Automatic Program Synthesis of Long Programs with a Learned Garbage Collector
Authors: Amit Zohar, Lior Wolf
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We ran a series of experiments testing the required runtime to reach a certain level of success. The results are reported in Tab. 1. |
| Researcher Affiliation | Collaboration | 1The School of Computer Science , Tel Aviv University 2Facebook AI Research |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code, including an implementation of various literature baselines, is publicly available at https: //github.com/amitz25/PCCoder |
| Open Datasets | No | We generate our train and test data similarly to [1]. First, we generate random programs from the DSL. Then, we prune away programs that contain redundant variables, and programs for which an equivalent program exists in the dataset (could be shorter). No concrete access information (link, DOI, repository, or citation with authors/year) is provided for this generated dataset. |
| Dataset Splits | No | The paper mentions 'train' and 'test' data, but does not explicitly specify a 'validation' dataset split or provide any details about it. |
| Hardware Specification | Yes | All our experiments were performed using F64s Azure cloud instances. |
| Software Dependencies | No | The paper mentions 'Cython program' and 'Adam [11]' as optimizer, but does not provide specific version numbers for any software dependencies or libraries (e.g., Python, PyTorch, etc.). |
| Experiment Setup | Yes | For optimization, we use Adam [11] with a learning rate of 0.001 and batch size of 100. We employ α = 100, β = 10, and c = 10. |