{"url":"/dataset/orchard","name":"Orchard","full_name":"A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning","description_markdown":"Orchard is a diagnostic dataset for systematically evaluating hierarchical reasoning in state-of-the-art neural sequence models","description_withheld":null,"homepage":"https://github.com/billptw/Orchard","introduced_date":"2021-11-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/orchard-a-benchmark-for-measuring-systematic","title":"ORCHARD: A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning","first_author":"Bill Tuck Weng Pung","url":null},"license":null,"modalities":[],"tasks":[{"name":"Syntax Representation","url":"/task/syntax-representation","datasets_with_task":"/datasets/task/syntax-representation"}],"languages":[],"variants":["Orchard"],"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."}