Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Online Access: | https://doi.org/10.5281/zenodo.19555331 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901527632805888 |
|---|---|
| author | Singh, Krishanu |
| author_facet | Singh, Krishanu |
| contents | <p>Artifact for the FSE 2026 paper "Speculate: Generating REST API Specifications Using LLMs".</p> <p>This artifact contains the Speculate tool, which generates OpenAPI specifications from Spring Boot, Jersey and Django REST API source code using LLMs. It includes:</p> <p>- The complete Speculate tool source code<br>- 15 Java benchmark repositories from the Respector dataset (Spring and Jersey frameworks)<br>- Pre-compiled class files for all benchmarks<br>- Pre-computed generation results across 5 LLM models (o4-mini, gpt-4.1, gpt-4.1-mini, o1, DeepSeek-R1)<br>- RQ1 evaluation reports with endpoint, parameter, and constraint metrics<br>- A Dockerized workflow for reproducible execution</p> <p> ▎ Quick start:<br> ▎ docker pull krishannu/speculate-artifact:latest<br> ▎ docker run --rm -v "$(pwd)/outputs:/artifact/outputs" krishannu/speculate-artifact</p> <p>LLM credentials are auto-fetched at runtime. See README.md for full documentation.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19555331 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Speculate: Generating REST API Specifications Using LLMs — Artifact Singh, Krishanu <p>Artifact for the FSE 2026 paper "Speculate: Generating REST API Specifications Using LLMs".</p> <p>This artifact contains the Speculate tool, which generates OpenAPI specifications from Spring Boot, Jersey and Django REST API source code using LLMs. It includes:</p> <p>- The complete Speculate tool source code<br>- 15 Java benchmark repositories from the Respector dataset (Spring and Jersey frameworks)<br>- Pre-compiled class files for all benchmarks<br>- Pre-computed generation results across 5 LLM models (o4-mini, gpt-4.1, gpt-4.1-mini, o1, DeepSeek-R1)<br>- RQ1 evaluation reports with endpoint, parameter, and constraint metrics<br>- A Dockerized workflow for reproducible execution</p> <p> ▎ Quick start:<br> ▎ docker pull krishannu/speculate-artifact:latest<br> ▎ docker run --rm -v "$(pwd)/outputs:/artifact/outputs" krishannu/speculate-artifact</p> <p>LLM credentials are auto-fetched at runtime. See README.md for full documentation.</p> |
| title | Speculate: Generating REST API Specifications Using LLMs — Artifact |
| url | https://doi.org/10.5281/zenodo.19555331 |