# Research

Canonical HTML: https://aogavrilov.com/research/
Machine-readable router: https://aogavrilov.com/research-guides.json

Decision-oriented routing for two evidence-based research guides. Routes identify a first diagnostic and required evidence; they do not create new empirical claims or replace validation on a new system.

## How to tell whether a compressed text generator fails in the codec or the generator

- Canonical guide: https://aogavrilov.com/research/codec-bottleneck-diagnosis/
- Markdown guide: https://aogavrilov.com/research/codec-bottleneck-diagnosis/index.md
- Use when: A pipeline compresses text into discrete codes before generation. Decoded quality is poor and the responsible stage is unknown. A latent-space proxy improves without a matching decoded-output improvement. Code-space and token-space masked diffusion language models must be compared under one decoded-text scorer.

## How can AI edit code without regenerating the entire program?

- Canonical guide: https://aogavrilov.com/research/discrete-latent-generation/
- Markdown guide: https://aogavrilov.com/research/discrete-latent-generation/index.md
- Use when: A generative model should modify a bounded code region without rewriting an entire function. Selected parts of a Python function need to be regenerated while protected parts remain stable. A task needs an explicit choice among localized editing, constrained code generation, AI-assisted refactoring, and inspectable latent control. Code-edit locality must be balanced with generation diversity under an observable preservation contract. A structure-preservation claim needs decoded program evidence rather than latent locking alone.

Focused research notes: https://aogavrilov.com/research-notes/