{"id":55042,"date":"2020-12-02T00:00:37","date_gmt":"2020-12-02T08:00:37","guid":{"rendered":"https:\/\/world.edu\/?p=55042"},"modified":"2020-12-01T11:50:24","modified_gmt":"2020-12-01T19:50:24","slug":"artificial-intelligences-should-be-able-to-reason-their-explanations","status":"publish","type":"post","link":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/","title":{"rendered":"Artificial intelligences should be able to reason their explanations"},"content":{"rendered":"<p><span><img fetchpriority=\"high\" decoding=\"async\" class=\"aligncenter size-full wp-image-55043\" src=\"https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs.jpeg\" alt=\"\" width=\"680\" height=\"204\" srcset=\"https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs.jpeg 680w, https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs-250x75.jpeg 250w, https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs-600x180.jpeg 600w\" sizes=\"(max-width: 680px) 100vw, 680px\" \/><\/span><\/p>\n<p><span>About a year ago, a small American company in the medical field,\u00a0<\/span><a href=\"https:\/\/www.geisinger.org\/\"><span>Geisenger<\/span><\/a><span>\u00a0, published surprising results on the application of artificial intelligence (AI) to estimate the short-term risk of death of patients with certain heart conditions, based on their electrocardiogram .<\/span><\/p>\n<p><span>To do this, they trained a neural network with almost two million electrocardiograms of almost 400,000 people.\u00a0In the end this AI, based on a technique known as &#8220;deep learning&#8221;, obtained better results than those of cardiologists.\u00a0In addition, the doctors were not able to subsequently find any pattern or sign of risk in those electrocardiograms that the machine had correctly identified where they had failed.<\/span><\/p>\n<p><span>The AI \u200b\u200bhad found something in the electrocardiographic signal that human experts were not able to detect.<\/span><\/p>\n<p><span>The problem is that the AI \u200b\u200bwas only designed to get the best possible response, but not to give a reason for it.\u00a0This is what is known in the field as a &#8220;black box&#8221; due to its lack of transparency and, therefore, the ability to know and give an explanation of its results.<\/span><\/p>\n<p><span>Explainable AIs are endowed with the ability to explain their operation.\u00a0They are able to communicate their results and the reasoning process they have followed to obtain them, in a way that is easy for people to understand.\u00a0There are two main approaches to designing machines like this.<\/span><\/p>\n<p><span>On the one hand, we can think of them as white boxes (transparent or semi-transparent).\u00a0For example, those that are based on computationally tractable representations of human knowledge.\u00a0Known as &#8220;expert systems&#8221;.\u00a0However, this approach is not possible or desirable on many occasions, either due to design difficulties or insufficient performance.<\/span><\/p>\n<h4><strong>Let&#8217;s open the black boxes<\/strong><\/h4>\n<p><span>Another approach is to\u00a0<\/span><em><span>open<\/span><\/em><span>\u00a0and see inside those black boxes.\u00a0This is the case of AI based on deep learning or, in general, on artificial neuron networks.\u00a0These use learning architectures made up of very simple mathematical models of neurons.\u00a0These, in a number of thousands or tens of thousands, and profusely interconnected &#8211; generally layered, like a lasagna &#8211; total hundreds of thousands or even millions of connections.\u00a0These connections are associated with values, called &#8220;weights&#8221;, which are essential in the process of obtaining a response to each input applied to the neural network.<\/span><\/p>\n<p><span>This response may correspond, depending on the case, with a diagnosis, with the identification of an object on an image or with the translation into Spanish of a phrase in English.\u00a0The proper selection of these weights is performed during network training on training data sets.\u00a0The process is usually very demanding in terms of the number and representativeness of the examples to learn about, as well as the computational resources required to do so.<\/span><\/p>\n<p><span>The ability to learn from this type of network is enormous, but what they learn is distributed, without any apparent relation to each other, in an endless number of parameters or weights.\u00a0That is why we can ignore what one of these AIs is based on to detect an incipient pneumonia or a potentially cancerous nodule on a chest X-ray.\u00a0Exaggerating, it would be like trying to find an explanation for how a radiologist reaches the same conclusion from a functional MRI of your brain.