{"url":"/dataset/gpr-bench","name":"GPR-bench","full_name":"General‑Purpose Reproducibility Benchmark","description_markdown":"GPR‑bench is an open‑source, multilingual benchmark for regression testing and reproducibility tracking in generative‑AI systems. It provides a compact yet diverse suite of prompts and reference outputs that let you verify whether a model (or prompt) change alters output quality in undesirable ways.","description_withheld":null,"homepage":"https://huggingface.co/datasets/galirage/GPR-bench","introduced_date":"2025-05-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/ensuring-reproducibility-in-generative-ai","title":"Ensuring Reproducibility in Generative AI Systems for General Use Cases: A Framework for Regression Testing and Open Datasets","first_author":"Masumi Morishige","url":null},"license":{"name":"MIT‑licensed","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["GPR-bench"],"data_loaders":[],"num_papers_in_archive":1,"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."}