Unverified50% confidenceCautionExact time
Boundary condition of TTSP: when the base policy's coverage of correct answers is close to zero, TTSP's gains no longer hold.
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAs verifier strength weakens, the performance gap between TTSP and the strongest baseline instead widens.70% similarVerifiedThe floating-point operation count of prefill grows approximately quadratically with input length, and is therefore the main source of TTFT (time to first token).61% similarUnverified传统混合部署中Prefill阶段的大批量计算会阻塞Decode阶段的token生成,导致TTFT波动剧烈61% similarUnverifiedTTL configuration requires a trade-off: too short may allow legitimate retries to go unblocked, while too long will prevent intentional repeated operations by users61% similarUnverifiedWith 8 concurrent requests each generating 128 output tokens, the single-flight strategy (releasing when the request completes) reduced both average TTFT and the completion latency of the slowest request compared with independent execution; but with only 2 requests, average TTFT was actually worse than independent execution.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1141628API
curl https://kongchang.com/api/v1/knowledge/claims/1141628MCP
get_claim(id=1141628)