Learning Conjecturing from Scratch

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F25%3A00388563" target="_blank" >RIV/68407700:21730/25:00388563 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1007/978-3-031-99984-0_23" target="_blank" >https://doi.org/10.1007/978-3-031-99984-0_23</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-99984-0_23" target="_blank" >10.1007/978-3-031-99984-0_23</a>

Result language

angličtina

Original language name

Learning Conjecturing from Scratch

Original language description

We develop a self-learning approach for conjecturing of induction predicates on a dataset of 14,005 problems derived from the OEIS. These problems are hard for today’s SMT and ATP systems because they require a combination of inductive and arithmetical reasoning. Starting from scratch, our approach consists of a feedback loop that iterates between (i) training a neural translator to learn the correspondence between the problems solved so far and the induction predicates useful for them, (ii) using the trained neural system to generate many new induction predicates for the problems, (iii) fast runs of the Z3 prover attempting to prove the problems using the generated predicates, (iv) using heuristics such as predicate size and solution speed on the proved problems to choose the best predicates for the next iteration of training. The algorithm discovers on its own many interesting induction predicates, ultimately solving 3,590 problems, compared to 835 problems solved by CVC5, Vampire or Z3 in 60 s.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Automated Deduction – CADE 30: 30th International Conference on Automated Deduction, Stuttgart, Germany, July 28-31, 2025, Proceedings

ISBN

978-3-031-99983-3

ISSN

0302-9743

e-ISSN

—

Number of pages

23

Pages from-to

423-445

Publisher name

Springer

Place of publication

Cham

Event location

Stuttgart

Event date

Jul 28, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—