oracle_forecast

io.github.tradewr333-lgtm/degenscan-intel · Verify this server

Get a CALIBRATED probability for a yes/no market question — e.g. "Will Bitcoin close above 120,000 USD on 2026-10-31?", "Will the Fed cut at the October FOMC?", "Will ETH touch 5,000 before 2026-10-31?". The oracle first assembles live context from Intel (spot, 30d realized vol, funding, OI, Polymarket odds, calendar, recent primary-source events) and computes a volatility base rate; then runs Monte Carlo simulations of LLM agent societies (distinct personas, social graph, optional news shocks) plus a 5-expert panel anchored on the base rate; a reasoning model aggregates with the rule "0.5 is never a default". ASYNC: this call returns { forecast_id, status: "queued", eta_s } in under a second; poll oracle_get(forecast_id) every ~20 s (free) until status = "done" (1–3 min). Result: probability, ci80, disagreement, base_rate, market_odds, edge (probability − market), drivers, failure_modes, confidence, runs[] with belief trajectories, panel[], commitment_hash (sha256 committed before resolution), context_used. Public Brier record: oracle_track_record. $0.25/call (covers ~70 LLM calls). Optional interventions=[{round, news, audience}] inject a shock into the simulated society.