{
 "license": "CC BY 4.0",
 "kind": "nearest-arenas",
 "as_of": "2026-10-21",
 "rule": "Dated 22.10.2026. Quoted from the paper's Table 9 (v5, as of 2026-10-21) and the pages of the projects. ND = not documented in the public materials reviewed. Nothing here is measured by the league and no number of the league is named.",
 "columns": [
  "forecast_or_traded",
  "time_secured_by",
  "proper_score",
  "several_horizons",
  "agreement_discounted",
  "human_before_ai",
  "open_data"
 ],
 "arenas": [
  {
   "arena": "RockAlpha",
   "first_public": "n.d.",
   "roster": "six Chinese and four US models, one per laboratory, 2x leverage",
   "source": "https://rockalpha.rockflow.ai/ai-stock",
   "forecast_or_traded": "Live AI stock trading",
   "time_secured_by": "ND",
   "proper_score": "No (returns)",
   "several_horizons": "No",
   "agreement_discounted": "ND",
   "human_before_ai": "No",
   "open_data": "ND"
  },
  {
   "arena": "AI-Trader (HKU)",
   "first_public": "Dec 2025",
   "roster": "three Chinese and three US models; US stocks, A-shares and cryptocurrencies",
   "source": "https://arxiv.org/abs/2512.10971",
   "forecast_or_traded": "Live trading agents on US stocks, A-shares and crypto",
   "time_secured_by": "Operator record",
   "proper_score": "No (returns)",
   "several_horizons": "No",
   "agreement_discounted": "ND",
   "human_before_ai": "No",
   "open_data": "Repository open"
  },
  {
   "arena": "Alpha Arena",
   "first_public": "Oct 2025",
   "roster": null,
   "source": null,
   "forecast_or_traded": "Real-money trading, crypto then US equities",
   "time_secured_by": "Operator record; organiser states trades are verifiable",
   "proper_score": "No (returns)",
   "several_horizons": "No",
   "agreement_discounted": "ND",
   "human_before_ai": "No",
   "open_data": "Stated by organiser"
  },
  {
   "arena": "Rallies AI Arena",
   "first_public": "Nov 2025",
   "roster": null,
   "source": null,
   "forecast_or_traded": "Virtual $100,000 per model in US stocks (press)",
   "time_secured_by": "ND",
   "proper_score": "No (returns)",
   "several_horizons": "No",
   "agreement_discounted": "ND",
   "human_before_ai": "ND",
   "open_data": "ND"
  },
  {
   "arena": "Agent Market Arena",
   "first_public": "Oct 2025",
   "roster": null,
   "source": null,
   "forecast_or_traded": "Live trading by LLM agents, stocks and crypto",
   "time_secured_by": "ND",
   "proper_score": "No (trading results)",
   "several_horizons": "No",
   "agreement_discounted": "ND",
   "human_before_ai": "ND",
   "open_data": "ND"
  },
  {
   "arena": "TradeRank",
   "first_public": "season 10, Oct 2026",
   "roster": "daily decisions of 22 models without a country design",
   "source": null,
   "forecast_or_traded": "Daily decisions on crypto and US large caps, $10,000 simulated",
   "time_secured_by": "ND",
   "proper_score": "ND",
   "several_horizons": "No",
   "agreement_discounted": "ND",
   "human_before_ai": "ND",
   "open_data": "Open JSON dataset, licence ND"
  },
  {
   "arena": "Foresight Arena",
   "first_public": "May 2026",
   "roster": null,
   "source": "https://arxiv.org/abs/2605.00420",
   "forecast_or_traded": "Binary Polymarket events, some on asset prices",
   "time_secured_by": "keccak256 commit-reveal per agent and round on Polygon PoS before the deadline (2; block time); paper results simulated, live agents in a companion study",
   "proper_score": "Yes (Brier; Alpha against the market mid-price)",
   "several_horizons": "No",
   "agreement_discounted": "No (outcomes of markets assumed independent)",
   "human_before_ai": "No",
   "open_data": "Contracts and analysis code open; data on-chain, licence ND"
  }
 ],
 "this_project": {
  "arena": "This project",
  "first_public": "Oct 2026",
  "roster": "US and Chinese models in equal numbers, on one snapshot",
  "source": null,
  "forecast_or_traded": "The chance of a rise of 12 markets on four horizons, and virtual portfolios",
  "time_secured_by": "Yes (OpenTimestamps in Bitcoin and RFC 3161 timestamps, before the open)",
  "proper_score": "Yes (Brier; against the crowd and a coin)",
  "several_horizons": "Yes (a day, a week, a month, six months)",
  "agreement_discounted": "Yes (effective voices from the correlation of the probabilities)",
  "human_before_ai": "Yes (readers call before seeing the AIs; a random half)",
  "open_data": "Yes (CSV, JSON, Parquet; CC BY 4.0)"
 }
}