Compound Fork — Robotaxi × $1T+ IPO
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
| Robotaxi ↓ × $1T+ IPO → | IPO_TRILLION_2026 prior 25% | IPO_TRILLION_2027 prior 40% | IPO_TRILLION_2028 prior 25% | IPO_TRILLION_NONE_5Y prior 10% |
|---|---|---|---|---|
ROBOTAXI_TESLA_2026 prior 40% | 129 claims · Σ|Δ| 18.54 | 128 claims · Σ|Δ| 18.49 | 128 claims · Σ|Δ| 18.67 | 128 claims · Σ|Δ| 18.63 |
ROBOTAXI_NATIONWIDE_2028 prior 45% | 131 claims · Σ|Δ| 18.68 | 130 claims · Σ|Δ| 18.63 | 130 claims · Σ|Δ| 18.81 | 130 claims · Σ|Δ| 18.77 |
ROBOTAXI_MASS_2030 prior 30% | 127 claims · Σ|Δ| 18.30 | 126 claims · Σ|Δ| 18.25 | 126 claims · Σ|Δ| 18.42 | 126 claims · Σ|Δ| 18.39 |
ROBOTAXI_DELAYED prior 20% | 131 claims · Σ|Δ| 18.69 | 130 claims · Σ|Δ| 18.64 | 130 claims · Σ|Δ| 18.82 | 130 claims · Σ|Δ| 18.79 |
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.