Unverified50% confidenceBenchmarkExact time
Experiments were conducted on two mathematical reasoning benchmarks, AIME and HMMT, and ST-OPSD improves accuracy over the original OPSD and other intervention methods.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedExperiments on multiple benchmarks show that SpatialOPSD's average accuracy is higher than SFT and GRPO, and this advantage appears simultaneously on spatial tasks and out-of-distribution (OOD) datasets.67% similarUnverifiedExperiments show that the efficiency of neural scoring is on par with the exact likelihood ratio and scores tailored to specific applications.65% similarUnverifiedExperimental results on multiple reasoning benchmarks show that DPT surpasses previous parallel thinking methods, achieving state-of-the-art performance in baseline comparisons.63% similarUnverifiedThe study explicitly decomposes the approximation error into two parts—spectral truncation error and circuit approximation error—making the overall approximation rate a quantifiable and controllable result.63% similarUnverifiedNumerical experiments show that when handling non-smooth and heavy-tailed target distributions, the non-reversible versions exhibit faster sampling efficiency compared to their reversible counterparts.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102394API
curl https://kongchang.com/api/v1/knowledge/claims/1102394MCP
get_claim(id=1102394)