CodeGemma: Open Code Models Based on Gemma (2024 · 82 citations)
CodeGemma is a family of open code models from Google. They are built by continuing the training of Gemma checkpoints on large amounts of mostly code data, with the aim of strong coding skills without losing general language and reasoning ability.
HOList: An Environment for Machine Learning of Higher-Order Theorem Proving (2019 · 78 citations)
Learning-based theorem proving has lacked a shared, large-scale benchmark. Existing proof assistants use incompatible logical foundations, and earlier datasets were either small or scored only with proxy metrics. HOList fills this gap. It is an open-source environment built on the HOL Light interactive prover…

All works

6 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

CodeGemma: Open Code Models Based on GemmaarXiv:2406.11409CodeGemma Team: Heri Zhao, Jeffrey Hui, Joshua Howland, et al.2024 · 82 citations
HOList: An Environment for Machine Learning of Higher-Order Theorem ProvingarXiv:1904.03241Kshitij Bansal, Sarah M. Loos, Markus N. Rabe, et al.2019 · 78 citations
Mathematical Reasoning via Self-supervised Skip-tree Training ↗arXiv:2006.04757 · no summary yetMarkus N. Rabe et al.2020 · 54 citations
Learning to Reason in Large Theories without Imitation ↗arXiv:1905.10501 · no summary yetKshitij Bansal et al.2019 · 36 citations
Mathematical Reasoning in Latent Space ↗arXiv:1909.11851 · no summary yetDennis Lee et al.2019 · 33 citations
Graph Representations for Higher-Order Logic and Theorem Proving ↗arXiv:1905.10006 · no summary yetAditya Paliwal et al.2019 · 33 citations

Co-authors here

6 co-authors with a page, the most papers together first.

Papers of our library cite their works 2,434 times (of the 149,439 papers whose bibliographies we read); 593 citing papers with a page here →.

Updated 2 November 2026