<\/span><\/p>\n<p><span>No matter how capable the machines are to give us answers, if they affect us significantly we need them, in addition to being good, to be understandable.\u00a0Otherwise we will not trust them.\u00a0It is an issue that is increasingly present in the legislative framework of the countries.\u00a0In fact, the new\u00a0<\/span><a href=\"https:\/\/eur-lex.europa.eu\/legal-content\/ES\/TXT\/?uri=celex%3A32016R0679\"><span>European General Data Protection Regulation<\/span><\/a><span>\u00a0grants the right to an explanation of the decisions that affect people, no matter who (or what machine) makes those decisions.\u00a0In addition to technical and legal issues, there are also ethical issues to consider, as highlighted in the\u00a0<\/span><a href=\"https:\/\/ec.europa.eu\/digital-single-market\/en\/news\/ethics-guidelines-trustworthy-ai\"><span>guidelines for trustworthy AI published by the European Commission<\/span><\/a><span>\u00a0.<\/span><\/p>\n<p><span>The\u00a0<\/span><a href=\"https:\/\/citius.usc.es\/\"><span>Citius<\/span><\/a><span>\u00a0(University of Santiago de Compostela) is committed to training\u00a0<\/span><a href=\"https:\/\/www.atlantis-press.com\/journals\/ijcis\/125942036\/view\"><span>explicable IA from primary school to university<\/span><\/a><span>\u00a0and coordinates the first European network for training researchers in this field.\u00a0It is the\u00a0<\/span><a href=\"https:\/\/nl4xai.eu\/\"><span>NL4XAI<\/span><\/a><span>\u00a0network\u00a0, an acronym for the project entitled &#8220;Natural Language Technologies for\u00a0<a href=\"https:\/\/nl4xai.eu\/\">Explainable<\/a>\u00a0Artificial Intelligence&#8221;.<\/span><\/p>\n<p><span>This network&#8217;s main objective is to train expert researchers in explainable AI.\u00a018 partners participate in it, between universities and companies, from 6 countries, who collaborate in the training of 11 doctors.\u00a0A common goal will be to use natural language technologies to build conversation agents capable of explaining themselves by interacting with people.\u00a0Furthermore, these agents will be able to handle verbal and non-verbal information, providing their users with multimodal explanations (that is, mixing visual and textual or narrative explanations).<\/span><\/p>\n<p><span>We would like an AI to be able to explain, as a judge does, the foundations of a sentence.\u00a0Also that he could explain to us how he manages to recognize the accused despite having grown a beard from the last sight, something that people, even if we are capable of doing it, cannot explain how, but we will talk about this another day.<\/span><\/p>\n<p><em><strong>Author Bios:<\/strong> Sen\u00e9n Barro Ameneiro is Director of the CiTIUS-Singular Center for Research in Intelligent Technologies of the University of Santiago de Compostela and Jose Maria Alonso Moral is a Ram\u00f3n y Cajal Researcher in the Intelligent Systems group both at the University of Santiago de Compostela<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>About a year ago, a small American company in the medical field,\u00a0Geisenger\u00a0, published surprising results on the application of artificial intelligence (AI) to estimate the short-term risk of death of patients with certain heart conditions, based on their electrocardiogram . To do this, they trained a neural network with almost two million electrocardiograms of almost [&hellip;]\n&hellip; <a href=\"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/\" class=\"more\">learn more&rarr;<\/a><\/p>","protected":false},"author":33,"featured_media":55043,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[59],"tags":[357530],"coauthors":[11733],"class_list":["post-55042","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-science-tech","tag-explainable-ais"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.2 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Artificial intelligences should be able to reason their explanations - World leading higher education information and services<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/\" class=\"yoast-seo-meta-tag\" \/>\n<meta property=\"og:locale\" content=\"en_US\" class=\"yoast-seo-meta-tag\" \/>\n<meta property=\"og:type\" content=\"article\" class=\"yoast-seo-meta-tag\" \/>\n<meta property=\"og:title\" content=\"Artificial intelligences should be able to reason their explanations - World leading higher education information and services\" class=\"yoast-seo-meta-tag\" \/>\n<meta property=\"og:description\" content=\"About a year ago, a small American company in the medical field,\u00a0Geisenger\u00a0, published surprising results on the application of artificial intelligence (AI) to estimate the short-term risk of death of patients with certain heart conditions, based on their electrocardiogram . To do this, they trained a neural network with almost two million electrocardiograms of