{"url":"/sota/type-prediction-on-manytypes4typescript","task":{"name":"Type prediction","url":"/task/type-prediction","note":null},"dataset":{"name":"ManyTypes4TypeScript","url":"/dataset/manytypes4typescript"},"category":"Computer Code","categories":["Computer Code"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Average Accuracy","Average Precision","Average Recall","Average F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average Accuracy":"higher","Average Precision":"higher","Average Recall":"higher","Average F1":"higher"}},"counts":{"rows":9,"rows_with_code":6,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CodeTIDAL5","metrics":{"Average Accuracy":"71.27"},"uses_additional_data":false,"paper_date":"2023-10-01","paper":"/paper/learning-type-inference-for-enhanced-dataflow","paper_url":"https://arxiv.org/abs/2310.00673v2","paper_title":"Learning Type Inference for Enhanced Dataflow Analysis","code":"https://github.com/joernio/joernti-codetidal5","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"GraphCodeBERT-MT4TS","metrics":{"Average Accuracy":"63.42"},"uses_additional_data":false,"paper_date":"2022-10-17","paper":"/paper/manytypes4typescript-a-comprehensive","paper_url":"https://dl.acm.org/doi/10.1145/3524842.3528507","paper_title":"ManyTypes4TypeScript: A Comprehensive TypeScript Dataset for Sequence-Based Type Inference","code":"https://huggingface.co/kevinjesse/graphcodebert-MT4TS","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"GraphCodeBERT","metrics":{"Average Accuracy":"62.51","Average F1":"60.57","Average Precision":"60.06","Average Recall":"61.08"},"uses_additional_data":false,"paper_date":"2020-09-17","paper":"/paper/graphcodebert-pre-training-code","paper_url":"https://arxiv.org/abs/2009.08366v4","paper_title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","code":"https://github.com/microsoft/CodeBERT","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CodeBERT","metrics":{"Average Accuracy":"61.72","Average F1":"59.57","Average Precision":"59.34","Average Recall":"59.80"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}},{"rank_in_archive_order":5,"model":"PolyGot","metrics":{"Average Accuracy":"61.29","Average F1":"58.86","Average Precision":"58.81","Average Recall":"58.91"},"uses_additional_data":false,"paper_date":"2021-12-03","paper":"/paper/multilingual-training-for-software","paper_url":"https://arxiv.org/abs/2112.02043v4","paper_title":"Multilingual training for Software Engineering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"GraphPolyGot","metrics":{"Average Accuracy":"61.00","Average F1":"58.63","Average Precision":"58.36","Average Recall":"58.91"},"uses_additional_data":false,"paper_date":"2021-12-03","paper":"/paper/multilingual-training-for-software","paper_url":"https://arxiv.org/abs/2112.02043v4","paper_title":"Multilingual training for Software Engineering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"RoBERTa","metrics":{"Average Accuracy":"59.84","Average F1":"57.54","Average Precision":"57.45","Average Recall":"57.62"},"uses_additional_data":false,"paper_date":"2019-07-26","paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","paper_url":"https://arxiv.org/abs/1907.11692v1","paper_title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","code":"https://github.com/huggingface/transformers","n_code_links":67,"syntology":{"n_ran":22,"n_unverified":26,"n_samples":48,"n_pointer_only_licence":23}},{"rank_in_archive_order":8,"model":"CodeBERTa","metrics":{"Average Accuracy":"59.81","Average F1":"56.71","Average Precision":"56.57","Average Recall":"56.85"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"BERT","metrics":{"Average Accuracy":"57.52","Average F1":"54.10","Average Precision":"54.18","Average Recall":"54.02"},"uses_additional_data":false,"paper_date":"2018-10-11","paper":"/paper/bert-pre-training-of-deep-bidirectional","paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":534,"syntology":{"n_ran":204,"n_unverified":455,"n_samples":659,"n_pointer_only_licence":149}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":228,"n_unverified":499,"n_samples":727,"n_pointer_only_licence":176,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":228,"n_unverified":499,"n_samples":727,"n_pointer_only_licence":176,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}