humanize-ai-text

人性化人工智能生成的文本以绕过检测。该人性化工具重写了 ChatGPT、Claude 和 GPT 内容，使其听起来更自然，并通过了 GPTZero、Turnitin 和 Originality.ai 等 AI 检测器。基于维基百科的综合“人工智能写作的标志”指南。使机器人人工智能书写无法被察觉并且像人类一样。

# Humanize AI Text

Comprehensive CLI for detecting and transforming AI-generated text to bypass detectors. Based on [Wikipedia's Signs of AI Writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing).

## Quick Start

```bash
# Detect AI patterns
python scripts/detect.py text.txt

# Transform to human-like
python scripts/transform.py text.txt -o clean.txt

# Compare before/after
python scripts/compare.py text.txt -o clean.txt
```

---

## Detection Categories

The analyzer checks for **16 pattern categories** from Wikipedia's guide:

### Critical (Immediate AI Detection)
| Category | Examples |
|----------|----------|
| Citation Bugs | `oaicite`, `turn0search`, `contentReference` |
| Knowledge Cutoff | "as of my last training", "based on available information" |
| Chatbot Artifacts | "I hope this helps", "Great question!", "As an AI" |
| Markdown | `**bold**`, `## headers`, ``` code blocks ``` |

### High Signal
| Category | Examples |
|----------|----------|
| AI Vocabulary | delve, tapestry, landscape, pivotal, underscore, foster |
| Significance Inflation | "serves as a testament", "pivotal moment", "indelible mark" |
| Promotional Language | vibrant, groundbreaking, nestled, breathtaking |
| Copula Avoidance | "serves as" instead of "is", "boasts" instead of "has" |

### Medium Signal
| Category | Examples |
|----------|----------|
| Superficial -ing | "highlighting the importance", "fostering collaboration" |
| Filler Phrases | "in order to", "due to the fact that", "Additionally," |
| Vague Attributions | "experts believe", "industry reports suggest" |
| Challenges Formula | "Despite these challenges", "Future outlook" |

### Style Signal
| Category | Examples |
|----------|----------|
| Curly Quotes | "" instead of "" (ChatGPT signature) |
| Em Dash Overuse | Excessive use of — for emphasis |
| Negative Parallelisms | "Not only... but also", "It's not just... it's" |
| Rule of Three | Forced triplets like "innovation, inspiration, and insight" |

---

## Scripts

### detect.py — Scan for AI Patterns

```bash
python scripts/detect.py essay.txt
python scripts/detect.py essay.txt -j  # JSON output
python scripts/detect.py essay.txt -s  # score only
echo "text" | python scripts/detect.py
```

**Output:**
- Issue count and word count
- AI probability (low/medium/high/very high)
- Breakdown by category
- Auto-fixable patterns marked

### transform.py — Rewrite Text

```bash
python scripts/transform.py essay.txt
python scripts/transform.py essay.txt -o output.txt
python scripts/transform.py essay.txt -a  # aggressive
python scripts/transform.py essay.txt -q  # quiet
```

**Auto-fixes:**
- Citation bugs (oaicite, turn0search)
- Markdown (**, ##, ```)
- Chatbot sentences
- Copula avoidance → "is/has"
- Filler phrases → simpler forms
- Curly → straight quotes

**Aggressive (-a):**
- Simplifies -ing clauses
- Reduces em dashes

### compare.py — Before/After Analysis

```bash
python scripts/compare.py essay.txt
python scripts/compare.py essay.txt -a -o clean.txt
```

Shows side-by-side detection scores before and after transformation

---

## Workflow

1. **Scan** for detection risk:
   ```bash
   python scripts/detect.py document.txt
   ```

2. **Transform** with comparison:
   ```bash
   python scripts/compare.py document.txt -o document_v2.txt
   ```

3. **Verify** improvement:
   ```bash
   python scripts/detect.py document_v2.txt -s
   ```

4. **Manual review** for AI vocabulary and promotional language (requires judgment)

---

## AI Probability Scoring

| Rating | Criteria |
|--------|----------|
| Very High | Citation bugs, knowledge cutoff, or chatbot artifacts present |
| High | >30 issues OR >5% issue density |
| Medium | >15 issues OR >2% issue density |
| Low | <15 issues AND <2% density |

---

## Customizing Patterns

Edit `scripts/patterns.json` to add/modify:
- `ai_vocabulary` — words to flag
- `significance_inflation` — puffery phrases
- `promotional_language` — marketing speak
- `copula_avoidance` — phrase → replacement
- `filler_replacements` — phrase → simpler form
- `chatbot_artifacts` — phrases triggering sentence removal

---

## Batch Processing

```bash
# Scan all files
for f in *.txt; do
  echo "=== $f ==="
  python scripts/detect.py "$f" -s
done

# Transform all markdown
for f in *.md; do
  python scripts/transform.py "$f" -a -o "${f%.md}_clean.md" -q
done
```

---

## Reference

Based on Wikipedia's [Signs of AI Writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. Patterns documented from thousands of AI-generated text examples.

