Exploratory Program Synthesis

Developing Exploratory Program Synthesis tools to enhance productivity and reliability in coding by enabling code generation even with incomplete specifications.

Subsidie
€ 1.500.000
2023

Projectdetails

Introduction

Our goal is to create Program Synthesis that can be used during Exploratory Programming to boost productivity and reliability when programmers write code. Program synthesis generates code for programmers so they can focus on the problem-solving aspects of their work.

Challenges in Specification

This often requires programmers to write a specification for the desired code, but this specification may not exist. Many aspects are initially undecided:

  • Implementation details
  • The division into subtasks
  • At times, even what the result should be

This leads programmers to use Exploratory Programming: refining their understanding of the code by writing the code. User studies we conducted to evaluate previous synthesis tools highlighted the chasm between what programmers know before writing code and the specifications program synthesis needs.

Development of Exploratory Program Synthesis

We will develop Exploratory Program Synthesis: tools that can support the programmer even when their initial specification of the task is lacking. Exploratory Program Synthesis will hinge on finding non-disruptive ways for the programmer to use synthesis while still using specifications so that results retain a notion of correctness.

Understanding User-Centric Challenges

This will require a better understanding of both exploratory programming and existing user-centric challenges in program synthesis, and will produce new synthesis interaction models backed by new synthesis algorithms. The conceptual leap is finding ways for programmers to interact with synthesis that are designed for the needs of both programmer and synthesizer by better understanding both, forming an interface between the two that is mutually beneficial.

Impact on Programming

Exploratory Program Synthesis will revolutionize programming by letting the wealth of synthesis research be integrated into programmers' day-to-day work, allowing programmers to generate code that is attuned to their work trajectory. The algorithms and interaction models developed in this research will significantly improve programmers' ability to write correct code quickly.

Financiële details & Tijdlijn

Financiële details

Subsidiebedrag€ 1.500.000
Totale projectbegroting€ 1.500.000

Tijdlijn

Startdatum1-12-2023
Einddatum30-11-2028
Subsidiejaar2023

Partners & Locaties

Projectpartners

  • TECHNION - ISRAEL INSTITUTE OF TECHNOLOGYpenvoerder

Land(en)

Israel

Vergelijkbare projecten binnen European Research Council

ERC Advanced...

Theoretical Foundations of Advanced Synthesis

This project aims to develop advanced synthesis methods for complex systems by enhancing quality measures, incorporating game-theoretic aspects, and addressing unpredictable environments.

€ 2.328.750
ERC Proof of...

Reactive Synthesis in Action

The SYNTACT PoC aims to test and promote reactive synthesis technologies in industrial settings to enhance software correctness and reduce development costs, paving the way for broader adoption.

€ 150.000
ERC Advanced...

Program Intelligence, Declaratively and Symbolically

The PINDESYM project aims to advance automatic program understanding by integrating symbolic reasoning and machine learning into a unified declarative analysis framework.

€ 2.395.875
ERC Consolid...

Automated Synthesis of Stochastic Cyber-Physical Systems: A Robust Approach

This project aims to revolutionize the design of cyber-physical systems by automating robust control software synthesis from high-level requirements, enhancing reliability and reducing costs in safety-critical applications.

€ 1.993.756
ERC Consolid...

Choreographies for Distributed Systems: Reasoning, Expressivity, and Development

This project aims to enhance choreographic programming by developing new constructs, verification logics, and a toolchain for effective compilation and deployment of distributed applications.

€ 1.999.498

Vergelijkbare projecten uit andere regelingen

EIC Pathfinder

A metapredictive model of synthetic awareness for enabling tool invention

METATOOL aims to develop a computational model of synthetic awareness in robots to enable self-evaluation and tool invention, advancing adaptive AI technology.

€ 3.298.843