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.