文档:分析结论里的占比、变化率由系统按百分数显示,比率的变化按百分点,写作者照常引用、不用自己写换算(写了照他的)。分析能力、证据与出具两份文档的中英各补一句,标题层级不动,check-docs 0 问题

This commit is contained in:
ThearchyHelios
2026-10-21 15:55:41 +00:00
parent d3ba6de882
commit 851506761c
4 changed files with 4 additions and 2 deletions
+1
View File
@@ -143,6 +143,7 @@ The built-in template 11, Anomaly Analysis (Traceable), is built this way: fetch
``` ```
- The Analysis Conclusions section of the writing catalog lists each conclusion's number, verdict phrase, named values, the top 10 segments of its result table, and caveats or the reason it couldn't be done. - The Analysis Conclusions section of the writing catalog lists each conclusion's number, verdict phrase, named values, the top 10 segments of its result table, and caveats or the reason it couldn't be done.
- The system shows shares and change rates in analysis conclusions as percentages (`[[a:A1.top_share]]` and `[[v:A1.r0.share]]` render as 62.0%), and changes in rates in percentage points (1.2 percentage points); writers cite them as usual and do not add a conversion. A conversion the writer does write is kept.
- Conclusions from analysis cards can always be cited. In formal issuance at the governed level, analyses an agent ran on the spot with analysis tools follow the same rule as the cells it queried: they can be cited only when the issuance contract turns on Cell Citations (they can still serve as the basis at the end of a sentence). - Conclusions from analysis cards can always be cited. In formal issuance at the governed level, analyses an agent ran on the spot with analysis tools follow the same rule as the cells it queried: they can be cited only when the issuance contract turns on Cell Citations (they can still serve as the basis at the end of a sentence).
- The measure name in a verdict phrase comes from the agent or the template; the system first strips digits, percent signs, units, and citation markers from it and cuts it to 20 characters, so text written by the system never smuggles in numbers written by the model. - The measure name in a verdict phrase comes from the agent or the template; the system first strips digits, percent signs, units, and citation markers from it and cuts it to 20 characters, so text written by the system never smuggles in numbers written by the model.
+1 -1
View File
@@ -98,7 +98,7 @@ In the report-writer node (`report`), the model writes only citation markers, an
[[see:m:gmv,Q1,A1]] basis of a claim sentence; attached at the end of the sentence, not rendered [[see:m:gmv,Q1,A1]] basis of a claim sentence; attached at the end of the sentence, not rendered
``` ```
Analysis conclusions are numbered A1, A2, … in ledger order, and the writing catalog has a separate Analysis Conclusions section. Judgment words such as "mainly from", "unusual", or "rising steadily" must cite a matching analysis conclusion and agree with its verdict; see [Analysis claim check](analysis.md#analysis-claim-check). Analysis conclusions are numbered A1, A2, … in ledger order, and the writing catalog has a separate Analysis Conclusions section. The system shows shares and change rates in analysis conclusions as percentages (`[[a:A1.top_share]]` renders as 62.0%), and changes in rates in percentage points (1.2 percentage points); writers cite them as usual and do not add a conversion. Judgment words such as "mainly from", "unusual", or "rising steadily" must cite a matching analysis conclusion and agree with its verdict; see [Analysis claim check](analysis.md#analysis-claim-check).
### Handling violations ### Handling violations
+1
View File
@@ -143,6 +143,7 @@
``` ```
- 写作目录里「分析结论」一段列出每份结论的编号、判定语、具名的数、结果表的前 10 段、附带说明或算不了的原因。 - 写作目录里「分析结论」一段列出每份结论的编号、判定语、具名的数、结果表的前 10 段、附带说明或算不了的原因。
- 分析结论里的占比、变化率由系统按百分数显示(`[[a:A1.top_share]]`、`[[v:A1.r0.share]]` 写出来是 62.0%),比率的变化按百分点(1.2 个百分点),写作者照常引用、不用自己写换算;自己写了换算的照他的。
- 分析卡的结论总能引用。受管级别的正式出具里,Agent 用分析工具现场做的分析和它查的格同一个规矩:出具契约开了「单元格引用」才能引用(句末依据照样能挂)。 - 分析卡的结论总能引用。受管级别的正式出具里,Agent 用分析工具现场做的分析和它查的格同一个规矩:出具契约开了「单元格引用」才能引用(句末依据照样能挂)。
- 判定语里的度量叫法是 Agent 或模板给的,系统先去掉里面的数字、百分号、单位和引用标记,截到 20 字以内:系统写的字里不会夹带模型写的数。 - 判定语里的度量叫法是 Agent 或模板给的,系统先去掉里面的数字、百分号、单位和引用标记,截到 20 字以内:系统写的字里不会夹带模型写的数。
+1 -1
View File
@@ -98,7 +98,7 @@ flowchart LR
[[see:m:gmv,Q1,A1]] 结论句的依据,挂在句末,不渲染 [[see:m:gmv,Q1,A1]] 结论句的依据,挂在句末,不渲染
``` ```
分析结论按台账先后编成 A1、A2……,写作目录里另有一段「分析结论」。「主要来自」「异常」「持续上升」这类判断词要挂对应的分析结论、判定对得上,见[分析说法核对](analysis.md#分析说法核对)。 分析结论按台账先后编成 A1、A2……,写作目录里另有一段「分析结论」。分析结论里的占比、变化率由系统按百分数显示(`[[a:A1.top_share]]` 写出来是 62.0%),比率的变化按百分点(1.2 个百分点),写作者照常引用、不用自己写换算。「主要来自」「异常」「持续上升」这类判断词要挂对应的分析结论、判定对得上,见[分析说法核对](analysis.md#分析说法核对)。
### 违规怎么处理 ### 违规怎么处理