# TypeWriter: Neural Type Prediction with Search-based Validation

arXiv: https://arxiv.org/abs/1912.03768 · HTML: https://mlsanity.com/paper/1912.03768/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2019.

## Built on by (most cited first, 30 of 32)

- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [SantaCoder: don't reach for the stars!](https://mlsanity.com/paper/2301.03988/) (2023)
- [MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation](https://mlsanity.com/paper/2208.08227/) (2022)
- [Can LLMs Replace Manual Annotation of Software Engineering Artifacts?](https://mlsanity.com/paper/2408.05534/) (2024)
- [Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code](https://mlsanity.com/paper/2206.01335/) (2022)
- [Counterfactual Explanations for Models of Code](https://mlsanity.com/paper/2111.05711/) (2021)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Type4Py: Practical Deep Similarity Learning-Based Type Inference for Python](https://mlsanity.com/paper/2101.04470/) (2021)
- [TypeT5: Seq2seq Type Inference using Static Analysis](https://mlsanity.com/paper/2303.09564/) (2023)
- [AutoPruner: Transformer-Based Call Graph Pruning](https://mlsanity.com/paper/2209.03230/) (2022)
- [CodeQueries: A Dataset of Semantic Queries over Code](https://mlsanity.com/paper/2209.08372/) (2022)
- [Studying LLM Performance on Closed- and Open-source Data](https://mlsanity.com/paper/2402.15100/) (2024)
- [ManyTypes4Py: A Benchmark Python Dataset for Machine Learning-based Type Inference](https://mlsanity.com/paper/2104.04706/) (2021)
- [Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing](https://mlsanity.com/paper/2305.18584/) (2023)
- [LExecutor: Learning-Guided Execution](https://mlsanity.com/paper/2302.02343/) (2023)
- [Type Prediction With Program Decomposition and Fill-in-the-Type Training](https://mlsanity.com/paper/2305.17145/) (2023)
- [NeuDep: Neural Binary Memory Dependence Analysis](https://mlsanity.com/paper/2210.02853/) (2022)
- [Cross-Lingual Transfer Learning for Statistical Type Inference](https://mlsanity.com/paper/2107.00157/) (2021)
- [Treefix: Enabling Execution with a Tree of Prefixes](https://mlsanity.com/paper/2501.12339/) (2025)
- [Doc2Spec: Synthesizing Formal Programming Specifications from Natural Language via Grammar Induction](https://mlsanity.com/paper/2602.04892/) (2026)
- [AgenticTyper: Automated Typing of Legacy Software Projects Using Agentic AI](https://mlsanity.com/paper/2602.21251/) (2026)
- [Cross-Domain Evaluation of a Deep Learning-Based Type Inference System](https://mlsanity.com/paper/2208.09189/) (2022)
- [Call Me Maybe: Enhancing JavaScript Call Graph Construction using Graph Neural Networks](https://mlsanity.com/paper/2506.18191/) (2025)
- [Report of the Workshop on Program Synthesis for Scientific Computing](https://mlsanity.com/paper/2102.01687/) (2021)
- [Serenity: Library Based Python Code Analysis for Code Completion and Automated Machine Learning](https://mlsanity.com/paper/2301.05108/) (2023)
- [Learning Type Inference for Enhanced Dataflow Analysis](https://mlsanity.com/paper/2310.00673/) (2023)
- [DocGen: Generating Detailed Parameter Docstrings in Python](https://mlsanity.com/paper/2311.06453/) (2023)
- [Inferring Pluggable Types with Machine Learning](https://mlsanity.com/paper/2406.15676/) (2024)

## Abstract (arXiv)

Maintaining large code bases written in dynamically typed languages, such as JavaScript or Python, can be challenging due to the absence of type annotations: simple data compatibility errors proliferate, IDE support is limited, and APIs are hard to comprehend. Recent work attempts to address those issues through either static type inference or probabilistic type prediction. Unfortunately, static type inference for dynamic languages is inherently limited, while probabilistic approaches suffer from imprecision. This paper presents TypeWriter, the first combination of probabilistic type prediction with search-based refinement of predicted types. TypeWriter's predictor learns to infer the return and argument types for functions from partially annotated code bases by combining the natural language properties of code with programming language-level information. To validate predicted types, TypeWriter invokes a gradual type checker with different combinations of the predicted types, while navigating the space of possible type combinations in a feedback-directed manner. We implement the TypeWriter approach for Python and evaluate it on two code corpora: a multi-million line code base at Facebook and a collection of 1,137 popular open-source projects. We show that TypeWriter's type predictor achieves an F1 score of 0.64 (0.79) in the top-1 (top-5) predictions for return types, and 0.57 (0.80) for argument types, which clearly outperforms prior type prediction models. By combining predictions with search-based validation, TypeWriter can fully annotate between 14% to 44% of the files in a randomly selected corpus, while ensuring type correctness. A comparison with a static type inference tool shows that TypeWriter adds many more non-trivial types. TypeWriter currently suggests types to developers at Facebook and several thousands of types have already been accepted with minimal changes.