{"id":606055,"date":"2026-04-25T18:19:14","date_gmt":"2026-04-25T18:19:14","guid":{"rendered":"https:\/\/www.newsbeep.com\/us\/606055\/"},"modified":"2026-04-25T18:19:14","modified_gmt":"2026-04-25T18:19:14","slug":"artificial-intelligence-just-cracked-the-text-of-a-burned-papyrus-that-would-crumble-if-touched","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us\/606055\/","title":{"rendered":"Artificial Intelligence Just Cracked the Text of a Burned Papyrus That Would Crumble if Touched"},"content":{"rendered":"<p>A charred papyrus, long considered impossible to read without destroying it, has finally revealed its contents. Thanks to artificial intelligence, researchers accessed the text without opening the document and managed to spot writing inside something no one had been able to read for over 2,000 years.<\/p>\n<p>For years, this ancient artifact remained sealed because of its extreme fragility. According to a release published by Oxford University, any attempt to unroll it risked wiping out the ink completely, leaving researchers with no safe method to study it.<\/p>\n<p>The work shows a new way to deal with ancient texts that are too fragile to touch. For historians, it\u2019s a big shift after decades of getting nowhere. The combination of advanced imaging and AI analysis now allows scientists to examine objects once considered permanently inaccessible.<\/p>\n<p>An Artifact Too Fragile To Be Opened<\/p>\n<p>The text is part of the Herculaneum scrolls, buried in 79 AD. When they were found, they looked more like lumps of charcoal than books. Trying to open them would just destroy them.<\/p>\n<p>As stated in the statement, one of these scrolls has been sitting at the Bodleian Library for years, with no real way to read it. Researchers tried different methods, but nothing worked. For a long time, it was basically a dead end. The papyrus was there, but its content remained completely out of reach.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"391\" src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/04\/The-exterior-of-the-scroll-is-too-damaged-and-carbonized-to-open-physically.webp.webp\" alt=\"The Exterior Of The Scroll Is Too Damaged And Carbonized To Open Physically\" class=\"wp-image-131932\"  \/>The exterior of the scroll is too damaged and carbonized to open physically. Credit: Vesuvius Challenge<\/p>\n<p>AI Reconstructs Text Without Physical Contact<\/p>\n<p>The turning point came in 2024 when researchers tried something different using the Diamond Light Source. This machine sends high-energy X-rays through objects to map their internal structure without damaging them.<\/p>\n<p>According to the same source, this technique made it possible to virtually reconstruct the papyrus document and reveal entire sections of text. Often referred to as digital unwrapping, the process relies entirely on data processing rather than physical interaction.<\/p>\n<p>\u201cResearchers are further refining the image using a new\u00a0segmentation approach, in the hopes that it will improve the coherence and clarity of the lines of\u00a0text currently visible, and perhaps reach the end of the papyrus (the innermost part of the\u00a0carbonised scroll) where the colophon with the title of the work may be preserved,\u201d explained the authors.<\/p>\n<p>A Long-Lost Papyrus Text Begins To Emerge<\/p>\n<p>One key detail made this scroll stand out: its ink. Researchers noticed it appears more clearly in <a href=\"https:\/\/dailygalaxy.com\/2026\/02\/mars-meteorite-reveals-water-vault-inside\/\" data-type=\"post\" data-id=\"120199\" rel=\"nofollow noopener\" target=\"_blank\">X-ray scans<\/a> than others, possibly because it contains lead.<\/p>\n<p>As reported by the Oxford team cited in the article, this made it easier for AI to detect letters. The system highlighted sections of text, which experts from the <a href=\"https:\/\/scrollprize.org\/\" target=\"_blank\" rel=\"noopener nofollow\">Vesuvius Challenge<\/a> then worked on manually.<\/p>\n<p>\u201cThe image of the virtually unrolled scroll shows a considerable part of the papyrus and \u2013 most\u00a0importantly \u2013 some columns of text (with about the last 26 lines of each column),\u201d stated the researchers \u201cWhilst efforts are\u00a0underway by University of Oxford scholars to interpret the text, the Vesuvius Challenge is inviting\u00a0others to come forward and join the collective effort to fully decipher its contents.\u201d<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"368\" src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/04\/AI-processed-scan-revealing-hidden-text-inside-a-carbonized-ancient-papyrus.webp.webp\" alt=\"Ai Processed Scan Revealing Hidden Text Inside A Carbonized Ancient Papyrus\" class=\"wp-image-131933\"  \/>AI-processed scan revealing hidden text inside a carbonized ancient papyrus. Credit: Oxford University<\/p>\n<p>Dr. <a href=\"https:\/\/www2.cs.uky.edu\/dri\/w-brent-seales\/\" target=\"_blank\" rel=\"noopener nofollow\">Brent Seales <\/a>pointed out that the results are promising, even if there\u2019s still a lot to figure out. <\/p>\n<p>\u201cWe\u00a0are thrilled with the successful imaging of this scroll from the Bodleian Libraries and are grateful to\u00a0our partners for their support and collaboration. This scroll contains more recoverable text than we\u00a0have ever seen in a scanned Herculaneum scroll.\u201d<\/p>\n<p>The <a href=\"https:\/\/dailygalaxy.com\/2025\/01\/roman-scroll-unveils-1890-year-old-fraud-scandal\/\" data-type=\"post\" data-id=\"77539\" rel=\"nofollow noopener\" target=\"_blank\">scroll <\/a>may contain more readable text than others scanned before, and researchers are continuing to improve their tools to uncover the rest.<\/p>\n","protected":false},"excerpt":{"rendered":"A charred papyrus, long considered impossible to read without destroying it, has finally revealed its contents. Thanks to&hellip;\n","protected":false},"author":2,"featured_media":606056,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[45],"tags":[182,181,507,74],"class_list":{"0":"post-606055","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/606055","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/comments?post=606055"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/606055\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media\/606056"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media?parent=606055"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/categories?post=606055"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/tags?post=606055"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}