Generated 2026-05-17 08:36 UTC (31.0 h ago; aging daily snapshot) · CME V0.1 · methodology · raw JSON · audit log

Where linked markets disagreed in the latest archived run

Track record immature

Coherence Signals answer one practical question: where do related markets disagree enough that a serious user should inspect the price before citing or trading it? The latest Coherent Markets Engine run (CME V0.1) checked 5,000 Polymarket markets against 701 linked-market rules, then emitted 89 signals after significance, cost, and resolution-risk gates. Modeled net EV for the surviving set is $62,216; realized PnL still waits on settlements. This snapshot is explicitly versioned as CME V0.1. The V0.2.0 walk-forward methodology is separately tracked in manifest #288046 and should only be cited for V0.2 outputs.

Track-record caveat

Coherence Signals are structural-mispricing candidates with modeled net EV until markets resolve. Positive realized-net rate, realized PnL, and matched controls govern any performance claim.

Freshness gate

CME archive is outside the current daily window. Show as latest archived evidence until the next fresh run lands. This page is still useful for methodology review, but it should not be cited as a current signal run until the archive refreshes.

What it is

A structural-disagreement ledger for linked markets.

What it is not

Not a profit promise or trade recommendation.

Evidence gate

Settlements and matched controls decide stronger claims.

Next build

Depth, capacity, and control-arm reporting tighten EV realism.

Study

Use this feed to find linked markets whose prices deserve review, not blind execution.

Monitor

Researcher keeps event identities, signal deltas, and daily digest context together.

Wait for outcomes

Stronger performance claims wait for resolved signals and matched controls.

Polymarket coherence-feed health (30d)

90/100· Healthy

generated 2026-05-18

Coverage30/30

223 of 150 conditions

Volume30/30

2,123 signals

Activity30/30

20 of 20 active days

Resolution0/10

0 pending fwd window

Score is the substrate's feed-health, not a venue-quality rating. Coverage + Volume + Activity = 90 max with the resolution gate (10 pts) deferred until the V0.2 forward pre-registration window matures. See pre-registrations.

Today's redacted signal · 1 of 90
8h ago

Type

Cme Structural

Tension

mild

Horizon

90d+

Event identity redacted on the free tier. Upgrade to Researcher for full event ID + trade construction + day-over-day deltas.

How the run narrowed today's markets

Markets evaluated
5,000
Constraints checked
701
Event groups with tension
317
Passed BH-FDR gate
132
Positive cost-adjusted EV
103
Coherence Signals (all 3 gates)
89

Sample redacted signals

81 more signals in the Researcher feed

Logged-out visitors see a small redacted sample. Researcher keeps event identities, the full archive, signal deltas, and trade construction in the signed-in workflow.

EventTypen marketsTension (pp)p-valueNet EV (%)Days to res.Modeled EV
Event #1mene1299.101.0e-492.4%44$763
Event #2mene694.401.0e-479.0%592$4,751
Event #3mene3594.301.0e-484.6%227$1,303
Event #4mene788.551.0e-478.8%227$362
Event #5mene387.301.0e-481.3%43$2,030
Event #6mene2584.901.0e-475.2%227$411
Event #7mene1579.901.0e-470.2%227$221
Event #8mene1978.351.0e-468.8%227$4,242

What is on this page

  • Daily three-gate signal counts + funnel summary (counts only)
  • Per-signal aggregate characterizations (constraint type, tension magnitude, p-value, net EV%, est PnL) — event identities redacted
  • Methodology + hash-chain audit log; V0.2 outputs are tracked under manifest #288046 with public receipt not yet verified

What the Researcher tier ($99/mo) adds

  • Event identities (which Polymarket markets each signal references)
  • The full 89-signal feed (not just top 30)
  • Trade construction (which markets to long/short, sizing, capital lockup)
  • Day-over-day signal delta (which signals appeared, persisted, resolved)
  • Search across the full dated archive (signals from any past day)
  • Daily email digest (Resend; opt-in)
  • 5-15 min delay relative to cron generation

The Coherent Markets Engine methodology is documented in full at /research/coherent-markets-engine-v1. Current snapshot version: CME V0.1. The V0.2.0 90-day walk-forward backtest is tracked in manifest #288046 (filed 2026-04-29; public receipt not yet verified; methodology frozen at commit 8616a63). The CFTC ANPRM comment on probability-axiom-feasible price coherence as a regulatory transparency standard was filed at regulations.gov on 2026-04-29 (docket CFTC-2026-0331-0001, comment tracking mok-lrhf-09it).

Audit-log row 2cfb58e6a7aafd97… cryptographically links the daily input artifacts (gamma metadata to the published outputs. The full hash chain is at /research/cme/audit_log.jsonl and verifies via python -m services.api.scripts.cme_v0_1.provenance verify.

This work used AI tools (Claude, GPT-4) as research aids during methodology design and pre-publication review. All claims and quantitative results on this page are reproducible from the public data bundle (cron output atapps/web/public/research/cme/) with the documented seed; no claim is taken as true on the basis of an AI tool's output.