almost [&hellip;]\" class=\"yoast-seo-meta-tag\" \/>\n<meta property=\"og:url\" content=\"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/\" class=\"yoast-seo-meta-tag\" \/>\n<meta property=\"og:site_name\" content=\"World leading higher education information and services\" class=\"yoast-seo-meta-tag\" \/>\n<meta property=\"article:published_time\" content=\"2020-12-02T08:00:37+00:00\" class=\"yoast-seo-meta-tag\" \/>\n<meta property=\"og:image\" content=\"https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs.jpeg\" class=\"yoast-seo-meta-tag\" \/>\n\t<meta property=\"og:image:width\" content=\"680\" class=\"yoast-seo-meta-tag\" \/>\n\t<meta property=\"og:image:height\" content=\"204\" class=\"yoast-seo-meta-tag\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" class=\"yoast-seo-meta-tag\" \/>\n<meta name=\"author\" content=\"Kevin\" class=\"yoast-seo-meta-tag\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" class=\"yoast-seo-meta-tag\" \/>\n\t<meta name=\"twitter:data1\" content=\"Kevin\" class=\"yoast-seo-meta-tag\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" class=\"yoast-seo-meta-tag\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" class=\"yoast-seo-meta-tag\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/\"},\"author\":{\"name\":\"Kevin\",\"@id\":\"https:\\\/\\\/world.edu\\\/#\\\/schema\\\/person\\\/42c1c1d5ff7ffbdf0bd50ed94c6ae6ee\"},\"headline\":\"Artificial intelligences should be able to reason their explanations\",\"datePublished\":\"2020-12-02T08:00:37+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/\"},\"wordCount\":890,\"image\":{\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/world.edu\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/Explainable-AIs.jpeg\",\"keywords\":[\"Explainable AIs\"],\"articleSection\":[\"Science and Technology\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/\",\"url\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/\",\"name\":\"Artificial intelligences should be able to reason their explanations - World leading higher education information and services\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/world.edu\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/world.edu\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/Explainable-AIs.jpeg\",\"datePublished\":\"2020-12-02T08:00:37+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/world.edu\\\/#\\\/schema\\\/person\\\/42c1c1d5ff7ffbdf0bd50ed94c6ae6ee\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/#primaryimage\",\"url\":\"https:\\\/\\\/world.edu\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/Explainable-AIs.jpeg\",\"contentUrl\":\"https:\\\/\\\/world.edu\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/Explainable-AIs.jpeg\",\"width\":680,\"height\":204},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/world.edu\\\/artificial-intelligences-should-be-able-to-reason-their-explanations\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/world.edu\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Artificial intelligences should be able to reason their explanations\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/world.edu\\\/#website\",\"url\":\"https:\\\/\\\/world.edu\\\/\",\"name\":\"World leading higher education information and services\",\"description\":\"Global Higher Education Jobs, University jobs, Lecturer &amp; tenure jobs.\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/world.edu\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/world.edu\\\/#\\\/schema\\\/person\\\/42c1c1d5ff7ffbdf0bd50ed94c6ae6ee\",\"name\":\"Kevin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1e8d491a5f9b9bf3db67c9e46abbba7bb06b26b458bd5025c55e0a4b9b60ea8a?s=96&d=mm&r=g8ba4c352a279c450aa9435d770c1ebf4\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1e8d491a5f9b9bf3db67c9e46abbba7bb06b26b458bd5025c55e0a4b9b60ea8a?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1e8d491a5f9b9bf3db67c9e46abbba7bb06b26b458bd5025c55e0a4b9b60ea8a?s=96&d=mm&r=g\",\"caption\":\"Kevin\"},\"description\":\"Kevin is founder of the world.edu project. The past 28 years have been involved in publishing to the education sector in print and the internet. Kevin has a degree in Education and has a many years experience in developing companies and projects.