[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"portal-settings:stajic:en":3,"public-menus:all":38,"post:how-far-is-an-ai-claim-from-the-evidence-evidence-distance:en":221,"related:post:how-far-is-an-ai-claim-from-the-evidence-evidence-distance:en:1":1066},{"statusCode":4,"data":5,"message":37},200,{"tenantId":6,"lang":7,"defaultLang":8,"siteUrl":9,"contactEmail":10,"brandName":11,"logoUrl":12,"siteName":11,"siteDescription":13,"ogImage":10,"robotsIndex":14,"socialLinks":10,"reservedSlugs":10,"seoPolicy":15},"stajic","en","de","https:\u002F\u002Fstajic.de",null,"Stajic Platform","\u002FLogo_Planet.svg","Stajic Portal",true,{"branding":16,"relatedContent":17,"crossDomainLinks":18},{"logoUrl":12},{"enabled":14},[19,22,25,28,31,34],{"url":20,"label":21,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Ffigure.rocks","figure.rocks",{"url":23,"label":24,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Floving.rocks","loving.rocks",{"url":26,"label":27,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.com","bazify.com",{"url":29,"label":30,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.de","bazify.de",{"url":32,"label":33,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.at","bazify.at",{"url":35,"label":36,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.ba","bazify.ba","Portal settings resolved",[39,45],{"id":40,"name":41,"location":42,"isActive":14,"isDefault":43,"items":44},1,"main-navigation","header",false,[],{"id":46,"name":47,"location":48,"isActive":14,"isDefault":14,"items":49},4,"main-menu","sidebar",[50,66,79,93,103,118,133],{"id":51,"title":52,"url":60,"target":61,"icon":62,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":64,"portfolioId":10,"children":65},"item-18",{"de":53,"en":54,"es":55,"fr":56,"it":54,"ru":57,"sr":58,"zh":59},"Startseite","Home","Inicio","Accueil","Главная","Почетна","首页","\u002Ffull-stack-web-developer-munich-performance-seo-and-maintainable-builds","_self","i-lucide-home","page",111,[],{"id":67,"title":68,"url":75,"target":61,"icon":76,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":77,"portfolioId":10,"children":78},"item-22",{"de":69,"en":69,"es":70,"fr":69,"it":71,"ru":72,"sr":73,"zh":74},"Vision","Visión","Visione","Видение","Визија","想象","\u002Fueber-uns-webdesign-muenchen-webaplikation","i-lucide-eye",113,[],{"id":80,"title":81,"url":89,"target":61,"icon":90,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":91,"portfolioId":10,"children":92},"item-19",{"de":82,"en":83,"es":84,"fr":83,"it":85,"ru":86,"sr":87,"zh":88},"Leistungen","Services","Servicios","Servizi","Услуги","Услуге","服务","\u002Fservices-dienstleistungen-muenchen","i-lucide-wrench",116,[],{"id":94,"title":95,"url":99,"target":61,"icon":100,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":101,"portfolioId":10,"children":102},"item-23",{"de":96,"en":96,"es":96,"fr":96,"it":96,"ru":97,"sr":97,"zh":98},"Blog","Блог","博客","\u002Fblog","i-lucide-book-open",112,[],{"id":104,"title":105,"url":114,"target":61,"icon":115,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":116,"portfolioId":10,"children":117},"item-32",{"de":106,"en":107,"es":108,"fr":109,"it":110,"ru":111,"sr":112,"zh":113},"Neue Technologien","New Technologies","Nuevas tecnologías","Nouvelles technologies","Nuove tecnologie","Новые технологии","Нове технологије","新技术！","\u002Fneue-webtechnologien","i-lucide-sparkles",122,[],{"id":119,"title":120,"url":129,"target":61,"icon":130,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":131,"portfolioId":10,"children":132},"item-20",{"de":121,"en":122,"es":123,"fr":124,"it":125,"ru":126,"sr":127,"zh":128},"Kontakt","Contact us!","Contacto","Contact","Contatto","Контакт","Контактирајте нас","联系我们！","\u002Fcontact","i-lucide-mail",115,[],{"id":134,"title":135,"url":144,"target":61,"icon":145,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":146,"portfolioId":10,"children":147},"item-21",{"de":136,"en":137,"es":138,"fr":139,"it":140,"ru":141,"sr":142,"zh":143},"Unsere Arbeit","Our Work","Nuestro trabajo","Nos réalisations","I nostri lavori","Наши работы","Наши радови","文件夹","\u002Fportfolio","i-lucide-briefcase",114,[148,161,175,191,206],{"id":149,"title":150,"url":144,"target":61,"icon":159,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":146,"portfolioId":10,"children":160},"item-24",{"de":151,"en":152,"es":153,"fr":154,"it":155,"ru":156,"sr":157,"zh":158},"Alle Projekte","All Projects","Todos los proyectos","Tous les projets","Tutti i progetti","Все проекты","Сви пројекти","所有项目","i-lucide-grid-3x3",[],{"id":162,"title":163,"url":171,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":174},"item-29",{"de":164,"en":165,"es":166,"fr":167,"it":168,"ru":169,"sr":170,"zh":143},"Local Roots, Global Reach","Local Roots - Global Reach","Empresa local ","Entreprise locale","Azienda locale","Местная компания","Локално предузеће глобално тржиште","\u002Fportfolio\u002Flocal-roots-global-reach-communication-media-systems-for-modern-business","i-lucide-globe-2","custom",[],{"id":176,"title":177,"url":186,"target":61,"icon":187,"isActive":14,"type":188,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":189,"children":190},"menu-2916d060-8681-482a-af9a-c107a8bc30d8",{"de":178,"en":179,"es":180,"fr":181,"it":182,"ru":183,"sr":184,"zh":185},"Von Rohdaten zu verifizierbarem KI-Kontext: Eine praktische Architektur für agentenbereite Informationen","From Raw Data to Verifiable AI Context:","De datos sin procesar a contexto de IA verificable: una arquitectura práctica para información lista para agentes","Des données brutes au contexte d'IA vérifiable : une architecture pratique pour des informations prêtes pour les agents","Dai dati grezzi a un contesto IA verificabile: Un'architettura pratica per informazioni pronte per gli agenti","От необработанных данных к верифицируемому контексту ИИ: практическая архитектура информации, готовой для агентов","Od sirovih podataka do proverljivog AI konteksta: Praktična arhitektura za informacije spremne za agente","从原始数据到可验证的 AI 上下文：面向智能体就绪信息的实用架构","\u002Fportfolio\u002Ffrom-raw-data-to-verifiable-ai-context-a-practical-architecture-for-agent-ready-information","i-lucide-database","portfolio",22,[],{"id":192,"title":193,"url":202,"target":61,"icon":203,"isActive":14,"type":188,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":204,"children":205},"menu-e2061cd7-ff53-49d5-a0e8-3d49090577c0",{"de":194,"en":195,"es":196,"fr":197,"it":198,"ru":199,"sr":200,"zh":201},"Präsenzplattformen — Unternehmenskommunikation","Presence Platforms — Enterprise Communication","Plataformas de presencia — Comunicación empresarial","Plateformes de présence — Communication d'entreprise","Presence Platforms — Comunicazione aziendale","Платформы присутствия — Корпоративные коммуникации","Presence platforme — Poslovna komunikacija","Presence 平台 — 企业通信","\u002Fportfolio\u002Fpresence-platforms-enterprise-communication-that-wins-without-competing","i-lucide-badge-percent",21,[],{"id":207,"title":208,"url":217,"target":61,"icon":218,"isActive":14,"type":188,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":219,"children":220},"menu-a781582e-e90d-418e-b8c9-b070bc37c37e",{"de":209,"en":210,"es":211,"fr":212,"it":213,"ru":214,"sr":215,"zh":216},"Maximierung des POS-ROI