TeleGen: Benchmark for Automated Code Generation and Execution Validation

TeleGen accompanies research on automated environment construction and execution-based evaluation for software and web development tasks. The dataset includes benchmark task metadata, structured input/output records, evaluation scripts, runtime observations, and experimental results. It was authored by Yujia Luo and released on figshare in May 2026.

Use Cases

• Analyzing environment setup and configuration based on benchmark task metadata
• Studying code execution and failure diagnosis based on runtime observations
• Evaluating observation-driven code refinement or repair based on structured input/output records
• Reproducing experiments on automated software engineering workflows based on evaluation scripts and results

Strengths

• Dataset size is 1.7 GB, indicating a substantial collection of materials.
• Includes multiple components such as benchmark metadata, structured records, scripts, and observations, suggesting a multifaceted resource.
• Released under a CC-BY-4.0 license, facilitating reuse and distribution.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Likely gathered for a research study on automated software engineering.

Freshness

Last updated 2026-05-25 17:14:31; freshness should be verified.