Back to Details

paper-audit

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Paper Audit Skill (论文审核)

Paper Audit Skill (论文审核)

Unified academic paper auditing across formats and languages.
跨格式、跨语言的统一学术论文审核能力。

Critical Rules

核心规则

  1. NEVER modify 
    \cite{}
    , 
    \ref{}
    , 
    \label{}
    , math environments in LaTeX
  2. NEVER modify 
    @cite
    , 
    #cite()
    , 
    #ref()
    , 
    <label>
    in Typst
  3. NEVER fabricate bibliography entries — only verify existing 
    .bib
    /
    .yml
    files
  4. NEVER change domain terminology without user confirmation
  5. Check 
    FORBIDDEN_TERMS
    lists before suggesting any terminology changes
  6. For PDF input, clearly flag sections where extraction quality is uncertain
  7. Always distinguish between automated findings and LLM-judgment scores
  1. 绝对不要修改LaTeX中的
    \cite{}
    、
    \ref{}
    、
    \label{}
    和数学环境
  2. 绝对不要修改Typst中的
    @cite
    、
    #cite()
    、
    #ref()
    、
    <label>
  3. 绝对不要捏造参考文献条目，仅可验证已有的
    .bib
    /
    .yml
    文件
  4. 未经用户确认不得修改领域专业术语
  5. 建议修改术语前需先检查
    FORBIDDEN_TERMS
    禁止术语列表
  6. 针对PDF输入，需明确标记提取质量不确定的段落
  7. 始终明确区分自动检查结果和LLM判定得分

Audit Modes

审核模式

Mode: 
self-check
(Pre-submission Self-Check)

模式：
self-check
（投稿前自查）

Trigger keywords: audit, check, self-check, pre-submission, score, review my paper
What it does: Runs all automated checks and generates a structured report with:
  • Per-dimension scores (Quality, Clarity, Significance, Originality) on 1-6 scale
  • Issue list sorted by severity (Critical > Major > Minor)
  • Improvement suggestions per section
  • Pre-submission checklist results
CLI: 
python scripts/audit.py paper.tex --mode self-check
触发关键词：audit、check、self-check、pre-submission、score、review my paper
功能说明：运行所有自动检查项，生成结构化报告，包含：
  • 各维度得分（质量、清晰度、重要性、原创性），采用1-6分制
  • 按严重程度排序的问题列表（Critical > Major > Minor）
  • 各章节改进建议
  • 投稿前检查清单结果
CLI命令：
python scripts/audit.py paper.tex --mode self-check

Online Bibliography Verification

在线参考文献验证

Add 
--online
to enable CrossRef/Semantic Scholar metadata verification:
python scripts/audit.py paper.tex --mode self-check --online --email user@example.com
添加
--online
参数启用CrossRef/Semantic Scholar元数据验证：
python scripts/audit.py paper.tex --mode self-check --online --email user@example.com

ScholarEval 8-Dimension Assessment

ScholarEval 8维度评估

Add 
--scholar-eval
to enable the 8-dimension evaluation framework:
python scripts/audit.py paper.tex --mode self-check --scholar-eval
Script-evaluable dimensions (Soundness, Clarity, Presentation, partial Reproducibility) are scored automatically. For complete assessment, supplement with LLM evaluation of Novelty, Significance, Ethics, and Reproducibility. See 
SCHOLAR_EVAL_GUIDE.md
.
ScholarEval LLM Assessment Prompt (for 
review
mode):
Read the full paper and provide 1-10 scores with evidence in JSON format:
json
{
  "novelty": {
    "score": "<1-10>",
    "evidence": "<Describe originality and distinction from prior work>"
  },
  "significance": {
    "score": "<1-10>",
    "evidence": "<Describe potential impact on the field>"
  },
  "reproducibility_llm": {
    "score": "<1-10>",
    "evidence": "<Assess experimental description completeness, code/data availability>"
  },
  "ethics": {
    "score": "<1-10>",
    "evidence": "<Assess ethical considerations, conflicts of interest, data privacy>"
  }
}
添加
--scholar-eval
参数启用8维度评估框架：
python scripts/audit.py paper.tex --mode self-check --scholar-eval
脚本可自动评估的维度（合理性、清晰度、呈现效果、部分可复现性）会自动打分。如需完整评估，需补充LLM对创新性、重要性、伦理、可复现性的评估，详见
SCHOLAR_EVAL_GUIDE.md
。
ScholarEval LLM评估提示词（适用于
review
模式）：
阅读完整论文，以JSON格式输出1-10分的得分及佐证依据：
json
{
  "novelty": {
    "score": "<1-10>",
    "evidence": "<Describe originality and distinction from prior work>"
  },
  "significance": {
    "score": "<1-10>",
    "evidence": "<Describe potential impact on the field>"
  },
  "reproducibility_llm": {
    "score": "<1-10>",
    "evidence": "<Assess experimental description completeness, code/data availability>"
  },
  "ethics": {
    "score": "<1-10>",
    "evidence": "<Assess ethical considerations, conflicts of interest, data privacy>"
  }
}