durch Konsistenz","Maximizing POS ROI Through Consistent","Maximizar el ROI del POS a través de constante","Maximiser le ROI du PDV grâce à la cohérence","Massimizzare il ROI del POS attraverso costante","Максимизация ROI POS за счет последовательного","Maksimizacija POS ROI-ja kroz dosledno","通过持续最大化 POS 投资回报率","\u002Fportfolio\u002Ffrom-vision-to-value-maximizing-pos-roi-through-consistent-ci-creation-and-strategic-branding","i-lucide-briefcase-business",11,[],{"statusCode":4,"data":222,"message":1065},{"id":223,"title":224,"slug":225,"content":226,"contentJson":227,"excerpt":742,"featuredImage":743,"featuredImageAlt":744,"featuredImageCaption":10,"featuredImageTitle":10,"featuredImageCopyright":10,"featuredImageAuthor":10,"featuredImageSourceUrl":10,"featuredImageLicense":10,"featuredImageIsAiGenerated":43,"status":745,"publishedAt":746,"createdAt":747,"updatedAt":748,"seoLocalePaths":749,"categories":758,"author":767,"translations":771},"497","How Far Is an AI Claim From the Evidence? — Evidence Distance","how-far-is-an-ai-claim-from-the-evidence-evidence-distance","{\"time\":1792096795538,\"blocks\":[{\"id\":\"g-2Ciyj8LJ\",\"type\":\"header\",\"data\":{\"text\":\"Question\",\"level\":2},\"tunes\":{}},{\"id\":\"SQWD7UraiX\",\"type\":\"paragraph\",\"data\":{\"text\":\"Two AI answers can both cite sources and still differ greatly in how directly those sources support the claims being made. How can we describe that difference?\"},\"tunes\":{}},{\"id\":\"Sj1fx2865j\",\"type\":\"paragraph\",\"data\":{\"text\":\"This article uses the term Evidence Distance for the distance between a claim and the directly inspectable evidence that supports it.\"},\"tunes\":{}},{\"id\":\"d5th-A-mq5\",\"type\":\"quote\",\"data\":{\"text\":\"Evidence Distance is the number and strength of transformations, assumptions and inferential steps separating a claim from the evidence that can directly verify it.\",\"caption\":\"Working definition — a reasoning concept introduced here, not a standardized metric.\",\"alignment\":\"left\"},\"tunes\":{}},{\"id\":\"X81jXC72FC\",\"type\":\"tableOfContents\",\"data\":{\"title\":\"Contents\",\"minLevel\":2,\"maxLevel\":3},\"tunes\":{}},{\"id\":\"_pZcnPEoil\",\"type\":\"header\",\"data\":{\"text\":\"What This Really Means\",\"level\":2},\"tunes\":{}},{\"id\":\"F5odO7xyha\",\"type\":\"paragraph\",\"data\":{\"text\":\"A citation proves that a source was referenced. It does not automatically prove that the source directly supports the sentence beside the citation.\"},\"tunes\":{}},{\"id\":\"8Gqlg-ArJS\",\"type\":\"paragraph\",\"data\":{\"text\":\"Between an original observation and a final AI answer there may be extraction, parsing, chunking, retrieval, summarization, interpretation, aggregation and inference.\"},\"tunes\":{}},{\"id\":\"lXkL5LV9ab\",\"type\":\"code\",\"data\":{\"code\":\"Primary evidence\\n   ↓\\nExtracted data\\n   ↓\\nRetrieved passage\\n   ↓\\nSummary\\n   ↓\\nInterpretation\\n   ↓\\nInference\\n   ↓\\nFinal claim\"},\"tunes\":{}},{\"id\":\"Z-8GPQIpCI\",\"type\":\"paragraph\",\"data\":{\"text\":\"Every step can be legitimate. But every step can also introduce distortion.\"},\"tunes\":{}},{\"id\":\"aXMwTGZ8Ia\",\"type\":\"header\",\"data\":{\"text\":\"Simplest Example\",\"level\":2},\"tunes\":{}},{\"id\":\"bZlU7KD3M2\",\"type\":\"paragraph\",\"data\":{\"text\":\"Suppose a temperature sensor reports 38.2 °C.\"},\"tunes\":{}},{\"id\":\"SP87UUPaU3\",\"type\":\"table\",\"data\":{\"withHeadings\":true,\"stretched\":false,\"content\":[[\"Claim\",\"Relationship to evidence\",\"Illustrative distance\"],[\"The sensor reports 38.2 °C.\",\"Direct reading\",\"Low\"],[\"The system is running hotter than yesterday.\",\"Requires comparison with yesterday's reading\",\"Moderate\"],[\"The cooling system is failing.\",\"Requires causal inference and alternative explanations\",\"High\"]]},\"tunes\":{}},{\"id\":\"eYar059d69\",\"type\":\"paragraph\",\"data\":{\"text\":\"The original sensor value directly supports the first claim. It does not by itself prove the third.\"},\"tunes\":{}},{\"id\":\"eCnFlByvHt\",\"type\":\"code\",\"data\":{\"code\":\"Evidence exists\\n        ≠\\nEvidence directly supports every derived claim\"},\"tunes\":{}},{\"id\":\"aXGkK6BpkF\",\"type\":\"header\",\"data\":{\"text\":\"Where the Example Stops Working\",\"level\":2},\"tunes\":{}},{\"id\":\"lAwb9QZ_yB\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence Distance is not simply a count of sentences or processing steps.\"},\"tunes\":{}},{\"id\":\"-SzYko9oIH\",\"type\":\"paragraph\",\"data\":{\"text\":\"One mathematically valid transformation may preserve evidence almost perfectly, while a single speculative interpretation may create a much larger epistemic jump.\"},\"tunes\":{}},{\"id\":\"XOQloBndLw\",\"type\":\"paragraph\",\"data\":{\"text\":\"The concept therefore includes both distance by transformation and distance by inference.\"},\"tunes\":{}},{\"id\":\"EOXbS4TAOR\",\"type\":\"header\",\"data\":{\"text\":\"Direct Answer\",\"level\":2},\"tunes\":{}},{\"id\":\"HcVL8vGM74\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence Distance increases when a claim depends on more transformations, more assumptions, weaker provenance or stronger inference than the underlying evidence directly warrants.\"},\"tunes\":{}},{\"id\":\"_f7WXjUOsS\",\"type\":\"code\",\"data\":{\"code\":\"Short distance:\\nsource → claim\\n\\nLonger distance:\\nsource → extraction → summary → assumption → inference → claim\"},\"tunes\":{}},{\"id\":\"zUEC-cDhqm\",\"type\":\"paragraph\",\"data\":{\"text\":\"A longer distance does not automatically make a claim false. It means the reasoning chain requires more validation.\"},\"tunes\":{}},{\"id\":\"ix7TUGNz_W\",\"type\":\"header\",\"data\":{\"text\":\"Why This Matters for AI\",\"level\":2},\"tunes\":{}},{\"id\":\"wrAy5PLtLB\",\"type\":\"paragraph\",\"data\":{\"text\":\"LLMs are particularly good at producing fluent bridges between pieces of information. That capability is useful, but fluency can hide how far the conclusion has moved beyond the directly retrieved evidence.\"},\"tunes\":{}},{\"id\":\"jJseLuTWdv\",\"type\":\"paragraph\",\"data\":{\"text\":\"An answer can therefore look well sourced while containing claims whose support exists only through several unstated inferential steps.\"},\"tunes\":{}},{\"id\":\"ox8fok9dzs\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fstajic.de\u002Fblog\u002Ffrom-research-protocol-to-a-general-ai-reasoning-framework\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"From Research Protocol to a General AI Reasoning Framework\",\"description\":\"Reliable reasoning requires explicit separation of evidence, assumptions, hypotheses and conclusions.\"}},\"tunes\":{}},{\"id\":\"6ipse6YG1U\",\"type\":\"header\",\"data\":{\"text\":\"Four Components of Evidence Distance\",\"level\":2},\"tunes\":{}},{\"id\":\"P4xQ7o96dR\",\"type\":\"header\",\"data\":{\"text\":\"1. Transformation Distance\",\"level\":3},\"tunes\":{}},{\"id\":\"dvN8TUNEYG\",\"type\":\"paragraph\",\"data\":{\"text\":\"How many times has the original evidence been converted, summarized, normalized or reformatted before reaching the model?