\",\"sameAs\":[\"https:\\\/\\\/world.edu\"],\"url\":\"https:\\\/\\\/world.edu\\\/author\\\/kevin\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Artificial intelligences should be able to reason their explanations - World leading higher education information and services","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/","og_locale":"en_US","og_type":"article","og_title":"Artificial intelligences should be able to reason their explanations - World leading higher education information and services","og_description":"About a year ago, a small American company in the medical field,\u00a0Geisenger\u00a0, published surprising results on the application of artificial intelligence (AI) to estimate the short-term risk of death of patients with certain heart conditions, based on their electrocardiogram . To do this, they trained a neural network with almost two million electrocardiograms of almost [&hellip;]","og_url":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/","og_site_name":"World leading higher education information and services","article_published_time":"2020-12-02T08:00:37+00:00","og_image":[{"width":680,"height":204,"url":"https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs.jpeg","type":"image\/jpeg"}],"author":"Kevin","twitter_misc":{"Written by":"Kevin","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/#article","isPartOf":{"@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/"},"author":{"name":"Kevin","@id":"https:\/\/world.edu\/#\/schema\/person\/42c1c1d5ff7ffbdf0bd50ed94c6ae6ee"},"headline":"Artificial intelligences should be able to reason their explanations","datePublished":"2020-12-02T08:00:37+00:00","mainEntityOfPage":{"@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/"},"wordCount":890,"image":{"@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/#primaryimage"},"thumbnailUrl":"https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs.jpeg","keywords":["Explainable AIs"],"articleSection":["Science and Technology"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/","url":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/","name":"Artificial intelligences should be able to reason their explanations - World leading higher education information and services","isPartOf":{"@id":"https:\/\/world.edu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/#primaryimage"},"image":{"@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/#primaryimage"},"thumbnailUrl":"https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs.jpeg","datePublished":"2020-12-02T08:00:37+00:00","author":{"@id":"https:\/\/world.edu\/#\/schema\/person\/42c1c1d5ff7ffbdf0bd50ed94c6ae6ee"},"breadcrumb":{"@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/#primaryimage","url":"https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs.jpeg","contentUrl":"https:\/\/world.edu\/wp-content\/uploads\/2020\/12\/Explainable-AIs.jpeg","width":680,"height":204},{"@type":"BreadcrumbList","@id":"https:\/\/world.edu\/artificial-intelligences-should-be-able-to-reason-their-explanations\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/world.edu\/"},{"@type":"ListItem","position":2,"name":"Artificial intelligences should be able to reason their explanations"}]},{"@type":"WebSite","@id":"https:\/\/world.edu\/#website","url":"https:\/\/world.edu\/","name":"World leading higher education information and services","description":"Global Higher Education Jobs, University jobs, Lecturer &amp; tenure jobs.","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/world.edu\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/world.edu\/#\/schema\/person\/42c1c1d5ff7ffbdf0bd50ed94c6ae6ee","name":"Kevin","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/1e8d491a5f9b9bf3db67c9e46abbba7bb06b26b458bd5025c55e0a4b9b60ea8a?s=96&d=mm&r=g8ba4c352a279c450aa9435d770c1ebf4","url":"https:\/\/secure.gravatar.com\/avatar\/1e8d491a5f9b9bf3db67c9e46abbba7bb06b26b458bd5025c55e0a4b9b60ea8a?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/1e8d491a5f9b9bf3db67c9e46abbba7bb06b26b458bd5025c55e0a4b9b60ea8a?s=96&d=mm&r=g","caption":"Kevin"},"description":"Kevin is founder of the world.edu project. The past 28 years have been involved in publishing to the education sector in print and the internet. Kevin has a degree in Education and has a many years experience in developing companies and projects.","sameAs":["https:\/\/world.edu"],"url":"https:\/\/world.edu\/author\/kevin\/"}]}},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/posts\/55042","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/users\/33"}],"replies":[{"embeddable":true,"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/comments?post=55042"}],"version-history":[{"count":1,"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/posts\/55042\/revisions"}],"predecessor-version":[{"id":55044,"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/posts\/55042\/revisions\/55044"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/media\/55043"}],"wp:attachment":[{"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/media?parent=55042"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/categories?post=55042"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/tags?post=55042"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/world.edu\/wp-json\/wp\/v2\/coauthors?post=55042"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}