{"url":"/dataset/manytypes4typescript","name":"ManyTypes4TypeScript","full_name":null,"description_markdown":"[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.6336113.svg)](https://doi.org/10.5281/zenodo.6336113) Type Inference dataset for TypeScript. Click on DOI tag for dataset files.","description_withheld":null,"homepage":"https://huggingface.co/datasets/kevinjesse/ManyTypes4TypeScript","introduced_date":"2022-03-07","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC-4.0","url":null},"modalities":[],"tasks":[{"name":"Type prediction","url":"/task/type-prediction","datasets_with_task":"/datasets/task/type-prediction"}],"languages":[],"variants":["ManyTypes4TypeScript"],"data_loaders":[{"repo":"https://github.com/kevinjesse/ManyTypes4TypeScript","url":"https://huggingface.co/datasets/kevinjesse/ManyTypes4TypeScript","frameworks":["pytorch"]}],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/type-prediction-on-manytypes4typescript","task":"Type prediction","dataset_variant":"ManyTypes4TypeScript","rows":9,"metrics":["Average Accuracy","Average Precision","Average Recall","Average F1"],"first_row_in_archive_order":{"model":"CodeTIDAL5","paper":"/paper/learning-type-inference-for-enhanced-dataflow","metrics":{"Average Accuracy":"71.27"},"code_links":[{"title":"joernio/joernti-codetidal5","url":"https://github.com/joernio/joernti-codetidal5"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/learning-type-inference-for-enhanced-dataflow","title":"Learning Type Inference for Enhanced Dataflow Analysis","date":"2023-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/manytypes4typescript-a-comprehensive","title":"ManyTypes4TypeScript: A Comprehensive TypeScript Dataset for Sequence-Based Type Inference","date":"2022-10-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multilingual-training-for-software","title":"Multilingual training for Software Engineering","date":"2021-12-03","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/graphcodebert-pre-training-code","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","date":"2020-09-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/codebert-a-pre-trained-model-for-programming","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","date":"2020-02-19","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":2,"samples_unverified":18,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":48,"samples_ran":22,"samples_unverified":26,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":659,"samples_ran":204,"samples_unverified":455,"pointer_only_for_licence":149,"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":3,"samples_harvested":727,"samples_ran":228,"samples_unverified":499,"pointer_only_for_licence":176,"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."}