\"},\"tunes\":{}},{\"id\":\"dXofACF9_x\",\"type\":\"header\",\"data\":{\"text\":\"2. Inferential Distance\",\"level\":3},\"tunes\":{}},{\"id\":\"kkEzV3ydId\",\"type\":\"paragraph\",\"data\":{\"text\":\"How many reasoning steps are required before the evidence supports the final conclusion?\"},\"tunes\":{}},{\"id\":\"PPYB0RuX5_\",\"type\":\"header\",\"data\":{\"text\":\"3. Provenance Distance\",\"level\":3},\"tunes\":{}},{\"id\":\"cAVBYebJr7\",\"type\":\"paragraph\",\"data\":{\"text\":\"Can the retrieved statement still be traced to an identifiable original source, or has it passed through summaries and copies whose origin is unclear?\"},\"tunes\":{}},{\"id\":\"254N_99Z7X\",\"type\":\"header\",\"data\":{\"text\":\"4. Applicability Distance\",\"level\":3},\"tunes\":{}},{\"id\":\"to3KWv5WSK\",\"type\":\"paragraph\",\"data\":{\"text\":\"How much reasoning is required to establish that the evidence applies to this exact version, user, jurisdiction, time period or situation?\"},\"tunes\":{}},{\"id\":\"3WnVPQ6wqw\",\"type\":\"header\",\"data\":{\"text\":\"Evidence Distance in RAG\",\"level\":2},\"tunes\":{}},{\"id\":\"r8s-75EBhA\",\"type\":\"paragraph\",\"data\":{\"text\":\"RAG can shorten one important distance: the distance between a model and external knowledge.\"},\"tunes\":{}},{\"id\":\"I_8h52A3Yc\",\"type\":\"paragraph\",\"data\":{\"text\":\"It does not automatically shorten the distance between a retrieved passage and the final claim.\"},\"tunes\":{}},{\"id\":\"jDDRUu2FUK\",\"type\":\"code\",\"data\":{\"code\":\"RAG solves:\\nmodel ↔ external information\\n\\nRAG does not automatically solve:\\nevidence ↔ justified conclusion\"},\"tunes\":{}},{\"id\":\"rm14qIVB1M\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fstajic.de\u002Fblog\u002Fwhere-does-an-llm-get-its-data-rag-data-sources-in-python\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"Where Does an LLM Get Its Data? RAG Data Sources in Python\",\"description\":\"Retrieval brings external information into context. Evidence Distance asks what happens between that information and the claim eventually produced.\"}},\"tunes\":{}},{\"id\":\"CRUZDXYloa\",\"type\":\"header\",\"data\":{\"text\":\"Connection to the Retrieval Trigger\",\"level\":2},\"tunes\":{}},{\"id\":\"-TPiYJ569c\",\"type\":\"paragraph\",\"data\":{\"text\":\"The Retrieval Trigger asks whether internal model knowledge is sufficient.\"},\"tunes\":{}},{\"id\":\"_VjLi5fs4x\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence Distance asks a later question: after evidence has been retrieved, how directly does it support what the system wants to claim?\"},\"tunes\":{}},{\"id\":\"EImPw6i617\",\"type\":\"code\",\"data\":{\"code\":\"Need evidence?\\n   ↓\\nRetrieval Trigger\\n   ↓\\nRetrieve\\n   ↓\\nHow directly does evidence support the claim?\\n   ↓\\nEvidence Distance\"},\"tunes\":{}},{\"id\":\"ZqyhB2bFtR\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fstajic.de\u002Fblog\u002Fwhen-should-an-ai-stop-trusting-its-own-knowledge-the-retrieval-trigger\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"When Should an AI Stop Trusting Its Own Knowledge? — The Retrieval Trigger\",\"description\":\"The trigger decides when evidence is needed. Evidence Distance evaluates how far the eventual claim moves beyond that evidence.\"}},\"tunes\":{}},{\"id\":\"ST2vnm6vwF\",\"type\":\"header\",\"data\":{\"text\":\"A Practical Diagnostic\",\"level\":2},\"tunes\":{}},{\"id\":\"qyoHcDcTKb\",\"type\":\"paragraph\",\"data\":{\"text\":\"For an important AI-generated claim, reconstruct the support chain backwards.\"},\"tunes\":{}},{\"id\":\"e3fDmLk0fe\",\"type\":\"code\",\"data\":{\"code\":\"CLAIM\\n  ↑\\nWhich inference produced it?\\n  ↑\\nWhich retrieved evidence supports that inference?\\n  ↑\\nWhich source produced that evidence?\\n  ↑\\nCan the original source still be inspected?\"},\"tunes\":{}},{\"id\":\"iQ60c7NRaE\",\"type\":\"paragraph\",\"data\":{\"text\":\"If the chain breaks, the system has encountered an evidence-traceability problem.\"},\"tunes\":{}},{\"id\":\"YQAKlNZ2gM\",\"type\":\"paragraph\",\"data\":{\"text\":\"If the chain remains intact but requires several strong assumptions, the Evidence Distance is still high.\"},\"tunes\":{}},{\"id\":\"clN7jFkUBf\",\"type\":\"header\",\"data\":{\"text\":\"Example: Product Data\",\"level\":2},\"tunes\":{}},{\"id\":\"CRF-A9O7Ot\",\"type\":\"paragraph\",\"data\":{\"text\":\"Suppose a manufacturer specification says a laptop weighs 1.48 kg.\"},\"tunes\":{}},{\"id\":\"JF3z6aF2q_\",\"type\":\"code\",\"data\":{\"code\":\"Manufacturer specification\\n→ 1.48 kg\\n→ \\\"The laptop weighs 1.48 kg\\\"\\n\\nLow Evidence Distance\"},\"tunes\":{}},{\"id\":\"vTMOOgkLPb\",\"type\":\"paragraph\",\"data\":{\"text\":\"Now consider:\"},\"tunes\":{}},{\"id\":\"Tuhfzor1yp\",\"type\":\"code\",\"data\":{\"code\":\"Manufacturer specification\\n→ 1.48 kg\\n→ comparison with three competitors\\n→ assumption about travel behavior\\n→ \\\"This is the best laptop for frequent travelers\\\"\\n\\nMuch higher Evidence Distance\"},\"tunes\":{}},{\"id\":\"JHFRGIgUJD\",\"type\":\"paragraph\",\"data\":{\"text\":\"The specification is real. The recommendation is still several reasoning steps away from it.\"},\"tunes\":{}},{\"id\":\"2lKERCrnW1\",\"type\":\"header\",\"data\":{\"text\":\"Example: Scientific Evidence\",\"level\":2},\"tunes\":{}},{\"id\":\"HA8DBYwUuK\",\"type\":\"paragraph\",\"data\":{\"text\":\"A paper may report an observed association. An AI answer can incorrectly compress that into a causal statement.\"},\"tunes\":{}},{\"id\":\"D9C2dVB7j_\",\"type\":\"code\",\"data\":{\"code\":\"Observed association\\n        ↓\\nInterpretation\\n        ↓\\nUnstated causal assumption\\n        ↓\\n\\\"X causes Y\\\"\"},\"tunes\":{}},{\"id\":\"CKNjK25pkL\",\"type\":\"paragraph\",\"data\":{\"text\":\"The problem is not that no evidence exists. The problem is that the final statement crosses a larger evidential distance than the study directly supports.\"},\"tunes\":{}},{\"id\":\"sR430N3cDd\",\"type\":\"header\",\"data\":{\"text\":\"Connection to Agent-Ready Context\",\"level\":2},\"tunes\":{}},{\"id\":\"v77YyG55ko\",\"type\":\"paragraph\",\"data\":{\"text\":\"Structured information objects can reduce avoidable Evidence Distance by preserving source identity, units, timestamps, conflicts and validity instead of forcing the model to reconstruct them from flattened text.\"},\"tunes\":{}},{\"id\":\"EX8darCIjd\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fstajic.de\u002Fportfolio\u002Ffrom-raw-data-to-verifiable-ai-context-a-practical-architecture-for-agent-ready-information\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"From Raw Data to Verifiable AI Context: A Practical Architecture for Agent-Ready Information\",\"description\":\"Preserving provenance and validity before retrieval reduces the number of unsupported reconstruction steps required later.\"}},\"tunes\":{}},{\"id\":\"dsfuoURj1e\",\"type\":\"header\",\"data\":{\"text\":\"A Simple Working Scale\",\"level\":2},\"tunes\":{}},{\"id\":\"BLi7Yth64O\",\"type\":\"table\",\"data\":{\"withHeadings\":true,\"stretched\":false,\"content\":[[\"Level\",\"Description\"],[\"ED0\",\"Directly reported source fact\"],[\"ED1\",\"Simple deterministic transformation or direct comparison\"],[\"ED2\",\"One meaningful interpretive step\"],[\"ED3\",\"Multiple assumptions or combined sources\"],[\"ED4\",\"Strong causal, predictive or prescriptive conclusion beyond direct evidence\"]]},\"tunes\":{}},{\"id\":\"8y8bzCcHBs\",\"type\":\"paragraph\",\"data\":{\"text\":\"This scale is illustrative, not a scientific standard. Its purpose is to force an explicit question: How much did we have to add between the evidence and the claim?