1<!DOCTYPE html><html lang="en-HK" dir="ltr"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="image" href="/__l5e/assets-v1/d4fe1b75-9cc4-4202-94d3-fac9ae4a0648/aikm-logo-160.webp" fetchPriority="high"/><link rel="stylesheet" href="/assets/styles-aRRp267-.css" data-precedence="default"/><link rel="stylesheet" href="/assets/index-BG0RvJPG.css" data-precedence="default"/><title>Research Focus: RAG, Knowledge Graphs & Agentic AI | AIKm</title><meta name="google-site-verification" content="swnrB4sTuKgmMtqolX2xRtVubzdj5YKTcFZNj4fFKDk"/><meta property="og:site_name" content="AIKm (AI ç¥è管ç叿)"/><meta property="og:locale" content="en_HK"/><meta property="og:locale:alternate" content="ar_AE"/><meta name="twitter:card" content="summary_large_image"/><meta name="description" content="AIKm's research covers RAG, enterprise knowledge graphs, agentic AI, multimodal generative AI and responsible AI governance."/><meta property="og:type" content="website"/><meta property="og:title" content="Research Focus: RAG, Knowledge Graphs & Agentic AI | AIKm"/><meta property="og:description" content="AIKm's research covers RAG, enterprise knowledge graphs, agentic AI, multimodal generative AI and responsible AI governance."/><meta property="og:url" content="https://aikm.ai/research-focus"/><meta property="og:image" content="https://aikm.ai/__l5e/assets-v1/267e21fd-7d4f-4f01-b6c2-6fe152bcbbb2/aikm-og-cover.jpg"/><meta name="twitter:title" content="Research Focus: RAG, Knowledge Graphs & Agentic AI | AIKm"/><meta name="twitter:description" content="AIKm's research covers RAG, enterprise knowledge graphs, agentic AI, multimodal generative AI and responsible AI governance."/><meta name="twitter:image" content="https://aikm.ai/__l5e/assets-v1/267e21fd-7d4f-4f01-b6c2-6fe152bcbbb2/aikm-og-cover.jpg"/><link rel="modulepreload" href="/assets/index-DOrqagtV.js"/><link rel="modulepreload" href="/assets/useRouter-Bbx_8wWX.js"/><link rel="modulepreload" href="/assets/4dtech-logo-400.webp.asset-B1ZI7YmY.js"/><link rel="modulepreload" href="/assets/research-focus-BHbpFbOX.js"/><link rel="alternate" type="application/rss+xml" title="AIKm updates" href="https://aikm.ai/feed.xml"/><link rel="icon" href="/__l5e/assets-v1/db51d525-363d-40ba-aa25-4fcea6857665/favicon.png" type="image/png"/><link rel="preload" as="image" href="/__l5e/assets-v1/d4fe1b75-9cc4-4202-94d3-fac9ae4a0648/aikm-logo-160.webp" fetchPriority="high"/><link rel="preconnect" href="https://fonts.googleapis.com"/><link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="anonymous"/><link rel="preload" as="style" href="https://fonts.googleapis.com/css2?family=Bricolage+Grotesque:opsz,[email protected],400;12..96,600;12..96,700&family=IBM+Plex+Mono:wght@400;500&
1family=IBM+Plex+Sans:wght@400;500;600;700&display=swap"/><link rel="canonical" href="https://aikm.ai/research-focus"/><link rel="alternate" hrefLang="en-HK" href="https://aikm.ai/research-focus"/><link rel="alternate" hrefLang="zh-Hant-HK" href="https://aikm.ai/zh-hant/research-focus"/><link rel="alternate" hrefLang="zh-Hans" href="https://aikm.ai/zh-hans/research-focus"/><link rel="alternate" hrefLang="ar" href="https://aikm.ai/ar/research-focus"/><link rel="alternate" hrefLang="x-default" href="https://aikm.ai/research-focus"/>
1<script type="application/ld+json">{"@context":"https://schema.org","@type":"WebSite","@id":"https://aikm.ai/#website","url":"https://aikm.ai/","name":"AIKm (AI ç¥è管ç叿)","alternateName":"AI and Machine Learning Institute for Enterprise Knowledge Management","inLanguage":["en-HK","zh-Hant-HK","zh-Hans","ar"],"publisher":{"@id":"https://aikm.ai/#organization"}}</script>
1<script>(function(){function add(h){var l=document.createElement('link');l.rel='stylesheet';l.media='print';l.onload=function(){this.media='all'};l.href=h;document.head.appendChild(l)} 2add("https://fonts.googleapis.com/css2?family=Bricolage+Grotesque:opsz,[email protected],400;12..96,600;12..96,700&family=IBM+Plex+Mono:wght@400;500&family=IBM+Plex+Sans:wght@400;500;600;700&display=swap"); 3var p=location.pathname,f=[];if(/^\/zh-hant(\/|$)/.test(p))f.push('Noto+Sans+TC:wght@400;500;600;700');else if(/^\/zh-hans(\/|$)/.test(p))f.push('Noto+Sans+SC:wght@400;500;600;700');else if(/^\/ar(\/|$)/.test(p))f.push('Noto+Sans+Arabic:wght@400;500;600;700','Noto+Naskh+Arabic:wght@400;500;600;700'); 4if(f.length)add('https://fonts.googleapis.com/css2?'+f.map(function(x){return'family='+x}).join('&')+'&display=swap');})();</script>
