Step 3000

<ROLE_AND_TASK>
你是一位验证规划专家。你的职责是为给定任务定义 evidence landmarks — 一组可通过屏幕截图独立确认的视觉特征，用于在任务执行后判断任务是否成功完成。

任务：操作 Ubuntu Linux，来达成目标: Given a partial calendar, please highlight all the weekends (Satureday & Sunday) by setting the cell background as red (#ff0000). Finish the work and don't touch irrelevant regions, even if they are blank.

你需要根据任务要求和已知信息，输出一组 evidence landmarks。

规则：
- 每个 landmark 必须是**可在截图中直接观察到的视觉特征**，如特定单元格的值、界面元素的状态、弹窗文字等。
- landmark 之间应相互独立，各自验证任务的不同方面。
- 所有 landmark 的组合应足以高置信度地证明任务已完成。
- 数量尽量少，但覆盖任务的所有关键变更点。不要列举未变更的内容。
- 避免模糊表述（如"文件已保存"），使用具体可观测的描述（如"标题栏不含未保存标记 *"）。

示例：
任务：在 LibreOffice Calc 创建 Sheet2, 汇总 Sheet1 中每月 API 调用量数据. A 列为 Month, B 列为 Total
背景信息：
- A 列为月份列, 包含 JAN-OCT 的数据
- B-G 为不同 API 的调用量数据列
evidence landmarks：
- "新增的 Sheet2 标签页在界面底部可见"
- "Sheet2 中 A7 单元格显示为 'JUN'"
- "Sheet2 中 A12 单元格为空"
- "Sheet2 中 B4 单元格的求和公式为 '=SUM(Sheet1.B4:G4)'"

</ROLE_AND_TASK>

<OUTPUT_SCHEMA>

调用 `define_evidence_landmarks`：
```json
{
    "evidence_landmarks": [
        str  // 可通过截图独立确认的视觉特征点
    ]
}
```

</OUTPUT_SCHEMA>


<ADDITIONAL_INFORMATION>
## Check if there are additional month columns with date data to the right of column F (October)
**回答**: No additional month columns visible to the right of column F. Columns G onwards appear empty.

**Context**: The calendar only contains data for June (B), July (C), August (D), September (E), and October (F). No need to check beyond column F.


## Reveal and record all date values in column F (October) for rows 12-33 that are currently displaying as '###' due to insufficient column width
**回答**: Column F October dates from rows 12-33 are currently hidden as '###'. Need to widen column F to reveal these dates.

**Context**: October column (F) has dates from 10/1/2022 to 10/31/2022. Rows 12-33 are displaying as '###' indicating the column needs to be widened to see the full dates.


## Identify the specific cell addresses containing weekend dates (Saturdays and Sundays) for each month: June (column B), July (column C), August (column D), September (column E), and October (column F)
**回答**: Weekend dates need to be identified by checking each date. From visible data: June 2022 starts on Wednesday (6/1/2022). Weekends would be Saturdays and Sundays. Need to calculate or verify each weekend date for all months.

**Context**: Dates are in M/D/YYYY format. To identify weekends, need to know which dates fall on Saturday or Sunday. June 1, 2022 was a Wednesday. This pattern continues through the months.


## Verify the last row number containing date data for each month column to confirm the complete vertical range of the calendar
**回答**: June: row 32 (6/30/2022), July: row 33 (7/31/2022), August: row 33 (8/31/2022), September: row 32 (9/30/2022), October: row 33 (estimated, need to verify)

**Context**: June has 30 days (ends row 32), July has 31 days (ends row 33), August has 31 days (ends row 33), September has 30 days (ends row 32), October has 31 days (should end row 33). Data starts at row 3.

<ADDITIONAL_INFORMATION>