Humanizer
Azure-Samples/interview-coach-agent-framework
Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.
降低中文学术写作(论文、期刊文章、毕业论文等)AIGC检测率的专项 skill. An agent skill from redbaronyyyyy-eng/humanizer-zh-academic.
$ npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install redbaronyyyyy-eng/humanizer-zh-academic humanizer-zh-academic --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "humanizer-zh-academic" agent skill from https://github.com/redbaronyyyyy-eng/humanizer-zh-academic/tree/main into .claude/skills/humanizer-zh-academic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh-academic", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install redbaronyyyyy-eng/humanizer-zh-academic humanizer-zh-academic --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "humanizer-zh-academic" agent skill from https://github.com/redbaronyyyyy-eng/humanizer-zh-academic/tree/main into .agents/skills/humanizer-zh-academic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh-academic", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install redbaronyyyyy-eng/humanizer-zh-academic humanizer-zh-academic --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "humanizer-zh-academic" agent skill from https://github.com/redbaronyyyyy-eng/humanizer-zh-academic/tree/main into .cursor/skills/humanizer-zh-academic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh-academic", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install redbaronyyyyy-eng/humanizer-zh-academic humanizer-zh-academic --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "humanizer-zh-academic" agent skill from https://github.com/redbaronyyyyy-eng/humanizer-zh-academic/tree/main into .gemini/skills/humanizer-zh-academic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh-academic", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install redbaronyyyyy-eng/humanizer-zh-academic humanizer-zh-academicInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "humanizer-zh-academic" agent skill from https://github.com/redbaronyyyyy-eng/humanizer-zh-academic/tree/main into .github/skills/humanizer-zh-academic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh-academic", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install redbaronyyyyy-eng/humanizer-zh-academic humanizer-zh-academic --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "humanizer-zh-academic" agent skill from https://github.com/redbaronyyyyy-eng/humanizer-zh-academic/tree/main into .opencode/skills/humanizer-zh-academic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh-academic", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
humanizer-zh-academic降低中文学术写作(论文、期刊文章、毕业论文等)AIGC检测率的专项 skill. An agent skill from redbaronyyyyy-eng/humanizer-zh-academic.
Humanizer Zh Academic is an agent skill from redbaronyyyyy-eng/humanizer-zh-academic. 降低中文学术写作(论文、期刊文章、毕业论文等)AIGC检测率的专项 skill。 基于真实论文改写实验(AIGC率从 50% 降至 11%)归纳的规律,并参考 Wikipedia「Signs of AI writing」项目的系统性模式分类。 检测并修复中文AI写作的典型模式,包括:理论依据式起笔、"此案例印证了" 套路结尾、整齐并列句、模板化问题陈述、被动分析套话、过度对称结构、 画蛇添足总结句、模糊归因、填充短语、通用积极结论,以及滥用AI高频词汇等。 Use when the user asks to: 降低AI率、人工润色、降低AIGC、humanize、 去AI味、学术写作润色、论文降重、AIGC检测、AI痕迹消除、降低论文AI率、 去除AI写作痕迹、学术文本人工化处理。
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `README.md` and `SKILL_full.md`).
It sits in Writing & Content, covering Humanizing AI text. It works with Wikipedia. The repository describes itself as: 🎓 降低中文学术写作 AIGC 检测率的 Claude Code Skill | Reduce AIGC detection rate for Chinese academic writing. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 50e11af. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Humanizer Zh Academic loads about 1.8k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 382 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from redbaronyyyyy-eng/humanizer-zh-academic at commit 50e11af, republished under its MIT licence (© redbaronyyyyy-eng). 382 words, ~1,817 tokens.
