2023-01-01 · article · Logic, programming, and type systems · en
highly citedfrom the source record
As a present to Mizar on its 50th anniversary, we develop an AI/TP system that automatically proves about 60% of the Mizar theorems in the hammer setting. We also automatically prove 75% of the Mizar theorems when the automated provers are helped by using only the premises used in the human-written Mizar proofs. We describe the methods and large-scale experiments leading to these results. This includes in particular the E and Vampire provers, their ENIGMA and Deepire learning modifications, a number of learning-based premise selection methods, and the incremental loop that interleaves growing a corpus of millions of ATP proofs with training increasingly strong AI/TP systems on them. We also present a selection of Mizar problems that were proved automatically.
Claims drawn from cited facts, not live model generation.
This paper is an article on logic, programming, and type systems. As a published article, this work has cleared peer review and should be given the weight of a peer-reviewed publication.
3 cited facts
This work is a small team of 3 researchers.
1 cited fact
It has received 76,645 citations, and its highly cited status indicates it is already an established reference point in its field. The work references 0 works, so its reception stands out independently of a large reference list.
3 cited facts
Exploiting Generative AI to Scale up Intelligent Tutoring Systems is an article, focusing on Logic, programming, and type systems, published in 2023.
Exploiting Generative AI to Scale up Intelligent Tutoring Systems has 76,645 citations in our record, placing it among the highly cited works we track.
Our record lists 3 authors for Exploiting Generative AI to Scale up Intelligent Tutoring Systems. Author names aren't in our data yet — the source link on the page lists the full byline.
Source facts, citations, and refresh stamp for this record.
Sources: openalex_works