITY = 100% HG=F today. No same-sector CRYPTO limit. A copper rally or single-coin crash can dwarf class diversification.new tier of quality_gates.py per-class concentration caps
P0.5-5Portfolio-level MDD limitCharter §7 specifies daily −3% cap; not verified wired anywhere. Per-class limits don't bite during correlated sell-offs.alpha_engine/portfolio_circuit_breaker.py already exists; verify wired or wire it

Sequencing: P0.5-1 (sizing) and P0.5-2 (slippage) are prerequisites for any live-capital decision. P0.5-3 (drift breaker) and P0.5-4 (concentration) are prerequisites for sizing > 0. P0.5-5 (portfolio MDD) is the kill-switch above all of these.

Updated per-class verdicts (post-this-session)

EQUITY — STABLE_EDGE confirmed

PF 1.55 / WR 53.2% / n=447 — meets Tier 2. Strongest broad candidate per all 5 v1 plans + this session's verification. Path to T2 live capital: after P0.5 infra ships.

Tier 2 ✓

COMMODITY — STABLE_EDGE PROVISIONAL pending COT lag re-run

Live PF 3.94 / WR 67.8% / n=425 verdict-grade. v1 plan called this "STABLE_EDGE" at PF 3.61. But: CT=F's cot_positioning 90% WR contribution is timing-leakage-confirmed (98%). PR #941 ships the 3-day publication-lag patch. 2026-05-23 paper-pilot graduation gate now requires lag-corrected WR ≥ 75% on full 100-pick history. If WR drops to predicted 45-55%, pilot returns to REHAB.

Provisional T1 candidate

CRYPTO — DECAYING_EDGE persists; class-specific gates shipped

PF 1.36 / WR 46.5% / n=7,800. v1's 3 quarantines all shipped (kimi_signal_tracking blacklist, crypto_soc_* quarantine, quan_engine 12% volume cap). Cloud-agent's confidence-inversion gate (+56 uncommitted lines) requires independent reproduction before merge per cloud_agent_claims_validation_2026-05-12.md — same audit produced the falsified "41 dormant strategies" claim.

decay-replacement pipeline still open

FOREX — DECAYING_EDGE / hard-capped

PF 0.29 / WR 46.3% / n=1,357. sizing_allowed=false per PR #909. FOREX deep-dive doc shipped this session per the v1 P1 mandate. Recovery path: COT/DXY/carry wiring + SHORT-only mutations + at least one full quarter of clean post-fix data.

BLOCKED until PF≥0.8

ETF — PAST charter n floor; PF push to T2

PF 1.34 / WR 56.1% / n=107. Crossed n≥100. 0.16 short of T2 PF floor.

Tier 3 → T2 next

BOND — 3-layer fix cluster open

PF 0.66 / WR 54.5% / n=21 legacy ZN=F (no real bond_* picks closed). Layer 1 shipped (BOND_ELITE_FLOOR=32); Layers 2 + 3 outstanding.

structural fix required

FUTURES — silent-dead, mutation-replay required

n=0. No emission. Universe is fine; strategies dead.

mutate-before-kill replay

Execution sequence (v2)

  1. P0.5 infrastructure — ship items 1-5 above. None of the asset classes can be sized for real capital without these. Estimated 2-3 PRs / 4-6 days.
  2. COT lag-corrected re-run — with PR #941 merged, re-run cot_paper_pilot backtest on full 100-pick history. Decide 2026-05-23 graduation based on lag-corrected WR ≥ 75% gate.
  3. BOND Layer 2 + 3 — ship the forward-gate override + active_picks merge. Unblocks live sizing path for bond_* strategies once they accumulate trades.
  4. COMMODITY shadow-universe expansion — permit PA=F + BZ=F + GC=F at 0% sizing for 60 days. Walk-forward picks up the new symbols; per-symbol mutate-before-kill decision at day 60.
  5. ETF push to T2 — Trust -20% / Score -15% / Smart 70 floors. Target PF 1.5 within 30 days.
  6. CRYPTO confidence-inversion independent reproduction — before merging the cloud-agent's +56-line gate.
  7. FOREX SHORT-only rehab — per the deep-dive doc; gated behind quarter of clean post-pnl_pct-clamp data.
  8. FUTURES mutation-replay — lowest priority; class re-enters rotation only after at least one mutated SHORT-axis variant clears WR ≥ 50% on n ≥ 20 paper.

Real-money gate (unchanged from v1): ≥ 2 asset classes at Tier 2 (PF > 1.5, WR > 50, MDD < 20, n ≥ 100, walk-forward consistency ≥ 70%) AND P0.5-1 through P0.5-5 all shipped.

Realistic 2-class T2 lineup at 60-day horizon (post-COT-correction): EQUITY + ETF (if PF clears 1.5) or EQUITY + COMMODITY (if lag-corrected WR holds ≥ 60%). BOND is 90-day horizon dependent on Layers 2 + 3.

Reports + PRs from this session

Procedural addition (v1 didn't have this)

External-model second-opinion is now part of the standard toolkit. When internal swarms converge on a plan, query 2-3 external models (DeepSeek V4-Pro, Loker 480B, GPT-OSS 120B via Ollama Cloud) in parallel. Where they converge on a specific hypothesis, dispatch an Explore subagent to code-audit. Where they converge on a generic infra gap, queue it as P0.5. Cost is trivial (~$0.02/round for DeepSeek); catches consensus risk that single-agent or single-internal-swarm sessions miss.

The COT timing-leakage caught this round — before any real capital touched the CT=F paper pilot — justifies the procedure indefinitely.