The registration is now open for authors, speakers and PC (if you didn't get the link in an email from the organizers, please let us know). If you got an email from someone else, do not provide any payment data in any other way - it is very likely a scam!
Background
Large-scale semantic processing and strong computer assistance of mathematics and science is our inevitable future. New combinations of AI and reasoning methods and tools deployed over large mathematical and scientific corpora will be instrumental to this task. The AITP conference is the forum for discussing how to get there as soon as possible, and the force driving the progress towards that.
Topics
- AI and big-data methods in theorem proving and mathematics
- Collaboration between automated and interactive theorem proving, in particular their AI/ML aspects
- Common-sense reasoning and reasoning in science
- Alignment and joint processing of formal, semi-formal, and informal libraries, Formal Abstracts
- Methods for large-scale computer understanding of mathematics and science
- Combinations of linguistic/learning-based and semantic/reasoning methods
- Formal verification of AI and machine learning algorithms, explainable AI
Sessions
There will be several focused sessions on AI for ATP, ITP, mathematics, relations to general AI (AGI), Formal Abstracts, linguistic processing of mathematics/science, modern AI and big-data methods, and several sessions with contributed talks. The focused sessions will be based on invited talks and discussion oriented. AITP'24 is planned as an in-person conference. Virtual participation may be possible in exceptional situations.
Confirmed Participants/Speakers/Panelists (TBC)
| João Araújo | Universidade Nova de Lisboa | |
| Henk Barendregt | Radboud University Nijmegen | |
| Mario Carneiro | Carnegie Mellon / Chalmers University | |
| Thibault Gauthier | Czech Technical University in Prague | |
| Ben Goertzel | SingularityNET | |
| Georges Gonthier | INRIA | |
| Sean Holden | University of Cambridge | |
| Jan Jakubuv | Czech Technical University in Prague | |
| Mikoláš Janota | University of Lisbon | |
| Moa Johansson | Chalmers University | |
| Cezary Kaliszyk | University of Innsbruck | |
| Peter Koepke | University of Bonn | |
| Konstantin Korovin | The University of Manchester | |
| Tomáš Mikolov | Czech Technical University in Prague | |
| Miroslav Olsak | University of Cambridge | |
| J.D. Phillips | Northern Michigan University | |
| Michael Rawson | TU Wien, Austria | |
| Stephan Schulz | DHBW Stuttgart | |
| Martin Suda | Czech Technical University in Prague | |
| Josef Urban | Czech Technical University in Prague | |
| Adam Vandervorst | Qoba.ai | |
| Sean Welleck | Carnegie Mellon University | |
| Zsolt Zombori | Alfréd Rényi Institute of Mathematics |
Invited talks (TBA)
Dates
- Submission deadline:
May 5Extended: May 12, 2024 - Author notification: June 20, 2024
- Conference registration: TBA
- Camera-ready versions: TBA
- Conference: September 1-6, 2024
Contributed talks
| Nil Geisweiller. Meta-Reasoning in MeTTa for Inference Control via Provably Pruning the Search Tree. |
| Thibault Gauthier and Josef Urban. Solving One-Third of the OEIS from Scratch. |
| Martin Suda. Two Learning Operators for Clause Selection Guidance: An Experimental Evaluation. |
| Thibault Gauthier. Synthesis of Arithmetical Programs for Ramsey Graphs. |
| Michael Rawson, Zsolt Zombori, Maximilian Doré and Christoph Wernhard. Project Proposal: Forward Reasoning in Hindsight. |
| Zsolt Zombori, Pál Zsámboki, Ádám Fraknói, Máté Gedeon and Andras Kornai. Language Models, Mathematics, Embeddings. |
| Jelle Piepenbrock, Mikolas Janota, Josef Urban and Jan Jakubuv. Integrating graph neural networks into cvc5. |
| Jonathan Julian Huerta Y Munive. Isabelle/RL Project Proposal: Reinforcement learning on the Isabelle proof assistant. |
| Zarathustra Goertzel. ATPs as Universal AIs: What Do AGI Architectures Suggest for ATP Research? |
| Daniel Ranalter and Cezary Kaliszyk. Learning to Prove in Dependent Higher-Order Logic. |
| Martin Kolář. MATPROVE Dataset - Mathematical Problem-solving Dataset of Lessons and Exercises. |
| Christoph Wernhard and Zsolt Zombori. Exploring Metamath Proof Structures. |
| Andrei Kozyrev, Gleb Solovev, Nikita Khramov and Anton Podkopaev. CoqPilot, a plugin for LLM-based generation of proofs. |
| Gonçalo Araújo. AI/TP Methods for maximizing generality and tractability of algebras. |
| Sujoy Mukherjee, Daniel Scofield and Petr Vojtechovsky. Recognizing algebraic properties from multiplication tables. |
| Brando Miranda. Lean4AI: Enhancing LLMs for General Reasoning Through Interactive Theorem Prover Integration. |
| Sho Sonoda, Naoto Onda, Kei Tsukamoto, Fumiya Uchiyama, Akiyoshi Sannai and Wataru Kumagai. Automated Theorem Proving by HyperTree Proof Search with Retrieval-Augmented Tactic Generator. |
