# Architecture and Knowledge Representation for Composable Inductive Programming

arXiv: https://arxiv.org/abs/2212.12320 · HTML: https://mlsanity.com/paper/2212.12320/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 25 references that are in the map.
- First posted on arXiv 22 Dec 2022.

## Builds on (most cited first, 4 of 4)

- [Automatic Code Generation using Pre-Trained Language Models](https://mlsanity.com/paper/2102.10535/) (2021)
- [Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches](https://mlsanity.com/paper/2009.07740/) (2020)
- [Zoea -- Composable Inductive Programming Without Limits](https://mlsanity.com/paper/1911.08286/) (2019)
- [A Visual Language for Composable Inductive Programming](https://mlsanity.com/paper/2009.08700/) (2020)

## Built on by (most cited first, 1 of 1)

- [Further Decimating the Inductive Programming Search Space with Instruction Digrams](https://mlsanity.com/paper/2305.13347/) (2023)

## Abstract (arXiv)

We present an update on the current architecture of the Zoea knowledge-based, Composable Inductive Programming system. The Zoea compiler is built using a modern variant of the black-board architecture. Zoea integrates a large number of knowledge sources that encode different aspects of programming language and software development expertise. We describe the use of synthetic test cases as a ubiquitous form of knowledge and hypothesis representation that sup-ports a variety of reasoning strategies. Some future plans are also outlined.