来源:paper:PDF pp.18–19, §B.5 and Table 5
这条 Claim 暂无已发布的不可变 Assessment。
这条 Claim 暂无关联执行。
已评估 0/36 项
保留同一结论下的完整结果组。已有评估排在前面;单项判断不替代整组结论。展开行查看条件、来源与历次证据。
| 指标与条件 | 论文报告 | 最近可用实测 | 证据判断 |
|---|---|---|---|
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: AIME25 · fixedDraftLength: 5 · refreshLayerPosition: 0 | 61.4% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: AIME25 · fixedDraftLength: 5 · refreshLayerPosition: N/4 | 82.1% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: AIME25 · fixedDraftLength: 5 · refreshLayerPosition: N/2 | 84.9% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: AIME25 · fixedDraftLength: 5 · refreshLayerPosition: 3N/4 | 87.5% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: AIME25 · fixedDraftLength: 5 · refreshLayerPosition: N-2 | 85.6% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: AIME25 · fixedDraftLength: 5 · refreshLayerPosition: N-1 | 82.6% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: LB[16k-18k] · fixedDraftLength: 5 · refreshLayerPosition: 0 | 47.8% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: LB[16k-18k] · fixedDraftLength: 5 · refreshLayerPosition: N/4 | 81.5% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: LB[16k-18k] · fixedDraftLength: 5 · refreshLayerPosition: N/2 | 92.7% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: LB[16k-18k] · fixedDraftLength: 5 · refreshLayerPosition: 3N/4 | 94.7% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: LB[16k-18k] · fixedDraftLength: 5 · refreshLayerPosition: N-2 | 93.4% | — | 尚未评估 |
model: Qwen3-1.7B (N=28) · method: ASPIRE-Fixed · dataset: LB[16k-18k] · fixedDraftLength: 5 · refreshLayerPosition: N-1 | 76.8% | — | 尚未评估 |