AI觉醒星球
Awakening is here
Knowledge File / AI技能杠杆
2026-06-20 0 浏览 会员

趋势解读:Data2Story turns a CSV file into a verified,讨论数据集与基础模型

牛津和斯坦福研究人员开发了Data2Story,一个基于Claude Code的AI系统,可将CSV文件转化为完整的交互式在线文章,包含研究背景、统计图表,并内置“检查器”将每个声明链接到证据。在评估中,74%的读者偏好AI生成的文章,尤其在透明度方面大幅领先人类作者。

SOURCE / AI技能杠杆 MIN / 9 ACCESS / 会员 POST / 2026-06-20 17:51:55

原贴

查看原文
作者:Jonathan Kemper 来源站点:the-decoder.com 原贴时间:

原文

Data journalism eats time like few other beats. A single investigation can keep a team busy for weeks. A new AI pipeline aims to automate most of that work without sacrificing verifiability. Researchers from Oxford and Stanford have built "Data Journalist Agent" (Data2Story), a Claude Code skill that turns a CSV file into a full interactive online article. The output includes research context, statistics, graphics, and a built-in feature linking every visible statement, chart, and interactive element to its evidence, be it code, data sources, or external URLs. The skill is a predefined task set that Claude Code loads and runs on command, orchestrating several specialized agent roles. The authors demo the system on a dataset that's gotten little coverage so far, the 2026 FIFA World Cup schedule. From the schedule and host cities, it generates a climate-focused article with an interactive map. About four in ten matches are slated for locations the players' union FIFPRO classifies as extremely high heat risk, with humidity rather than air temperature as the main driver. The authors stress these are typical climate conditions, not a forecast for the actual tournament. The system's core feature is the "Inspector," a panel showing structured evidence for each sentence and asset. Every annotated sentence, chart, and interactive element gets its own index card displaying either the exact line of code (plus the data file behind it) or the external URL backing a claim. This lets 93 percent of all visible statements be checked for their origin. That doesn't mean they're correct, the researchers stress, just verifiable. Doubt a figure? Run the code. The baseline for human-written articles is 25 percent, partly because journalists rarely publish analysis code. The gap reflects both a hole in journalism practice and a strength of the system, the researchers claim. Behind each article sits a chain of seven specialized agents the team calls a "virtual newsroom." The "Detective" runs web searches for context, since a table alone rarely tells the full story. For the World Cup data, it links host cities to FIFPRO heat risk ratings and Open-Meteo climate data. The "Analyst" runs code instead of guessing numbers. The "Editor" picks which findings drive the narrative. The "Designer" chooses the right medium, say a map for geography or an audio clip for music. The "Programmer" builds the HTML page, the "Auditor" checks layout for errors, and the "Inspector" ties everything back to sources. Each agent role in Data2Story's virtual newsroom handles one step from research to layout. The Inspector links every statement back to its source. | Image: Lin et al.[ The base model is Claude Opus 4.7 running on Claude Code. For images, video, and audio, the system pulls in OpenRouter models like gpt-5.4-image-2 , seedance-2.0 , and lyria-3-pro-preview . The researchers paired 18 public datasets with matching human-written originals from three distinct sources. They used the concise briefings from The Economist , the lavishly designed long reads from The Pudding , and the community datasets from TidyTuesday . 53 recruited readers rated both versions across five categories, including visual design, narrative rhythm, data transparency, verifiability of claims, and insight gained. Data2Story won all five categories. The biggest lead was in transparency, at +1.49 on a seven-point scale. Overall, 74 percent preferred the agent article, 25 percent the human version, and 2 percent called it a draw. By source, the picture shifts. The agent won clearly in data-heavy Economist briefings and TidyTuesday pieces. Against Pudding reports, which design teams often spend weeks crafting, it was a statistical tie. The agent couldn't beat handcrafted presentation.

