alt Hacker NewsI am on the vesuvius challenge team that did the segmentation, unwrapping, and ink detection, so feel free to ask any questions.
Replies
Massive kudos to the whole team. I've been waiting 30 years for this announcement, ever since I first heard about the scrolls. Fantastic work!
Outstanding work! I've participated in the challenge, but didn't get far. One of the questions I had at the time was - if I'm going to use ML to detect ink, could it invent hallucinated letters, or even parts of text, and how to prevent that?
I'm interested to know about the approaches that you tried with the ML, and then decided to not use. In practice, the options are so many. How did you come up with the final approach - and was there a systematic way to decide which options to go for?
Absolutely incredible work. This is one of the most amazing news articles I’ve encountered in decades. Congratulations team!
What are the wildest, most exciting but plausible things that might be discovered in these documents?
how many scrolls have been scanned so far? what's the main limitation on scan amount?
have any attempts (or just ideas) been made to recreate such charring on known texts?
How do get to do that? As in what did you study to get the prerequisite knowledge, and how did you find this particular job? When I see interesting jobs I'm anyways curious what path lead there
Amazing work, fantastic!
Given the current rate of progress, how long do you think it will take to decipher the entire collection?
No questions, but I just want to say this is really exciting work!
Did anyone on the team come from a non-science, non-math, non-academia background? Did anyone working on this just teach themselves and start contributing?
this is überragend. by many means!
Are the fragments destroyed in ‘69 and ‘80 available to be read similarly? Or were they disposed of?
I don't have any questions, just a comment.
You have a potential to rewrite the history of European Antiquity quite substantially. The Herculaneum set of scrolls is enormous and must contain a lot of hitherto unknown.
That comes with a set of peculiar risks. Once your work starts producing something that contradicts previous work of Very Important People, they will lobby to stop you. Be prepared for that.
Science should be neutral and always value new evidence. Scientists as humans are unfortunately subject to all sorts of passions.
How fast is the process?
Could it be automated to the point where it's faster to scan a book closed than opened?