Mode: 
review
(Peer Review Simulation)

模式：
review
（模拟同行评审）

Trigger keywords: simulate review, peer review, reviewer perspective, what would reviewers say
What it does: Everything in self-check PLUS:
  • Paper summary from reviewer perspective
  • Strengths analysis
  • Weaknesses analysis with severity
  • Questions a reviewer would ask
  • Accept/reject recommendation with confidence
CLI: 
python scripts/audit.py paper.tex --mode review
触发关键词：simulate review、peer review、reviewer perspective、what would reviewers say
功能说明：包含self-check模式的所有功能，额外提供：
  • 评审视角的论文摘要
  • 优势分析
  • 带严重等级的劣势分析
  • 评审可能提出的问题
  • 带置信度的接收/拒稿建议
CLI命令：
python scripts/audit.py paper.tex --mode review

Mode: 
gate
(Quality Gate)

模式：
gate
（质量门控）

Trigger keywords: quality gate, pass/fail, can I submit, ready to submit, advisor check
What it does: Fast mandatory checks only:
  • Format validation
  • Bibliography integrity
  • Figure/table references
  • Pre-submission checklist
  • Binary PASS/FAIL verdict with blocking issues
CLI: 
python scripts/audit.py paper.tex --mode gate
触发关键词：quality gate、pass/fail、can I submit、ready to submit、advisor check
功能说明：仅运行快速强制检查项：
  • 格式校验
  • 参考文献完整性
  • 图表引用正确性
  • 投稿前检查清单
  • 二元通过/不通过判定及阻塞性问题说明
CLI命令：
python scripts/audit.py paper.tex --mode gate

Mode: 
polish
(Adversarial Dual-Agent Deep Polish)

模式：
polish
（对抗式双Agent深度润色）

Trigger keywords: polish, deep polish, adversarial review, refine writing, improve writing, paragraph polish
What it does:
  • Phase 1 (Python): Fast rule-based precheck → .polish-state/precheck.json
  • Phase 2 (Critic Agent): LLM adversarial review → per-section logic/expression scores
  • Phase 3 (Mentor Agent × N): Per-section polish suggestions → Original vs Revised table
  • Outputs: Structured polish report with diff-comment suggestions
Style options (
--style
):
  • A
    Plain Precise (default): Short sentences, active voice, technical precision
  • B
    Narrative Fluent: Story-driven, transitions, accessible prose
  • C
    Formal Academic: Passive voice acceptable, formal register, hedge words
Skip logic: 
--skip-logic
bypasses Critic logic scoring; Mentor runs expression-only polish. Equivalent to 
/polish
quick command.
CLI: 
python scripts/audit.py paper.tex --mode polish --style A --journal neurips
触发关键词：polish、deep polish、adversarial review、refine writing、improve writing、paragraph polish
功能说明：
  • 阶段1（Python脚本）：快速规则预检查 → 输出
    .polish-state/precheck.json
  • 阶段2（批评Agent）：LLM对抗式评审 → 输出各章节逻辑/表达得分
  • 阶段3（导师Agent × N）：各章节润色建议 → 输出原文与修改对照表
  • 输出：带差异注释建议的结构化润色报告
风格选项（
--style
参数）：
  • A
    简洁精准（默认）：短句、主动语态、技术精准
  • B
    叙事流畅：故事驱动、过渡自然、通俗易懂
  • C
    正式学术：可使用被动语态、正式语体、缓冲表述
跳过逻辑检查：
--skip-logic
参数会跳过批评Agent的逻辑打分，导师Agent仅进行表达层面润色，等价于
/polish
快速命令。
CLI命令：
python scripts/audit.py paper.tex --mode polish --style A --journal neurips

