AI Is Beginning To Identify Who Wrote The Oldest Bible Copies - TechTheLead
Smart Life

AI Is Beginning To Identify Who Wrote The Oldest Bible Copies

(Image: Mladen PopovićMaruf A. DhaliLambert Schomaker)

Artificial Intelligence (AI) analysis done on the longest text of the Dead Sea Scrolls, known as the Great Isaiah Scroll, has uncovered the possibility that 2 different scribes wrote the oldest known copies of the Bible while using near-identical handwriting. The group of researchers, led by Mladen Popovic, from the University of Groningen’s Faculty of Theology and Religious Studies, presented their findings in the April 21st edition of the journal PLOS ONE.

“[…] Demonstrating that two main scribes, each showing different writing patterns, were responsible for the Great Isaiah Scroll,” the authors wrote in the published paper. “This study sheds new light on the Bible’s ancient scribal culture by providing new, tangible evidence that ancient biblical texts were not copied by a single scribe only but that multiple scribes, while carefully mirroring another scribe’s writing style, could closely collaborate on one particular manuscript.”

12×12 Kohonen maps (blue colormaps) of (full) character aleph and bet from the DSS collection. Each of the characters in the Kohonen maps is formed from multiple instances of similar characters (shown with a zoomed box with red lines). These maps are useful for chronological style development analysis. In our current study of writer identification, Fraglets will be used instead of full character shapes to achieve more precise (robust) results. (Image: Mladen PopovićMaruf A. DhaliLambert Schomaker)

Can AI Decode the Dead Sea Scrolls ?

The Dead Sea Scrolls are ancient manuscripts dating from around 2000 years ago that were discovered by Bedouin teenagers on the northwestern shores of the Dead Sea – hence the name of the manuscripts. Following their initial discovery from 1946 – or early 1947 according to some sources – archaeologists and Bedouin treasure hunters have swamped the area and managed to find 10 more caves near the ancient settlement of Qumran on the West Bank. Combined, these caves contained tens of thousands of scroll fragments, forming around 900 manuscripts, all dating from the 3rd century B.C. and written in Hebrew, as well as Aramaic and Greek, which makes the discovery a priceless literary treasure cove for the study of the history of the Jewish people in ancient times.

From the red boxes of the last two images one can see how the rotation and the geometric transformation is corrected to yield a better image for further processing. Reprinted from under a CC BY license, with permission from Brill Publishers, original copyright 1995. (Image: Mladen PopovićMaruf A. DhaliLambert Schomaker)

And now, by using “cutting edge” pattern recognition and AI, the team of researchers have examined the Great Isaiah Scroll, one of the original seven Dead Sea Scrolls discovered in Qumran in 1947 and also the largest and best-preserved of all the biblical scrolls. During their tests, “the ancient ink traces as they appear on digital images,” were successfully extracted and gave them the necessary evidence that the uniform handwriting was the work of two scribes with very similar writing styles.

An illustration of how heatmaps of normalized average character shapes are generated for individual letters. (Image: Mladen PopovićMaruf A. DhaliLambert Schomaker)

“We will never know their names,” Popovic said in a statement. “But after 70 years of study, this feels as if we can finally shake hands with them through their handwriting.” Suggesting that the writers were trained together, perhaps in the same school or even the same family, such as “a father having taught a son to write.”

Individual character heatmaps of alephperesh, and shin from 1QIsa.On the top left, the first aleph is aggregated from all the columns, the next one is from columns 1–27, and the final one is from columns 28–54. The same applies to the other three characters. (Image: Mladen PopovićMaruf A. DhaliLambert Schomaker)

According to the release, Computer Science and Artificial Intelligence professor in the University’s Faculty of Science and Engineering, Lambert Schoemaker, and Ph.D. candidate Maruf Dhali were key people in the effort. The former of the two had already spent years performing studies to investigate how biomechanical traits, like how someone holds a pen or stylus, would affect handwriting while the latter developed a state-of-the-art neural network, training his AI so that it could differentiate the handwritten text from the background document. “This scroll contains the letter aleph, or “a”, at least five thousand times,” says Schomaker. “It is impossible to compare them all just by eye. This is important because the ancient ink traces relate directly to a person’s muscle movement and are person-specific.”

In the case of aleph: the subtle difference in positioning of the left downstroke (a), the right upper stroke vis-à-vis the diagonal stroke (b), and the slight difference in thickness of the diagonal stroke (c). in the case of resh: the curvature of the top stroke (a), and the slight difference in thickness and length of the horizontal stroke (b). (Image: Mladen PopovićMaruf A. DhaliLambert Schomaker)

The Dead Sea Scrolls Mistery is About to be Solved

Although the researchers cannot rule out completely that the clear separation between the two halves of the manuscript and the difference in writing patterns are due to a change of writing implement (or a different pen), writing burnout, or some trauma that the author experienced when moving on to the second half of the manuscript, the more candid explanation is that a change in writers occurred at some point (speculative). The presence of two scribes in 1QIsaa better demonstrates the combined data regarding the fraglet and allographic levels of handwriting.

One of the significant results of the research is the need for paleographers (specialists who decipher, localize, date, and edit ancient and medieval texts), in Dead Sea Scrolls studies, to be conscious of similarities in handwriting future endeavors and findings. Instead of questioning whether traditional paleography captures everything, the study shows the need and benefit of collaboration between the disciplines. This may also refer to other ancient corpora that face similar palaeographic challenges, such as ancient Greek manuscripts that put up an interesting theory: “Same Book or Same Scribe? A Case Study of some Plato Papyri”. Throughout history, we will find similar anecdotes that will enlighten us about our ancestors. 

An AI outlook on a 70 years old discovery

This is great news for future research. Ever since their discovery 70 years ago, these ancient documents – which also include the oldest known version of the Bible – have been fascinating scholars of religious history, archaeologists, and common people alike. And now, with this new tool and technique, we can have a better understanding of the people behind these sacred texts and perhaps of their identities as well.

Subscribe to our website and stay in touch with the latest news in technology.

AI Is Beginning To Identify Who Wrote The Oldest Bible Copies
1 Comment

1 Comment

  1. Pingback: New York News: Now Auto-Generated by AI - Robot Writers AI

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

To Top