There is a PBS documentary about this very thing and how it got started. Very cool and worth the watch. Needless to say, the researcher had quite a few hurdles to overcome.
This is really exciting. If you're not aware, the scrolls at Herculaneum are an entire pagan library from the first century. They're burned, hard to recover, mostly still buried. Being able to decode them without physically digging them up and damaging them is awesome.
Who knows what we could find. So many books have been lost.
By sauerweb 19 hours ago
Seems a bit confusing to call it a "pagan library" when it's just the personal library of a very rich ancient Roman.
The ancient Roman elite often had extensive personal libraries which they shared with their friends, almost like a very primitive book publishing industry.
By philosophty 18 hours ago
From the Christian, anyone who wasn't part of the Christian or Jewish faiths was considered pagan. In the first century CE, Epicureans were part of the broader category of Hellenistic pagan philosophers—which included Stoics, Platonists, and others—who were polytheistic or at least non-Christian. So since Philodemus makes up most of the library here, it's pretty safe to call it a "pagan" library.
By TrapLord_Rhodo 18 hours ago
But there is no reason to situate it in a Christian context. We are in a global multi religious community here. I could call your comment bad, supported by it being a trite semantic argument without relevancy for the subject. But that would do nothing to further the discussion here. Calling the library non-confucianist would be even more correct as Platonists are an important foundation for Christian thought. Though a completely useless labeling just as the pegan label.
By tokai 17 hours ago
> Calling the library non-confucianist would be even more correct as Platonists are an important foundation for Christian thought.
Epicureans aren't Platonists. We know that the library went heavy on Epicurean texts.
The word "pagan" is still used by Classicists today.
By flir 17 hours ago
There is a reason to situate it in a roman context. Rome eventually becomes christianized and it makes sense to talk about before and after that. Obviously the old still influences the new, its not a hard line, but it is a major change in roman society.
By bawolff 17 hours ago
You are right.
it's just that the romans themselves had an identity crisis of "pagan" vs. "monothestic". So yes, you are right to call out the fact that situating it in the christian context would be follie.
But the original point still stands. Calling it pagan is still a correct classification of the works in the library.
By TrapLord_Rhodo 14 hours ago
Christianity didn't even really exist at that point, if would have been a minor cult.
So it doubly makes no sense.
It is definitely not correct, it's the equivalent of calling the ruins Italian instead of Roman.
By mattmanser 3 hours ago
I mean, part of what makes this library interesting is that nearly all of the classical Greek and Latin texts we have access to have been passed through the filter of generations of Christian monks copying those texts. Being able to see what these texts looked like without that filter is inherently interesting.
By duskwuff 12 hours ago
Wrong. This is essentially the context in which we still live today though we’ve secularized substantially over the past centuries. But Rome was on the path to Christianity at this time and later converted, so this is a very common way to understand things. Generally a work is one of a few things: Christian, Jewish, maybe Muslim depending on whom you ask, as it’s also an Abrahamic faith, or Pagan.
To be honest this feels more like you have an axe to grind with Christianity or its dominance, similar to the people pushing for “BCE/CE” over BC/AD. I don’t know why, but don’t expect the rest of the world to carry that cross for you.
By _bin_ 15 hours ago
> This is essentially the context in which we still live today
Who's "we"? - It doesn't apply to everyone in the world, so you're assuming some limitations in who you're referring to.
GP makes a fair point. If you mean by "pagan" simply non-Christian and non-Jewish, then to make it relevant to call it a pagan library you would need to establish that it was curated specifically to exclude Christain or Jewish themes. You might as well call it a "non-Mithraic library", if it happens to exclude mention of Mithras, which was also an up-and-coming cult among the Romans in the first century. Then it would be incorrect or presumptious to call it "non-Mithraic", unless you'd first established that it contained no mention of Mithras. And the only reason you'd do that is if Mithras held a particular parochial relevance to you. You understand that not everyone holds up an image of Mithras as a prism through which to view everything else.
OTOH, if you mean by "pagan" just that it's Roman, but from before Rome converted to Christianity, then just say it's a first century Roman library.
By griffzhowl 12 hours ago
To be honest, adding the word "pagan" just seem needlessly divisive. When I read about the past, nobody is going out of their way to point out that it's Pagan.
By kiba 12 hours ago
When a scientist in India publishes a study, we don't call it a "pagan" study.
The word "pagan" adds nothing to the original post. "An entire library from the first century" conveys just as much information.
By Arainach 13 hours ago
Before Christian Era and Christian Era.
