`包裹，如果长文可以用`
/
`划分，这里只有一小段，显然只适用`
`即可。 3. 特定元素处理：列表用`
- `，引用用`
`，代码用`
`，重要句子用``。 4. 核心铁律：保留原文所有信息，绝对不得增删改内容。 5. 不要输出`//`等文档级标签。 现在分析一下原文内容： "We present ICJ-Graph, a machine-readable resource connecting documents of the International Court of Justice (ICJ) to cited cases, legal provisions and United Nations resolutions. Court decisions, written pleadings and oral records form distinct document layers, preserving the distinction between the Court's reasoning and the parties' submissions. The collection contains 6,396 ICJ documents and 505 documents from other courts and legal bodies, together with 12,375 provisions and 20,291 UN resolutions. The data files contain text, metadata and embeddings. The accompanying pipeline lets users load the graph and generate embeddings for use in their own retrieval systems. To illustrate the resource's use, we evaluate five models on citation prediction for 199 decisions using documents available before each decision. Tools designed for citation research improve citation-prediction F1 over answering without tools for all five models across case, provision and resolution citations." 我需要对其进行信息提取与语义划分，看看能不能套用一些HTML标签。 第一句：“We present ICJ-Graph, a machine-readable resource connecting documents of the International Court of Justice (ICJ) to cited cases, legal provisions and United Nations resolutions.” 这是文章的核心论点和总起，介绍了ICJ-Graph。为了让标题醒目，我可以把“ICJ-Graph”提取出来用``加粗。 第二句：“Court decisions, written pleadings and oral records form distinct document layers, preserving the distinction between the Court's reasoning and the parties' submissions.” 这一句讲的是文档结构层次。包含三个并列的关键文档类型：“Court decisions”、“written pleadings”、“oral records”。作为排版工程师，遇到这种并列的名词短语，使用无序列表`- `会显得非常专业且结构清晰。同时，为了不破坏原有句子结构，这部分可以作为一段的开头。
第三句：“The collection contains 6,396 ICJ documents and 505 documents from other courts and legal bodies, together with 12,375 provisions and 20,291 UN resolutions.” 这一句是列举数据资源统计。有四个核心数据：6,396 ICJ documents, 505 documents from other courts and legal bodies, 12,375 provisions, 20,291 UN resolutions。同样地，将其拆分为列表，能让读者快速抓住海量数据的重点。
第四句：“The data files contain text, metadata and embeddings.” 讲数据格式，包含text, metadata, embeddings三项，也适合做成列表。
第五句：“The accompanying pipeline lets users load the graph and generate embeddings for use in their own retrieval systems.” 讲配套工作流的作用。里面提到“load the graph”、“generate embeddings”、“retrieval systems”，这几个词可以作为关键对象加粗，凸显出技术性。
第六句：“To illustrate the resource's use, we evaluate five models on citation prediction for 199 decisions using documents available before each decision.” 讲应用评估。可以把核心任务“citation prediction”加粗，强调研究的具体内容。
第七句：“Tools designed for citation research improve citation-prediction F1 over answering without tools for all five models across case, provision and resolution citations.” 这是最终结论。可以提取“improve citation-prediction F1”作为结果亮点进行加粗。
接下来把这些碎片化的分析拼装成符合HTML语法规则的代码块。
注意第二到第四句，原文都在讲数据的构成，可以放在一个大的`
`内，通过`
`换行来衔接上下文，避免语义断裂。而第一句作为独立段落，第五句到第七句也独立成段。 梳理一下最终结构： `We present ICJ-Graph, a machine-readable resource connecting documents of the International Court of Justice (ICJ) to cited cases, legal provisions and United Nations resolutions.
` `-
Court decisions, written pleadings and oral records form distinct document layers, preserving the distinction between the Court's reasoning and the parties' submissions. The collection contains:
- 6,396 ICJ documents
- 505 documents from other courts and legal bodies
- 12,375 provisions
- 20,291 UN resolutions
` 不，`
`不能用在`-
`后面来直接当做下一个`
- ...
- Court decisions, written pleadings and oral records form distinct document layers, preserving the distinction between the Court's reasoning and the parties' submissions. The collection contains 6,396 ICJ documents
- 505 documents from other courts and legal bodies
- 12,375 provisions
- 20,291 UN resolutions
- `包起来，那前半句怎么办？ 如果直接这样排版： `
-
Court decisions, written pleadings and oral records form distinct document layers, preserving the distinction between the Court's reasoning and the parties' submissions. The collection contains:
- 6,396 ICJ documents
- 505 documents from other courts and legal bodies
- 12,375 provisions
- 20,291 UN resolutions
-
`里，不增加原文内容（如冒号），这种排版是允许的，因为原文是"contains 6,396 ICJ documents and 505 documents..."，可以用列表符替代and。 那就统一结构： `
- 505 documents from other courts and legal bodies
- 12,375 provisions
- 20,291 UN resolutions
- metadata
- embeddings
- `前保留原文，例如： `
- Court decisions, written pleadings and oral records form distinct document layers, pre
We present ICJ-Graph, a machine-readable resource connecting documents of the International Court of Justice (ICJ) to cited cases, legal provisions and United Nations resolutions.
` `-
Court decisions, written pleadings and oral records form distinct document layers, preserving the distinction between the Court's reasoning and the parties' submissions. The collection contains 6,396 ICJ documents
-
The data files contain text
The accompanying pipeline lets users load the graph and generate embeddings for use in their own retrieval systems.
` `To illustrate the resource's use, we evaluate five models on citation prediction for 199 decisions using documents available before each decision.
` `Tools designed for citation research improve citation-prediction F1 over answering without tools for all five models across case, provision and resolution citations.
` 等一下，如果我不加冒号，原文有 "contains ... and ..." 用列表排版是否算改变了原意？如果我不加冒号，而是在`
`。应该把并列数据列表嵌在一个段落里。比如：`
We present ICJ-Graph, a machine-readable resource connecting documents of the International Court of Justice (ICJ) to cited cases, legal provisions and United Nations resolutions.
` 段落2： `
- `会显得非常专业且结构清晰。同时，为了不破坏原有句子结构，这部分可以作为一段的开头。
第三句：“The collection contains 6,396 ICJ documents and 505 documents from other courts and legal bodies, together with 12,375 provisions and 20,291 UN resolutions.” 这一句是列举数据资源统计。有四个核心数据：6,396 ICJ documents, 505 documents from other courts and legal bodies, 12,375 provisions, 20,291 UN resolutions。同样地，将其拆分为列表，能让读者快速抓住海量数据的重点。
第四句：“The data files contain text, metadata and embeddings.” 讲数据格式，包含text, metadata, embeddings三项，也适合做成列表。
第五句：“The accompanying pipeline lets users load the graph and generate embeddings for use in their own retrieval systems.” 讲配套工作流的作用。里面提到“load the graph”、“generate embeddings”、“retrieval systems”，这几个词可以作为关键对象加粗，凸显出技术性。
第六句：“To illustrate the resource's use, we evaluate five models on citation prediction for 199 decisions using documents available before each decision.” 讲应用评估。可以把核心任务“citation prediction”加粗，强调研究的具体内容。
第七句：“Tools designed for citation research improve citation-prediction F1 over answering without tools for all five models across case, provision and resolution citations.” 这是最终结论。可以提取“improve citation-prediction F1”作为结果亮点进行加粗。
接下来把这些碎片化的分析拼装成符合HTML语法规则的代码块。
注意第二到第四句，原文都在讲数据的构成，可以放在一个大的`