explore-run

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

explore-run

When to apply

适用场景

When the researcher explicitly authorizes exploratory runs.
When the task is a small-subset validation, short-cycle training probe, batch sweep, idle-GPU search, or quick transfer-learning trial.
When the output should rank candidate runs rather than certify trusted success.

当研究人员明确授权探索性运行时。
当任务为小子集验证、短周期训练探测、批量调参扫描、闲置GPU搜索或快速迁移学习试验时。
当输出用于对候选运行进行排名而非验证可信成功结果时。

When not to apply

不适用场景

When the user wants trusted training execution or conservative verification.
When there is no explicit exploratory authorization.
When the task is repository setup, intake, or debugging.

当用户需要可信训练执行或保守验证时。
当没有明确的探索性授权时。
当任务为仓库搭建、数据导入或调试时。

Clear boundaries

明确边界

This skill owns exploratory execution planning and summary only.
Use
```
ai-research-explore
```
instead when the task spans both current_research coordination and exploratory code changes.
It may hand off actual command execution to
```
minimal-run-and-audit
```
or
```
run-train
```
.
It should keep experiment state isolated from the trusted baseline.
It should prefer small-subset and short-cycle checks before heavier exploratory runs.

本技能仅负责探索性执行的规划与结果汇总。
当任务同时涉及
```
current_research
```
协调和探索性代码变更时，请使用
```
ai-research-explore
```
替代。
可将实际命令执行任务移交至
```
minimal-run-and-audit
```
或
```
run-train
```
。
应将实验状态与可信基线隔离。
在进行更繁重的探索性运行前，优先选择小子集和短周期检查。

Ranking Semantics

排名语义

Pre-execution candidate selection uses three factors:
```
cost
```
,
```
success_rate
```
, and
```
expected_gain
```
.
Default weights should stay conservative unless the researcher explicitly provides
```
selection_weights
```
.
Budget pruning still applies after scoring through
```
max_variants
```
and
```
max_short_cycle_runs
```
.
If runs are executed later, downstream ranking should switch to real execution evidence, not stay purely heuristic.

执行前的候选选择基于三个因素：
```
cost
```
（成本）、
```
success_rate
```
（成功率）和
```
expected_gain
```
（预期收益）。
除非研究人员明确提供
```
selection_weights
```
（选择权重），否则默认权重应保持保守。
评分后仍需通过
```
max_variants
```
（最大变体数）和
```
max_short_cycle_runs
```
（最大短周期运行数）进行预算裁剪。
如果后续执行了运行任务，下游排名应切换为基于实际执行证据，而非纯启发式方法。

Variant Spec Hints

变体规格提示

Use
```
variant_axes
```
to define the candidate dimension grid.
Use
```
subset_sizes
```
and
```
short_run_steps
```
to express exploratory run scale.

Use

selection_weights

to rebalance

cost

success_rate

, and

expected_gain

Use
```
primary_metric
```
and
```
metric_goal
```
so downstream ranking can order executed candidates consistently.

使用
```
variant_axes
```
定义候选维度网格。
使用
```
subset_sizes
```
和
```
short_run_steps
```
指定探索性运行的规模。

使用

selection_weights

重新平衡

cost

、

success_rate

和

expected_gain

的权重。

使用
```
primary_metric
```
（主指标）和
```
metric_goal
```
（指标目标），以便下游排名能一致地对已执行的候选进行排序。

Output expectations

输出要求

```
explore_outputs/CHANGESET.md
```
```
explore_outputs/TOP_RUNS.md
```
```
explore_outputs/status.json
```

```
explore_outputs/CHANGESET.md
```
```
explore_outputs/TOP_RUNS.md
```
```
explore_outputs/status.json
```

Notes

注意事项

Use

references/execution-policy.md

../../references/explore-variant-spec.md

scripts/plan_variants.py

, and

scripts/write_outputs.py

请参考

references/execution-policy.md

、

../../references/explore-variant-spec.md

、

scripts/plan_variants.py

和

scripts/write_outputs.py

文件。