| Adam Dingle. A Natural-Language Proof Assistant for Higher-Order Logic. |
| Thomas Reichel and Talia Ringer. ProofDB: A prototype natural language Coq search engine. |
| Jan Jakubuv, Mikolas Janota and Josef Urban. Solving Hard Mizar Problems with Instantiation and Strategy Invention. |
| Kristina Aleksandrova, Jan Jakubuv and Cezary Kaliszyk. Prover9 Unleashed: Automated Configuration for Enhanced Proof Discovery. |
| Jan Hula, Jiří Janeček, David Mojžíšek and Mikoláš Janota. Do Language Models See a Space? |
| Nour Dekhil, Adnan Rashid and Sofiene Tahar. Proof Recommendation System for the HOL4 Theorem Prover. |
| Jiewen Hu, Thomas Zhu and Sean Welleck. miniCTX: Neural Theorem Proving with Long Contexts. |
| Adrian De Lon. Naproche-ZF: lessons learned from implementing a new natural-language-oriented theorem prover. |
| Irina Starikova. Can AI prove creatively?. |
| Adam Vandervorst and Anneline Daggelinckx. Towards Safe Agents with Graph Rewriting. |
| Evan Lohn and Sean Welleck. miniCodeProps: a Minimal Benchmark for Proving Properties of Code. |
| Sólrún Halla Einarsdóttir, Emily First and Moa Johansson. On Lemma Conjecturing using Neural, Symbolic and Neuro-symbolic approaches. |
| Shubhra Mishra. A Study of Knowledge Distillation for Theorem Proving in Small Language Models. |
| Michail Karatarakis. Leveraging Large Language Models for Autoformalizing Theorems: A Case Study. |
| Yutaka Nagashima and Daniel Sebastian Goc. Proof By Abduction in Isabelle/HOL. |
| David Valente, Manuel Eberl, Cezary Kaliszyk and Josef Urban. Project Description: Experiments with Language Models for Isabelle Autoformalization. |
| Brando Miranda, Aryan Gulati, Eric Chen, Kai Fronsdal, Emily Xia and Bruno Dumont. Putnam-MATH: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning. |
Program Committee (TBC)
| Jasmin Christian Blanchette | LMU Munich |
| David Cerna | Czech Academy of Sciences |
| Michael R. Douglas (co-chair) | Stony Brook University |
| Ulrich Furbach | University of Koblenz |
| Thibault Gauthier | Czech Technical University in Prague |
| Thomas C. Hales (co-chair) | University of Pittsburgh |
| Sean Holden | University of Cambridge |
| Mikoláš Janota | University of Lisbon |
| Moa Johansson | Chalmers University |
| Cezary Kaliszyk (co-chair) | University of Innsbruck |
| Michael Kinyon | University of Denver |
| Peter Koepke | University of Bonn |
| Konstantin Korovin | The University of Manchester |
| Mirek Olsak | University of Cambridge |
| Bartosz Piotrowski | IDEAS NCBR |
| Michael Rawson | TU Wien |
| Stephan Schulz (co-chair) | DHBW Stuttgart |
| Martin Suda | Czech Technical University in Prague |
| Josef Urban (co-chair) | Czech Technical University in Prague |
| Sean Welleck | Carnegie Mellon University |
| Zsolt Zombori | Alfréd Rényi Institute of Mathematics |
Organizers
| Georges Gonthier | INRIA |
| Cezary Kaliszyk | University of Innsbruck |
| Josef Urban | Czech Technical University in Prague |
Pictures from the previous conferences
Location, Prices and Further Local Information
The conference will take place from September 1 to September 6 2024 in
the
CNRS Paul-Langevin Conference Center
located in
the mountain village of Aussois in Savoy. Dominated by the "Dent
Parrachée", one of the highest peaks of La Vanoise, Aussois is located
on a sunny plateau at 1500 m altitude, offering a magnificent panorama
of the surrounding mountains and a direct access to the downhill ski
slopes or cross country slopes in winter.
The total price for accommodation and food for the five days will be around
600 EUR.
Arrival/Departure:
The first meal is dinner on September 1st and the last meal is lunch on September 6th. Aussois is less than 2h from the airports of Lyon, Geneve, Chambery, Annecy, Grenoble and Turin.
We will organize a bus to Aussois from Saint-Jean-de-Maurienne at around 19:10 pm on Sunday, September 1st. (Note that the Modane station is still not reachable by trains, but you can get there by a bus.) Our bus will wait for the TGV train from Paris arriving to Saint-Jean-de-Maurienne at 18:25 (starting at 14:48 in Paris) and the train from Milan arriving at 19:00 (starting at 14:10 in Milan). If you plan to travel to Aussois on your own, there are taxis and alternative buses from Modane (http://www.altibus.com/ - the Aussois Le Coin stop is just above the center).
We have not yet set the time for the departure of the bus/taxis after lunch on September 6th. This will be optimized based on your departure flights. The center will likely close after our last session on Friday. If you want to stay for the weekend, the center recommends Hotel des Mottets which is 5 minutes from the center and their prices are very reasonable: https://www.hotel-lesmottets.com/ . If you have more questions/notes, put them into the registration form and/or look into the FAQ.