Geopol Forecasts Index
April 18, 2026 · View on GitHub
Index of prediction runs across two related pipelines:
- Geopol Forecaster — two-stage pipeline combining Snowglobe-style actor simulation with LLM Council-style multi-perspective analytical review.
- Geopol Forecast Council — lean spin-off that skips actor simulation and polls a lineage-diverse LLM panel for concrete predictions per horizon over a grounded SITREP.
Each run is seeded with live news data and produces probabilistic or structured-prediction forecasts across multiple time horizons. Accuracy analysis is added as prediction windows close.
Prediction Runs — Geopol Forecaster
| # | Date | Topic | Actors | Lenses | Model | Open-Sourced Report | Key Finding |
|---|---|---|---|---|---|---|---|
| 3 | 10/04/2026 | Iran forced regime change probability | 10 | 6 | Claude Sonnet 4.5 | Iran-Regime-Change-Forecast-1004 | <1% / 1-3% / 4-9% at +1wk/+1mo/+1yr. IRGC institutional resilience exceeds military degradation; opposition fragmentation is binding constraint |
| 2 | 09/04/2026 | Iran-Israel-US ceasefire durability | 38 | 6 | Claude Sonnet 4.5 | Iran-Israel-Ceasefire-Prediction-090426 | 22% chance ceasefire holds at +72h (simulation: 28% -- 6-point convergence between independent stages) |
| 1 | 24/03/2026 | Iran-Israel-US conflict trajectory (Day 25) | -- | 6 | -- | Iran-Israel-Conflict-Trajectory-240326 | 5/5 high-confidence predictions validated; ceasefire (April 8) was not anticipated |
Prediction Runs — Geopol Forecast Council
| # | Date | Topic | Panel | Horizons | Head / Author | Run Directory | Key Finding |
|---|---|---|---|---|---|---|---|
| C1 | 18/04/2026 | Iran-Israel-US conflict evolution | GLM 5.1 · DeepSeek v3.2 · Gemini 3 Flash · Claude Sonnet 4.6 · Kimi k2.5 | 24h / 1w / 1m | Claude Sonnet 4.6 / Claude Sonnet 4.6 | 2026-04-18_235440 (main PDF · full PDF) | Panel confidence range 0.31–0.52 at 24h; escalatory predictions outweighed conciliatory at 24h. Modal views: nominal Lebanon ceasefire deteriorating, Hormuz closed, Hormuz/proxy-violence risks dominating short horizon |
Accuracy Rubric
All predictions are graded on a standard scale. The /validate-predictions skill uses Tavily to search for real-world outcomes and applies this rubric automatically.
| Grade | Score | Criteria |
|---|---|---|
| Correct | 1.0 | Core prediction matched reality in direction and approximate magnitude/timing |
| Largely Correct | 0.75 | Direction right, magnitude or timing off by a modest margin |
| Partially Correct | 0.5 | General direction right but significantly off on timing, magnitude, or mechanism |
| Incorrect | 0.0 | Prediction contradicted by what actually happened |
| Not Yet Testable | — | Window still open or insufficient data to assess |
Scoring rules: Direction is scored first, then adjusted for timing and magnitude. A >2x timing error drops Correct to Largely Correct or below. Binary predictions ("X won't happen") are scored on the stated claim, not the probability. Wire services (Reuters, AP) take precedence over opinion sources.
Accuracy Tracking
Run 1 — Iran-Israel-US Conflict Trajectory (24/03/2026)
Run Score: 0.75 (5 Correct, 1 Incorrect out of 6 graded)
| # | Window | Prediction | Outcome | Grade | Score |
|---|---|---|---|---|---|
| 1.1 | 24h-1wk | Israeli operations continue at full intensity | IDF continued strikes through to April 8 ceasefire | Correct | 1.0 |
| 1.2 | 24h-1wk | Iranian proxy retaliations continue | Hezbollah maintained 55+ attacks/day through the period | Correct | 1.0 |
| 1.3 | 1mo | Iranian ballistic missile capabilities degraded 50%+ | Coalition struck ~330/470 known launchers (70%) | Correct | 1.0 |
| 1.4 | 1mo | IDF maintains/extends Lebanon buffer zone to Litani | IDF reached Litani River by March 24 | Correct | 1.0 |
| 1.5 | 1wk | March 27 deadline fails (no deal reached) | No deal reached; war continued until April 8 ceasefire | Correct | 1.0 |
| 1.6 | 1mo | No ceasefire holds before March 27 | Ceasefire reached April 8 — model assessed this as improbable | Incorrect | 0.0 |
Run 2 — Iran-Israel-US Ceasefire Durability (09/04/2026)
Run Score: TBD (0 of 1 predictions graded)
| # | Window | Prediction | Outcome | Grade | Score |
|---|---|---|---|---|---|
| 2.1 | +72h | 22% chance ceasefire holds at 72h (simulation: 28%) | Not yet assessed | Not Yet Testable | — |
Pipeline Overview
Stage 0: Gather fresh data (Tavily news search + ISW/RSS feeds)
Freeze into identical world state for all participants
|
Stage A: Snowglobe-style actor simulation
N actors x T timesteps, referee-narrated world state
Each actor commits privately and independently
|
Stage B: LLM Council 6-lens analytical panel
Independent answers --> blind peer review --> chairman synthesis
Sees: prompt + fresh data + Stage A simulation summary
|
Output: Chairman report, per-lens answers, cross-reviews,
simulation transcript, executive PDF, archival PDF
What makes the convergence interesting
Stages A and B are completely independent analytical processes:
- Stage A simulates actors making decisions in a game-theoretic loop -- it produces emergent outcomes from 38 agents reasoning from their own persona
- Stage B runs six analytical lenses through structured deliberation -- it produces calibrated probabilities from expert-style reasoning
Neither stage has access to the other's reasoning during execution. When they converge on similar probability estimates (as in the 09/04/2026 run where the simulation gave 28% and the council gave 22% for the 72-hour window), it suggests the pipeline is surfacing genuine signal rather than averaging noise.
Related Repositories
- Geopol-Forecaster -- the full (expensive) two-stage pipeline source code
- Geopol-Forecast-Council -- the lean council-only spin-off
- Geopol-Forecaster-Planning -- design docs and planning
- AI-Geopol-Projects -- curated list of AI geopolitical simulation projects
- Geopolitical-And-OSINT-Index -- broader OSINT and geopolitical analysis index
Author
Daniel Rosehill danielrosehill.com