4<script>(function(){var ID='G-BLJXEJWMSY';window.dataLayer=window.dataLayer||[];window.gtag=function(){window.dataLayer.push(arguments)};gtag('js',new Date());gtag('config',ID); 5var done=false;function load(){if(done)return;done=true;var pc=document.createElement('link');pc.rel='preconnect';pc.href='https://www.googletagmanager.com';document.head.appendChild(pc);var s=document.createElement('script');s.async=true;s.src='https://www.googletagmanager.com/gtag/js?id='+ID;document.head.appendChild(s)} 6function schedule(){(window.requestIdleCallback||function(cb){setTimeout(cb,1500)})(load,{timeout:5000})} 7if(document.readyState==='complete')schedule();else window.addEventListener('load',schedule,{once:true}); 8['pointerdown','keydown','touchstart'].forEach(function(e){window.addEventListener(e,load,{once:true,passive:true})});})();</script>
8<script type="application/ld+json">{"@context":"https://schema.org","@type":"CollectionPage","dateModified":"2026-07-28","datePublished":"2024-09-01","name":"AIKm Research Focus","url":"https://aikm.ai/research-focus","about":["Retrieval-augmented generation","Enterprise knowledge graphs","Agentic AI systems","Multimodal generative AI","Responsible AI governance"],"breadcrumb":{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://aikm.ai/"},{"@type":"ListItem","position":2,"name":"Research Focus","item":"https://aikm.ai/research-focus"}]}}</script>
8<script type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://aikm.ai/"},{"@type":"ListItem","position":2,"name":"Research Focus","item":"https://aikm.ai/research-focus"}]}</script>
8<script type="application/ld+json">{"@context":"https://schema.org","@type":"FAQPage","speakable":{"@type":"SpeakableSpecification","cssSelector":["#faq summary","#faq p"]},"mainEntity":[{"@type":"Question","name":"What does AIKm research?","acceptedAnswer":{"@type":"Answer","text":"AIKm researches five connected areas: retrieval-augmented generation (RAG) for enterprise Q&A on bilingual EnglishâChinese content, enterprise knowledge graphs with LLM-based extraction and GraphRAG, agentic AI systems with human-in-the-loop control, multimodal and generative AI for business, and responsible AI governance under Hong Kong PDPO and international AI regulation."}},{"@type":"Question","name":"How does AIKm's research connect to real enterprise deployments?","acceptedAnswer":{"@type":"Answer","text":"AIKm's research programme is applied: methods developed in the lab are proven in live enterprise deployments in Hong Kong and the Greater Bay Area. Consulting engagements feed back into research priorities, and every recommendation rests on measured retrieval accuracy, agent reliability and generation quality, not vendor claims."}},{"@type":"Question","name":"Which industries benefit from AIKm's research?","acceptedA
8nswer":{"@type":"Answer","text":"AIKm's work applies to finance and insurance, retail and F&B, logistics and freight, property and facilities, and professional services. Bilingual retrieval and PDPO-aware governance make it particularly relevant to Hong Kong enterprises operating across Cantonese, Mandarin and English."}},{"@type":"Question","name":"Does AIKm collaborate on research?","acceptedAnswer":{"@type":"Answer","text":"Yes. AIKm collaborates with universities, industry bodies (including HKIE) and enterprises on joint research and student placements. Fellow Members Prof Kenneth Lam and Dr W.M. Tsang are both on Stanford University's list of the world's top 2% most-cited scientists."}},{"@type":"Question","name":"What is the difference between RAG and a knowledge graph?","acceptedAnswer":{"@type":"Answer","text":"RAG retrieves passages of your text and feeds them to a language model so answers cite your documents. A knowledge graph turns the entities and relationships inside those documents into a structured, navigable network. GraphRAG combines both: structural search over the graph plus semantic search over the text, for more complete and traceable answers."}}]}</script>