中文翻译

数据新闻比其他任何领域都更耗费时间。一次调查可能让一个团队忙上数周。一个新的AI管道旨在自动化大部分工作,同时不牺牲可验证性。牛津和斯坦福的研究人员构建了“Data Journalist Agent”(Data2Story),一个Claude Code技能,能将CSV文件转化为完整的交互式在线文章。输出包括研究背景、统计、图形,以及一个内置功能,将每个可见的陈述、图表和交互元素链接到其证据,无论是代码、数据源还是外部URL。该技能是一个预定义的任务集,Claude Code加载并按命令运行,协调多个专门的代理角色。作者们在迄今为止鲜有报道的数据集——2026年世界杯赛程上演示了该系统。从赛程和主办城市,它生成了一篇聚焦气候的文章,带有交互式地图。约四成的比赛安排在了球员协会FIFPRO归类为极高热风险的地点,湿度而非气温是主要驱动因素。作者强调这些是典型气候条件,而非对实际赛事的预测。该系统的核心功能是“Inspector”,一个显示每个句子和资产结构化证据的面板。每个注释过的句子、图表和交互元素都有自己的索引卡,显示支持主张的确切代码行(及背后的数据文件)或外部URL。这使得93%的可见陈述可以检查其来源。研究人员强调,这并不意味着它们正确,只是可验证。怀疑某个数字?运行代码。人类撰写文章的可验证基线是25%,部分原因是记者很少发布分析代码。研究人员称,这一差距既反映了新闻实践的漏洞,也反映了该系统的优势。每篇文章背后是一系列七个专门代理,团队称之为“虚拟新闻编辑室”。“侦探”运行网络搜索以获取背景,因为单靠表格很少能讲述完整故事。对于世界杯数据,它将主办城市链接到FIFPRO热风险评级和Open-Meteo气候数据。“分析师”运行代码而非猜测数字。“编辑”选择哪些发现驱动叙事。“设计师”选择正确的媒介,比如地理的地图或音乐的音效。“程序员”构建HTML页面,“审计员”检查布局错误,“检查员”将所有内容链接回来源。每个代理角色处理从研究到布局的一步。基础模型是Claude Opus 4.7在Claude Code上运行。对于图像、视频和音频,系统引入OpenRouter模型如gpt-5.4-image-2、seedance-2.0和lyria-3-pro-preview。研究人员将18个公开数据集与来自三个不同来源的匹配人工撰写原文配对。他们使用了《经济学人》的简洁简报、The Pudding的华丽长篇阅读以及TidyTuesday的社区数据集。53名招募读者从五个类别(视觉设计、叙事节奏、数据透明度、声明可验证性、获得的洞见)对两个版本进行评分。Data2Story在所有五个类别中获胜。最大的领先在于透明度,在七分制中高出1.49分。总体而言,74%偏好代理文章,25%偏好人类版本,2%认为平局。按来源看,情况有所变化。代理在数据密集的《经济学人》简报和TidyTuesday文章中明显胜出。对于The Pudding报告(设计团队通常花费数周精心制作),则是统计上的平局。代理无法击败手工制作的呈现。

核心信息

牛津和斯坦福研究人员开发了Data2Story,一个基于Claude Code的AI系统,可将CSV文件转化为完整的交互式在线文章,包含研究背景、统计图表,并内置“检查器”将每个声明链接到证据。在评估中,74%的读者偏好AI生成的文章,尤其在透明度方面大幅领先人类作者。

  • Data2Story将CSV转化为可验证的交互式文章
  • 93%的陈述可追溯到代码或数据源
  • 评估中74%读者偏好AI生成的文章
  • 七代理虚拟新闻编辑室实现全流程自动化
  • 在透明度上以1.49分优势领先人类作者
试看内容

成为会员查看完整内容

你已经看到了这篇内容的前置整理,剩余深度部分仅对会员开放。

详细解读 信息差价值 参考来源
成为会员查看完整内容
上一篇 开源教程《Deep Agents 实战》发布 下一篇 趋势解读:baoyu-design Skill迭代,解读最新 AI 进展