{"url":"/dataset/synthetic-grade-school-math-sgsm","name":"Educational Grade School Math (EGSM)","full_name":null,"description_markdown":"Educational Grade School Math (EGSM) contains 2,093 question/answer pairs generated by MATHWELL, a reference-free educational grade school math word problem generator that outputs a word problem and Program of Thought (PoT) solution based solely on an optional student interest, as introduced in MATHWELL: Generating Educational Math Word Problems Using Teacher Annotations. The question/answer pairs are verified by human experts. EGSM is the first teacher-annotated math word problem training dataset for LLMs.\r\n\r\nEGSM is designed to train reference-free educational grade school math word problem generators, but can also be used to train math QA models. Please refer to our paper for more information on the dataset.","description_withheld":null,"homepage":"https://huggingface.co/datasets/bryanchrist/SGSM","introduced_date":"2024-02-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/mathwell-generating-educational-math-word","title":"MATHWELL: Generating Educational Math Word Problems Using Teacher Annotations","first_author":"Bryan R Christ","url":null},"license":{"name":"GPL-3.0","url":"https://github.com/bryanchrist/MATHWELL?tab=GPL-3.0-1-ov-file"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"},{"name":"Math Word Problem Solving","url":"/task/math-word-problem-solving","datasets_with_task":"/datasets/task/math-word-problem-solving"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Educational Grade School Math (EGSM)"],"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":"2026-09-25T09:33:49+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."}