My main gripe with it is the low entropy. In BC/AD each letter is unique. Even if you only heared 1 letter you still know what was said.
By gsich 10 hours ago
These people were non-Christian the same way they were non-Scientologists. They were unaware of Christianity and it had little to no impact on elite Romans by 79 AD.
"So since Philodemus makes up most of the library here, it's pretty safe to call it a "pagan" library."
You're confusing the tiny number of scrolls which have been preserved with what was likely in the complete library.
The complete library was much larger and likely contained the typical mix of philosophy, drama, poetry, and speeches copied over centuries from all over the Roman and Greek world.
By philosophty 17 hours ago
So is the “pagan” moniker a way of dating the work to before the rise of Christianity with the Roman Empire?
By JoBrad 17 hours ago
To put it simply, "pagan" was a Christian insult towards non-Christians. It is not a reasonable description for anything unless you're in a very Christian context, and even then viewing it from a modern context "pagan" is a bit of a slur.
By colechristensen 17 hours ago
Christianity had a really transformative impact on the Roman world so it makes sense to classify texts as pre and post Christianity. The date - literally BC and AD - don’t work so scholars have for a very long time clarified by calling the pre-Christian “pagan”.
By wood_spirit 17 hours ago
In the first century CE, Christianity was barely on anyone’s radar. It’s indeed very odd to frame it this way?
By lazide 3 hours ago
it isn't. besides this library and a few a few texts that survived via the East, almost every Roman text that has survived to today has survived through being copied by Christians, and stored in a Christian library. the word pagan perhaps has negative connotations, but it's a very relevant distinction
By permo-w an hour ago
Would monotheistic be a more appropriate description of non-pagers?
I don’t know anything about paganism but it seems like if the grouping excludes Jews and Christians non-Christian describes Jews and pagans.
By detourdog 17 hours ago
Abrahamic (= worshipping the God of Abraham) is the word I've most often seen used.
By wizzwizz4 16 hours ago
That works for me but I'm still curious what a pagan is.
By detourdog 14 hours ago
yes, it would. Monotheistic would be a much better term as that's how the people at the time viewed the divide.
By TrapLord_Rhodo 14 hours ago
In context its clear what is meant and that terminology has a long history.
Sure you could argue the terminology is very christian-centric, perhaps even offensive to pre-christian romans, but quite frankly that's a very uninteresting debate compared to the topic at hand.
By bawolff 17 hours ago
In the sense that the later Christian Romans were very very eager to lean on the good ol' book burning.
One of the reasons only a fraction of a percent of the classical texts reached our days is the fact that Christians suppressed those texts, directly (by destroying them) and indirectly (by closing the libraries and temples and institutions of learning which preserved those texts).
By andrepd 11 hours ago
I actually find this strange tendency of online commenters to link something to their own obscure interest very amusing. It's been a classic for as long as I recall but I encountered another today which I thought was very entertaining where a commenter remarked that he only just realized that "Suno" is the Hindi word for what we'd say in Latin as "Audi". In Latin! Hahaha!
I have decided that I, too, shall use obscure things as benchmarks and references. It's pretty good fun. In this post-Ragnarok-Online world one can imagine we need more such milestones to judge other things by.
By renewiltord 17 hours ago
> Being able to decode them without physically digging them up and damaging them is awesome.
Can you provide some citations on the technology being used in situ without digging up? As far as I understood this is the application of technology widely popularized by the Herculaneum Challenge, where scrolls are still physically dug up, and x-rayed (which will slowly still damage the scrolls) but without physically breaking them open as was repeatedly attempted in the past.
I don't care much about the slow damage from x-rays: as long as the content is succesfully extracted, one can imagine little other use for the scrolls as is.
I mostly hope some lost works on mathematics will be recovered..
By DoctorOetker 18 hours ago
They have been dug up already. IIRC they have undergone extensive scanning over the years - X-Ray, CT etc - while not being unrolled.
So they have the scans of the rolled up scrolls, this is "just" (ha!) using the scan data with lots of algorithms and compute (AI? I presume so) to virtually unroll the scrolls and read the ink off the page.
By mattlondon 16 hours ago
Actually, they are CT scanning them as the project continues. IIRC they reported about scanning a new (big) batch of them about a month ago.
You are right about not unrolling them though. Many scrolls were destroyed in previous attempts to unroll them physically, so it is fascinating to see how the technology has progressed to allow reading without unrolling.
