Home/Developer Tools/self-repair

self-repair

theoxo/self-repair

Supports research on self-repair mechanisms for code generation

GitHub

GraphCanon updated Oct 7, 2026 · GitHub synced Oct 7, 2026

27views this month

15 stars3 forksLast push May 2, 2024 Python

Decision brief

Self-repair provides tools to replicate research experiments on code generation systems self-reparation techniques.

Good fit when

When aiming to replicate specific experimental data from the ICLR 2024 paper on self-repair in code generation
If your project requires evaluation of pre-existing datasets like HumanEval for new self-repair strategies

Avoid when

For creating entirely new datasets or conducting large-scale human studies, as this repository focuses on replicating existing experiments
When the internal dependencies or incomplete code functions such as exec_sample in APPS are critical for your application without modification

Observed Jul 16, 2026 · Source: enrich:decision_facts

self-repair alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Archived (887d since push); As of Oct 7, 2026
Provenance: Not a fork · Personal account; As of Oct 7, 2026
Security (OSV): No criticals; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install self-repair

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

SWE-bench

Benchmark for assessing language models' capability to resolve real-world Github issues

6.0k★

CodeBERT

CodeBERT series models for code pretraining in Python and programming languages

2.8k★

agentic-ai-prompt-research

Research into agentic AI coding assistants focusing on prompt patterns and security

2.5k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Source code and scripts to replicate experiments from the ICLR 2024 paper investigating whether self-repair is effective in code generation systems.

Capability facts

Languages: python
Source: github.language · Oct 7, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Oct 7, 2026)

- `analysis/sample-and-estimate.py`: Python script to generate bootstrapped estimates of pass rates at various budgets.

Source link

README

[ICLR 2024]: Is Self Repair a Silver Bullet for Code Generation? This is is the accompanying repository for the paper Is Self Repair a Silver Bullet for Code Generation?, presented at the Twelfth International Conference on Learning Representations (Vienna, May 2024). It contains...

For agents

This page has a .md twin and JSON over the API.

/tools/theoxo-self-repair.md GET /api/graphcanon/tools/theoxo-self-repair GET /api/graphcanon/graph?tool=theoxo-self-repair