Vestigium (Publicaciones sobre AlphaGeometry)

Readings shared March 4, 2025

José A. Alonso — Tue, 04 Mar 2025 04:00:00 GMT

The readings shared in Bluesky on 4 March 2025 are

Formalizing zeta and L-functions in Lean. ~ David Loeffler, Michael Stoll. #ITP #LeanProver #Math
Lean Copilot: Large language models as copilots for theorem proving in Lean. ~ Peiyang Song, Kaiyu Yang, Anima Anandkumar. #LLMs #ITP #LeanProver
Gold-medalist performance in solving olympiad geometry with AlphaGeometry2. ~ Yuri Chervonyi et als. #AI #AlphaGeometry #Math
NL2FOL: Translating natural language to first-order logic for logical fallacy detection. ~ Abhinav Lalwani et als. #LLMs #Logig #SMT
Utilizing ChatGPT in a data structures and algorithms course: A teaching assistant's perspective. ~ Pooriya Jamie, Reyhaneh Hajihashemi, Sharareh Alipour. #LLMs #CompSci
Performance review on LLM for solving Leetcode problems. ~ Lun Wang et als. #LLMs #Programming
InductionBench: LLMs fail in the simplest complexity class. ~ Wenyue Hua et als. #LLMs #Reasoning

Readings shared November 29, 2024

José A. Alonso — Fri, 29 Nov 2024 04:00:00 GMT

The readings shared in Bluesky on 29 November 2024 are

Readings shared November 28, 2024. #ITP #IsabelleHOL #Logic #Math #Haskell #FunctionalProgramming
Proof of "If the limit of the sequence u(n) is a and c ∈ ℝ, then the limit of u(n)c is ac" in Lean4. #ITP #Lean4 #Math #Calculemus
Machine learning and mathematics (The twin catalysts poised to accelerate twenty-first century mathematics: formalisation and machine learning). ~ Harald Carlens. #Math #ITP #Lean4 #MachineLearning #LLMs #AIMO #AlphaProof #AlphaGeometry
Deep embedding of intuitionistic linear logic. ~ Filip Smola, Jacques D. Fleuriot. #ITP #IsabelleHOL #Logic #Math
Brillo: Painless 2D vector graphics, animations, and simulations powered by GLFW (Fork of gloss). ~ Adrian Sieber. #Haskell #FunctionalProgramming
Effectiveness of Large Language Models to generate formally verified C code. ~ Merlijn Sevenhuijsen. #LLMs #Programming #FormalVerification
dafny-annotator: AI-assisted verification of Dafny programs. ~ Gabriel Poesia, Chloe Loughridge, Nada Amin. #LLMs #Dafny #FormalVerification

Readings shared September 11, 2024

José A. Alonso — Wed, 11 Sep 2024 04:00:00 GMT

The readings shared in Mastodon on September 11, 2024 are

Readings shared September 10, 2024. #ITP #Lean4 #IsabelleHOL #Math #Calculemus #Haskell #Python #Math
Mathematical Olympiad (To the geometry and beyond…). ~ Mirek Olšák. #Math #ITP #AI #IMO #AlphaGeometry #AlphaProof #LeanProver
Isabelle/RL project proposal: Reinforcement learning on the Isabelle proof assistant. ~ Jonathan Julián Huerta y Munive. #ITP #IsabelleHOL #MachineLearning
CoqPilot, a plugin for LLM-based generation of proofs. ~ Andrei Kozyrev, Gleb Solovev, Nikita Khramov & Anton Podkopaev. #ITP #Coq #LLMs
ATPs as universal AIs: What do AGI architectures suggest for ATP research? ~ Zarathustra Goertzel. #ATP #AI
The formal theory of monads, univalently. ~ Niels van der Weide. #ITP #Coq
The last mile: How do we make AI theorem provers which work in the real world for real users and not just on benchmarks? ~ Jason Rute. #ITP #AI #LLMs
Naproche-ZF: Lessons learned from implementing a new natural-language-oriented theorem prover. ~ Adrian De Lon. #ITP #NaprocheZF #Math
Natural-language proof assistant for higher-order logic. ~ Adam Dingle. #ITP #Natty #Math
Natty: a natural-language proof assistant with an embedded automatic prover for higher-order logic. ~ Adam Dingle. #ITP #Natty #Math #OCaml
A few open problems in neural theorem proving (in Lean). ~ Sean Welleck. #ITP #LeanProver #LLMs
Project description: Experiments with language models for Isabelle autoformalization. ~ David Valente, Manuel Eberl, Cezary Kaliszyk & Josef Urban. #ITP #IsabelleHOL #Autoformalization
Provably safe systems: Prospects and approaches. ~ Mario Carneiro. #ITP #AI
With fifth busy beaver, researchers approach computation’s limits. ~ Ben Brubaker. #ITP #Coq #Math #CompSci
Kids should be taught to think logically. ~ Vinay K. Chaudhri. #Logic