Unverified50% confidenceFactExact time
After re-running with archived forecast data, the MASE was 0.66, only a slight improvement over the original 0.71.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/10/2026
First Seen
Valid until: 2/8/2027
Sources
Related Entities
Related Claims
UnverifiedTimestral still outperforms the original gradient boosting model in the corrected backtest: MASE 0.66 versus 0.71, but the improvement is far smaller than the initially reported 0.49.77% similarUnverifiedTimestral's MASE on GIFT-Eval is 0.658, close to the engineer's corrected 0.66, while the original leaked result of 0.49 deviates markedly.67% similarUnverifiedAll models averaged 0.91 on explicit memory updates but only 0.67 on implicit updates; Opus 5.5 and Gemini 3.1 Pro caught every implicit change, while gpt-oss-20b caught zero.65% similarUnverifiedThe framework achieved a precision of 0.82, a recall of 0.85, and an F1 score of 0.82.64% similarUnverifiedThe recommended starting alpha value is 0.10; a stronger alpha value does not mean better results, the degree of variation differs across seeds, and this method is not a universal improvement.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1156090API
curl https://kongchang.com/api/v1/knowledge/claims/1156090MCP
get_claim(id=1156090)