Unverified50% confidenceBenchmarkExact time
Timestral'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.
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 0.49.78% similarUnverifiedAfter re-running with archived forecast data, the MASE was 0.66, only a slight improvement over the original 0.71.67% similarUnverifiedAfter introducing representational transformations, orbit accuracy dropped to 0.848–0.981 and orbit invariance dropped to 0.851–0.981.62% similarUnverifiedAfter the first round of fine-tuning, the number of unseen everyday commands the model directly allowed dropped from 25/50 to 23/50, incorrectly flagging ordinary operations such as git status and mkdir -p src/utils as requiring confirmation.60% similarUnverifiedIn the prompt-injection defense task (N=250), System 1 models with 4B parameters or more achieve an AUROC of 0.988 to 0.998, a recall of up to 95.2%, and a 0.0% false positive rate at 48 to 60 milliseconds of latency.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1156098API
curl https://kongchang.com/api/v1/knowledge/claims/1156098MCP
get_claim(id=1156098)