verify

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/verify — DeepCitation Verification

/verify — DeepCitation 验证功能

Verify claims against source documents using the DeepCitation API, saving JSON artifacts at each step.

使用DeepCitation API验证声明与源文档的一致性，并在每个步骤保存JSON工件。

Prerequisites

前置条件

```
DEEPCITATION_API_KEY
```
environment variable must be set. If not set, try loading saved credentials:
bash
```
eval "$(npx -y deepcitation env 2>/dev/null)"
```
If that also fails, tell the user to run
```
npx -y deepcitation login
```
first, then retry.
Source files (PDF, DOCX, images, etc.) must be accessible on disk or via URL
Accepted file types: PDF, images (JPG, PNG), Office files (DOCX, XLSX, PPTX), CSV, TSV, ODF

必须设置
```
DEEPCITATION_API_KEY
```
环境变量。如果未设置，请尝试加载已保存的凭据：
bash
```
eval "$(npx -y deepcitation env 2>/dev/null)"
```
如果仍失败，请告知用户先运行
```
npx -y deepcitation login
```
，然后重试。
源文件（PDF、DOCX、图片等）必须可通过本地磁盘或URL访问
支持的文件类型：PDF、图片（JPG、PNG）、Office文件（DOCX、XLSX、PPTX）、CSV、TSV、ODF

Key Rules

核心规则

page_id
and
line_ids
MUST come from the
deepTextPromptPortion
— see rules/line-ids.md for details.
Coverage audit: After generating citations, spawn a subagent to audit the report/chat and confirm all facts, sources, names, dates, and values have deepcitations. The subagent should flag any uncited claims.

page_id
和
line_ids
必须来自
deepTextPromptPortion
——详情请参见rules/line-ids.md。
覆盖范围审核：生成引用后，启动子代理审核报告/对话，确认所有事实、来源、名称、日期和数值都已添加deepcitations。子代理应标记任何未引用的声明。

Workflow

工作流

Step 0: Analyze input

步骤0：分析输入

Load rules/analyze-input.md to determine which path to follow (A–F) based on what's in the conversation, arguments, and working directory.

加载rules/analyze-input.md，根据对话内容、参数和工作目录确定要遵循的路径（A–F）。

Step 1: Prepare sources

步骤1：准备源文件

Load rules/prepare-sources.md for CLI usage and what to retain from each prepare response.

加载rules/prepare-sources.md了解CLI用法以及需要从每个准备响应中保留的内容。

Step 2: Build citations

步骤2：构建引用

Load rules/build-citations.md for the full citation-building workflow:

Path A: Existing
```
<<<CITATION_DATA>>>
```
— skip to Step 3
Path B: Existing HTML with claims — identify claims, build citation data, generate keys, annotate HTML
Path C: Generate new cited response from scratch using the canonical citation format spec

加载rules/build-citations.md查看完整的引用构建工作流：

路径A：已有
```
<<<CITATION_DATA>>>
```
——跳至步骤3
路径B：已有包含声明的HTML——识别声明、构建引用数据、生成密钥、标注HTML
路径C：使用标准引用格式规范从头生成新的带引用响应

Step 3–5: Verify, inject, validate

步骤3–5：验证、注入、校验

Load rules/verify-and-inject.md for verification, HTML injection, and pre-delivery validation.

加载rules/verify-and-inject.md了解验证、HTML注入和交付前校验的流程。

When building citations

构建引用时的注意事项

When dealing with

lineIds

and

pageNumber

values, load rules/line-ids.md for how sparse line IDs work and how to find the right one.

When annotating HTML with

data-citation-key

attributes, load rules/annotate-html.md for placement rules, key-map building, and citation drawer triggers.