Supported Formats

支持格式

FormatParserNotes
LaTeX (.tex)
LatexParser
Full support — all checks available
Typst (.typ)
TypstParser
Full support — all checks available
PDF (.pdf) basic
PdfParser
(pymupdf)		Text extraction with font-size heading detection
PDF (.pdf) enhanced
PdfParser
(pymupdf4llm)		Structured Markdown with table/header preservation
PDF Limitations: Math formulas may be lost; some checks (format, figures) skip for PDF. Recommend providing source files (.tex/.typ) for maximum accuracy.
格式解析器备注
LaTeX (.tex)
LatexParser
完全支持，可使用所有检查功能
Typst (.typ)
TypstParser
完全支持，可使用所有检查功能
PDF (.pdf) 基础版
PdfParser
(pymupdf)		文本提取，支持字号标题识别
PDF (.pdf) 增强版
PdfParser
(pymupdf4llm)		结构化Markdown输出，保留表格/标题
PDF限制：数学公式可能丢失，部分检查（格式、图表）对PDF不可用，建议提供源文件（.tex/.typ）以获得最高准确率。

Language Support

语言支持

LanguageDetectionExtra Checks
EnglishAuto (default)Standard suite
ChineseAuto (CJK ratio > 30%)+ consistency check, + GB/T 7714 compliance
Force with 
--lang en
or 
--lang zh
.
语言检测方式额外检查项
English自动检测（默认）标准检查套件
Chinese自动检测（中日韩字符占比>30%）额外包含一致性检查、GB/T 7714格式合规检查
可通过
--lang en
或
--lang zh
强制指定语言。

Check Modules

检查模块

ModuleScript SourceDimensions AffectedApplicable Formats
Format Check
check_format.py
Clarity.tex, .typ
Grammar Analysis
analyze_grammar.py
Clarity.tex, .typ, .pdf
Logic & Coherence
analyze_logic.py
Quality, Significance.tex, .typ, .pdf
Sentence Complexity
analyze_sentences.py
Clarity.tex, .typ, .pdf
De-AI Detection
deai_check.py
Clarity, Originality.tex, .typ, .pdf
Bibliography
verify_bib.py
Quality.tex, .typ
Figure/Table Refs
check_figures.py
Clarity.tex
Reference Integrity
check_references.py
Clarity, Quality.tex, .typ
Visual Layout
visual_check.py
Clarity.pdf
Consistency (ZH)
check_consistency.py
Clarity.tex (Chinese only)
GB/T 7714 (ZH)
verify_bib.py
(GB mode)		Quality.tex (Chinese only)
Pre-submission ChecklistBuilt-inAllAll formats
模块脚本源文件影响维度适用格式
格式检查
check_format.py
清晰度.tex, .typ
语法分析
analyze_grammar.py
清晰度.tex, .typ, .pdf
逻辑连贯性
analyze_logic.py
质量、重要性.tex, .typ, .pdf
句子复杂度
analyze_sentences.py
清晰度.tex, .typ, .pdf
AI生成检测
deai_check.py
清晰度、原创性.tex, .typ, .pdf
参考文献检查
verify_bib.py
质量.tex, .typ
图表引用检查
check_figures.py
清晰度.tex
引用完整性
check_references.py
清晰度、质量.tex, .typ
视觉布局
visual_check.py
清晰度.pdf
一致性检查（中文）
check_consistency.py
清晰度.tex（仅中文）
GB/T 7714合规检查（中文）
verify_bib.py
(GB模式)		质量.tex（仅中文）
投稿前检查清单内置所有维度所有格式

Scoring System

评分体系

Based on REVIEWER_PERSPECTIVE.md criteria:
基于
REVIEWER_PERSPECTIVE.md
标准：

Four Dimensions

四个评分维度

  • Quality (30%): Technical soundness, well-supported claims
  • Clarity (30%): Clear writing, reproducible, good organization
  • Significance (20%): Community impact, advances understanding
  • Originality (20%): New insights, not obvious extensions
  • 质量（30%）：技术合理性、论据充分性
  • 清晰度（30%）：表述清晰、可复现、结构合理
  • 重要性（20%）：社区影响力、推动领域认知进展
  • 原创性（20%）：新见解、非显而易见的扩展

