jevbooks

← All projects

jev-polymarket-desk

lazuli111/jev-polymarket-desk · Homepage

Shadow-mode Polymarket desk using Jev as a typed judgment layer.

Automated README summary

Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A shadow-mode trading desk for Polymarket prediction markets. Code handles all computation, filtering and accounting; Jev supplies independent probability judgments on market outcomes and rule clarity. Every simulated trade is logged and scored against market prices after settlement.

How it uses Jev

Jev answers twice per market: given a profile (question, resolution rules, source, time left, recent news headlines) it returns outcome probability p_a and an info score; given only the rules it returns rule clarity and dispute risk. Fair price = market price + 0.25 × (Jev − market price); at most one market is chosen, or none.

Primitives:choicescorenoul

Technique worth stealing

Keep prices out of Jev's state so its judgment stays independent of the market, and give it only a 0.25 weight in fair value until live calibration proves it adds information.

Try it

Run main.py locally; the dashboard updates every 15 minutes via GitHub Actions.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.94
  • Shows a System One patternFound in material0.85
  • Describes handling uncertaintynot found in the excerpt0.05
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolunclear0.46
  • Top-10 learning shortlist signalFound in material0.64
  • Is a replica of the modelnot found in the excerpt0.03
  • Solves a common problem (0–2)score on a 0–2 scale0.47 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.94Shows a System One pattern0.85Describes handling uncertainty0.05Reports measured numbers0.04Is a runnable tool0.46Top-10 learning shortlist signal0.64Is a replica of the model0.0300.51Solves a common problem (0–2)0.47 / 2012

no-judgment band (0.40–0.60)

Design patterns
Check-up0.98Funnel0.94Scorecard0.92Inspection0.68Flight recorder0.65Traffic light0.62Blind review0.55Viewfinder0.29Menu0.2000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 23 Oct 2026.