8<script defer src="/~flock.js" data-proxy-url="/~api/analytics"></script>
8</head><body><a href="#main-content" class="skip-link">Skip to content</a><header class="site"><div class="wrap bar"><a aria-label="AIKm home" href="/" class="brand"><img class="logo" src="/__l5e/assets-v1/d4fe1b75-9cc4-4202-94d3-fac9ae4a0648/aikm-logo-160.webp" alt="AIKm logo" width="52" height="52" decoding="async" fetchPriority="high"/><span class="wordmark">AIKmâ¢<small>AI ç¥è管ç叿</small></span></a><nav class="primary" aria-label="Primary"><a href="/">Home</a><a href="/about">About</a><a aria-current="page" href="/research-focus" data-status="active">Research</a><a href="/courses">Courses</a><a href="/certification">Certification</a><a href="/consulting">Consulting</a><a href="/case-studies">Case studies</a><a href="/events">Events</a><a href="/members">Members</a><a href="/contact">Contact</a><a class="nav-cta" href="https://forms.gle/aTHJ1uifBT7tCDfH7" target="_blank" rel="noopener noreferrer">JOIN</a><div class="lang-switch compact" role="group" aria-label="Language"><span class="lang-switch-item"><a lang="en" aria-label="English" aria-current="page" class="lang-link active active" href="/research-focus" data-status="active">EN</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="zh-Hant" aria-label="ç¹é«ä¸æ" href="/zh-hant/research-focus" class="lang-link">ç¹</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="zh-Hans" aria-label="ç®ä½ä¸æ" href="/zh-hans/research-focus" class="lang-link">ç®</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="ar" aria-label="Ø§ÙØ¹Ø±Ø¨ÙØ©" href="/ar/research-focus" class="lang-link">ع</a></span></div></nav><div class="header-right"><a class="cta-btn blue join-cta" href="https://forms.gle/aTHJ1uifBT7tCDfH7" target="_blank" rel="noopener noreferrer">JOIN</a><div class="lang-switch" role="group" aria-label="Language"><span class="lang-switch-item"><a lang="en" aria-label="English" aria-current="page" class="lang-link active active" href="/research-focus" data-status="active">EN</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="zh-Hant" aria-label="ç¹é«ä¸æ" href="/zh-hant/research-focus" class="lang-link">ç¹</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="zh-Hans" aria-label="ç®ä½ä¸æ" href="/zh-hans/research-focus" class="lang-link">ç®</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="ar" aria-label="Ø§ÙØ¹Ø±Ø¨ÙØ©" href="/ar/research-focus" class="lang-link">ع</a></span></div><button class="nav-toggle" aria-label="Toggle navigation" aria-expanded="false"><svg width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round"><line x1="4" y1="7" x2="20" y2="7"></line><line x1="4" y1="12" x2="20" y2="12"></line><line x1="4" y1="17" x2="20" y2="17"></line></svg></button></div></div></header><main id="main-content" tabindex="-1"><!--$--><div class="page-head"><div class="wrap"><nav class="crumbs" aria-label="Breadcrumb"><a href="/">Home</a> / <span aria-current="page">Research Focus</span></nav><p class="eyebrow">Research focus</p><h1>Five connected areas, one programme</h1><p class="intro">As one of Hong Kong's pioneering institutes in enterprise knowledge management, our research runs from how machines find knowledge, to how they structure it, act on it, generate with it, and govern it. Each area feeds the next, all validated against real enterprise data, and all shaped by a farsighted team attentive to the societal impact of deep learning and AI.</p></div></div><section><div class="wrap"><div class="research-list"><div id="rag" class="r-row reveal"><div class="field">Retrieval</div><div><h2>Retrieval-augmented generation (RAG)</h2><p>Large language models are fluent but forgetful: they know the public internet, not your organisation. RAG grounds model answers in an enterprise's own documents so responses are accurate, current and citable, the foundation of trustworthy enterprise Q&A, search and assistant systems.