处理

lineIds

和

pageNumber

值时，请加载rules/line-ids.md了解稀疏行ID的工作原理以及如何找到正确的行ID。

使用

data-citation-key

属性标注HTML时，请加载rules/annotate-html.md了解放置规则、密钥映射构建和引用抽屉触发方式。

Output artifacts

输出工件

All artifacts are saved in

.deepcitation/

. Use

{topic}-{timestamp}

naming so re-runs don't clobber each other:

File	Contents
`prepare-{source}-{timestamp}.json`	Upload response with `attachmentId` and `deepTextPromptPortion`
`llm-output-{timestamp}.txt`	Full LLM response including `<<<CITATION_DATA>>>` block
`citations-{timestamp}.json`	Extracted `CitationRecord` with human-readable keys
`citations-keyed-{timestamp}.json`	Re-keyed citations with hashed keys (from `keygen` )
`key-map-{timestamp}.json`	Human-readable key → hashed key mapping
`annotated-{timestamp}.html`	HTML with `data-citation-key` attributes (before injection)
`verify-response-{timestamp}.json`	Verification results with statuses and evidence
`injected-{timestamp}.html`	Injected HTML with CDN runtime (Path B output)

所有工件都保存在

.deepcitation/

目录下。使用

{topic}-{timestamp}

命名格式，避免重新运行时覆盖现有文件：

文件	内容
`prepare-{source}-{timestamp}.json`	包含 `attachmentId` 和 `deepTextPromptPortion` 的上传响应
`llm-output-{timestamp}.txt`	包含 `<<<CITATION_DATA>>>` 块的完整LLM响应
`citations-{timestamp}.json`	提取的 `CitationRecord` ，带人类可读密钥
`citations-keyed-{timestamp}.json`	使用哈希密钥重新标记的引用（来自 `keygen` ）
`key-map-{timestamp}.json`	人类可读密钥→哈希密钥的映射
`annotated-{timestamp}.html`	带有 `data-citation-key` 属性的HTML（注入前）
`verify-response-{timestamp}.json`	包含状态和证据的验证结果
`injected-{timestamp}.html`	注入CDN运行时的HTML（路径B输出）

Important rules

重要规则

Product name: Always "DeepCitation" (never "DeepCite")
Track attachmentId: Always retain the
```
attachmentId
```
from Step 1 — it's the key for verification lookups
Strip before display: Use
```
extractVisibleText()
```
to remove
```
<<<CITATION_DATA>>>
```
before showing text to user
CitationRecord is an object: Check emptiness with
```
Object.keys(citations).length === 0
```
API key security: Never log or display
```
DEEPCITATION_API_KEY
```
Verbatim quotes:
```
fullPhrase
```
must be copied exactly from the source — do not paraphrase

产品名称：始终使用“DeepCitation”（绝不能用“DeepCite”）
跟踪attachmentId：务必保留步骤1中的
```
attachmentId
```
——它是验证查找的关键
显示前剥离内容：使用
```
extractVisibleText()
```
在向用户显示文本前移除
```
<<<CITATION_DATA>>>
```
CitationRecord是对象：通过
```
Object.keys(citations).length === 0
```
检查是否为空
API密钥安全：绝不要记录或显示
```
DEEPCITATION_API_KEY
```
精确引用：
```
fullPhrase
```
必须完全从源文件复制——不得意译

References

参考资料

Citation format spec:

$DC_ROOT/docs/prompts/citation-format.md

(resolve

DC_ROOT

with

node -e "..."

as shown in Path C)

SDK prompt:
```
$DC_ROOT/src/prompts/citationPrompts.ts
```
Citation parser: https://github.com/DeepCitation/deepcitation/blob/main/src/parsing/parseCitation.ts
API docs: https://deepcitation.com/docs

ARGUMENTS: $ARGUMENTS

引用格式规范：

$DC_ROOT/docs/prompts/citation-format.md

（如路径C所示，使用

node -e "..."

解析

DC_ROOT

）

SDK提示：
```
$DC_ROOT/src/prompts/citationPrompts.ts
```
引用解析器：https://github.com/DeepCitation/deepcitation/blob/main/src/parsing/parseCitation.ts
API文档：https://deepcitation.com/docs

参数：$ARGUMENTS