Compound Fork — Humanoid deployment × 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
| Humanoid deployment ↓ × Robotaxi → | ROBOTAXI_TESLA_2026 prior 40% | ROBOTAXI_NATIONWIDE_2028 prior 45% | ROBOTAXI_MASS_2030 prior 30% | ROBOTAXI_DELAYED prior 20% |
|---|---|---|---|---|
HUMANOID_FACTORY_2026 prior 40% | 126 claims · Σ|Δ| 15.55 | 126 claims · Σ|Δ| 15.62 | 122 claims · Σ|Δ| 15.19 | 126 claims · Σ|Δ| 15.63 |
HUMANOID_ENTERPRISE_2028 prior 50% | 127 claims · Σ|Δ| 15.51 | 127 claims · Σ|Δ| 15.58 | 123 claims · Σ|Δ| 15.15 | 127 claims · Σ|Δ| 15.59 |
HUMANOID_CONSUMER_2030 prior 20% | 125 claims · Σ|Δ| 15.60 | 125 claims · Σ|Δ| 15.67 | 121 claims · Σ|Δ| 15.24 | 125 claims · Σ|Δ| 15.68 |
HUMANOID_MASS_2033 prior 10% | 125 claims · Σ|Δ| 15.46 | 125 claims · Σ|Δ| 15.52 | 121 claims · Σ|Δ| 15.09 | 125 claims · Σ|Δ| 15.53 |
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.