Unverified50% confidenceFactExact time
All of Timestral's median forecasts for the 24 months were below the actual values, with a constant deviation of -44.93.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/20/2026
First Seen
Valid until: 11/3/2026
Sources
Related Entities
Related Claims
UnverifiedIn 24-month forecasts, Timestral's 80% quantile interval had an actual coverage of only 16.7%, at 25% for the first 12 months and dropping to 8.3% for the last 12 months.76% similarUnverifiedOn the first day tested against real data, three models including TabPFN ranked the cleanliness of all 24 hours of the day in reverse order, with Spearman coefficients all negative.65% similarUnverifiedThe Timestral-209M model reads up to 32,768 historical steps, predicts up to 1,024 steps per forward pass, and outputs 21 quantiles (0.01 to 0.99) per prediction.65% similarUnverifiedTheoretically reliable clustered standard error estimation typically requires at least 30–50 clusters, whereas this study has only 19 independent time units, making the sample size relatively small.63% similarUnverifiedWhen the 35B model switched to a wider context, its pass rate plummeted to 46/90, with 43 responses truncated due to a fixed output budget.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1072905API
curl https://kongchang.com/api/v1/knowledge/claims/1072905MCP
get_claim(id=1072905)