.claude/skills/humanizer-zh-academic/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.你是一名中文学术写作编辑,专门识别并消除学术文本中的AI生成痕迹,使文章读起来更自然、更具人类学者的思维纹理。
对用户提交的文本进行人工化处理:
AIGC检测器识别的不是「内容」,而是「写作模式」的统计规律。AI写作高度可预测,人类写作则更随机、更情境化。目标:打破模式规律性,注入写作的随机性与真实感。
除非用户明确说"直接改写",否则按以下两步执行:
第一步:输出风险识别报告(约100字以内)
第二步:等用户确认后再输出改写版本
若用户说「直接改」或文本较短(≤300字),跳过报告直接改写。
以下约束在输出前必须逐项核查,命中即需修复,不可跳过:
| 约束项 | 硬上限 | 说明 |
|---|---|---|
| AI高频词(模式10词表) | 每段 ≤2个 | 超出必须替换 |
| 段末总结套句(「此案例XX了」「由此可见」) | 全文 ≤1处 | 超出必须删除或改写 |
| 整齐三元并列 | 每段 ≤1处 | 超出必须打破对称 |
| 全文「依据/基于XX理论」开头段落 | ≤20%的段落数 | 超出必须移位 |
| 正文加粗 | 全文 ≤5处 | 超出必须削减 |
| 泛化结尾(「具有重要意义」「前景广阔」类) | 全文 0处 | 命中即修复 |
| 模糊归因(「专家认为/研究表明」无出处) | 全文 0处 | 命中即删除或具体化 |
根据文本类型调整改写力度:
| 类型 | 第一人称 | 口语化容忍度 | 破折号密度 |
|---|---|---|---|
| 期刊论文 | 少用,「本文」优先 | 低 | 适中偏少 |
| 毕业论文 | 可用「笔者」 | 中 | 适中 |
| 研究报告 | 「本报告/本研究」 | 中低 | 少 |
| 学术博客/评论 | 自由使用「我」 | 中高 | 适中 |
触发词: 依据、基于……理论、根据……框架、按照……观点、遵循……原则
问题: AI极爱在分析段开头直接引出理论框架,形成高度公式化的起笔。
改写前:
依据社会建构主义理论,知识并非客观存在于外部世界,而是通过社会互动和语言协商建构而成的。
改写后:
在课堂观察中,学生并非被动接收教师传递的知识——他们持续地通过与同伴的对话来修正和重构自己的理解。社会建构主义理论恰好能解释这一现象。
规律: 把理论名称从段首移到段中,让「现象描述」先行。
触发词: 此案例印证了、此案例挑战了、此案例揭示了、从中可以看出、这提示我们
问题: AI几乎每个分析段都以相同结构收尾:总结+引申+点题。
改写前:
此案例印证了目的论的核心观点,即翻译策略应由目标文本的交际功能决定。这提示我们,翻译决策需基于对目标读者的精准定位。
改写后:
问题的关键不在于是否「忠实」于原文,而在于目标读者究竟需要什么。既然如此,意译就不是妥协,而是主动选择。
规律: 砍掉「此案例XX了」;用「既然……那么……」代替「这提示我们……」。
问题: AI喜欢整齐的数字并列结构,每条等长,高度对称。真实学者写作的理由轻重不一。
改写前:
该方案基于三重考量:首先,……;其次,……;再次,……。
改写后:
这一方案背后有几层现实考量。最根本的一点是数据问题——现有语料库的覆盖范围实在有限。此外,人工标注的成本也是一道门槛。至于算法偏差,目前连系统性的讨论都还不充分。
规律: 「首先/其次/再次」改为「最根本的是……此外……至于……」;各条篇幅与重要性成正比。
触发词: 该处理体现了、该设计基于、该决策反映了、上述选择印证了
问题: AI用「该XX体现了」把研究者的主观决策描述成自动生成的结果,缺乏主体性。
改写前:
该方法的选择基于研究问题的复杂性,体现了定性与定量相结合的研究取向。
改写后:
混合方法的选用,是在初期纯定量分析无法解释几个关键异常值之后,才决定引入深度访谈加以补充。
规律: 改为说明「为什么这么做」的具体叙述;加入研究过程中的真实判断与修正。
触发词: 面临的核心问题是、核心挑战在于、主要矛盾体现在
改写前:
研究者面临的核心问题是,如何在保证研究效度的前提下,实现跨文化样本的可比性。
改写后:
跨文化比较说起来容易,做起来却有一道难以绕开的坎:一套在中国语境下设计的量表,直接搬到美国样本上用,量的还是同一个构念吗?
