zenodoopen
Let's Ask AI About Their Programs
<p>The dataset includes:</p> <ul> <li>60 small Python programs generated by OpenAI GPT-3.5 (10 functionally correct program variations for each of the selected 6 publicly available introductory programming assignments)</li> <li>399 program comprehension questions that target the generated programs</li> <li>798 answers to those questions by OpenAI GPT-3.5 and GPT-4</li> <li>Researcher annotation on the correctness of each answer and developed codes for the error types</li> </ul> <p>In addition, scripts for processing and analyzing the data are included.</p> <p> </p>
ShareScore
36/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 8
- Harmonization
- 4
- Access
- 16
- Reuse readiness
- 8
- Engagement
- 0