msuvakov

For anyone else interested in the math behind the shape sphere coordinates and topological free group classification, I put together an agent skill with code examples here: https://github.com/suvakov/vibes/blob/main/skills/shape_sphe...

I have a quick question: how are you currently checking if a new candidate is genuinely novel rather than a rotated, time-shifted, or rescaled duplicate of an existing solution?

If you are not already computing it, topological classification (mapping orbits to free group words) would be a great way to quickly prune duplicates before heavy numerical checks, and it's also really useful metadata to display in the atlas itself. Also, showing shape sphere projections of the orbits would be a nice visual addition.

https://suvakov.github.io/vibes/SlidingPuzzleChess/index.htm...

      ___                        ___                     ___           ___     
     /  /\           ___        /  /\      ___          /  /\         /  /\    
    /  /::|         /__/\      /  /:/     /__/\        /  /::\       /  /::\   
   /  /:|:|         \__\:\    /  /:/      \  \:\      /  /:/\:\     /__/:/\:\  
  /  /:/|:|__       /  /::\  /  /:/        \__\:\    /  /:/  \:\   _\_ \:\ \:\ 
 /__/:/_|::::\   __/  /:/\/ /__/:/         /  /::\  /__/:/ \__\:\ /__/\ \:\ \:\
 \__\/  /~~/:/  /__/\/:/~~  \  \:\        /  /:/\:\ \  \:\ /  /:/ \  \:\ \:\_\/
       /  /:/   \  \::/      \  \:\      /  /:/__\/  \  \:\  /:/   \  \:\_\:\  
      /  /:/     \  \:\       \  \:\    /__/:/        \  \:\/:/     \  \:\/:/  
     /__/:/       \__\/        \  \:\   \__\/          \  \::/       \  \::/   
     \__\/                      \__\/                   \__\/         \__\/

https://news.ycombinator.com/item?id=42946317

You're absolutely right that some characters are missing even in those short books, and there are likely many more relationships that haven't been fully captured. That said, I’m still quite impressed by how much data the LLM extracted in a single pass, especially given the complexity of the task, the size of the input, and the strict output format.

My estimate of quality was subjective. To truly quantify accuracy, we’d need to establish a "ground truth" with a better approach and measure the difference between the generated and actual relationship graphs. One possible way to do that would be to process the text in multiple passes: first extracting characters, then identifying relationships, both steps with more sophisticated prompt engineering. Another way is to manually annotate the network. The only book I found with a publicly available, human-annotated character network is Les Misérables, based on Donald Knuth’s work: https://github.com/MADStudioNU/lesmiserables-character-netwo...

However, there is an additional challenge. Even with human annotation, the question remains: how to define relationship network? What is a relationship in a book? Should it be limited to explicitly stated connections in the text, or it also can include deduced relationships based on context with some probability? Defining these criteria is crucial to quantify quality of the result.

The T2T team published a preprint [1] last December and released the data [2] in March. However, due to the peer review process, the findings have only just been formally published in Nature. The publication timeline can indeed be slow, and in cases like this one, the question is: what's the point when all scientists interested in the topic already know about it and working with this assembly?

[1] https://www.biorxiv.org/content/10.1101/2022.12.01.518724v1.... [2] https://github.com/marbl/CHM13

Only outlier is Djokovic's positive test. It perfectly fits to 26. December, the same date timestamp was created.

38 million km2 (Moon area) : 150 million km2 (land area of the Earth) = 25%

  def tail_factorial(n, accumulator=1):
    if n == 0: return accumulator
    else: return tail_factorial(n-1, accumulator * n)