| Date | Predicted | Market Price | Confidence |
|---|---|---|---|
| 2026-05-02 | 4% | 11% | 70% |
| 2026-04-22 | 2% | 11% | 78% |
| Tool | Status | Time | Items | Summary |
|---|---|---|---|---|
| wikipedia_lookup | OK | 2.1s | - | |
| article_search | OK | 0.6s | - | |
| web_search | OK | 66.7s | - | |
| kalshi_data | OK | 2.3s | - | |
| kalshi_orderbook | OK | 0.2s | - | |
| code_execution | OK | 0.0s | - |
| # | Strength | Credibility | Direction | Source | Claim | Priced In |
|---|---|---|---|---|---|---|
| 1 | STRONG | 85 | ↓ DOWN | code_execution | UCERF3-based Poisson calculation yields a ~0.64% probability of M8.0+ in California over the ~2.64-year window (May 2026–Dec 2028), with a range of 0.36%–1.12% depending on the base rate assumption used. | Yes |
| 2 | STRONG | 80 | ↓ DOWN | wikipedia_lookup | The 1906 San Francisco earthquake is estimated at Mw 7.9 (not 8.0+), suggesting California has had zero confirmed M8.0+ events in recorded instrumental history, consistent with a very long recurrence interval for such events. | Yes |
| 3 | MODERATE | 75 | ↓ DOWN | wikipedia_lookup | The San Andreas Fault is a ~750-mile continental strike-slip fault with slip rates of 0.79–1.38 inches/year; its southern locked segment is capable of ~M8.2, but recurrence intervals are on the order of centuries. | Yes |
| 4 | MODERATE | 45 | ↑ UP | kalshi_data | The Kalshi market for M8.0+ in California before 2035 (a ~9-year window) is priced at 31%, implying roughly 4% per year or ~10% over 2.6 years — substantially higher than the UCERF3 Poisson estimate of 0.64%. | Yes |
| 5 | MODERATE | 65 | NEUTRAL | web_search | Multiple earthquake swarms occurred in California in late 2025–early 2026, including a prolonged tectonic swarm near San Ramon (Nov 2025–Feb 2026+) with ~90 small quakes in November and a M3.8 event, and a Coachella Valley swarm near the southern San Andreas with a M4.9 mainshock in January 2026. | Yes |
| 6 | STRONG | 72 | ↓ DOWN | web_search | Scientists explicitly state that swarms can only slightly increase the statistical likelihood of a larger earthquake by a very small amount, and California's past swarms have not reliably preceded M8+ events. | Yes |
| 7 | STRONG | 70 | ↓ DOWN | web_search | San Ramon swarms are historically recurrent (occurring in 1970, 1976, 1990, 2002, 2003, 2015, 2018, and now 2025), with no volcanic component, confirming these are routine tectonic swarms rather than anomalous precursors. | Yes |
| 8 | MODERATE | 68 | ↓ DOWN | article_search | Recent California seismic events in 2025–2026 are all in the M3–M5 range (M4.6 near Santa Cruz, M4.0 near Santa Rosa, M4.9 near Indio), which is normal background seismicity — none approaching the M6–7+ threshold that might more meaningfully precede an M8+ event. | Yes |
| 9 | MODERATE | 70 | ↑ UP | wikipedia_lookup | The San Andreas Fault's southern locked segment (Coachella/San Bernardino) has not ruptured in ~330 years and is considered overdue for a major earthquake, potentially up to M8.2, though 'overdue' is not a precise predictor of imminent occurrence. | Yes |
| 10 | MODERATE | 60 | ↓ DOWN | article_search | No recent articles report any USGS or scientific advisories, geodetic anomalies, or fault-locking changes that would signal an elevated near-term probability of M8+ rupture on California fault systems. | Yes |
| 11 | MODERATE | 40 | ↑ UP | kalshi_data | The Kalshi market for M8.0+ in California before 2028 is priced at 16%, which is dramatically higher (~25x) than the UCERF3 Poisson base rate of ~0.64%, suggesting significant market overpricing or resolution criteria ambiguity. | Yes |
| 12 | MODERATE | 55 | NEUTRAL | kalshi_orderbook | The orderbook shows very wide spread ($0.01 bid vs $0.99 implied ask, spread of $0.98) despite high nominal depth of 14,068 contracts, suggesting low genuine two-sided liquidity and poor price discovery — market price of 16% should be treated with low confidence. | Yes |