背景

学术训练中的一个核心盲区：

• "隐性知识"困境：阅读论文是一项关键技能，但几乎所有研究生项目都不系统教授

• 试错成本高昂：新生通过"试错法"自学，浪费大量时间，且容易产生挫败感

• 导师指导缺失：导师通常假设学生"自然会读"，不提供结构化方法

论文基本信息

标题： How to Read a Paper
作者： S. Keshav
单位： David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada
邮箱： keshav@uwaterloo.ca
发表： ACM SIGCOMM Computer Communication Review, Vol. 37, No. 3, pp. 83–84, 2007
DOI： 10.1145/1273445.1273458

1. ABSTRACT（摘要）

原始文字： "Researchers spend a great deal of time reading research papers. However, this skill is rarely taught, leading to much wasted effort. This article outlines a practical and efficient three-pass method for reading research papers. I also describe how to use this method to do a literature survey."

【中文注释】 研究者每年花费大量时间阅读论文，但这项技能很少被正式教授，导致大量精力被浪费。本文提出了一种实用且高效的三遍阅读法，并说明如何运用该方法进行文献综述。

2. INTRODUCTION（引言）

原始文字： "Researchers must read papers for several reasons: to review them for a conference or a class, to keep current in their field, or for a literature survey of a new field. A typical researcher will likely spend hundreds of hours every year reading papers."

【中文注释】 研究者阅读论文有多种目的：为会议或课程审稿、跟踪领域前沿、或对新领域进行文献调研。典型研究者每年可能花费数百小时阅读论文。

原始文字： "Learning to efficiently read a paper is a critical but rarely taught skill. Beginning graduate students, therefore, must learn on their own using trial and error. Students waste much effort in the process and are frequently driven to frustration."

【中文注释】 高效阅读论文是一项关键但极少被教授的技能。因此，刚入学的研究生必须通过试错自学，在此过程中浪费大量精力，并经常感到沮丧。

原始文字： "For many years I have used a simple 'three-pass' approach to prevent me from drowning in the details of a paper before getting a bird's-eye-view. It allows me to estimate the amount of time required to review a set of papers. Moreover, I can adjust the depth of paper evaluation depending on my needs and how much time I have."

【中文注释】 作者多年来使用一种简单的"三遍法"，避免在获得全局视角之前陷入细节泥潭。该方法还能帮助估算审阅一组论文所需时间，并根据需求和时间灵活调整阅读深度。

3. THE THREE-PASS APPROACH（三遍阅读法）

原始文字： "The key idea is that you should read the paper in up to three passes, instead of starting at the beginning and plowing your way to the end. Each pass accomplishes specific goals and builds upon the previous pass: The first pass gives you a general idea about the paper. The second pass lets you grasp the paper's content, but not its details. The third pass helps you understand the paper in depth."

【中文注释】 核心思想：不要从头到尾线性阅读，而应分三遍递进式阅读。每遍完成特定目标，并建立在前一遍基础上：

• 第一遍：获得论文的整体印象
• 第二遍：掌握内容，但不深入细节
• 第三遍：深度理解论文

3.1 The First Pass（第一遍）

原始文字： "The first pass is a quick scan to get a bird's-eye view of the paper. You can also decide whether you need to do any more passes. This pass should take about five to ten minutes and consists of the following steps:

1. Carefully read the title, abstract, and introduction
2. Read the section and sub-section headings, but ignore everything else
3. Glance at the mathematical content (if any) to determine the underlying theoretical foundations
4. Read the conclusions
5. Glance over the references, mentally ticking off the ones you've already read"

【中文注释】 第一遍是快速扫描，获得鸟瞰视角，同时决定是否需继续阅读。耗时约5-10分钟，包含五个步骤：

1. 仔细读标题、摘要和引言 —— 获取核心问题和方法
2. 读章节和子章节标题，忽略其他内容 —— 把握论文结构
3. 扫视数学内容（如有） —— 判断理论基础
4. 读结论 —— 了解主要发现
5. 浏览参考文献，标记已读文献 —— 建立知识关联

原始文字： "At the end of the first pass, you should be able to answer the five Cs:

1. Category: What type of paper is this? A measurement paper? An analysis of an existing system? A description of a research prototype?
2. Context: Which other papers is it related to? Which theoretical bases were used to analyze the problem?
3. Correctness: Do the assumptions appear to be valid?
4. Contributions: What are the paper's main contributions?
5. Clarity: Is the paper well written?"

【中文注释】 第一遍结束后，应能回答"五个C"：

1. 类别（Category）：论文类型是什么？测量类？现有系统分析？研究原型描述？
2. 背景（Context）：与哪些论文相关？使用哪些理论基础分析问题？
3. 正确性（Correctness）：假设是否有效？
4. 贡献（Contributions）：论文的主要贡献是什么？
5. 清晰度（Clarity）：论文写作是否良好？

原始文字： "Using this information, you may choose not to read further (and not print it out, thus saving trees). This could be because the paper doesn't interest you, or you don't know enough about the area to understand the paper, or that the authors make invalid assumptions. The first pass is adequate for papers that aren't in your research area, but may someday prove relevant."

