Table 9 reports per-method batch size, tokens committed per verification, acceptance rate, average generated length, and homogeneous draft/verify step timings for LB-v2[30k-40k] on all three models.

报告指标与观测值

这条 Claim 暂无已发布的不可变 Assessment。

这条 Claim 暂无关联执行。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]	18 requests	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]	13.58 tokens/verification	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]	96.3%	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]	1,805 tokens/request	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]	5.84 ms/forward step	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB-v2[30k-40k]	18 requests	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB-v2[30k-40k]	5.85 tokens/verification	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB-v2[30k-40k]	97%	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB-v2[30k-40k]	1,816 tokens/request	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB-v2[30k-40k]	6.18 ms/forward step	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB-v2[30k-40k]	28.2 ms/forward step	—	尚未评估
model: Qwen3-1.7B · method: Vegas · dataset: LB-v2[30k-40k]	17 requests	—	尚未评估

指标与条件

论文报告

最近可用实测

证据判断

model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]

18 requests

—

尚未评估

model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]

13.58 tokens/verification

—

尚未评估

model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]

96.3%

—

尚未评估

model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]

1,805 tokens/request

—

尚未评估

model: Qwen3-1.7B · method: ASPIRE · dataset: LB-v2[30k-40k]

5.84 ms/forward step

—

尚未评估