[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84853-en":3,"doc-seo-84853-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84853,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Plainbook Data Science in Plain Language","Plainbook turns Jupyter-style computational notebooks into natural-language-first documents, designed for scientists who want data analysis and computation but cannot read or write code. It preserves the natural language cell descriptions and generates the code automatically, using a linear, top-to-bottom execution order that prevents hidden state and out-of-order runs. Verification is built in via cell-level checks and global mechanisms centered on values, supported by a snapshot kernel that caches execution states to keep execution and verification efficient.","Plainbook: Data Science, in Plain Language  \nLuca de Alfaro  \n[luca@ucsc.edu](luca@ucsc.edu)[ ](luca@ucsc.edu)University of California Santa Cruz, California, USA  \nMathis Aubert  \n[maubert@ucsc.edu](maubert@ucsc.edu)[ ](maubert@ucsc.edu)University of California Santa Cruz, California, USA  \nRanjit Jhala  \n[rjhala@ucsd.edu](rjhala@ucsd.edu)[ ](rjhala@ucsd.edu)University of California San Diego, California, USA  \nEliana Pastor  \neliana.pastor@polito.it Politecnico di Torino Torino, Italy  \nElena Baralis  \neliana.pastor@polito.it Politecnico di Torino Torino, Italy  \narXiv :2607 .057 17v 1 [ cs .HC] 7 Jul 2026  \nAbstract  \nJupyter Notebooks have become widely adopted in data science, as they allow the sharing of reproducible computational analysis. They are, however, accessible only to people who understand computer code. To reach the broader audience of scientists interested in data analysis and computation, but unfamiliar with code, we introduce Plainbook, notebooks centered on natural language rather than code.  \nPlainbook is based on two principles: promote the natural language descriptions, and verify the values. In Plainbook, the natural language descriptions are preserved, rather than the resulting code; the code is generated automatically from the cell descriptions. As natural language is read top to bottom, Plainbook adopts a linear execution semantics, in which cells are guaranteed to be executed in the order in which they appear; there is no “hidden state” or out-of-order execution as in Jupyter. To allow users who may not understand code to verify the correctness of the computation, we have built into Plainbook verification mechanisms centered on values and value inspection. These include mechanisms that focus on individual cells, akin to unit tests, as well as global mechanisms. Both the linear execution semantics, and the verification mechanisms, are underpinned by a snapshot kernel that caches execution states and makes execution and verification efficient.  \nKeywords: Jupyter Notebooks, Data Science, AI Generated Code, Coding in Natural Language, AI Assisted Programming, Conversational Notebooks, Computational Notebooks, Linear Execution Semantics, Unit Testing, Reproducible Research, Software Verification.  \n1 Introduction  \nJupyter Notebooks have become very widely adopted in data science, because they allow users to create and share analysis and results in a way that is verifiable, reproducible, and extensible [15, 19, 24, 26] . AJupyter Notebook consists of computer code (most commonly Python, but also otherlanguages such as R, Julia, and SQL), along with the output created by the code [27] . The output includes text output and also graphics, such as plots, diagrams, maps, and other  \nvisualizations that enable researchers and data scientists to include, in a single document, both the code that produced the results and the results themselves. The complete analysis can be shared in a way that makes it easy to reproduce and verify [32] . Anyone can read the code and run it to reproduce the results and check that the results included in the notebook are indeed generated by the code performing the analysis. Prior to notebooks, users had to keep extra metadata to associate the results with the analysis and code that produced them. Notebooks make this connection explicit: one can simply “re-run” the notebook to reproduce and validate the results. Further, when a notebook and its underlying data is shared, recipients can see how the results are obtained, and can modify the code to perform additional analyses or alter the settings of the analysis in the notebook.  \nThe above is only true if the notebook authors and recipients can read computer code. Data science has become very widely used, and its results are often shared with people who are not computer scientists. Furthermore, since AI has become quite proficient in generating code from natural language prompts, notebooks are often created by people who cannot wri","cbCaihzIhxX6ASQz","https://ap.wps.com/l/cbCaihzIhxX6ASQz","pdf",1127082,1,12,"English","en",105,"# Abstract\n# Introduction\n## Motivation: Limitations of code-centric notebooks\n## Core idea: Natural language descriptions as primary content\n## Linear execution semantics\n## Verification mechanisms","[{\"question\":\"What problem does Plainbook address compared with Jupyter Notebooks?\",\"answer\":\"Plainbook addresses the fact that Jupyter Notebooks are difficult to access for people who cannot read computer code, even though notebooks are meant to support verifiable and reproducible analysis.\"},{\"question\":\"How does Plainbook ensure execution order and avoid hidden state?\",\"answer\":\"Plainbook adopts a linear execution semantics where cells are executed in the same order they appear, with no out-of-order execution and no hidden state.\"},{\"question\":\"How does Plainbook verify that computations are correct?\",\"answer\":\"Plainbook includes verification mechanisms centered on values and value inspection, with both individual-cell checks (similar to unit tests) and global verification mechanisms.\"}]",1784198814,30,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"plainbook-data-science-in-plain-language","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/plainbook-data-science-in-plain-language/84853/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Plainbook address compared with Jupyter Notebooks?","Question",{"text":75,"@type":76},"Plainbook addresses the fact that Jupyter Notebooks are difficult to access for people who cannot read computer code, even though notebooks are meant to support verifiable and reproducible analysis.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Plainbook ensure execution order and avoid hidden state?",{"text":80,"@type":76},"Plainbook adopts a linear execution semantics where cells are executed in the same order they appear, with no out-of-order execution and no hidden state.",{"name":82,"@type":73,"acceptedAnswer":83},"How does Plainbook verify that computations are correct?",{"text":84,"@type":76},"Plainbook includes verification mechanisms centered on values and value inspection, with both individual-cell checks (similar to unit tests) and global verification mechanisms.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]