</p><p>Our research examines the full pipeline: document chunking and embedding strategies for mixed EnglishâChinese corpora, hybrid dense-plus-keyword retrieval, re-ranking, and citation fidelity. We place particular weight on evaluation: frameworks that measure faithfulness and answer completeness, not just fluency.</p><p class="themes"><strong>Current themes:</strong> <!-- -->bilingual retrieval quality · long-document strategies · retrieval evaluation benchmarks · hallucination reduction</p></div></div><div id="knowledge-graphs" class="r-row reveal"><div class="field">Structure</div><div><h2>Enterprise knowledge graphs</h2><p>Most institutional knowledge is trapped in unstructured content: contracts, reports, emails, wikis. Knowledge graphs extract the entities and relationships inside that c
8ontent and connect them into a navigable structure: who worked on what, which product depends on which supplier, how decisions trace to evidence.</p><p>We study automated graph construction with LLMs, graph-augmented retrieval (GraphRAG) that combines structural and semantic search, and the harder operational problem: keeping a graph current as the organisation, its people and its products change.</p><p class="themes"><strong>Current themes:</strong> <!-- -->LLM-based entity and relation extraction · GraphRAG architectures · graph maintenance and versioning · ontology design for business domains</p></div></div><div id="agentic-ai" class="r-row reveal"><div class="field">Autonomy</div><div><h2>Agentic AI systems</h2><p>The next layer above retrieval is action: AI agents that plan multi-step work, call tools, query systems and produce finished outputs such as research memos, reports and process runs. The engineering challenge is reliability; the organisational challenge is control.</p><p>Our work covers task decomposition, tool-use robustness, multi-agent coordination, and human-in-the-loop checkpoints that let enterprises delegate real workflows without surrendering oversight. We benchmark agent behaviour on realistic enterprise tasks rather than synthetic puzzles.</p><p class="themes"><strong>Current themes:</strong> <!-- -->agent reliability measurement · tool and MCP integration patterns · approval and escalation design · agentic workflow economics</p></div></div><div id="generative-ai" class="r-row reveal"><div class="field">Generation</div><div><h2>Multimodal & generative AI</h2><p>Enterprise knowledge is not only text. We research generative models across text, image and video for business use, from technical documentation and marketing assets to full AIGC production pipelines for product design and communication.</p><p>The questions we pursue are practical: how to keep generated output consistent with brand and factual source material, how to track provenance and comply with emerging disclosure rules, and how the economics of generation at scale change content operations.</p><p class="themes"><strong>Current themes:</strong> <!-- -->video generation pipelines · brand-consistent generation · content provenance and watermarking · AIGC workflow design</p></div></div><div id="governance" class="r-row reveal"><div class="field">Governance</div><div><h2>Responsible AI & governance</h2><p>None of the above reaches production in a serious enterprise without governance. We develop frameworks for deploying AI in regulated, bilingual business environments: data privacy under Hong Kong's PDPO and cross-border rules, model risk assessment, auditability of AI-assisted decisions, and readiness for international AI regulation affecting companies that operate globally.</p><p>This area cuts across every project we run: governance designed in at the start, not retrofitted after an incident.</p><p class="themes"><strong>Current themes:</strong> <!