Unverified50% confidenceBenchmarkExact time
On six benchmark datasets with a 90-minute forecast horizon, GAS-PFN reduces MSE by an average of 34.0% relative to its closest PFN predecessor, TimePFN.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/28/2026
First Seen
Valid until: 1/26/2027
Sources
Related Entities
Related Claims
UnverifiedIn the same evaluation, GAS-PFN reduces MSE by an average of 27.7% relative to four recently industry-developed general zero-shot forecasters.80% similarUnverifiedComputing p95 from twelve samples actually lands between the 11th and 12th samples—essentially the second-slowest run—and is extremely unstable.64% similarUnverified量化推理从FP16降至FP8可将显存需求减半，从FP8降至FP4可进一步减半63% similarUnverifiedOn nonlinear designs beyond the prior range with p up to 500, SelectPFN's false discovery proportion was controlled at about 0.07.62% similarUnverifiedRLDS reduces wall-clock time per step on ScienceWorld by 10.9% compared to scalar GRPO, because long trajectories amortize the fixed overhead of reflection and scoring.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1105976API
curl https://kongchang.com/api/v1/knowledge/claims/1105976MCP
get_claim(id=1105976)