\"},\"tunes\":{}},{\"id\":\"aFK0YiAlYO\",\"type\":\"header\",\"data\":{\"text\":\"Misconceptions\",\"level\":2},\"tunes\":{}},{\"id\":\"07KSk6xDx-\",\"type\":\"paragraph\",\"data\":{\"text\":\"A citation means Evidence Distance is low. No. A citation can sit beside a claim that substantially exceeds what the cited source establishes.\"},\"tunes\":{}},{\"id\":\"t_cf-Zfan9\",\"type\":\"paragraph\",\"data\":{\"text\":\"Long Evidence Distance means the claim is wrong. No. Complex conclusions can be well supported, but they require a stronger reasoning chain.\"},\"tunes\":{}},{\"id\":\"Pu9PRX67Q6\",\"type\":\"paragraph\",\"data\":{\"text\":\"Primary sources eliminate inference. No. Primary evidence can still require interpretation.\"},\"tunes\":{}},{\"id\":\"oF1xNsOHHq\",\"type\":\"paragraph\",\"data\":{\"text\":\"More sources automatically reduce distance. Ten weak repetitions of the same unsupported claim do not create direct evidence.\"},\"tunes\":{}},{\"id\":\"IkolK5baph\",\"type\":\"header\",\"data\":{\"text\":\"Edge Case: Derived Data\",\"level\":2},\"tunes\":{}},{\"id\":\"jRH36fwdR3\",\"type\":\"paragraph\",\"data\":{\"text\":\"Some derived values are more reliable than raw human descriptions. A correctly calculated total from verified transactions can be highly dependable even though it is one transformation away from the original records.\"},\"tunes\":{}},{\"id\":\"SXbdKiNDst\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence Distance therefore measures epistemic separation, not a simplistic preference for untouched data.\"},\"tunes\":{}},{\"id\":\"mUbvdnFChM\",\"type\":\"header\",\"data\":{\"text\":\"Limitations\",\"level\":2},\"tunes\":{}},{\"id\":\"N_EskxFOep\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence Distance is a conceptual diagnostic, not a universal quantitative score.\"},\"tunes\":{}},{\"id\":\"nW_-E08So_\",\"type\":\"paragraph\",\"data\":{\"text\":\"Different domains require different treatment of inference. Mathematical proof, clinical evidence, software logs, market analysis and historical interpretation cannot share one universal numerical threshold.\"},\"tunes\":{}},{\"id\":\"_Bd95wXkri\",\"type\":\"header\",\"data\":{\"text\":\"What Would Change This Answer?\",\"level\":2},\"tunes\":{}},{\"id\":\"OqCaMc2_OX\",\"type\":\"paragraph\",\"data\":{\"text\":\"Future AI systems may generate explicit provenance graphs, machine-checkable claim-evidence links and typed reasoning traces. That could make parts of Evidence Distance measurable automatically.\"},\"tunes\":{}},{\"id\":\"58Hf3O9-Iz\",\"type\":\"paragraph\",\"data\":{\"text\":\"The underlying problem remains: a claim can move farther from its evidence even while every intermediate sentence sounds plausible.\"},\"tunes\":{}},{\"id\":\"8WOq5oE_e_\",\"type\":\"header\",\"data\":{\"text\":\"Conclusion\",\"level\":2},\"tunes\":{}},{\"id\":\"1pr1TfwnKc\",\"type\":\"paragraph\",\"data\":{\"text\":\"The important distinction is not merely between sourced and unsourced answers.\"},\"tunes\":{}},{\"id\":\"54CysT_NXa\",\"type\":\"paragraph\",\"data\":{\"text\":\"It is between claims that remain close to directly inspectable evidence and claims that depend on increasingly long chains of interpretation and assumption.\"},\"tunes\":{}},{\"id\":\"Qrjo3WEUSL\",\"type\":\"code\",\"data\":{\"code\":\"Evidence\\n   ↓\\nEvidence Distance\\n   ↓\\nReasoning\\n   ↓\\nAnswer Validity Boundary\"},\"tunes\":{}},{\"id\":\"6ir8aIAfd3\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence Distance gives us a language for describing that space.\"},\"tunes\":{}},{\"id\":\"vPhupXcbeN\",\"type\":\"header\",\"data\":{\"text\":\"Primary Sources\",\"level\":2},\"tunes\":{}},{\"id\":\"BaO4JmWRQL\",\"type\":\"paragraph\",\"data\":{\"text\":\"Patrick Lewis et al., \u003Ca href=\\\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401\\\" target=\\\"_blank\\\">Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks\u003C\u002Fa> (2020).\"},\"tunes\":{}},{\"id\":\"eg4Z4G6Cgs\",\"type\":\"paragraph\",\"data\":{\"text\":\"Nelson F. Liu et al., \u003Ca href=\\\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172\\\" target=\\\"_blank\\\">Lost in the Middle: How Language Models Use Long Contexts\u003C\u002Fa> (2023).\"},\"tunes\":{}},{\"id\":\"BJH7zUd4T8\",\"type\":\"paragraph\",\"data\":{\"text\":\"W3C, \u003Ca href=\\\"https:\u002F\u002Fwww.w3.org\u002FTR\u002Fprov-overview\u002F\\\" target=\\\"_blank\\\">PROV Overview\u003C\u002Fa>. A standardized model for representing provenance relationships.\"},\"tunes\":{}}],\"version\":\"2.31.6\"}",{"time":228,"blocks":229,"version":741},1792096795538,[230,236,242,247,255,262,267,272,277,283,288,293,298,320,325,330,335,340,345,350,355,360,365,370,375,380,385,396,401,406,411,416,421,426,431,436,441,446,451,456,461,470,475,480,485,490,499,504,509,514,519,524,529,534,539,544,549,554,559,564,569,574,579,584,593,598,621,626,631,636,641,646,651,656,661,666,671,676,681,686,691,696,701,706,711,716,721,726,731,736],{"id":231,"data":232,"type":42,"tunes":235},"g-2Ciyj8LJ",{"text":233,"level":234},"Question",2,{},{"id":237,"data":238,"type":240,"tunes":241},"SQWD7UraiX",{"text":239},"Two AI answers can both cite sources and still differ greatly in how directly those sources support the claims being made. How can we describe that difference?","paragraph",{},{"id":243,"data":244,"type":240,"tunes":246},"Sj1fx2865j",{"text":245},"This article uses the term Evidence Distance for the distance between a claim and the directly inspectable evidence that supports it.",{},{"id":248,"data":249,"type":253,"tunes":254},"d5th-A-mq5",{"text":250,"caption":251,"alignment":252},"Evidence Distance is the number and strength of transformations, assumptions and inferential steps separating a claim from the evidence that can directly verify it.","Working definition — a reasoning concept introduced here, not a standardized metric.","left","quote",{},{"id":256,"data":257,"type":260,"tunes":261},"X81jXC72FC",{"title":258,"maxLevel":259,"minLevel":234},"Contents",3,"tableOfContents",{},{"id":263,"data":264,"type":42,"tunes":266},"_pZcnPEoil",{"text":265,"level":234},"What This Really Means",{},{"id":268,"data":269,"type":240,"tunes":271},"F5odO7xyha",{"text":270},"A citation proves that a source was referenced. It does not automatically prove that the source directly supports the sentence beside the citation.",{},{"id":273,"data":274,"type":240,"tunes":276},"8Gqlg-ArJS",{"text":275},"Between an original observation and a final AI answer there may be extraction, parsing, chunking, retrieval, summarization, interpretation, aggregation and inference.",{},{"id":278,"data":279,"type":281,"tunes":282},"lXkL5LV9ab",{"code":280},"Primary evidence\n   ↓\nExtracted data\n   ↓\nRetrieved passage\n   ↓\nSummary\n   ↓\nInterpretation\n   ↓\nInference\n   ↓\nFinal claim","code",{},{"id":284,"data":285,"type":240,"tunes":287},"Z-8GPQIpCI",{"text":286},"Every