-- -->AI risk assessment for SMEs and enterprises · audit trails for agentic systems · regulatory horizon scanning · bilingual policy documentation</p></div></div></div><p style="margin-top:40px;display:flex;gap:14px;flex-wrap:wrap"><a href="/contact" class="cta-btn blue">Collaborate with us</a><a href="/research/ai-km-roi" class="cta-btn ghost">Guide: measuring AI KM ROI</a><a href="/about" class="cta-btn ghost">About the institute</a></p></div></section><section class="tint"><div class="wrap"><div class="sec-head reveal"><p class="eyebrow">Research briefs</p><h2>In-depth notes from our engagements</h2></div><ul style="list-style:none;padding:0;display:grid;gap:12px"><li><a href="/research/rag-enterprise-patterns">RAG patterns for enterprise knowledge â</a></li><li><a href="/research/enterprise-knowledge-graphs">Enterprise knowledge graphs: construction and use â</a></li><li><a href="/research/agentic-ai-governance">Agentic AI governance checklist â</a></li><li><a href="/research/multimodal-enterprise-ai">Multimodal AI for enterprise content â</a></li><li><a href="/research/evaluating-enterprise-ai">Evaluating enterprise AI: groundedness and drift â</a></li><li><a href="/research/llm-cost-optimization">Cost optimisation for enterprise LLM deployments â</a></li><li><a href="/research/ai-km-roi">Measuring AI KM ROI â</a></li></ul></div></section><section id="faq" class="faq"><div class="wrap"><div class="sec-head reveal"><p class="eyebrow">Frequently asked questions</p><h2>AIKm research focus: FAQ</h2></div><details><summary>What does AIKm research?</summary><p>AIKm researches five connected areas: retrieval-augmented generation (RAG) for enterprise Q&A on bilingual EnglishâChinese content, enterprise knowledge graphs with LLM-based extraction and GraphRAG, agentic AI systems with human-in-the-loop control, multimodal and generative AI for business, and responsible AI governance under Hong Kong PDPO and international AI regulation.</p></details>
8<details><summary>How does AIKm's research connect to real enterprise deployments?</summary><p>AIKm's research programme is applied: methods developed in the lab are proven in live enterprise deployments in Hong Kong and the Greater Bay Area. Consulting engagements feed back into research priorities, and every recommendation rests on measured retrieval accuracy, agent reliability and generation quality, not vendor claims.</p></details><details><summary>Which industries benefit from AIKm's research?</summary><p>AIKm's work applies to finance and insurance, retail and F&B, logistics and freight, property and facilities, and professional services. Bilingual retrieval and PDPO-aware governance make it particularly relevant to Hong Kong enterprises operating across Cantonese, Mandarin and English.</p></details><details><summary>Does AIKm collaborate on research?</summary><p>Yes. AIKm collaborates with universities, industry bodies (including HKIE) and enterprises on joint research and student placements. Fellow Members Prof Kenneth Lam and Dr W.M. Tsang are both on Stanford University's list of the world's top 2% most-cited scientists.</p></details><details><summary>What is the difference between RAG and a knowledge graph?</summary><p>RAG retrieves passages of your text and feeds them to a language model so answers cite your documents. A knowledge graph turns the entities and relationships inside those documents into a structured, navigable network. GraphRAG combines both: structural search over the graph plus semantic search over the text, for more complete and traceable answers.</p></details></div></section>
8<script>(function(a,f){let l;try{l=JSON.parse(sessionStorage.getItem(a)||"{}")}catch{return}const n=l?.[f||history.state?.__TSR_key];let c=!1;for(const t in n){const e=n[t],o=e?.scrollX,s=e?.scrollY;if(Number.isFinite(o)&&Number.isFinite(s)){if(t==="window")scrollTo(o,s),c=!0;else if(t)try{const r=document.querySelector(t);r&&(r.scrollLeft=o,r.scrollTop=s)}catch{}}}if(c)return;const i=location.hash.slice(1);if(i){const t=history.state?.__hashScrollIntoViewOptions??!0;if(t){const e=document.getElementById(i);e&&e.scrollIntoView(t)}return}scrollTo(0,0)})("tsr-scroll-restoration-v1_3");document.currentScript.remove()</script>
