{"url":"/dataset/codequeries","name":"CodeQueries","full_name":null,"description_markdown":"CodeQueries Benchmark dataset consists of instances of semantic queries, code context and code spans in the context corresponding to the semantic queries. The dataset can be used in experiments involving semantic query comprehension with an extractive question-answering methodology over code. More details can be found in the [paper](https://arxiv.org/abs/2209.08372).","description_withheld":null,"homepage":"https://huggingface.co/datasets/thepurpleowl/codequeries","introduced_date":"2022-09-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-to-answer-semantic-queries-over-code","title":"CodeQueries: A Dataset of Semantic Queries over Code","first_author":"Surya Prakash Sahu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Multi-Hop Reading Comprehension","url":"/task/multi-hop-reading-comprehension","datasets_with_task":"/datasets/task/multi-hop-reading-comprehension"},{"name":"Extractive Question-Answering","url":"/task/extractive-question-answering","datasets_with_task":"/datasets/task/extractive-question-answering"}],"languages":[],"variants":["CodeQueries"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}