step can be legitimate. But every step can also introduce distortion.",{},{"id":289,"data":290,"type":42,"tunes":292},"aXMwTGZ8Ia",{"text":291,"level":234},"Simplest Example",{},{"id":294,"data":295,"type":240,"tunes":297},"bZlU7KD3M2",{"text":296},"Suppose a temperature sensor reports 38.2 °C.",{},{"id":299,"data":300,"type":318,"tunes":319},"SP87UUPaU3",{"content":301,"stretched":43,"withHeadings":14},[302,306,310,314],[303,304,305],"Claim","Relationship to evidence","Illustrative distance",[307,308,309],"The sensor reports 38.2 °C.","Direct reading","Low",[311,312,313],"The system is running hotter than yesterday.","Requires comparison with yesterday's reading","Moderate",[315,316,317],"The cooling system is failing.","Requires causal inference and alternative explanations","High","table",{},{"id":321,"data":322,"type":240,"tunes":324},"eYar059d69",{"text":323},"The original sensor value directly supports the first claim. It does not by itself prove the third.",{},{"id":326,"data":327,"type":281,"tunes":329},"eCnFlByvHt",{"code":328},"Evidence exists\n        ≠\nEvidence directly supports every derived claim",{},{"id":331,"data":332,"type":42,"tunes":334},"aXGkK6BpkF",{"text":333,"level":234},"Where the Example Stops Working",{},{"id":336,"data":337,"type":240,"tunes":339},"lAwb9QZ_yB",{"text":338},"Evidence Distance is not simply a count of sentences or processing steps.",{},{"id":341,"data":342,"type":240,"tunes":344},"-SzYko9oIH",{"text":343},"One mathematically valid transformation may preserve evidence almost perfectly, while a single speculative interpretation may create a much larger epistemic jump.",{},{"id":346,"data":347,"type":240,"tunes":349},"XOQloBndLw",{"text":348},"The concept therefore includes both distance by transformation and distance by inference.",{},{"id":351,"data":352,"type":42,"tunes":354},"EOXbS4TAOR",{"text":353,"level":234},"Direct Answer",{},{"id":356,"data":357,"type":240,"tunes":359},"HcVL8vGM74",{"text":358},"Evidence Distance increases when a claim depends on more transformations, more assumptions, weaker provenance or stronger inference than the underlying evidence directly warrants.",{},{"id":361,"data":362,"type":281,"tunes":364},"_f7WXjUOsS",{"code":363},"Short distance:\nsource → claim\n\nLonger distance:\nsource → extraction → summary → assumption → inference → claim",{},{"id":366,"data":367,"type":240,"tunes":369},"zUEC-cDhqm",{"text":368},"A longer distance does not automatically make a claim false. It means the reasoning chain requires more validation.",{},{"id":371,"data":372,"type":42,"tunes":374},"ix7TUGNz_W",{"text":373,"level":234},"Why This Matters for AI",{},{"id":376,"data":377,"type":240,"tunes":379},"wrAy5PLtLB",{"text":378},"LLMs are particularly good at producing fluent bridges between pieces of information. That capability is useful, but fluency can hide how far the conclusion has moved beyond the directly retrieved evidence.",{},{"id":381,"data":382,"type":240,"tunes":384},"jJseLuTWdv",{"text":383},"An answer can therefore look well sourced while containing claims whose support exists only through several unstated inferential steps.",{},{"id":386,"data":387,"type":394,"tunes":395},"ox8fok9dzs",{"link":388,"meta":389},"https:\u002F\u002Fstajic.de\u002Fblog\u002Ffrom-research-protocol-to-a-general-ai-reasoning-framework",{"image":390,"title":392,"description":393},{"url":391},"","From Research Protocol to a General AI Reasoning Framework","Reliable reasoning requires explicit separation of evidence, assumptions, hypotheses and conclusions.","linkTool",{},{"id":397,"data":398,"type":42,"tunes":400},"6ipse6YG1U",{"text":399,"level":234},"Four Components of Evidence Distance",{},{"id":402,"data":403,"type":42,"tunes":405},"P4xQ7o96dR",{"text":404,"level":259},"1. Transformation Distance",{},{"id":407,"data":408,"type":240,"tunes":410},"dvN8TUNEYG",{"text":409},"How many times has the original evidence been converted, summarized, normalized or reformatted before reaching the model?",{},{"id":412,"data":413,"type":42,"tunes":415},"dXofACF9_x",{"text":414,"level":259},"2. Inferential Distance",{},{"id":417,"data":418,"type":240,"tunes":420},"kkEzV3ydId",{"text":419},"How many reasoning steps are required before the evidence supports the final conclusion?",{},{"id":422,"data":423,"type":42,"tunes":425},"PPYB0RuX5_",{"text":424,"level":259},"3. Provenance Distance",{},{"id":427,"data":428,"type":240,"tunes":430},"cAVBYebJr7",{"text":429},"Can the retrieved statement still be traced to an identifiable original source, or has it passed through summaries and copies whose origin is unclear?",{},{"id":432,"data":433,"type":42,"tunes":435},"254N_99Z7X",{"text":434,"level":259},"4. Applicability Distance",{},{"id":437,"data":438,"type":240,"tunes":440},"to3KWv5WSK",{"text":439},"How much reasoning is required to establish that the evidence applies to this exact version, user, jurisdiction, time period or situation?",{},{"id":442,"data":443,"type":42,"tunes":445},"3WnVPQ6wqw",{"text":444,"level":234},"Evidence Distance in RAG",{},{"id":447,"data":448,"type":240,"tunes":450},"r8s-75EBhA",{"text":449},"RAG can shorten one important distance: the distance between a model and external knowledge.",{},{"id":452,"data":453,"type":240,"tunes":455},"I_8h52A3Yc",{"text":454},"It does not automatically shorten the distance between a retrieved passage and the final claim.",{},{"id":457,"data":458,"type":281,"tunes":460},"jDDRUu2FUK",{"code":459},"RAG solves:\nmodel ↔ external information\n\nRAG does not automatically solve:\nevidence ↔ justified conclusion",{},{"id":462,"data":463,"type":394,"tunes":469},"rm14qIVB1M",{"link":464,"meta":465},"https:\u002F\u002Fstajic.de\u002Fblog\u002Fwhere-does-an-llm-get-its-data-rag-data-sources-in-python",{"image":466,"title":467,"description":468},{"url":391},"Where Does an LLM Get Its Data? RAG Data Sources in Python","Retrieval brings external information into context. Evidence Distance asks what happens between that information and the claim eventually produced.",{},{"id":471,"data":472,"type":42,"tunes":474},"CRUZDXYloa",{"text":473,"level":234},"Connection to the Retrieval Trigger",{},{"id":476,"data":477,"type":240,"tunes":479},"-TPiYJ569c",{"text":478},"The Retrieval Trigger asks whether internal model knowledge is sufficient.",{},{"id":481,"data":482,"type":240,"tunes":484},"_VjLi5fs4x",{"text":483},"Evidence Distance asks a later question: after evidence has been retrieved, how directly does it support what the system wants to claim?",{},{"id":486,"data":487,"type":281,"tunes":489},"EImPw6i617",{"code":488},"Need evidence?\n   ↓\nRetrieval Trigger\n   ↓\nRetrieve\n   ↓\nHow directly does evidence support the claim?\n   ↓\nEvidence Distance",{},{"id":491,"data":492,"type":394,"tunes":498},"ZqyhB2bFtR",{"link":493,"meta":494},"https:\u002F\u002Fstajic.de\u002Fblog\u002Fwhen-should-an-ai-stop-trusting-its-own-knowledge-the-retrieval-trigger",{"image":495,"title":496,"description":497},{"url":391},"When Should an AI Stop Trusting Its Own Knowledge? — The Retrieval Trigger","The trigger decides when evidence is needed. Evidence Distance evaluates how far the eventual claim moves beyond that evidence.",{},{"id":500,"data":501,"type":42,"tunes":503},"ST2vnm6vwF",{"text":502,"level":234},"A Practical Diagnostic",{},{"id":505,"data":506,"type":240,"tunes":508},"qyoHcDcTKb",{"text":507},"For an important AI-generated claim, reconstruct the support chain backwards.",{},{"id":510,"data":511,"type":281,"tunes":513},"e3fDmLk0fe",{"code":512},"CLAIM\n  ↑\nWhich inference produced it?