{"url":"/dataset/decompile-ghidra-100k","name":"decompile-ghidra-100k","full_name":null,"description_markdown":"Release decompile-ghidra-100k, a subset of 100k training samples (25k per optimization level). We provide a training script that runs in ~3.5 hours on a single A100 40G GPU. It achieves a 0.26 re-executability rate, with a total cost of under $20 for quick replication of LLM4Decompile.\r\n\r\nhttps://github.com/albertan017/LLM4Decompile/blob/main/train/README.md","description_withheld":null,"homepage":"https://huggingface.co/datasets/LLM4Binary/decompile-ghidra-100k","introduced_date":"2024-10-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/llm4decompile-decompiling-binary-code-with","title":"LLM4Decompile: Decompiling Binary Code with Large Language Models","first_author":"Hanzhuo Tan","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["decompile-ghidra-100k"],"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."}