Six-Point Scale (NeurIPS standard)

6分制评分标准（NeurIPS标准）

ScoreRatingMeaning
5.5-6.0Strong AcceptGroundbreaking, technically flawless
4.5-5.4AcceptTechnically solid, high impact
3.5-4.4Borderline AcceptSolid but limited evaluation/novelty
2.5-3.4Borderline RejectMerits but weaknesses outweigh
1.5-2.4RejectTechnical flaws, insufficient evaluation
1.0-1.4Strong RejectFundamental errors or known results
分数评级含义
5.5-6.0强烈接收突破性成果，技术上无瑕疵
4.5-5.4接收技术扎实，影响力高
3.5-4.4临界接收成果扎实，但评估/创新性有限
2.5-3.4临界拒稿有可取之处，但缺陷占优
1.5-2.4拒稿存在技术缺陷，评估不充分
1.0-1.4强烈拒稿存在根本性错误或属于已知成果

Output Protocol

输出规范

All issues follow the unified format:
[MODULE] (Line N) [Severity: Critical|Major|Minor] [Priority: P0|P1|P2]: Issue description
  Original: ...
  Revised:  ...
  Rationale: ...
  • Severity: Critical (must fix), Major (should fix), Minor (nice to fix)
  • Priority: P0 (blocking), P1 (important), P2 (low priority)
所有问题遵循统一格式：
[MODULE] (Line N) [Severity: Critical|Major|Minor] [Priority: P0|P1|P2]: Issue description
  Original: ...
  Revised:  ...
  Rationale: ...
  • 严重程度：Critical（必须修复）、Major（应该修复）、Minor（建议修复）
  • 优先级：P0（阻塞性问题）、P1（重要问题）、P2（低优先级问题）

Workflow

工作流程

When a user requests a paper audit:
  1. Identify the file — locate the .tex, .typ, or .pdf file
  2. Determine mode — self-check (default), review, or gate based on user intent
  3. Run the orchestrator — 
    python scripts/audit.py <file> --mode <mode>
  4. Present the report — show the Markdown report to the user
  5. Discuss findings — help the user address Critical and Major issues first
  6. Re-audit if needed — run again after fixes to verify improvements
For 
review
mode, supplement the automated report with LLM analysis of:
  • Overall paper strengths (what works well)
  • Key weaknesses (what reviewers would criticize)
  • Questions a reviewer would ask
  • Missing related work or baselines
当用户发起论文审核请求时：
  1. 识别文件：定位.tex、.typ或.pdf文件
  2. 确定模式：根据用户意图选择self-check（默认）、review或gate模式
  3. 运行调度程序：执行
    python scripts/audit.py <file> --mode <mode>
  4. 展示报告：向用户呈现Markdown格式的报告
  5. 讨论结果：协助用户优先处理Critical和Major级问题
  6. 如需重新审核：修复后再次运行以验证改进效果
针对
review
模式，需在自动报告基础上补充LLM分析：
  • 论文整体优势（亮点内容）
  • 核心缺陷（评审可能批评的点）
  • 评审可能提出的问题
  • 缺失的相关工作或基线

Polish Mode Workflow

润色模式工作流程

  1. Run Python precheck
    python scripts/audit.py <file> --mode polish [--style A|B|C] [--journal <name>] [--skip-logic]
    Read 
    .polish-state/precheck.json
    from the paper's directory.
  2. Check hard blockers If 
    precheck.json["blockers"]
    is non-empty, display them and STOP. Say: "Fix these Critical issues before polish can proceed:" + list. Do NOT spawn any agent until user confirms fixes.
  3. Handle non-IMRaD structure (if 
    precheck.json["non_imrad"] == true
    ) Show detected sections, ask user: "Proceed with polish on these sections?"
  4. Spawn Critic Agent via Task:
    Subagent type: 
    general-purpose
    Prompt template:
    You are an adversarial academic reviewer.
Paper: {file_path}  |  Language: {lang}  |  Journal: {journal}  |  Style: {style}