\n  ↑\nWhich retrieved evidence supports that inference?\n  ↑\nWhich source produced that evidence?\n  ↑\nCan the original source still be inspected?",{},{"id":515,"data":516,"type":240,"tunes":518},"iQ60c7NRaE",{"text":517},"If the chain breaks, the system has encountered an evidence-traceability problem.",{},{"id":520,"data":521,"type":240,"tunes":523},"YQAKlNZ2gM",{"text":522},"If the chain remains intact but requires several strong assumptions, the Evidence Distance is still high.",{},{"id":525,"data":526,"type":42,"tunes":528},"clN7jFkUBf",{"text":527,"level":234},"Example: Product Data",{},{"id":530,"data":531,"type":240,"tunes":533},"CRF-A9O7Ot",{"text":532},"Suppose a manufacturer specification says a laptop weighs 1.48 kg.",{},{"id":535,"data":536,"type":281,"tunes":538},"JF3z6aF2q_",{"code":537},"Manufacturer specification\n→ 1.48 kg\n→ \"The laptop weighs 1.48 kg\"\n\nLow Evidence Distance",{},{"id":540,"data":541,"type":240,"tunes":543},"vTMOOgkLPb",{"text":542},"Now consider:",{},{"id":545,"data":546,"type":281,"tunes":548},"Tuhfzor1yp",{"code":547},"Manufacturer specification\n→ 1.48 kg\n→ comparison with three competitors\n→ assumption about travel behavior\n→ \"This is the best laptop for frequent travelers\"\n\nMuch higher Evidence Distance",{},{"id":550,"data":551,"type":240,"tunes":553},"JHFRGIgUJD",{"text":552},"The specification is real. The recommendation is still several reasoning steps away from it.",{},{"id":555,"data":556,"type":42,"tunes":558},"2lKERCrnW1",{"text":557,"level":234},"Example: Scientific Evidence",{},{"id":560,"data":561,"type":240,"tunes":563},"HA8DBYwUuK",{"text":562},"A paper may report an observed association. An AI answer can incorrectly compress that into a causal statement.",{},{"id":565,"data":566,"type":281,"tunes":568},"D9C2dVB7j_",{"code":567},"Observed association\n        ↓\nInterpretation\n        ↓\nUnstated causal assumption\n        ↓\n\"X causes Y\"",{},{"id":570,"data":571,"type":240,"tunes":573},"CKNjK25pkL",{"text":572},"The problem is not that no evidence exists. The problem is that the final statement crosses a larger evidential distance than the study directly supports.",{},{"id":575,"data":576,"type":42,"tunes":578},"sR430N3cDd",{"text":577,"level":234},"Connection to Agent-Ready Context",{},{"id":580,"data":581,"type":240,"tunes":583},"v77YyG55ko",{"text":582},"Structured information objects can reduce avoidable Evidence Distance by preserving source identity, units, timestamps, conflicts and validity instead of forcing the model to reconstruct them from flattened text.",{},{"id":585,"data":586,"type":394,"tunes":592},"EX8darCIjd",{"link":587,"meta":588},"https:\u002F\u002Fstajic.de\u002Fportfolio\u002Ffrom-raw-data-to-verifiable-ai-context-a-practical-architecture-for-agent-ready-information",{"image":589,"title":590,"description":591},{"url":391},"From Raw Data to Verifiable AI Context: A Practical Architecture for Agent-Ready Information","Preserving provenance and validity before retrieval reduces the number of unsupported reconstruction steps required later.",{},{"id":594,"data":595,"type":42,"tunes":597},"dsfuoURj1e",{"text":596,"level":234},"A Simple Working Scale",{},{"id":599,"data":600,"type":318,"tunes":620},"BLi7Yth64O",{"content":601,"stretched":43,"withHeadings":14},[602,605,608,611,614,617],[603,604],"Level","Description",[606,607],"ED0","Directly reported source fact",[609,610],"ED1","Simple deterministic transformation or direct comparison",[612,613],"ED2","One meaningful interpretive step",[615,616],"ED3","Multiple assumptions or combined sources",[618,619],"ED4","Strong causal, predictive or prescriptive conclusion beyond direct evidence",{},{"id":622,"data":623,"type":240,"tunes":625},"8y8bzCcHBs",{"text":624},"This scale is illustrative, not a scientific standard. Its purpose is to force an explicit question: How much did we have to add between the evidence and the claim?",{},{"id":627,"data":628,"type":42,"tunes":630},"aFK0YiAlYO",{"text":629,"level":234},"Misconceptions",{},{"id":632,"data":633,"type":240,"tunes":635},"07KSk6xDx-",{"text":634},"A citation means Evidence Distance is low. No. A citation can sit beside a claim that substantially exceeds what the cited source establishes.",{},{"id":637,"data":638,"type":240,"tunes":640},"t_cf-Zfan9",{"text":639},"Long Evidence Distance means the claim is wrong. No. Complex conclusions can be well supported, but they require a stronger reasoning chain.",{},{"id":642,"data":643,"type":240,"tunes":645},"Pu9PRX67Q6",{"text":644},"Primary sources eliminate inference. No. Primary evidence can still require interpretation.",{},{"id":647,"data":648,"type":240,"tunes":650},"oF1xNsOHHq",{"text":649},"More sources automatically reduce distance. Ten weak repetitions of the same unsupported claim do not create direct evidence.",{},{"id":652,"data":653,"type":42,"tunes":655},"IkolK5baph",{"text":654,"level":234},"Edge Case: Derived Data",{},{"id":657,"data":658,"type":240,"tunes":660},"jRH36fwdR3",{"text":659},"Some derived values are more reliable than raw human descriptions. A correctly calculated total from verified transactions can be highly dependable even though it is one transformation away from the original records.",{},{"id":662,"data":663,"type":240,"tunes":665},"SXbdKiNDst",{"text":664},"Evidence Distance therefore measures epistemic separation, not a simplistic preference for untouched data.",{},{"id":667,"data":668,"type":42,"tunes":670},"mUbvdnFChM",{"text":669,"level":234},"Limitations",{},{"id":672,"data":673,"type":240,"tunes":675},"N_EskxFOep",{"text":674},"Evidence Distance is a conceptual diagnostic, not a universal quantitative score.",{},{"id":677,"data":678,"type":240,"tunes":680},"nW_-E08So_",{"text":679},"Different domains require different treatment of inference. Mathematical proof, clinical evidence, software logs, market analysis and historical interpretation cannot share one universal numerical threshold.",{},{"id":682,"data":683,"type":42,"tunes":685},"_Bd95wXkri",{"text":684,"level":234},"What Would Change This Answer?",{},{"id":687,"data":688,"type":240,"tunes":690},"OqCaMc2_OX",{"text":689},"Future AI systems may generate explicit provenance graphs, machine-checkable claim-evidence links and typed reasoning traces. That could make parts of Evidence Distance measurable automatically.",{},{"id":692,"data":693,"type":240,"tunes":695},"58Hf3O9-Iz",{"text":694},"The underlying problem remains: a claim can move farther from its evidence even while every intermediate sentence sounds plausible.",{},{"id":697,"data":698,"type":42,"tunes":700},"8WOq5oE_e_",{"text":699,"level":234},"Conclusion",{},{"id":702,"data":703,"type":240,"tunes":705},"1pr1TfwnKc",{"text":704},"The important distinction is not merely between sourced and unsourced answers.",{},{"id":707,"data":708,"type":240,"tunes":710},"54CysT_NXa",{"text":709},"It is between claims that remain close to directly inspectable evidence and