[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84196-en":3,"doc-seo-84196-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},84196,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Granularity in Action Graphing Sources for Social History","This working paper presents a pipeline that converts historical sources into structured data by treating foregrounded action as the primary unit of analysis for granular social history. Built on the GRAM-framework (Graph of Roles and Actions Model), the approach uses machine-learning tools for automated, skeletal graphing of actions while supporting integration with close readings and manual graphing. An application demonstrates action graphing of pretending across four Danish archival collections, linking runaways and itinerants in the eighteenth and nineteenth centuries.","arXiv :2607 .07 183v 1 [ cs .IR] 8 Jul 2026  \nGranularity in Action  \nGraphing sources for social history Sofus Landor Dam and Johan Heinsen 1  \nThis working paper describes a pipeline for turning historical sources into structured data organised around the principle of foregrounding action as the basic and constitutive unit of analysis. It is rooted in a desire for pipelines that suit a granular approach to social history. The pipeline rests on the principles developed in the GRAM-framework (Graph of Roles and Actions Model), but leverages a range of machine learning tools to allow for an automated, skeletal graphing of actions. Ideally, such auto-GRAMS would integrate with close readings, including extensive manual graphing. Finally, we provide an example of how this approach might work in practice by graphing actions of pretending across four separate archival collections, relating to runaways and itinerants in eighteenth and nineteenth-century Denmark.  \nKeywords: Granular social history, graph database, archival reconstruction, machine learning  \nAFFILIATION 1 MASSHINE, Aalborg University CORRESPONDENCE [sld@society.aau.dk](sld@society.aau.dk)[ ](sld@society.aau.dk)VERSION July 9, 2026  \n1 INTRODUCTION  \nAs historians transform archival sources into research data, those data should have textures that align with the granularity of the materials from which they are derived. In this context, this means to work from the explicit descriptions ofactions as embedded in verbs and their contexts. Preserving that texture might inform querying for a practice-oriented, granular social history centered on what people did to one another, and the specifics under which they did it. That is not to deny the role of interpretation  \nor theory, but to make a case for empirical studies to rest on a data structure that aligns with a conception of social relations as configurations of multiple distinct elements and practices that manipulate those elements [4]. In a way, we attempt to background theoretically informed (pre)suppositions, and instead let the actions of historical actors do the talking.  \nThis approach is in contrast to other recent methodological scholarship in digital history contexts, that instead foregrounds the role of theory when constructing data structures or computational tools for historical inquiry [11, 2]. These studies call for theory to be built-in and used as a guiding principle-especially when non-deterministic elements such as machine learning and artificial intelligence are involved in the workflow. We, instead, try to reduce the interpretive role of language models to a minimum and adjust the unit of analysis to its smallest and most meaningful unit-the action.  \nHere, we will outline an approach designed to allow social historians to query textual representations ofactions in ways that can incorporate substantial amounts of data (more than human eyes could otherwise process) without losing sight of granularity. This is not an argu-  \nment for a quantitative history, but rather one that has the tools to look past the artificial constructs of quantitative/qualitative (or macro/micro) by partially aligning data sources in the same data structure, big or small. In so far as this is considered a question of scale, it only relates to the amounts of sources and not the ontology of what is studied [3].  \nWe developed this approach as part of our ongoing research project Run Away in which we study what people did while on the run, typically from either labour relations or state institutions.1 The project focuses on Denmark in the eighteenth and nineteenth-centuries and studies a range of people including convicts, soldiers, sailors, apprentices and servants. During the period we study, we see strong indicators that running away and becoming someone else went from being a very real possibility to being virtually impossible, but that this was a slow, gradual process owing to a host offactors. We study that process on the b","cbCaiu4bZmUkb0KQ","https://ap.wps.com/l/cbCaiu4bZmUkb0KQ","pdf",3031645,1,21,"English","en",105,"# Introduction\n# Pipeline Overview","[{\"question\":\"What is the core idea of the proposed pipeline?\",\"answer\":\"It structures historical data around foregrounding action as the basic unit of analysis, extracting action descriptions embedded in verbs and their contexts.\"},{\"question\":\"How does the pipeline relate to the GRAM framework?\",\"answer\":\"It is rooted in the GRAM-framework principles, while leveraging machine-learning tools to enable automated, skeletal graphing of actions.\"},{\"question\":\"What example application is used to illustrate the method?\",\"answer\":\"The paper graphes actions of pretending across four separate archival collections, relating runaways and itinerants in eighteenth- and nineteenth-century Denmark.\"}]",1784193872,53,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"granularity-in-action-graphing-sources-for-social-history","",{"@graph":35,"@context":84},[36,53,67],{"@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/granularity-in-action-graphing-sources-for-social-history/84196/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the core idea of the proposed pipeline?","Question",{"text":74,"@type":75},"It structures historical data around foregrounding action as the basic unit of analysis, extracting action descriptions embedded in verbs and their contexts.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the pipeline relate to the GRAM framework?",{"text":79,"@type":75},"It is rooted in the GRAM-framework principles, while leveraging machine-learning tools to enable automated, skeletal graphing of actions.",{"name":81,"@type":72,"acceptedAnswer":82},"What example application is used to illustrate the method?",{"text":83,"@type":75},"The paper graphes actions of pretending across four separate archival collections, relating runaways and itinerants in eighteenth- and nineteenth-century Denmark.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"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":105,"slug":137},19,"General","general"]