Research programme

Research

CSK is the research programme of STUDIO HAZE, with CodeImage as its main focus. Our research directions are introduced first, followed by the library of published papers.

CodeImage

Program Representation and Generation

We are preparing three papers on CodeImage, covering visual program representation, joint generation and refinement of connected structures, and evaluation through program behavior. The existing image format and deterministic recovery path provide the foundation for this work.

Representing and Recovering Programs as Images

How can an image record a program’s nodes, values and references so that a decoder can read them unambiguously? This paper will examine the visual grammar and the rules that connect program structure to a canonical image. It will describe how deterministic decoding reconstructs that image and checks it against the input PNG.

The paper will distinguish two recovery paths. Within the supported profile, the image alone recovers executable source in a canonical form. A matching exact-recovery key contains the original source separately and restores its bytes, including formatting and comments. We will make each path’s information requirements and recovery guarantees explicit.

Parallel Generation and Refinement of Program Structure

Can several connected parts of a program be proposed together and brought into agreement through repeated revision? We plan to study a shared structural state in which some positions are masked. A model would propose nodes, values and references for several positions using the surrounding structure and a specification. Syntax and reference constraints would guide which parts to mask again and refine.

We plan to begin with small programs whose relationships are easy to inspect. Validated candidates would be expressed as supported source and passed through the existing encoding and rendering path. This keeps the question of how to generate a coherent structure separate from the task of recording it precisely in the CodeImage format.

Behavioral Evaluation and Representation Studies for Program Generation

When a generated program satisfies structural constraints, does it also do what the specification requires? We plan to evaluate small functions with explicit inputs and expected behavior, including boundary cases and tasks with different structures. For small, finite input domains, we will compare every input’s result with an independently defined expected result. This will distinguish formal validity from behavioral correctness within the evaluated domain.

We also plan to compare text, linear intermediate representations, graphs and grids carrying the same program information under matched training and generation budgets. By varying the representation and revision strategy separately, we will examine their effects on behavioral errors and computation. The aim is to establish when visual and spatial structure helps program generation, and where it adds cost.

Read the CodeImage story

Published research library

Published papers with their PDFs and reproduction materials. The research topics above describe the papers we are preparing.

ICSE 2027 NIER

1 paper

ICSE 2027 New Ideas and Emerging Results

A track of the International Conference on Software Engineering. Published deadlines use AoE (UTC−12).

deadline: notification: camera-ready:
  1. Auditing What Program Images Hide and Preserve

    A bounded audit of one pinned CodeImage deployment tests independence from hidden completions and preservation of promised context. Fixed masks leave a 36-pixel reference-class difference, while a separate control loses an allowed operator. No learned generator or model-accuracy gain is claimed.

SCORED '26

3 papers

Workshop on Software Supply Chain Offensive Research and Ecosystem Defenses

October 6, 2026, Prague. Co-located with OpenSSF Community Day Europe.

deadline: notification: presentation:

LMPL 2026

1 paper

International Workshop on Language Models and Programming Languages

October 8, 2026, Oakland. Co-located with SPLASH and ISSTA 2026.

deadline: notification: presentation:
Core Semantic Kernel