claims that depend on increasingly long chains of interpretation and assumption.",{},{"id":712,"data":713,"type":281,"tunes":715},"Qrjo3WEUSL",{"code":714},"Evidence\n   ↓\nEvidence Distance\n   ↓\nReasoning\n   ↓\nAnswer Validity Boundary",{},{"id":717,"data":718,"type":240,"tunes":720},"6ir8aIAfd3",{"text":719},"Evidence Distance gives us a language for describing that space.",{},{"id":722,"data":723,"type":42,"tunes":725},"vPhupXcbeN",{"text":724,"level":234},"Primary Sources",{},{"id":727,"data":728,"type":240,"tunes":730},"BaO4JmWRQL",{"text":729},"Patrick Lewis et al., \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401\" target=\"_blank\">Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks\u003C\u002Fa> (2020).",{},{"id":732,"data":733,"type":240,"tunes":735},"eg4Z4G6Cgs",{"text":734},"Nelson F. Liu et al., \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172\" target=\"_blank\">Lost in the Middle: How Language Models Use Long Contexts\u003C\u002Fa> (2023).",{},{"id":737,"data":738,"type":240,"tunes":740},"BJH7zUd4T8",{"text":739},"W3C, \u003Ca href=\"https:\u002F\u002Fwww.w3.org\u002FTR\u002Fprov-overview\u002F\" target=\"_blank\">PROV Overview\u003C\u002Fa>. A standardized model for representing provenance relationships.",{},"2.31.6","Not all supported answers are equally close to their evidence. Evidence Distance is a practical way to describe how many transformations, summaries, assumptions and inferential steps separate an AI claim from directly inspectable evidence.","\u002Fuploads\u002F2026\u002F10\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance-1792095863209-3c1mog.webp","how-far-is-an-ai-claim-from-the-evidence-evidence-distance-1792095863209-3c1mog","PUBLISHED","2026-10-15T00:23:00.000Z","2026-10-15T20:23:08.634Z","2026-10-15T20:43:52.893Z",{"en":750,"de":751,"sr":752,"es":753,"fr":754,"it":755,"ru":756,"zh":757},"\u002Fblog\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance","\u002Fde\u002Fblog\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance","\u002Fsr\u002Fblog\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance","\u002Fes\u002Fblog\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance","\u002Ffr\u002Fblog\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance","\u002Fit\u002Fblog\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance","\u002Fru\u002Fblog\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance","\u002Fzh\u002Fblog\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance",[759,763],{"id":760,"name":761,"slug":762},68,"Risks, Controls & Evidence","risks-and-controls",{"id":764,"name":765,"slug":766},49,"Controls & Evidence","controls",{"id":768,"login":769,"email":391,"displayName":770},"20","rooth8233","Aleksandar Stajić",[772],{"lang":7,"title":224,"content":226,"contentJson":773,"excerpt":742},{"time":228,"blocks":774,"version":741},[775,778,781,784,787,790,793,796,799,802,805,808,811,819,822,825,828,831,834,837,840,843,846,849,852,855,858,863,866,869,872,875,878,881,884,887,890,893,896,899,902,907,910,913,916,919,924,927,930,933,936,939,942,945,948,951,954,957,960,963,966,969,972,975,980,983,993,996,999,1002,1005,1008,1011,1014,1017,1020,1023,1026,1029,1032,1035,1038,1041,1044,1047,1050,1053,1056,1059,1062],{"id":231,"data":776,"type":42,"tunes":777},{"text":233,"level":234},{},{"id":237,"data":779,"type":240,"tunes":780},{"text":239},{},{"id":243,"data":782,"type":240,"tunes":783},{"text":245},{},{"id":248,"data":785,"type":253,"tunes":786},{"text":250,"caption":251,"alignment":252},{},{"id":256,"data":788,"type":260,"tunes":789},{"title":258,"maxLevel":259,"minLevel":234},{},{"id":263,"data":791,"type":42,"tunes":792},{"text":265,"level":234},{},{"id":268,"data":794,"type":240,"tunes":795},{"text":270},{},{"id":273,"data":797,"type":240,"tunes":798},{"text":275},{},{"id":278,"data":800,"type":281,"tunes":801},{"code":280},{},{"id":284,"data":803,"type":240,"tunes":804},{"text":286},{},{"id":289,"data":806,"type":42,"tunes":807},{"text":291,"level":234},{},{"id":294,"data":809,"type":240,"tunes":810},{"text":296},{},{"id":299,"data":812,"type":318,"tunes":818},{"content":813,"stretched":43,"withHeadings":14},[814,815,816,817],[303,304,305],[307,308,309],[311,312,313],[315,316,317],{},{"id":321,"data":820,"type":240,"tunes":821},{"text":323},{},{"id":326,"data":823,"type":281,"tunes":824},{"code":328},{},{"id":331,"data":826,"type":42,"tunes":827},{"text":333,"level":234},{},{"id":336,"data":829,"type":240,"tunes":830},{"text":338},{},{"id":341,"data":832,"type":240,"tunes":833},{"text":343},{},{"id":346,"data":835,"type":240,"tunes":836},{"text":348},{},{"id":351,"data":838,"type":42,"tunes":839},{"text":353,"level":234},{},{"id":356,"data":841,"type":240,"tunes":842},{"text":358},{},{"id":361,"data":844,"type":281,"tunes":845},{"code":363},{},{"id":366,"data":847,"type":240,"tunes":848},{"text":368},{},{"id":371,"data":850,"type":42,"tunes":851},{"text":373,"level":234},{},{"id":376,"data":853,"type":240,"tunes":854},{"text":378},{},{"id":381,"data":856,"type":240,"tunes":857},{"text":383},{},{"id":386,"data":859,"type":394,"tunes":862},{"link":388,"meta":860},{"image":861,"title":392,"description":393},{"url":391},{},{"id":397,"data":864,"type":42,"tunes":865},{"text":399,"level":234},{},{"id":402,"data":867,"type":42,"tunes":868},{"text":404,"level":259},{},{"id":407,"data":870,"type":240,"tunes":871},{"text":409},{},{"id":412,"data":873,"type":42,"tunes":874},{"text":414,"level":259},{},{"id":417,"data":876,"type":240,"tunes":877},{"text":419},{},{"id":422,"data":879,"type":42,"tunes":880},{"text":424,"level":259},{},{"id":427,"data":882,"type":240,"tunes":883},{"text":429},{},{"id":432,"data":885,"type":42,"tunes":886},{"text":434,"level":259},{},{"id":437,"data":888,"type":240,"tunes":889},{"text":439},{},{"id":442,"data":891,"type":42,"tunes":892},{"text":444,"level":234},{},{"id":447,"data":894,"type":240,"tunes":895},{"text":449},{},{"id":452,"data":897,"type":240,"tunes":898},{"text":454},{},{"id":457,"data":900,"type":281,"tunes":901},{"code":459},{},{"id":462,"data":903,"type":394,"tunes":906},{"link":464,"meta":904},{"image":905,"title":467,"description":468},{"url":391},{},{"id":471,"data":908,"type":42,"tunes":909},{"text":473,"level":234},{},{"id":476,"data":911,"type":240,"tunes":912},{"text":478},{},{"id":481,"data":914,"type":240,"tunes":915},{"text":483},{},{"id":486,"data":917,"type":281,"tunes":918},{"code":488},{},{"id":491,"data":920,"type":394,"tunes":923},{"link":493,"meta":921},{"image":922,"title":496,"description":497},{"url":391},{},{"id":500,"data":925,"type":42,"tunes":926},{"text":502,"level":234},{},{"id":505,"data":928,"type":240,"tunes":929},{"text":507},{},{"id":510,"data":931,"type":281,"tunes":932},{"code":512},{},{"id":515,"data":934,"type":240,"tunes":935},{"text":517},{},{"id":520,"data":937,"type":240,"tunes":938},{"text":522},{},{"id":525,"data":940,"type":42,"tunes":941},{"text":527,"level":234},{},{"id":530,"data":943,"type":240,"tunes":944},{"text":532},{},{"id":535,"data":946,"type":281,"tunes":947},{"code":537},{},{"id":540,"data":949,"type":240,"tunes":950},{"text":542},{},{"id":545,"data":952,"type":281,"tunes":953},{"code":547},{},{"id":550,"data":955,"type":240,"tunes":956},{"text":552},{},{"id