优先展示覆盖情况与实测结果；需要审计时再打开运行记录和技术细节。
0/6
条结论获得证据支持
0
获得支持
0
受到挑战或冲突
0
遭到反驳
0
无法判定
6
尚未评估
每一行是一条真实执行记录；命令、日志、哈希和签名都收纳在详情中。
尚无复现运行
论文中的实验方案开始执行后，运行记录会显示在这里。
逐个实验展示当前执行状态、阻塞原因、恢复动作和证据去向；技术执行与科研结论始终分开。
执行成功不等于论文结论成立
目标状态回答平台有没有跑完；右侧科学结论只由不可变证据和 Assessment 决定。资源不足或平台故障不会被写成反驳论文的科研结论。
当前任务创建于目标级记录上线之前。下方状态来自历史任务的保守投影，不会伪造运行尝试、资源决策或证据关系。
The architecture ablation table reports that removing ContextNorm fails to converge, while additive fusion, auxiliary-loss budget control, and removing P-mask reduce the reported recall average relative to LoGo.
Optional independent architecture-ablation reconstruction
实验方案已经存在，但当前处理任务没有对应的执行目标。
On the paper's 32k-checkpoint short-context recall aggregate, LoGo is reported as competitive with the other methods and scores 57.65 percentage points across six recall tasks.
Optional independent short-context recall reconstruction
实验方案已经存在，但当前处理任务没有对应的执行目标。
In the controlled 1.5B comparison, LoGo reports the best language-modeling loss and Lambada perplexity among the listed full-attention and matched-budget static hybrid variants, with a higher commonsense-reasoning average than the full Transformer.
Optional independent matched-budget reconstruction
实验方案已经存在，但当前处理任务没有对应的执行目标。
LoGo preserves the reported scaling behavior of full-attention Transformers from 200M through 3.3B parameters, matching or improving the baseline on the listed language-modeling and commonsense metrics.
Optional independent scaling-direction reconstruction
实验方案已经存在，但当前处理任务没有对应的执行目标。
The paper reports that its query-sparse Triton kernel reaches a 1.99x forward-plus-backward speedup over the dense Triton baseline at 64k sequence length and a 0.5 attention budget.
这条结论尚无可执行实验方案。
LoGo reports higher average needle-style RULER recall than the three comparison paradigms at both the 32k and 128k context-extension stages, with averages of 83.0 and 65.4 percentage points.
Optional independent long-range recall reconstruction
实验方案已经存在，但当前处理任务没有对应的执行目标。
