AI Is Decoding the Vatican Secret Archives, One Pen Stroke at a Time

Tiziana Fabi, AFP/Getty Image
Tiziana Fabi, AFP/Getty Image

The Vatican Secret Archives comprise 600 collections of texts spanning 12 centuries, most of which are nearly impossible to access. The Atlantic reports that a team of scientists is hoping to change that with help from some high school students and artificial intelligence software.

In Codice Ratio is a new research project dedicated to analyzing the vast majority of Vatican manuscripts that have never been digitized. When other libraries wish to make a digital archive of their inventory, they often use optical-character-recognition (OCR) software. Such programs can be trained to recognize the letters in a certain alphabet, pick them out of hard-copy manuscripts, and convert them to searchable text. This technology posed a challenge for the Vatican, however: The many older texts in its collections are written by hand in a cursive-like script. With no spaces between the characters, it's impossible for OCR to determine what's a letter and what isn't.

To get around this, the research team at In Codice Radio tweaked OCR software so that it could recognize pen strokes instead of letters. The OCR can identify the pen strokes that make up letters in an alphabet by looking for spots in the text where the ink narrows rather than presents full gaps between characters. The strokes aren't very useful on their own, but the software can combine the pieces to form possible letters.

To help the software perform even better, researchers recruited students from 24 Italian high schools to check its work. As the researchers explain in their paper, the students were shown a list of acceptable versions of a real letter, such as the letter A, and were then given a list of characters the software had guessed might be the real letter. By selecting the characters that matched the acceptable versions, they were able to slowly teach the software the medieval Latin alphabet.

All this information, plus a database of 1.5 million Latin words that had already been digitized, eventually brought the OCR to a place where it could use artificial intelligence to identify real letters on its own. The final results aren't perfect—a good portion of the words transcribed so far contain typos—but Vatican archivists are a lot better off than they were before: The software can identify individual handwritten letters with 96 percent accuracy, and misspelled words can still provide important context to readers. The goal is to eventually use the software to digitize every document in the Vatican Secret Archives.

[h/t The Atlantic]

Does Pushing the Button at a Crosswalk Actually Do Anything?

Pressing this crosswalk button may or may not do something.
Pressing this crosswalk button may or may not do something.
David Tran/iStock via Getty Images

Since crosswalk signals rarely seem to give you the green light (or more accurately, the white, human-shaped light) right after you press the button, you may find yourself wondering if those buttons actually work. The potentially exasperating answer is this: It depends.

First and foremost, it’s important to understand that crosswalk buttons aren’t designed to have an immediate effect; they’re just supposed to tell the system that a person is waiting to cross. As CityLab explained, some systems won’t ever give pedestrians the crossing signal unless someone has pressed the button, while others are programmed to shorten the wait time for walkers when the button has been pressed. No matter what, the system still has to cycle through its other phases to give cars enough time to pass through the intersection, so you’ll probably still have to stand there for a moment.

During busy traffic times or under other extenuating circumstances, however, cities can switch the system to what’s known as “recall mode,” when pedestrian crossings are part of the cycle already and pressing the button quite literally changes nothing. Unfortunately, there’s no way to tell if a particular button is in recall mode, short of calling your city officials and asking an expert to come inspect it.

But if you feel like a button isn’t doing anything, there’s a pretty good chance it’s been permanently deactivated. As congestion has increased and the systems to manage it have become more advanced over the years, cities have moved away from using crosswalk buttons at all. In 2018, for example, CNN reported that only around 100 of New York City’s 1000 buttons were still functioning. Since actually removing the buttons from crosswalks would be a costly endeavor, cities have opted to leave them intact, just waiting to be pummeled by impatient pedestrians who don’t know any better.

What about 'close door' buttons on elevators, you ask? That depends, too.

Have you got a Big Question you'd like us to answer? If so, let us know by emailing us at bigquestions@mentalfloss.com.

China's Coronavirus App Is Alerting Citizens When They're in Danger of Being Infected

Coronavirus fears have spread throughout China and beyond.
Coronavirus fears have spread throughout China and beyond.
Kevin Frayer, Getty Images

Questions continue to linger around the new coronavirus, currently plaguing parts of China and other countries. In an effort to combat the spread of the virus, the Chinese government recently introduced a smartphone app that claims to alert users when someone suspected of having the virus has been nearby.

According to the BBC, the app, dubbed the “close contact detector," works by having phone users register their name and government ID number. Once they activate the service, they’ll be notified if they’ve been in a place where someone diagnosed with coronavirus has been. Patient A, for example, might have reported being on a train, in a classroom, or in an office space that the app user also occupied. The user would get an alert along with a notice to stay home in the event they might have contracted the virus.

Whether a user has been in close contact is determined by their physical proximity to someone suspected of having the virus. Airplane passengers in the three rows surrounding someone suspected of being infected would be considered in close contact. Other passengers may not be considered close.

The scope of the app appears to be limited to information provided by transit authorities and other institutions and does not appear to be an all-inclusive method of determining exposure.

The app is state-sponsored and was developed by the General Office of the State Council, the National Health Commission, and the China Electronics Technology Group Corporation. While critics have said the app presents an invasion of privacy and a way for government to track any user's movements, others have argued that the risk to public health warrants it.

"In this case the public good and the public health has to outweigh the privacy concerns, otherwise we have no shot of doing anything about this," Dr. Irwin Redlener, the director of the National Center for Disaster Preparedness at Columbia University, told ABC News.

[h/t BBC]

SECTIONS

arrow
LIVE SMARTER