[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82412-en":3,"doc-seo-82412-105":28,"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":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":13,"seo_description":14,"update_tm":26,"read_time":27},82412,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Knowledge Graphs and Explainable AI as Complementary Resources for Urban Mining","Pre-demolition assessment (PDA) anchors regulated urban mining in an information workflow where AI must support qualified auditors while keeping them accountable for decisions. Defensibility—not prediction accuracy—drives requirements: decisions need legibility, plausibility, clear sourcing, and contestability in regulatory documentation. Existing KG–XAI integration work is descriptive yet structurally underspecified about why pairings create defensibility-bearing audit artifacts. The paper proposes a complementarity-theoretic account in four KG–XAI modes: Lifting, Constraining, Typing, and Revising, illustrated with a fire-door example using the W3C Linked Building Data stack.","arXiv :2607 .09578v 1 [ cs .AI] 10 Jul 2026  \nKnowledge Graphs and Explainable AI as Complementary Resources for Urban Mining  \nJan Gronewald, Andreas Emrich, and Nijat Mehdiyev  \nGerman Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany {jan.gronewald,andreas.emrich,[nijat.mehdiyev}@dfki.de](nijat.mehdiyev}@dfki.de)  \n[Abstract.](Abstract. Pre-demolition assessment)[ Pre-demolition assessment](Abstract. Pre-demolition assessment), [the regulated audit process at](the regulated audit process at)the heart of urban mining, is an information process in which AI support must serve qualified auditors who remain accountable for the decisions taken. The relevant unit of value is not prediction accuracy alone, but the defensibility of the supported decisions: their legibility, plausibility, sourcing, and contestability. Explainable AI techniques and domain knowledge graphs each address parts of this requirement, and existing taxonomies have catalogued their integration. The literature is descriptively rich but structurally under-specified: what remains less developed is a structural account of why specific integrations produce artefacts neither resource can provide alone. This paper offers a complementarity-theoretic interpretation grounded in the IS resource-based tradition. We propose four consolidated KG–XAI integration modes (Lifting, Constraining, Typing, and Revising), each defined as a typed operation over XAI artefacts and knowledge-graph substrate structures. Each mode unlocks a distinct property of defensibility and contributes to the kind of regulatory artefact pre-demolition assessment demands. A fire-door example from the urban-mining process illustrates the modes using the W3C Linked Building Data stack and valuation extensions.  \nKeywords: Knowledge Graphs · Explainable AI · Urban Mining · Trustworthy AI · Technology Complementarity  \n1 Introduction  \nUrban mining, the systematic recovery of secondary materials from existing building stock, depends on a regulated audit process at the building’s end of life: pre-demolition assessment (PDA) . PDA structures this process as a multi-stage workflow in which a qualified auditor inventories components, characterises their materials and conditions, and routes them toward reuse, recycling, or disposal; in Germany the workflow is formalised by DIN SPEC 91484:2023 [1] . The performance of urban mining at scale is bounded less by the accuracy of any single technical component embedded in this process than by whether the decisions it supports are defensible: explainable to the auditor, traceable in documentation, and accountable to the regulatory regime under which they are taken [2] .  \nTwo technological resources speak to this requirement. Explainable AI offers a now-standard repertoire of techniques, such as feature attribution [3,4] and  \n2 J. Gronewald et al.  \ncounterfactual explanation [5,6], backed by a social-science account of useful explanations [7] . These techniques operate on the input space of the underlying model, however, and their outputs are correspondingly expressed in that space rather than in the regulatory categories within which the auditor must document. Symbolic structures are therefore needed to translate model-facing explanations into audit-facing categories. Knowledge graphs allow heterogeneous domain knowledge to be defined, linked, queried, and reasoned over at both conceptual and instance levels. The W3C Linked Building Data Working Group has defined a set of matching ontologies for buildings (semantic descriptions of elements, floor plans, material compositions, geometries, and product and pricing data [8]), with valuation indices such as the Urban Mining Index [9] providing the circular-construction layer on top.  \nThe integration of these resources has been taxonomised before [10,11] . The existing literature is descriptively rich but structurally under-specified. Where existing taxonomies classify KG–XAI integration by direct","cbCaitNtOxRKNFIU","https://ap.wps.com/l/cbCaitNtOxRKNFIU","pdf",332866,1,"English","en",105,"# Introduction\n## Urban mining audits and defensibility requirements\n## Roles of Explainable AI and Knowledge Graphs\n# Technology Complementarity as Methodological Lens\n## Complementarity and defensibility profile","[{\"question\":\"Why is explainability in urban-mining audits focused on defensibility rather than prediction accuracy?\",\"answer\":\"The regulated process requires supported decisions to be legible to auditors, plausible under domain constraints, traceable in documentation, and contestable within the regulatory regime. Defensibility is the accountability-relevant objective.\"},{\"question\":\"How do knowledge graphs and Explainable AI complement each other in this framework?\",\"answer\":\"Knowledge graphs translate and structure domain knowledge into queryable, reasoning-ready forms, while Explainable AI provides model-facing explanations. Their integration yields joint properties such as plausibility in the regulatory sense, sourcing of uncertainty, and contestability that neither resource alone ensures.\"},{\"question\":\"What are the four consolidated KG–XAI integration modes proposed in the paper?\",\"answer\":\"The paper defines four typed integration modes: Lifting, Constraining, Typing, and Revising. Each mode is treated as an operation over XAI artifacts and knowledge-graph substrate structures, linked to a distinct property of defensibility.\"}]",1784180185,20,{"code":4,"msg":29,"data":30},"ok",{"site_id":23,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":26},"knowledge-graphs-and-explainable-ai-as-complementary-resources-for-urban-mining","",{"@graph":34,"@context":84},[35,52,67],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/knowledge-graphs-and-explainable-ai-as-complementary-resources-for-urban-mining/82412/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is explainability in urban-mining audits focused on defensibility rather than prediction accuracy?","Question",{"text":74,"@type":75},"The regulated process requires supported decisions to be legible to auditors, plausible under domain constraints, traceable in documentation, and contestable within the regulatory regime. Defensibility is the accountability-relevant objective.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How do knowledge graphs and Explainable AI complement each other in this framework?",{"text":79,"@type":75},"Knowledge graphs translate and structure domain knowledge into queryable, reasoning-ready forms, while Explainable AI provides model-facing explanations. Their integration yields joint properties such as plausibility in the regulatory sense, sourcing of uncertainty, and contestability that neither resource alone ensures.",{"name":81,"@type":72,"acceptedAnswer":82},"What are the four consolidated KG–XAI integration modes proposed in the paper?",{"text":83,"@type":75},"The paper defines four typed integration modes: Lifting, Constraining, Typing, and Revising. Each mode is treated as an operation over XAI artifacts and knowledge-graph substrate structures, linked to a distinct property of defensibility.","https://schema.org",{"og:url":50,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":44,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":44,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":44,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":44,"category_name":124,"show_sort_weight":27,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":127,"show_sort_weight":27,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":44,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":44,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]