Compound Fork — $1T+ IPO × Recession
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
| $1T+ IPO ↓ × Recession → | RECESSION_2026 prior 20% | RECESSION_2027 prior 30% | RECESSION_2028 prior 30% | NO_RECESSION_5Y prior 20% |
|---|---|---|---|---|
IPO_TRILLION_2026 prior 25% | 136 claims · Σ|Δ| 19.15 | 137 claims · Σ|Δ| 19.23 | 137 claims · Σ|Δ| 19.23 | 138 claims · Σ|Δ| 19.28 |
IPO_TRILLION_2027 prior 40% | 136 claims · Σ|Δ| 19.17 | 137 claims · Σ|Δ| 19.25 | 137 claims · Σ|Δ| 19.25 | 138 claims · Σ|Δ| 19.30 |
IPO_TRILLION_2028 prior 25% | 136 claims · Σ|Δ| 19.34 | 137 claims · Σ|Δ| 19.42 | 137 claims · Σ|Δ| 19.42 | 138 claims · Σ|Δ| 19.48 |
IPO_TRILLION_NONE_5Y prior 10% | 136 claims · Σ|Δ| 19.31 | 137 claims · Σ|Δ| 19.39 | 137 claims · Σ|Δ| 19.39 | 138 claims · Σ|Δ| 19.44 |
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.