Compound Fork — Energy / grid × Robotaxi
Each cell = a joint scenario "Both branches fire". Cell intensity = total |Δ| across the 200 highest-conviction tradeable predictions vs their unconditional posterior. Joint probabilities approximated via log-odds combination (assumes conditional independence given the prediction — coarse but bounded). Click a cell to drill into the dominant single-fork view.
Pick two fork families
| Energy / grid ↓ × Robotaxi → | ROBOTAXI_TESLA_2026 prior 40% | ROBOTAXI_NATIONWIDE_2028 prior 45% | ROBOTAXI_MASS_2030 prior 30% | ROBOTAXI_DELAYED prior 20% |
|---|---|---|---|---|
GRID_50GW_2027 prior 40% | 123 claims · Σ|Δ| 15.00 | 123 claims · Σ|Δ| 15.07 | 119 claims · Σ|Δ| 14.64 | 123 claims · Σ|Δ| 15.08 |
GRID_50GW_2029 prior 50% | 126 claims · Σ|Δ| 15.20 | 126 claims · Σ|Δ| 15.26 | 122 claims · Σ|Δ| 14.84 | 126 claims · Σ|Δ| 15.28 |
GRID_50GW_DELAYED prior 10% | 124 claims · Σ|Δ| 15.09 | 124 claims · Σ|Δ| 15.16 | 120 claims · Σ|Δ| 14.73 | 124 claims · Σ|Δ| 15.17 |
Method note
Joint conditional probability is approximated via log-odds combination: logit(P(pred|A,B)) ≈ logit(P(pred|A)) + logit(P(pred|B)) − logit(P(pred)). This is the closed-form Bayesian update assuming A and B are conditionally independent given the prediction. It's correct when the two scenarios act on the prediction through different causal paths; it's pessimistic when they overlap. The exact joint requires running the Gibbs sampler with both scenarios clamped, which would be N×M=16 sampling runs (~12 minutes per refresh) instead of N+M=8 — a 2× cost for higher fidelity.