{"url":"/dataset/stepgame","name":"StepGame","full_name":"StepGame","description_markdown":"A Benchmark for Robust Multi-Hop Spatial Reasoning in Texts","description_withheld":null,"homepage":"https://github.com/ZhengxiangShi/StepGame","introduced_date":"2022-02-22","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","datasets_with_task":"/datasets/task/common-sense-reasoning"},{"name":"Pancreas Segmentation","url":"/task/pancreas-segmentation","datasets_with_task":"/datasets/task/pancreas-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["StepGame"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-stepgame","task":"Question Answering","dataset_variant":"StepGame","rows":1,"metrics":["1-of-100 Accuracy"],"first_row_in_archive_order":{"model":"TP-MANN","paper":"/paper/stepgame-a-new-benchmark-for-robust-multi-hop-1","metrics":{"1-of-100 Accuracy":"52.99"},"code_links":[{"title":"ZhengxiangShi/StepGame","url":"https://github.com/ZhengxiangShi/StepGame"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/stepgame-a-new-benchmark-for-robust-multi-hop-1","title":"StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts","date":"2022-04-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":7,"samples_ran":5,"samples_unverified":2,"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."}