8<!--/$--></main><footer><div class="wrap"><div class="cols"><div class="brand-col"><div class="brand-foot"><img src="/__l5e/assets-v1/d4fe1b75-9cc4-4202-94d3-fac9ae4a0648/aikm-logo-160.webp" alt="AIKm logo" width="48" height="48" loading="lazy" decoding="async" style="height:48px;width:auto;border-radius:8px"/><span class="wordmark">AIKm · AI ç¥è管ç叿<small>AI and Machine Learning Institute for Enterprise Knowledge Management</small></span></div><p style="max-width:32em">AI and Machine Learning Institute for Enterprise Knowledge Management. Research, consulting and training in AI for enterprise knowledge, based at Hong Kong Science Park.</p></div><div class="link-col"><h3>Institute</h3><ul><li><a href="/about">About</a></li><li><a class="active" href="/research-focus" data-status="active" aria-current="page">Research focus</a></li><li><a href="/courses">AI courses (HK)</a></li><li><a href="/certification">AIKm CAIP⢠certification</a></li><li><a href="/consulting">AI consulting</a></li><li><a href="/case-studies">Case studies</a></li><li><a href="/events">Events</a></li><li><a href="/guides/ai-native-organization">AI-native organization guide</a></li><li><a href="/members">Members</a></li></ul></div><div class="link-col"><h3>Resources</h3><ul><li><a href="/guides/choosing-ai-training-hong-kong">Choosing AI training in Hong Kong</a></li><li><a href="/research/ai-km-roi">AI knowledge management ROI</a></li><li><a href="/facts">Facts & figures</a></li><li><a href="/glossary">AI glossary</a></li></ul></div><div class="link-col connect-col"><h3>Contact</h3><ul><li><a href="mailto:[email protected]">[email protected]</a></li><li><a href="/contact">Enquiry form</a></li></ul><div class="foot-group"><h3>Follow</h3><ul><li><a href="https://www.youtube.com/watch?v=VRNb1m_YXPg" target="_blank" rel="noopener noreferrer">YouTube</a></li><li><a href="https://www.facebook.com/AIKmHongKong/" target="_blank" rel="noopener noreferrer">Facebook Page</a></li><li><a href="https://github.com/AI-KM" target="_blank" rel="noopener noreferrer">GitHub</a></li></ul></div><div class="foot-group"><h3>Language</h3><div class="lang-switch" role="group" aria-label="Language"><span class="lang-switch-item"><a lang="en" aria-label="English" aria-current="page" class="lang-link active active" href="/research-focus" data-status="active">EN</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="zh-Hant" aria-label="ç¹é«ä¸æ" href="/zh-hant/research-focus" class="lang-link">ç¹</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="zh-Hans" aria-label="ç®ä½ä¸æ" href="/zh-hans/research-focus" class="lang-link">ç®</a></span><span class="lang-switch-item"><span class="lang-sep" aria-hidden="true">·</span><a lang="ar" aria-label="Ø§ÙØ¹Ø±Ø¨ÙØ©" href="/ar/research-focus" class="lang-link">ع</a></span></div></div></div></div><div class="legal"><span>© 2024 - <!-- -->2026<!-- --> <!-- -->AI and Machine Learning Institute for Enterprise Knowledge Management</span></div></div></footer>
8<script class="$tsr" id="$tsr-stream-barrier">(self.$R=self.$R||{})["tsr"]=[];self.$_TSR={h(){this.hydrated=!0,this.c()},e(){this.streamEnded=!0,this.c()},c(){this.hydrated&&this.streamEnded&&(delete self.$_TSR,delete self.$R.tsr)},p(e){this.initialized?e():this.buffer.push(e)},buffer:[]};$_TSR.router=($R=>$R[0]={manifest:$R[1]={routes:$R[2]={__root__:$R[3]={preloads:$R[4]=["/assets/index-DOrqagtV.js","/assets/useRouter-Bbx_8wWX.js","/assets/4dtech-logo-400.webp.asset-B1ZI7YmY.js"],scripts:$R[5]=[$R[6]={attrs:$R[7]={type:"module",async:!0,src:"/assets/index-DOrqagtV.js"}}],css:$R[8]=["/assets/index-BG0RvJPG.css"]},"/research-focus":$R[9]={preloads:$R[10]=["/assets/research-focus-BHbpFbOX.js"]}}},matches:$R[11]=[$R[12]={i:"__root__�",u:1790903439080,s:"success",ssr:!0},$R[13]={i:"�research-focus�research-focus",u:1790903439080,s:"success",ssr:!0}],lastMatchId:"�research-focus�research-focus"})($R["tsr"]);$_TSR.e();document.currentScript.remove()</script>
8<script type="module" async="" src="/assets/index-DOrqagtV.js"></script>
8</body></html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.