【中文注释】 根据这些信息，你可以选择不再继续阅读（也不必打印，节省纸张）。原因可能是：论文不感兴趣、领域知识不足无法理解、或作者假设无效。第一遍对于非研究领域但未来可能相关的论文已经足够。

原始文字： "Incidentally, when you write a paper, you can expect most reviewers (and readers) to make only one pass over it. Take care to choose coherent section and sub-section titles and to write concise and comprehensive abstracts. If a reviewer cannot understand the gist after one pass, the paper will likely be rejected; if a reader cannot understand the highlights of the paper after five minutes, the paper will likely never be read. For these reasons, a 'graphical abstract' that summarizes a paper with a single well-chosen figure is an excellent idea and can be increasingly found in scientific journals."

【中文注释】 写作启示：当你写论文时，预期大多数审稿人和读者只读一遍。因此务必：

• 选择连贯的章节和子章节标题
• 撰写简洁而全面的摘要
• 如果审稿人一遍后无法理解要点，论文可能被拒
• 如果读者五分钟后无法理解亮点，论文可能永远不会被读
• 使用"图形摘要"（graphical abstract）—— 用一张精心选择的图概括论文，这在科学期刊中越来越常见

3.2 The Second Pass（第二遍）

原始文字： "In the second pass, read the paper with greater care, but ignore details such as proofs. It helps to jot down the key points, or to make comments in the margins, as you read. Dominik Grusemann from Uni Augsburg suggests that you 'note down terms you didn't understand, or questions you may want to ask the author.' If you are acting as a paper referee, these comments will help you when you are writing your review, and to back up your review during the program committee meeting."

【中文注释】 第二遍更仔细地阅读，但忽略证明等细节。建议边读边记录关键点或在页边做注释。奥格斯堡大学的Dominik Grusemann建议："记录不理解的术语，或想向作者提出的问题。"如果你担任论文审稿人，这些注释将帮助撰写审稿意见，并在程序委员会会议上支持你的观点。

原始文字： "Look carefully at the figures, diagrams and other illustrations in the paper. Pay special attention to graphs. Are the axes properly labeled? Are results shown with appropriate error bars, so that conclusions are statistically significant? These mistakes will often differentiate a sloppy paper from a careful one."

【中文注释】 仔细查看图表和插图，特别关注图形：

• 坐标轴是否适当标注？
• 结果是否显示适当的误差条，以确保结论具有统计显著性？
• 这些错误通常能区分粗心和严谨的论文。

原始文字： "After the second pass, you should be able to summarize the main thrust of the paper, with evidence, to someone else. This level of understanding is appropriate for a paper in which you are interested, but does not lie in your research specialty."

【中文注释】 第二遍后，你应能用证据向他人总结论文的核心论点。这种理解程度适用于你感兴趣但不属于你的研究专业的论文。

原始文字： "Sometimes you won't understand a paper even at the end of the second pass. This may be because the subject matter is new to you, with unfamiliar terminology and acronyms. Or the authors may use a proof or experimental technique that you don't understand, so that the bulk of the paper is incomprehensible. The paper may be poorly written, with unsubstantiated assertions and numerous forward references. Or it could just be that it's late at night and you're tired. You can now choose to: (a) set the paper aside, hoping you don't need to understand the material to be successful in your career, (b) return to the paper later, perhaps after reading background material or (c) persevere and go on to the third pass."

【中文注释】 有时即使读完第二遍仍无法理解论文。原因可能包括：

• 主题陌生，术语和缩写不熟悉
• 作者使用了你不理解的证明或实验技术
• 论文写作质量差，断言缺乏依据，大量前向引用
• 或只是深夜疲劳

此时可选择：

• (a) 搁置论文，希望职业生涯中不需要理解这些内容
• (b) 稍后重读，先读背景材料
• (c) 坚持并进入第三遍

3.3 The Third Pass（第三遍）

原始文字： "To fully understand a paper, particularly if you are reviewer, requires a third pass. The key to the third pass is to attempt to virtually re-implement the paper: that is, making the same assumptions as the authors, re-create the work. By comparing this re-creation with the actual paper, you can easily identify not only a paper's innovations, but also its hidden failings and assumptions."

【中文注释】 要完全理解论文，特别是作为审稿人，需要第三遍。第三遍的关键是尝试虚拟复现论文：即做出与作者相同的假设，在脑中重新构建这项工作。通过将虚拟复现与实际论文比较，你不仅能识别论文的创新点，还能发现其隐藏的缺陷和假设。

原始文字： "This pass requires great attention to detail. You should identify and challenge every assumption in every statement. Moreover, you should think about how you yourself would present a particular idea. This comparison of the actual with the virtual lends a sharp insight into the proof and presentation techniques in the paper and you can very likely add this to your repertoire of tools."

