I wrote a game (SAT solving was the inspiration) back in 2022.

https://vivegi.github.io/Trek/

This sounds like a shortcut, unless it isn't.

I have a feeling this is going to make debugging code written just a few months ago incrementally difficult. At least the explicit if statements are easier to follow the intent from months ago.

The syntax is clean though. I'll give it that.

Cool. I used the Windows snipping tool and just screen-recorded it.

Layout analysis is the key. Quite a bit of work has been going on recently in this area.

Some papers of relevance:

  - Xu Zhong, Jianbin Tang, Antonio Jimeno Yepes. "PubLayNet: largest dataset ever for document layout analysis," Aug 2019. Preprint: https://arxiv.org/abs/1908.07836 Code/Data: https://github.com/ibm-aur-nlp/PubLayNet

  - B. Pfitzmann, C. Auer, M. Dolfi, A. S. Nassar and P. Staar, "DocLayNet: a large human-annotated dataset for document-layout analysis," 13 August 2022. [Online]. Available: https://developer.ibm.com/exchanges/data/all/doclaynet/.

  - S. Appalaraju, B. Jasani, B. U. Kota, Y. Xie and R. Manmatha, "Docformer: End-to-end transformer for document understanding.," in The International Conference on Computer Vision (ICCV 2021), 2021.

The first one is for publications. From the abstract: "...the PubLayNet dataset for document layout analysis by automatically matching the XML representations and the content of over 1 million PDF articles that are publicly available on PubMed Central. The size of the dataset is comparable to established computer vision datasets, containing over 360 thousand document images, where typical document layout elements are annotated".

The second is for documents. It contains 80K manually annotated pages from diverse data sources to represent a wide variability in layouts. For each PDF page, the layout annotations provide labelled bounding-boxes with a choice of 11 distinct classes. DocLayNet also provides a subset of double- and triple-annotated pages to determine the inter-annotator agreement.

Synthesis capability: When the system is capable of deriving established knowledge from first principles (similar to theorem proving from axioms)

Gap detection: The system is able to identify gaps in established knowledge

Path/problem decomposition: The system is able to decompose a problem (i.e., an identified gap) and break down the solution into a set of subproblems that can be independently solved.

Improvement/Optimization: Given a known solution, the system is able to discover objectively better approaches to solution.

There are probably other dimensions, but I would start with these.

ArXiv preprint [PDF] here: https://arxiv.org/pdf/2310.20689.pdf

Landed successfully at the Lunar south pole area.