By bornfreddy 15 hours ago
And still plenty more to be dug up, allegedly.
By qingcharles 16 hours ago
At the start of the article it links to a previous article on the scroll from February 2025 which has some more background details:
Researchers are further refining the image using a new segmentation approach in the hopes that it will improve the coherence and clarity of the lines of text currently visible, and perhaps reach the end of the papyrus, the innermost part of the carbonised scroll, where the colophon with the title of the work may be preserved.
So the new article is indicating they were able now to decipher the title, and also indicates maybe why the title was not the first thing deciphered (presumably it is hardest to read the innermost parts.)
I'm curious why the title is in the inside of the scroll. That implies you have to completely open it to read the title - is that the way scrolls are usually written?
By martinpw 17 hours ago
If you're rolling the scroll up as you read (or, I guess, write) it, you'll leave it rolled up like that. I presume you're expected to rewind the tape before you return it, if you borrowed it from somebody else.
By wizzwizz4 16 hours ago
This is awesome but I get so worried that we're just hallucinating meaning in those little splotches.
By qoez 19 hours ago
> Both images were independently reviewed by the Vesuvius Challenge papyrological team, led by Federica Nicolardi. The simultaneous reproduction of the title image from multiple sources, along with independent scholarly review, provides a high degree of confidence in the reading.
You have 2 teams using the same data, getting to the same conclusion. You also have an author that's known from other sources, with writings that we already "have". Then you have a team of experts reviewing this. Chances are these are real findings and not "hallucinations". Not everything in ML is gen-ai...
By NitpickLawyer 19 hours ago
To add to this, the main ML parts, as I understand it, are for the initial unrolling of layers, and for the detection of ink vs. no-ink (the position of the 'splotches'). Both of these are trained and calibrated from human observations.
All interpretation of ink as Greek letters is done purely by human inference. This may lead to errors, especially in parts where the ink is preserved especially poorly or where the text is totally different from expectations, but it would be classic human error instead of AI hallucination.
By LegionMammal978 18 hours ago
> You have 2 teams using the same data, getting to the same conclusion.
> You also have an author that's known from other sources, with writings that we already "have".
> Then you have a team of experts reviewing this.
Only the first of those points is evidence against the result being hallucinated.
By thaumasiotes 6 hours ago
>You also have an author that's known from other sources, with writings that we already "have".
Well, that's exactly what you'd expect from a hallucination no? If the model is overfit enough on the relevant corpus, a title that already exists should be much more likely.
By suddenlybananas 18 hours ago
The ML models are looking at tiny patches for areas of ink vs. no-ink, trained on the boundaries of more visible letters found by humans. They don't know what proper Greek letters look like, and they definitely don't know what correct Greek words would be (in particular, they have no "corpus" of words). Any possible overfitting is ordinary human overfitting.
By LegionMammal978 18 hours ago
If they have learned on ink areas shaped as letters, what prevents them from having a bias towards such shapes?
By anabab 18 hours ago
Because they don't get to see the entire letter shapes. The page at [0] shows the basic idea: they're forced to make decisions based on each part of each stroke of the letter. If they were heavily overfitting on the strokes of the letters in the training sample, then they'd be so inaccurate outside the sample that the assembled outputs would hardly resemble letters at all, much less words.
(Also, this is heavily-damaged handwriting, not clear print, so each letter isn't even uniform in shape. A model trying to cheat at ink detection would have an uphill battle trying to guess what all the variant letter shapes might be.)
We are not. This is more forensics (using ML to learn what the clues are) than "AI".
By bornfreddy 15 hours ago
> Philodemus was an Epicurean philosopher and poet from Gadara whose ethical teachings emphasise the pursuit of pleasure as central to a good life. He argued against rigid logic and formal rhetoric, believing that philosophy should serve practical human happiness rather than abstract intellectual debate.
As a layman admirer of Epicurean thought, I’m so glad that even after so many wars, destruction and tragedy over the centuries, such wonderful works have survived.
By FlyingSnake 5 hours ago
Brent Seales was my second CS professor and taught me how to do OOP in C++. It’s always cool to randomly see the work he’s done every few months. He was working on this project nearly twenty years ago.
By helsinki 12 hours ago
This really is a herculean act. bravo. my condolences to all those archeology students who will never brush ash away with the same carelessness as before today. Is it really worth digging destructively ?
By ashoeafoot 15 hours ago
This is so cool
As a history nerd and jaded software developer, I've been wondering a lot lately how I can use my tech skills for archeological research. Is there any way for someone with most of a bachelors to get into this kind of thing?
