{"url":"/dataset/hi-phy","name":"Hi-Phy","full_name":null,"description_markdown":"**Hi-Phy** is a benchmark for physical reasoning that allows researchers to test individual physical reasoning capabilities. Inspired by how humans acquire these capabilities, the benchmark proposes a general hierarchy of physical reasoning capabilities with increasing complexity. this benchmark tests capabilities according to this hierarchy through generated physical reasoning tasks in the video game Angry Birds.","description_withheld":null,"homepage":"https://github.com/Cheng-Xue/Hi-Phy","introduced_date":"2021-06-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/hi-phy-a-benchmark-for-hierarchical-physical","title":"Hi-Phy: A Benchmark for Hierarchical Physical Reasoning","first_author":"Cheng Xue","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Hi-Phy"],"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."}