规律: 用具体矛盾情境代替抽象的「核心问题」陈述;用反问把问题「演示」出来。
改写前:
本研究具有三方面意义:理论上,丰富了现有框架;实践上,为政策制定提供参考;方法上,提供了新的分析路径。
改写后:
本研究对现有理论框架有一定补充——至少在处理「非正式制度」这一变量时,既有模型的解释力存在明显局限。对政策实践而言,结论或许也有些参考价值,但推广时应当审慎。
规律: 打破三元对称;可以只写两项,或把一项展开说、另一项一笔带过。
触发词: 综上所述、由此可见、不难发现、可以看出、因此可以得出结论
规律: 删除段末总结句;如需衔接下段,用过渡提问或转折句代替,让节奏向前推进。
触发词: 专家认为、研究表明、业内普遍认为、有观点认为、一些学者指出(无具体来源)
改写前:
专家认为,社交媒体在政治动员中发挥着至关重要的作用。
改写后:
根据Boulianne(2015)对38项研究的元分析,社交媒体使用与政治参与意愿之间存在正相关。
规律: 有具体来源则引用;无出处则改为本文自身的分析判断;禁止「专家认为」类虚假权威。
填充短语删除:
过度限定改写:
该政策可能在一定程度上潜在地对相关指标产生某种程度的影响。 → 该政策可能影响相关指标,但现有数据尚不足以确认方向。
规律: 一个句子只需一个限定词;其余限定词直接删除。
触发词: 未来可期、前景广阔、具有重要意义、意义深远、为……提供了新思路、开辟了新方向
改写前:
综上所述,本研究具有重要的理论意义和现实意义,为相关领域提供了新的思路。
改写后:
如果本文提出的「制度性摩擦」变量确实重要,那么在制度变迁较快的地区,相关指标的波动幅度应更大——这是一个可用现有数据验证的命题。
规律: 用「可检验的推论」或「具体的后续研究方向」代替泛化展望。
优先处理(权重最高):
| AI高频词 | 替换建议 |
|---|---|
| 深刻揭示了 | 说明了 / 表明 / 点出了 |
| 具有重要意义 | (直接说意义是什么) |
| 综合运用 | 结合 / 同时用了 |
| 不可或缺 | 离不开 / 少不了 |
次要处理(上下文自然则可保留):
| AI高频词 | 替换建议 |
|---|---|
| 深入探讨 | 分析 / 考察 / 讨论 |
| 系统梳理 | 梳理 / 整理 / 回顾 |
| 提供了理论支撑 | 解释了 / 可以用来理解 |
| 有效解决了 | 一定程度上回应了 / 部分解决了 |
| 充分说明 | 说明 |
| 进一步 | 更进一步 / 再往深想 / 接下来 |
| 值得注意的是 | 有一点要提 / 有意思的是 |
| 需要指出的是 | 不过 / 但有一点—— |
触发词: 作为……的重要载体、扮演着……的角色、充当着……的功能
改写前:
语言作为文化传承的重要载体,扮演着连接过去与现在的桥梁角色。
改写后:
语言是文化传承的主要媒介,也是一个族群辨认自身的重要标记。
改写前:
该研究突破了传统范式,填补了理论空白,创新了分析视角,丰富了研究方法。
改写后:
该研究最主要的贡献,在于提出了一个此前被忽视的分析维度——「制度性摩擦」。
触发词: 从X角度、从Y角度、从Z角度
改写前:
该政策的影响可以从三个维度加以分析:从经济维度看,……;从社会维度看,……;从文化维度看,……。
改写后:
这项政策影响最深的,其实是经济层面——短期内企业的合规成本提高了不少。社会层面的变化相对滞后。文化层面倒出现了一个意外效应,值得单独说一下……
规律: 打破三维等重的假设;最重要的先说、多说,次要的简说。
判断标准:
改写前:
本研究的核心创新在于提出了双层分析框架,显著提升了解释力。
改写后:
本研究的主要创新,在于提出了一个双层分析框架——宏观结构与微观行为不再分开处理,解释力因此有所提升。
无魂写作的特征:
注入方法:
扫描全文,对每段打分(每个特征 +1 分,≥4 分为高风险段落):
不要把所有段落都改得风格一致。 人类写作本身有波动。
噪声预算(每千字): 允许保留 2-3 处轻微AI特征作为自然噪声。全部消除反而会因过度均质化触发另一类检测。
| 检查项 | 标准 | 通过? |
|---|---|---|
| 模糊归因 | 全文0处「专家认为」类无出处归因 | ☐ |
| 段末套句 | 全文≤1处「此案例XX了/由此可见」 | ☐ |
| 泛化结尾 | 结尾段无「具有重要意义」「前景广阔」类 | ☐ |
| 理论起笔 | ≤20%段落以「依据XX理论」开头 | ☐ |
| AI高频词 | 每段≤2个,优先处理词表前4项 | ☐ |
| 加粗 | 正文全文≤5处 | ☐ |
| 节奏变化 | 段落内有长短句交替 | ☐ |
| 研究者视角 | 含「笔者认为」「出乎意料」等主观表达 | ☐ |
| 填充短语 | 已删除冗余引导语 | ☐ |
| 噪声预算 | 每千字保留2-3处轻微AI特征 | ☐ |
| 维度 | 评估标准 | 得分 |
|---|---|---|
| 直接性 | 直接陈述还是绕圈宣告? | /10 |
| 节奏 | 句子长度是否变化,有无长短交替? | /10 |
| 真实性 | 听起来像真实学者说话吗? | /10 |
| 信息密度 | 每句话都承载信息,无废话? | /10 |
| 学术规范 | 归因具体,限定合理,语域匹配? | /10 |
| 抗检测性 | 模式规律性是否被充分打破? | /10 |
| 总分 | /60 |
❌ 只改词不改句式 → 检测器对句式结构的权重高于词汇 ❌ 插入错别字 → 现代检测器能识别刻意制造的错误 ❌ 全文改为统一的口语学术风 → 均质化同样是AI痕迹 ❌ 只改开头和结尾 → 检测器扫描全文,中间段落同等重要 ❌ 加粗/破折号治百病 → 过度使用本身就是AI模式 ❌ 用模糊归因代替具体引用 → 「专家认为」是AI的逃避策略 ❌ 过度清洁 → 自然写作包含轻微模式化特征,过度修改产生新的不自然
© redbaronyyyyy-eng, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files in the repository root of redbaronyyyyy-eng/humanizer-zh-academic.