":555,"data":958,"type":42,"tunes":959},{"text":557,"level":234},{},{"id":560,"data":961,"type":240,"tunes":962},{"text":562},{},{"id":565,"data":964,"type":281,"tunes":965},{"code":567},{},{"id":570,"data":967,"type":240,"tunes":968},{"text":572},{},{"id":575,"data":970,"type":42,"tunes":971},{"text":577,"level":234},{},{"id":580,"data":973,"type":240,"tunes":974},{"text":582},{},{"id":585,"data":976,"type":394,"tunes":979},{"link":587,"meta":977},{"image":978,"title":590,"description":591},{"url":391},{},{"id":594,"data":981,"type":42,"tunes":982},{"text":596,"level":234},{},{"id":599,"data":984,"type":318,"tunes":992},{"content":985,"stretched":43,"withHeadings":14},[986,987,988,989,990,991],[603,604],[606,607],[609,610],[612,613],[615,616],[618,619],{},{"id":622,"data":994,"type":240,"tunes":995},{"text":624},{},{"id":627,"data":997,"type":42,"tunes":998},{"text":629,"level":234},{},{"id":632,"data":1000,"type":240,"tunes":1001},{"text":634},{},{"id":637,"data":1003,"type":240,"tunes":1004},{"text":639},{},{"id":642,"data":1006,"type":240,"tunes":1007},{"text":644},{},{"id":647,"data":1009,"type":240,"tunes":1010},{"text":649},{},{"id":652,"data":1012,"type":42,"tunes":1013},{"text":654,"level":234},{},{"id":657,"data":1015,"type":240,"tunes":1016},{"text":659},{},{"id":662,"data":1018,"type":240,"tunes":1019},{"text":664},{},{"id":667,"data":1021,"type":42,"tunes":1022},{"text":669,"level":234},{},{"id":672,"data":1024,"type":240,"tunes":1025},{"text":674},{},{"id":677,"data":1027,"type":240,"tunes":1028},{"text":679},{},{"id":682,"data":1030,"type":42,"tunes":1031},{"text":684,"level":234},{},{"id":687,"data":1033,"type":240,"tunes":1034},{"text":689},{},{"id":692,"data":1036,"type":240,"tunes":1037},{"text":694},{},{"id":697,"data":1039,"type":42,"tunes":1040},{"text":699,"level":234},{},{"id":702,"data":1042,"type":240,"tunes":1043},{"text":704},{},{"id":707,"data":1045,"type":240,"tunes":1046},{"text":709},{},{"id":712,"data":1048,"type":281,"tunes":1049},{"code":714},{},{"id":717,"data":1051,"type":240,"tunes":1052},{"text":719},{},{"id":722,"data":1054,"type":42,"tunes":1055},{"text":724,"level":234},{},{"id":727,"data":1057,"type":240,"tunes":1058},{"text":729},{},{"id":732,"data":1060,"type":240,"tunes":1061},{"text":734},{},{"id":737,"data":1063,"type":240,"tunes":1064},{"text":739},{},"Post erfolgreich abgerufen",{"items":1067,"source":1124,"manualIds":1125,"manualMatchedIds":1126},[1068,1075,1082,1089,1096,1103,1110,1117],{"id":1069,"slug":1070,"title":1071,"excerpt":1072,"featuredImage":1073,"publishedAt":1074},"481","generative-ai-explained-models-retrieval-tools-and-applications-are-not-the-same-thing","Generative AI Explained: Models, Retrieval, Tools and Applications Are Not the Same Thing","Generative AI is more than a model. Learn how models, retrieval, tools, context, runtimes and applications fit together in production AI systems.","\u002Fuploads\u002F2026\u002F10\u002Fgenerative-ai-explained-models-retrieval-tools-and-applications-are-not-the-same-thing-1791475411822-pp0dvz.webp","2026-10-08T12:00:00.000Z",{"id":1076,"slug":1077,"title":1078,"excerpt":1079,"featuredImage":1080,"publishedAt":1081},"491","ai-governance-models-data-permissions-risk-and-auditability","AI Governance: Models, Data, Permissions, Risk and Auditability","AI governance defines who can approve, operate, change and audit AI systems across models, providers, data, permissions, risk, evaluation and the full lifecycle.","\u002Fuploads\u002F2026\u002F10\u002Fai-governance-models-data-permissions-risk-and-auditability-1791485901301-g60xyu.webp","2026-10-08T12:56:00.000Z",{"id":1083,"slug":1084,"title":1085,"excerpt":1086,"featuredImage":1087,"publishedAt":1088},"495","sovereign-ai-control-of-models-data-infrastructure-and-dependencies","Sovereign AI: Control of Models, Data, Infrastructure and Dependencies","Sovereign AI is about effective control over models, data, infrastructure, software, operations and strategic dependencies — not simply where an AI model is hosted.","\u002Fuploads\u002F2026\u002F10\u002Fsovereign-ai-control-of-models-data-infrastructure-and-dependencies-1791488833132-niy85x.webp","2026-10-08T15:45:00.000Z",{"id":1090,"slug":1091,"title":1092,"excerpt":1093,"featuredImage":1094,"publishedAt":1095},"492","mcp-explained-what-it-connects-what-it-does-not-do-and-where-it-fits","MCP Explained: What It Connects, What It Does Not Do and Where It Fits","Model Context Protocol connects AI applications to external tools, resources and prompts through a standard client-server boundary. Learn what MCP does, what it does not do, and where it fits in agent architecture.","\u002Fuploads\u002F2026\u002F10\u002Fmcp-explained-what-it-connects-what-it-does-not-do-and-where-it-fits-1791486640275-7ub1cq.webp","2026-10-08T15:09:00.000Z",{"id":1097,"slug":1098,"title":1099,"excerpt":1100,"featuredImage":1101,"publishedAt":1102},"498","can-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","Can Evidence Survive the AI Pipeline? — The Evidence Preservation Chain","Evidence can be correct at the source and still become unreliable after parsing, normalization, chunking, retrieval and context assembly. The Evidence Preservation Chain tracks whether identity, provenance, scope and meaning survive the entire AI pipeline.","\u002Fuploads\u002F2026\u002F10\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain-1792096396174-urdg9z.webp","2026-10-15T16:31:00.000Z",{"id":1104,"slug":1105,"title":1106,"excerpt":1107,"featuredImage":1108,"publishedAt":1109},"482","adr-vs-nfr-architecture-decisions-and-system-quality-are-not-the-same-thing","ADR vs NFR: Architecture Decisions and System Quality Are Not the Same Thing","ADR vs NFR explained: learn how system quality requirements drive architecture decisions, how ADRs record trade-offs, and why validation stays separate.","\u002Fuploads\u002F2026\u002F10\u002Fadr-vs-nfr-architecture-decisions-and-system-quality-are-not-the-same-thing-1791475921511-6zgen1.webp","2026-10-08T12:11:00.000Z",{"id":1111,"slug":1112,"title":1113,"excerpt":1114,"featuredImage":1115,"publishedAt":1116},"381","enterprise-grade-multi-tenant-architecture-for-an-international-platform","Enterprise-Grade Multi-Tenant Architecture for an International Platform","Loving Rocks is an enterprise-grade wedding platform designed with a true multi-tenant architecture, isolated databases per tenant, and built-in internationalization for global scalability, security, and long-term operational stability.","\u002Fuploads\u002F2026\u002F01\u002Fenterprise-grade-multi-tenant-architecture-for-an-international-platform-1769789121298-b6v7ak.webp","2026-01-30T12:04:00.000Z",{"id":1118,"slug":1119,"title":1120,"excerpt":1121,"featuredImage":1122,"publishedAt":1123},"494","air-gapped-ai-how-ai-systems-work-without-internet-or-cloud-access","Air-Gapped AI: How AI Systems Work Without Internet or Cloud Access","Air-gapped AI runs models, RAG and AI applications inside an isolated security domain without internet or cloud dependencies. Learn how models, data, updates and tools operate offline.","\u002Fuploads\u002F2026\u002F10\u002Fair-gapped-ai-how-ai-systems-work-without-internet-or-cloud-access-1791487983978-e6xqf0.webp","2026-10-08T11:32:00.000Z","fallback",[],[]]