Step 1: Read the paper using the Read tool (file: {file_path}).
Step 2: The rule-based precheck found these issues: {precheck_issues_summary}
Step 3: Produce a CRITIC REPORT as valid JSON (no markdown fencing):
{
  "global_verdict": "ready_to_polish" | "needs_revision_first" | "major_restructure_needed",
  "global_rationale": "2-3 sentences",
  "section_verdicts": [
    {
      "section": "<name>",
      "logic_score": 1-5,
      "expression_score": 1-5,
      "blocks_mentor": false,
      "blocking_reason": "",
      "top_issues": [{"type": "logic|expression|argument", "description": "..."}]
    }
  ],
  "cross_section_issues": ["..."]
}
blocks_mentor = true ONLY when logic_score <= 2 or section is structurally absent.
    Save the Critic's JSON output to 
    .polish-state/critic_report.json
    using Bash:
    python -c "import pathlib; pathlib.Path('.polish-state/critic_report.json').write_text('<critic_json_here>', encoding='utf-8')"
  5. Display Critic Dashboard and gate Render the Critic report as a markdown table (see dashboard format). Show blocked sections. Ask: "How to proceed? [1] Polish all sections (override blocks) [2] Skip blocked sections, polish the rest [3] Stop and revise blocked sections first" Wait for response.
  6. Spawn Mentor Agents per section (sequential, one at a time): For each approved section in IMRaD order:
    Subagent type: 
    general-purpose
    Prompt template:
    You are a writing mentor specializing in academic polish.

CRITICAL RULES (NEVER VIOLATE):
- Never modify \cite{}, \ref{}, \label{}, \eqref{} in LaTeX
- Never modify @cite, #cite(), #ref(), <label> in Typst
- Never modify math environments: $...$, \begin{equation}..., \begin{align}...
- Never add/remove citations
- Mark any domain terminology changes as [TERM CHANGE: confirm?]

Section: {section_name} (lines {start}-{end})
Target style: {style} ({style_description from POLISH_GUIDE.md})
Critic scores — Logic: {logic_score}/5, Expression: {expression_score}/5
Critic top issues: {top_issues}
Pre-check expression issues in this section: {filtered_expression_issues}

Read lines {start}-{end} of {file_path}:
  Use Read tool with offset={start-1} and limit={end-start+1}.

Produce MENTOR REPORT in this format:

## Section: {section_name}

### Polish Suggestions
[MENTOR] (Line N) [Severity: Major|Minor] [Priority: P1|P2]: description
  Original: <exact original text>
  Revised:  <revised text preserving all LaTeX/Typst commands>
  Rationale: <one sentence>

### Section Summary
<2-3 sentences on overall quality and key improvements>
    After each Mentor completes:
    • Display its output
    • Ask: "Section {name} polish done. Accept and continue to next section?"
    • Wait for confirmation before spawning next Mentor.
  7. Final status dashboard (after all sections done): See dashboard format below.
  1. 运行Python预检查
    python scripts/audit.py <file> --mode polish [--style A|B|C] [--journal <name>] [--skip-logic]
    读取论文目录下的
    .polish-state/precheck.json
    文件。
  2. 检查硬阻塞问题 如果
    precheck.json["blockers"]
    非空，展示问题并终止流程，提示：「润色前请先修复以下严重问题：」+ 问题列表，用户确认修复前不要启动任何Agent。
  3. 处理非IMRaD结构（如果
    precheck.json["non_imrad"] == true
    ） 展示检测到的章节，询问用户：「是否继续对这些章节进行润色？」
  4. 通过任务启动批评Agent：
    子Agent类型：
    general-purpose
    提示词模板：
    You are an adversarial academic reviewer.
Paper: {file_path}  |  Language: {lang}  |  Journal: {journal}  |  Style: {style}

