[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-648088-105":59,"doc-detail-648088-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","blueprint-rebuilding-a-legacy-multimodal-retrieval-for-complex-engineering-drawings-and-documents-success3-and-ndcg3-evaluation","BLUEPRINT - Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents - Success@3 and nDCG3 Evaluation","","Decades of engineering drawings and technical records are trapped in legacy archives with inconsistent or missing metadata, making retrieval difficult and often manual. BLUEPRINT is a layout-aware multimodal retrieval system for large-scale engineering repositories. It detects canonical drawing regions, performs region-restricted VLM-based OCR, normalizes engineering identifiers, and fuses lexical with dense retrieval using a lightweight region-level reranker. Evaluated on 5k files with 350 expert-curated queries, BLUEPRINT improves Success@3 by 10.1% absolute and nDCG3 by 18.9% relative, and releases resources for reproducible assessment.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/blueprint-rebuilding-a-legacy-multimodal-retrieval-for-complex-engineering-drawings-and-documents-success3-and-ndcg3-evaluation/648088/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/blueprint-rebuilding-a-legacy-multimodal-retrieval-for-complex-engineering-drawings-and-documents-success3-and-ndcg3-evaluation/648088.png","ImageObject",300,407,{"name":92,"@type":93},"Putri","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-26","2026-10-23",true,{"@type":102,"interactionType":103,"userInteractionCount":8},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does BLUEPRINT address in legacy engineering archives?","Question",{"text":112,"@type":113},"Engineering drawings and technical records are often stored with inconsistent or missing metadata, so relevant documents are hard to find. BLUEPRINT targets scalable retrieval by leveraging both visual layout regions and textual signals.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does BLUEPRINT retrieve information from engineering drawings and documents?",{"text":117,"@type":113},"It detects layout regions, applies region-restricted VLM-based OCR on the vision path, parses identifiers into structured metadata, and extracts entities and structure from procedural text. The system fuses sparse and dense retrieval and uses a lightweight region-level reranker at query time.",{"name":119,"@type":110,"acceptedAnswer":120},"How is BLUEPRINT evaluated and what improvements does it achieve?",{"text":121,"@type":113},"On a 5k-file benchmark with expert-curated queries and graded relevance, BLUEPRINT shows a 10.1% absolute gain in Success@3 and an 18.9% relative improvement in nDCG3 over the strongest vision-language baseline.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},648088,1793051661,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":46,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":31},962085571259,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","BLUEPRINT – Rebuilding a Legacy: Multimodal Retrieval for Complex  \nEngineering Drawings and Documents  \narXiv :2602 . 13345v1 [ cs .LG] 12 Feb 2026  \nEthan Seefried 1 ,2 Ran Eldegaway 1 Sanjay Das 1 Nathaniel Blanchard2 Tirthankar Ghosal 1  \n1 Oak Ridge National Laboratory, Oak Ridge, Tennessee  \n2 Colorado State University, Fort Collins, Colorado  \n[seefriedej@ornl.gov](seefriedej@ornl.gov) , [ghosalt@ornl.gov](ghosalt@ornl.gov)  \nAbstract  \nDecades of engineering drawings and technical records remain locked in legacy archives with inconsistent or missing metadata, making retrieval difficult and often manual. We present BLUEPRINT, a layout-aware multimodal retrieval system designed for large-scale engineering repositories. BLUEPRINT detects canonical drawing regions, applies region-restricted VLM-based OCR, normalizes identifiers (e.g., DWG, part, facility), and fuses lexical and dense retrieval with a lightweight region-level reranker. Deployed on ∼ 770k unlabeled files, it automatically produces structured metadata suitable for cross-facility search.  \nWe evaluate BLUEPRINT on a 5k-file benchmark with 350 expert-curated queries using pooled, graded (0/1/2) relevance judgments. BLUEPRINT delivers a 10.1% absolute gain in Success@3 and an 18.9% relative improvement innDCG3 over the strongest vision-language baseline, consistently outperforming across vision, text, and multimodal intents. Oracle ablations reveal substantial headroom under perfect region detection and OCR. We release all queries, runs, annotations, and code to facilitate reproducible evaluation on legacy engineering archives.  \n1. Introduction  \nEngineering organizations rely on diagrams, drawings, and linked documentation to design, operate, and maintain complex systems [47, 49] . Over decades, these assets accumulate across heterogeneous and siloed repositories (e.g., shared drives, PLM/EDRM systems, vendor portals), with idiosyncratic authoring styles and inconsistent conventions [68] . As sites modernize digital infrastructure and senior experts retire, critical knowledge risks becoming inaccessible [8, 10, 16, 24, 44, 57] . Fully re-cataloging legacy archives would require annotating hundreds of thousands of files, costly, slow, and error-prone, making scalable retrieval  \nHybrid search (lexical + ANN) → Faceted filters → Region-aware reranker → Result cards (thumbnail + type + title)  \nFigure 1 . BLUEPRINT processes an engineer’s natural-language query and returns multimodal results across drawings, schematics, and procedural documents.  \nrather than re-labeling the core challenge.  \nLegacy corpora are heterogeneous in format (vector CAD, raster scans, TIFF/PDF, mixed-mode), quality (lowresolution scans, skew, bleed-through), and metadata (often missing or unreliable) . Collections are inherently multimodal: visual drawings co-exist with policies, procedures, and narrative reports. Engineers query in text, but evidence often resides in visual regions such as title blocks, revision tables, or symbols. OCR noise, domain abbreviations, and near-duplicate revisions further complicate retrieval [7, 46] . These constraints motivate systems that fuse sparse textual signals with layout-and region-aware visual cues for robust, scalable retrieval over engineering documents.  \nWe propose BLUEPRINT: Multimodal Retrieval for Engineering Archives, a framework that unifies computer vision and NLP for legacy engineering corpora. A lightweight modality router sends each file down a vision-first path (drawings, scans) or a text-first path (policies, procedures) . On the vision path, the system detects layout regions (e.g., title block, revisions, parts list), applies region-restricted  \nOCR, and parses identifiers into structured metadata (e.g., drawing number, revision, facility tags, parts-list entries) . On the text path, BLUEPRINT extracts key entities and sectionlevel structure from procedural documents. These signals are fused into a joint embedding and indexed in a","cbCaivpKn3hnsWTg","https://ap.wps.com/l/cbCaivpKn3hnsWTg","pdf",1396822,"English","# Introduction\n## Engineering legacy challenges\n## Proposed BLUEPRINT framework\n## Experimental evaluation and contributions\n# Related Work\n## Document Retrieval Systems","[{\"question\":\"What problem does BLUEPRINT address in legacy engineering archives?\",\"answer\":\"Engineering drawings and technical records are often stored with inconsistent or missing metadata, so relevant documents are hard to find. BLUEPRINT targets scalable retrieval by leveraging both visual layout regions and textual signals.\"},{\"question\":\"How does BLUEPRINT retrieve information from engineering drawings and documents?\",\"answer\":\"It detects layout regions, applies region-restricted VLM-based OCR on the vision path, parses identifiers into structured metadata, and extracts entities and structure from procedural text. The system fuses sparse and dense retrieval and uses a lightweight region-level reranker at query time.\"},{\"question\":\"How is BLUEPRINT evaluated and what improvements does it achieve?\",\"answer\":\"On a 5k-file benchmark with expert-curated queries and graded relevance, BLUEPRINT shows a 10.1% absolute gain in Success@3 and an 18.9% relative improvement in nDCG3 over the strongest vision-language baseline.\"}]","BLUEPRINT - Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents - Success@3 and nDCG3 Evaluation | PDF",1792792176]