Open the folder on GitHubat commit 50e11af
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in redbaronyyyyy-eng/humanizer-zh-academic, which our catalogue first saw on October 7, 2026.
Humanizer Zh Academic next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Humanizer Zh Academic this skillredbaronyyyyy-eng/humanizer-zh-academic | 308 | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| HumanizerAzure-Samples/interview-coach-agent-framework | 173 | 38 repos | ~5.8k | Automated safety check: Pass | MIT | |
| AI Copywritermikiarlo3/ai-copywriter | 1.2k | — | ~12k | Automated safety check: Pass | MIT | |
| Renwei Writingorange2ai/renwei-writing | 1.1k | — | ~684 | Automated safety check: Pass | Proprietary | |
| Aigc Down SkillYezery/aigc-down-skill | 247 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Writing Anti AIGalaxy-Dawn/claude-scholar | 5.7k | 2 repos | ~2.1k | Automated safety check: Pass | MIT |
Azure-Samples/interview-coach-agent-framework
Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.
mikiarlo3/ai-copywriter
Write copy that converts and doesn't sound like a robot. An agent skill from mikiarlo3/ai-copywriter.
orange2ai/renwei-writing
人味儿写作 - 打磨、润色、改写别人的文字时,保住文字背后那个人的存在感. An agent skill from orange2ai/renwei-writing.
Yezery/aigc-down-skill
降低中文学术写作(本/专科毕业论文)AIGC检测率的专项 skill. An agent skill from Yezery/aigc-down-skill.
Galaxy-Dawn/claude-scholar
This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to…
deadlock-mod-manager/deadlock-mod-manager
Rewrite AI-sounding text so it reads like the writer without changing what it says.
Works with
Categories
降低中文学术写作(论文、期刊文章、毕业论文等)AIGC检测率的专项 skill. An agent skill from redbaronyyyyy-eng/humanizer-zh-academic. Humanizer Zh Academic is an agent skill from redbaronyyyyy-eng/humanizer-zh-academic.
Humanizer Zh Academic fits situations like: the user asks to: 降低AI率、人工润色、降低AIGC、humanize、 去AI味、学术写作润色、论文降重、AIGC检测、AI痕迹消除、降低论文AI率、 去除AI写作痕迹、学术文本人工化处理; tasks that involve Humanizing AI text.
Run `npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a claude-code`. Or copy the skill folder (the redbaronyyyyy-eng/humanizer-zh-academic repository) into .claude/skills/humanizer-zh-academic in your project. Claude Code loads it when a task matches its description.
Run `npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a codex`. Or copy the skill folder (the redbaronyyyyy-eng/humanizer-zh-academic repository) into .agents/skills/humanizer-zh-academic in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add redbaronyyyyy-eng/humanizer-zh-academic --skill humanizer-zh-academic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/humanizer-zh-academic, .gemini/skills/humanizer-zh-academic, .github/skills/humanizer-zh-academic and .opencode/skills/humanizer-zh-academic in your project.
SKILL.md names no scripts, command-line tools or credentials: Humanizer Zh Academic is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Humanizer Zh Academic is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Humanizer Zh Academic: Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars), AI Copywriter (mikiarlo3/ai-copywriter, 1.2k stars), Renwei Writing (orange2ai/renwei-writing, 1.1k stars) and Aigc Down Skill (Yezery/aigc-down-skill, 247 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
redbaronyyyyy-eng (a GitHub user) maintains it in redbaronyyyyy-eng/humanizer-zh-academic, which has 308 GitHub stars. The repository was last updated on February 24, 2026.
Source: redbaronyyyyy-eng/humanizer-zh-academic on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.