By popctrl 16 hours ago
My experience with academia is that most of this hard work is done by undergrads, and conception and management by professors; developers aren't hired to do this. So besides "going back to school", there's no way in for an outsider.
By worewood 15 hours ago
Well, they are hiring [0]. Sounds like a great way to start. Or you can join the Vesuvius Challenge if you prefer competing.
They say they're hiring but I didn't even get an email back about my application and I've been awarded $20k through the vesuvius challenge and have 10 years experience in the exact job they're hiring for so I really don't know what they're looking for or if they're looking that hard.
By verditelabs 12 hours ago
Sorry to hear this happened as this shouldn't have been lost. I'll make sure we get in touch with you.
By blackstache 11 hours ago
they say they deciphered it - ok, so what does it say!? the most important information is omitted... so annoying.
By webdevver 19 hours ago
The Greek writing visible in the image reads:
ΦΙΛΟΔΗΜΟΥ ΠΕΡΙ ΦΥΣΕΩΣ
This translates into English as:
Of Philodemus, On Nature
By number6 18 hours ago
ΠΕΡΙ ΚΑΚΙΩΝ Ά
About vices - part A
By seydor 16 hours ago
Interestingly, as written, it is ΚΑΚΙωΝ not ΚΑΚΙΩΝ.
By sanxiyn 4 hours ago
They identified it by title as a copy of a known work. This information appears very early in the article.
By throwanem 18 hours ago
It is not very common to find pre-Kanishka works. I hope that we get some insight into human lives around this time. One of the things I find fascinating about ancient times is how similar humans of then were to us. Akrotiri (similarly preserved by volcanic eruption) was millennia before even the works in this discovery and yet seemed strangely familiar and normal when visiting.
By renewiltord 17 hours ago
> Using ‘virtual unwrapping’, the scroll PHerc. 172 which is housed at the Bodleian Libraries at the University of Oxford has been identified as On Vices by the Greek philosopher Philodemus
Instead of an interesting discussion about the technologies used to unravel these documents, it quickly degraded into the usual politicized issues that plague the United States, and sadly it seems, now this forum.
I tried emailing Dang, to remove my account with no response. HN administrators, if you read this can please remove my account?
By xpose2000 17 hours ago
By FirmwareBurner 16 hours ago
By 93po 15 hours ago
By deadbabe 15 hours ago
By sauerweb 19 hours ago
By philosophty 18 hours ago
By TrapLord_Rhodo 18 hours ago
By tokai 17 hours ago
By flir 17 hours ago
By bawolff 17 hours ago
By TrapLord_Rhodo 14 hours ago
By mattmanser 3 hours ago
By duskwuff 12 hours ago
By _bin_ 15 hours ago
By griffzhowl 12 hours ago
By kiba 12 hours ago
By Arainach 13 hours ago
By gsich 10 hours ago
By philosophty 17 hours ago
By JoBrad 17 hours ago
By colechristensen 17 hours ago
By wood_spirit 17 hours ago
By lazide 3 hours ago
By permo-w an hour ago
By detourdog 17 hours ago
By wizzwizz4 16 hours ago
By detourdog 14 hours ago
By TrapLord_Rhodo 14 hours ago
By bawolff 17 hours ago
By andrepd 11 hours ago
By renewiltord 17 hours ago
By DoctorOetker 18 hours ago
By mattlondon 16 hours ago
By bornfreddy 15 hours ago
By qingcharles 16 hours ago
By martinpw 17 hours ago
By wizzwizz4 16 hours ago
By qoez 19 hours ago
By NitpickLawyer 19 hours ago
By LegionMammal978 18 hours ago
By thaumasiotes 6 hours ago
By suddenlybananas 18 hours ago
By LegionMammal978 18 hours ago
By anabab 18 hours ago
By LegionMammal978 18 hours ago
By bornfreddy 15 hours ago
By FlyingSnake 5 hours ago
By helsinki 12 hours ago
By ashoeafoot 15 hours ago
By popctrl 16 hours ago
By worewood 15 hours ago
By bornfreddy 15 hours ago
By verditelabs 12 hours ago
By blackstache 11 hours ago
By webdevver 19 hours ago
By number6 18 hours ago
By seydor 16 hours ago
By sanxiyn 4 hours ago
By throwanem 18 hours ago
By renewiltord 17 hours ago
By 01HNNWZ0MV43FF 19 hours ago
By thewanderer1983 9 hours ago