Key insight: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."

---

## 中文说明

# Humanize AI Text

用于检测并转换 AI 生成文本以绕过检测器的综合性 CLI。基于 [Wikipedia's Signs of AI Writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing)。

## 快速开始

```bash
# Detect AI patterns
python scripts/detect.py text.txt

# Transform to human-like
python scripts/transform.py text.txt -o clean.txt

# Compare before/after
python scripts/compare.py text.txt -o clean.txt
```

---

## 检测类别

分析器会检查来自 Wikipedia 指南的 **16 个模式类别**：

### 严重（立即判定为 AI）
| 类别 | 示例 |
|----------|----------|
| Citation Bugs | `oaicite`、`turn0search`、`contentReference` |
| Knowledge Cutoff | "as of my last training"、"based on available information" |
| Chatbot Artifacts | "I hope this helps"、"Great question!"、"As an AI" |
| Markdown | `**bold**`、`## headers`、``` code blocks ``` |

### 高信号
| 类别 | 示例 |
|----------|----------|
| AI Vocabulary | delve、tapestry、landscape、pivotal、underscore、foster |
| Significance Inflation | "serves as a testament"、"pivotal moment"、"indelible mark" |
| Promotional Language | vibrant、groundbreaking、nestled、breathtaking |
| Copula Avoidance | 用 "serves as" 代替 "is"，用 "boasts" 代替 "has" |

### 中信号
| 类别 | 示例 |
|----------|----------|
| Superficial -ing | "highlighting the importance"、"fostering collaboration" |
| Filler Phrases | "in order to"、"due to the fact that"、"Additionally," |
| Vague Attributions | "experts believe"、"industry reports suggest" |
| Challenges Formula | "Despite these challenges"、"Future outlook" |

### 风格信号
| 类别 | 示例 |
|----------|----------|
| Curly Quotes | "" 代替 ""（ChatGPT 标志） |
| Em Dash Overuse | 过度使用 — 来强调 |
| Negative Parallelisms | "Not only... but also"、"It's not just... it's" |
| Rule of Three | 生硬的三元组，如 "innovation, inspiration, and insight" |

---

## 脚本

### detect.py —— 扫描 AI 模式

```bash
python scripts/detect.py essay.txt
python scripts/detect.py essay.txt -j  # JSON output
python scripts/detect.py essay.txt -s  # score only
echo "text" | python scripts/detect.py
```

**输出：**
- 问题数量和字数
- AI 概率（low/medium/high/very high）
- 按类别细分
- 标记出可自动修复的模式

### transform.py —— 重写文本

```bash
python scripts/transform.py essay.txt
python scripts/transform.py essay.txt -o output.txt
python scripts/transform.py essay.txt -a  # aggressive
python scripts/transform.py essay.txt -q  # quiet
```

**自动修复：**
- Citation bugs（oaicite、turn0search）
- Markdown（**、##、```）
- Chatbot 语句
- Copula avoidance → "is/has"
- Filler phrases → 更简单的形式
- Curly → 直引号

**激进模式 (-a)：**
- 简化 -ing 从句
- 减少破折号

### compare.py —— 前后对比分析

```bash
python scripts/compare.py essay.txt
python scripts/compare.py essay.txt -a -o clean.txt
```

并排显示转换前后的检测分数

---

## 工作流

1. **扫描**检测风险：
   ```bash
   python scripts/detect.py document.txt
   ```

2. **转换**并对比：
   ```bash
   python scripts/compare.py document.txt -o document_v2.txt
   ```

3. **验证**改进效果：
   ```bash
   python scripts/detect.py document_v2.txt -s
   ```

4. **人工复审** AI 词汇和宣传性语言（需要判断力）

---

## AI 概率评分

| 评级 | 标准 |
|--------|----------|
| Very High | 存在 citation bugs、knowledge cutoff 或 chatbot artifacts |
| High | >30 个问题 或 问题密度 >5% |
| Medium | >15 个问题 或 问题密度 >2% |
| Low | <15 个问题 且 密度 <2% |

---

## 自定义模式

编辑 `scripts/patterns.json` 以添加/修改：
- `ai_vocabulary` —— 要标记的词
- `significance_inflation` —— 夸大性短语
- `pro