Code execution trace generation with pre-trained large language model
US12314154B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 24, 2023 |
| Grant date | May 27, 2025 |
| Priority date | — |
| Expiry date | Aug 16, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A large language model, previously pre-trained on multiple source code modeling tasks, is pre-trained, through curriculum learning, to learn to predict a code execution trace given a source code program. The model is pre-trained using a variety of pre-training datasets consisting of pairs of a source code sample and a corresponding execution trace. The curriculum pre-training starts with a pre-training dataset of single line executions and adds in additional pre-training datasets with more increasing complex behaviors. The pre-training datasets include mutation-augmented source code samples and their corresponding execution traces.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.