Software Engineering
NESTER
NESTER: dataflow-guided neuro-symbolic type inference for Python. Released per-item data covers the human evaluation of high-level program generation on ManyTypes4Py samples: GPT-4, GPT-4o and GPT-4o mini generations each graded on four binary criteria (correctness, explainability, factuality, consistency) by human annotators. Recovered from deleted xlsx blobs in the authors' GitHub repository.
90items
3subjects
99%observed
unknownlicense
software_engineeringdomain
textmodality
Response matrix
Fit to width. Hover for subject & item; click a cell for details.
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect