Unverified50% confidenceBenchmarkExact time
On BrowseComp-Plus, attribution-guided PPO is 4.1 percentage points higher than PPO using only outcome rewards.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedVASPO improves average accuracy by 2.59 percentage points over PPO on Qwen3-4B and by 1.81 percentage points on OLMo3-7B.64% similarUnverifiedPiPMRE achieves an average improvement of 4.4 percentage points in precision over the previous state-of-the-art methods on two public datasets.59% similarUnverifiedOn the avg@16 metric for math tasks, BranchOPD improves over Vanilla OPD by 18.55 percentage points.58% similarUnverifiedAfter re-evaluating with non-overlapping anchors, the net advantage instead grew from +4.1pp to +5.5pp, but significance dropped from 2.4 standard errors to 1.4 standard errors; the inflation factor is about 2.4x, exactly equal to sqrt(912/163).57% similarUnverifiedNVFP4量化方案相比BF16基线实现了1.5倍的推理加速，同时在top-1准确率上保留了92%到97%的水平56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073980API
curl https://kongchang.com/api/v1/knowledge/claims/1073980MCP
get_claim(id=1073980)