【中文注释】 这一遍需要极度关注细节。你应该识别并挑战每个陈述中的每个假设。此外，思考如果是你自己，会如何呈现某个特定观点。这种实际与虚拟的对比，能深刻洞察论文的证明和展示技巧，你很可能会将其加入自己的工具库。

原始文字： "During this pass, you should also jot down ideas for future work."

【中文注释】 在此过程中，还应记录未来工作的想法。

原始文字： "This pass can take about four or five hours for beginners, and about an hour for an experienced reader. At the end of this pass, you should be able to reconstruct the entire structure of the paper from memory, as well as be able to identify its strong and weak points. In particular, you should be able to pinpoint implicit assumptions, missing citations to relevant work, and potential issues with experimental or analytical techniques."

【中文注释】 第三遍耗时：初学者约4-5小时，有经验的读者约1小时。结束后，你应能：

• 凭记忆重构论文的完整结构
• 识别其优点和弱点
• 特别是能 pinpoint（精准定位）：
  • 隐含假设
  • 遗漏的相关文献引用
  • 实验或分析技术的潜在问题

4. DOING A LITERATURE SURVEY（文献综述方法）

原始文字： "If you are reading papers to do a literature survey, you may also need to read tens of papers, perhaps in an unfamiliar field. What should you read? Here is how you can use the three-pass approach to help."

【中文注释】 如果为了文献综述而阅读论文，你可能需要阅读数十篇论文，或许是在不熟悉的领域。应该读什么？以下是运用三遍法的方法。

原始文字： "First, use an academic search engine such as Google Scholar or CiteSeer and some well-chosen keywords to find three to five recent highly-cited papers in the area. Do one pass on each paper to get a sense of the work, then read their related work sections. You will find a thumbnail summary of the recent work, and perhaps, if you are lucky, a pointer to a recent survey paper. If you can find such a survey, you are done."

【中文注释】 第一步：使用Google Scholar或CiteSeer等学术搜索引擎，配合精心挑选的关键词，找到该领域3-5篇近期高引用论文。对每篇做第一遍阅读，了解工作概况，然后读它们的"相关工作"（Related Work）部分。你会找到近期工作的缩略总结，如果幸运，还可能发现近期综述论文的线索。如果找到这样的综述，任务完成。

原始文字： "Read the papers thoroughly. If so, you are done. Otherwise, in the next step, you find shared citations and repeated author names in the bibliography. These are the key papers and researchers in that area. Download the key papers and set them aside. Then go to the websites of the key researchers and see where they've published recently. That will help you identify the top conferences in that field because the best researchers usually publish in the top conferences."

【中文注释】 第二步：在参考文献中寻找共同引用和重复出现的作者名。这些就是该领域的关键论文和研究者。下载关键论文并搁置。然后访问关键研究者的网站，查看他们最近在哪里发表。这将帮助你识别该领域的顶级会议，因为最优秀的研究者通常发表在顶级会议上。

原始文字： "The third step is to go to the website for these top conferences and look through their recent proceedings. A quick scan will usually identify recent high-quality related work. These papers, along with the ones you set aside earlier, constitute the first version of your survey. Make two passes through these papers. If they all cite a key paper that you had not set aside earlier, obtain and read it, iterating as necessary."

【中文注释】 第三步：访问这些顶级会议的网站，浏览近期会议论文集。快速扫描通常能识别出近期高质量的相关工作。这些论文加上之前搁置的论文，构成你综述的初版。对这些论文进行两遍阅读。如果它们都引用了一篇你之前未搁置的关键论文，获取并阅读它，必要时迭代进行。

5. 核心要点总结

表格

6. 实践建议（论文中的补充提示）

Read critically（批判性阅读） "Should not assume that the authors are always correct. Asking appropriate questions."

【中文注释】 不要假设作者总是正确的。提出适当的问题。

Read creatively（创造性阅读） "What are the good ideas in this paper? Do these ideas have other applications or extensions? Are there possible improvements? What would be the next thing you would do?"

【中文注释】 思考：论文中的好想法是什么？这些想法是否有其他应用或扩展？是否存在改进可能？下一步你会做什么？

Do one pass on each paper（每篇论文先做一遍） "Make notes as you read the paper"

【中文注释】 边读边做笔记。

Agent Skills

https://skillhub.cn/skills/keshav-paper-reader

skillhub install keshav-paper-reader

用一篇Paper《Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks》

测试skills

输出，再生成HTML

以上图片生成参考

Nano Banana生成论文标注图片

总结

    Keshav的《How to Read a Paper》之所以成为经典，在于它精准地识别并解决了一个被忽视但普遍存在的学术痛点：在信息过载时代，研究者如何高效、系统、批判性地阅读论文。其价值不仅在于提供了一个具体方法，更在于建立了一种元认知框架——让读者意识到"阅读方式本身需要被设计"，从而将被动接受转化为主动建构。