Unverified50% confidenceBenchmarkExact time
On the CVRP-100 benchmark, RELAGRAM's gaps relative to PyVRP are: 13.4% for greedy decoding, 9.8% for eight-fold symmetry augmentation, and 8.3% for 256-candidate search.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRELAGRAM is trained only on CVRP-100, yet generalizes zero-shot to CVRP-500 (15.6% gap under 256-candidate search) and CVRP-1000 (21.7% gap under 256-candidate search).77% similarVerifiedReAct's errors amplify in a chain: if the accuracy per step is p, the overall success rate after n steps is approximately p to the power of n; with a per-step accuracy of 95%, the overall success rate drops to approximately 59.9% after 10 steps and only 35.8% after 20 steps.65% similarUnverifiedWith the prompt unchanged, simply adjusting the thin direction encoding "who is endorsing" can shift compliance by 11 to 32 percentage points and close 55% to 61% of the gap between source and user.62% similarUnverified若单帧误检率为p，连续8帧独立误检的概率为p^8，即使单帧误检率高达10%，8帧连续误检概率也只有10^-862% similarUnverifiedThe combination of Pythia's first 5 layers plus RWKV's remaining 27 layers reduced the Transformer's KV cache by 84.4%, with no significant difference in accuracy compared to using RWKV alone.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1029528API
curl https://kongchang.com/api/v1/knowledge/claims/1029528MCP
get_claim(id=1029528)