Step 1: Read the paper using the Read tool (file: {file_path}).
Step 2: The rule-based precheck found these issues: {precheck_issues_summary}
Step 3: Produce a CRITIC REPORT as valid JSON (no markdown fencing):
{
  "global_verdict": "ready_to_polish" | "needs_revision_first" | "major_restructure_needed",
  "global_rationale": "2-3 sentences",
  "section_verdicts": [
    {
      "section": "<name>",
      "logic_score": 1-5,
      "expression_score": 1-5,
      "blocks_mentor": false,
      "blocking_reason": "",
      "top_issues": [{"type": "logic|expression|argument", "description": "..."}]
    }
  ],
  "cross_section_issues": ["..."]
}
blocks_mentor = true ONLY when logic_score <= 2 or section is structurally absent.
    通过Bash将批评Agent的JSON输出保存到
    .polish-state/critic_report.json
    ：
    python -c "import pathlib; pathlib.Path('.polish-state/critic_report.json').write_text('<critic_json_here>', encoding='utf-8')"
  5. 展示批评面板和门控选项 将批评报告渲染为Markdown表格（参考面板格式），展示被阻塞的章节，询问： "如何继续？ [1] 润色所有章节（覆盖阻塞设置） [2] 跳过阻塞章节，润色其余部分 [3] 停止，先修改阻塞章节问题" 等待用户回复。
  6. 按章节启动导师Agent（顺序执行，一次一个）： 按IMRaD顺序处理每个获批章节：
    子Agent类型：
    general-purpose
    提示词模板：
    You are a writing mentor specializing in academic polish.

CRITICAL RULES (NEVER VIOLATE):
- Never modify \cite{}, \ref{}, \label{}, \eqref{} in LaTeX
- Never modify @cite, #cite(), #ref(), <label> in Typst
- Never modify math environments: $...$, \begin{equation}..., \begin{align}...
- Never add/remove citations
- Mark any domain terminology changes as [TERM CHANGE: confirm?]

Section: {section_name} (lines {start}-{end})
Target style: {style} ({style_description from POLISH_GUIDE.md})
Critic scores — Logic: {logic_score}/5, Expression: {expression_score}/5
Critic top issues: {top_issues}
Pre-check expression issues in this section: {filtered_expression_issues}

Read lines {start}-{end} of {file_path}:
  Use Read tool with offset={start-1} and limit={end-start+1}.

Produce MENTOR REPORT in this format:

## Section: {section_name}

### Polish Suggestions
[MENTOR] (Line N) [Severity: Major|Minor] [Priority: P1|P2]: description
  Original: <exact original text>
  Revised:  <revised text preserving all LaTeX/Typst commands>
  Rationale: <one sentence>

### Section Summary
<2-3 sentences on overall quality and key improvements>
    每个导师Agent完成后：
    • 展示其输出
    • 询问：「{name}章节润色完成，是否确认并继续下一个章节？」
    • 启动下一个Agent前等待用户确认。
  7. 最终状态面板（所有章节完成后）： 参考下方的面板格式。

Polish Status Dashboard Format

润色状态面板格式

Print at end of each phase and at completion:
╭─ 🔴🔵 paper-audit Polish Mode ──────────────────────────╮
│ 📄 File: {filename} | Style: {A/B/C} | Journal: {venue} │
│ ⚔️  Critic: {global_verdict}                             │
│                                                           │
│ Section      │ Logic │ Expr │ Mentor      │ Suggestions  │
│ abstract     │  4/5  │ 3/5  │ ✅ Done     │      3       │
│ introduction │  3/5  │ 2/5  │ ✅ Done     │      7       │
│ method       │ BLOCK │ 2/5  │ ⏭️  Skipped  │      0       │
│ experiment   │  4/5  │ 4/5  │ ✅ Done     │      2       │
│ conclusion   │  5/5  │ 3/5  │ ✅ Done     │      4       │
│                                                           │
│ 👉 Next: {明确的下一步指示}                               │
╰───────────────────────────────────────────────────────────╯
每个阶段结束及全部完成后输出：
╭─ 🔴🔵 paper-audit Polish Mode ──────────────────────────╮
│ 📄 File: {filename} | Style: {A/B/C} | Journal: {venue} │
│ ⚔️  Critic: {global_verdict}                             │
│                                                           │
│ Section      │ Logic │ Expr │ Mentor      │ Suggestions  │
│ abstract     │  4/5  │ 3/5  │ ✅ Done     │      3       │
│ introduction │  3/5  │ 2/5  │ ✅ Done     │      7       │
│ method       │ BLOCK │ 2/5  │ ⏭️  Skipped  │      0       │
│ experiment   │  4/5  │ 4/5  │ ✅ Done     │      2       │
│ conclusion   │  5/5  │ 3/5  │ ✅ Done     │      4       │
│                                                           │
│ 👉 Next: {明确的下一步指示}                               │
╰───────────────────────────────────────────────────────────╯