A Survey on Deep Learning for Software Engineering
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
In 2006, Geoffrey Hinton proposed the concept of training “Deep Neural Networks (DNNs)” and an improved model training method to break the bottleneck of neural network development. More recently, the introduction of AlphaGo in 2016 demonstrated the powerful learning ability of deep learning and its enormous potential. Deep learning has been increasingly used to develop state-of-the-art software engineering (SE) research tools due to its ability to boost performance for various SE tasks. There are many factors, e.g., deep learning model selection, internal structure differences, and model optimization techniques, that may have an impact on the performance of DNNs applied in SE. Few works to date focus on summarizing, classifying, and analyzing the application of deep learning techniques in SE. To fill this gap, we performed a survey to analyze the relevant studies published since 2006. We first provide an example to illustrate how deep learning techniques are used in SE. We then conduct a background analysis (BA) of primary studies and present four research questions to describe the trend of DNNs used in SE (BA), summarize and classify different deep learning techniques (RQ1), and analyze the data processing including data collection, data classification, data pre-processing, and data representation (RQ2). In RQ3, we depicted a range of key research topics using DNNs and investigated the relationships between DL-based model adoption and multiple factors (i.e., DL architectures, task types, problem types, and data types). We also summarized commonly used datasets for different SE tasks. In RQ4, we summarized the widely used optimization algorithms and provided important evaluation metrics for different problem types, including regression, classification, recommendation, and generation. Based on our findings, we present a set of current challenges remaining to be investigated and outline a proposed research road map highlighting key opportunities for future work.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Deep learning models accelerate and enhance the accuracy of complex coding tasks [122, 214, 234].”
From A 2030 Roadmap for Software Engineering (2025) · cites this paper as [234]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 1×
“[40] proposed the concept of “Deep Learning (DL)”.”
BackgroundGuidelines for conducting systematic mapping studies in software engineering: An update
Petersen, K., Vakkalanka, S., & Kuzniarz, L. (2015) · Information and Software Technology · doi:10.1016/j.infsof.2015.03.007 · Cited by 2,669
Hawkins, D. M. (2004) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci0342472 · Cited by 2,522 · cited 1×
“We describe 9 general ways to combat overfitting [38, 107] by considering 3 aspects: data processing, model construction as well as model training, and then analyzed the usage distribution of these methods in relevant studies.”
MethodDECKARD: Scalable and Accurate Tree-Based Detection of Code Clones
Jiang, L., Misherghi, G., Su, Z., & Glondu, S. (2007) · 29th International Conference on Software Engineering (ICSE'07) · doi:10.1109/icse.2007.30 · Cited by 1,039
A tutorial survey of architectures, algorithms, and applications for deep learning
Deng, L. (2014) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2013.9 · Cited by 725 · cited 1×
“We classified the architecture of various DNNs into 3 categories: the layered architecture, AutoEncoder (AE), and Encoder-Decoder [20, 91].”
MethodSourcererCC: scaling code clone detection to big-code
Sajnani, H., Saini, V., Svajlenko, J., Roy, C. K., & Lopes, C. V. (2016) · Proceedings of the 38th International Conference on Software Engineering · doi:10.1145/2884781.2884877 · Cited by 447
A Systematic Literature Review and Meta-Analysis on Cross Project Defect Prediction
Hosseini, S., Turhan, B., & Gunarathna, D. (2019) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2017.2770124 · Cited by 317 · cited 1×
“Following previous studies [43, 47, 67], we selected 22 widely read SE journals (10) and conferences (12) listed in Table 1 to conduct a comprehensive literature review.”
MethodLearning to rank relevant files for bug reports using domain knowledge
Ye, X., Bunescu, R., & Liu, C. (2014) · Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering · doi:10.1145/2635868.2635874 · Cited by 290 · cited 1×
“Bug localization code-based data Defects4J benchmark [IEEE40] text-based data [13] bug report benchmark [IEEE40] code- and text-based data AspectJ in Bugzilla, SWT, JDT, Tomcat [IEEE135]”
Research works printed but not linked: 3
- Staffs Keele et al. 2007. Guidelines for Performing Systematic Literature Reviews in Software Engineering. Technical Report. Technical report, Ver. 2.3 EBSE Technical Report. EBSE.
- Abdel-rahman Mohamed, George Dahl, and Geoffrey Hinton. 2009. Deep belief networks for phone recognition. In NIPS Workshop on Deep Learning for Speech Recognition and Related Applications, Vol. 1. 39.
- Chao Liu Cuiyun Gao Xin Xia David Lo John Grundy and Xiaohu Yang. 2020. On the Replicability and Reproducibility of Deep Learning in Software Engineering. arXiv preprint arXiv:2006.14244. · arXiv
Cited by
Items 201–264 of 264
Integrating Counterfactual Evaluations into Traditional Interactive Recommendation Frameworks
Andrade, Y., Silva, N., Pereira, A. C. M., Tuler, E., Vieira, C., Guimarães, M. D. P., Dias, D. R. C., & da Rocha, L. C. D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36805-9_41
Priority of Requirements Sorting Method in Software Engineering Based on Genetic Algorithm
Cui, H., & Du, Y. (2024) · International Conference on Software, Systems and Information Technology (SSITCON) · doi:10.1109/ssitcon62437.2024.10796000
Enhancing Software Testing with Machine Learning
Mothey, M. (2023) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit2390682
Data Enhancement-Based Approach to Requirements Specification Dataset Construction
Zhang, J., Li, Y., & Sun, C. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-3161-2_15
Automatic Software Vulnerability Detection in Binary Code
Liu, S., Li, L., Ban, X., Chen, C., Zhang, J., Camtepe, S. A., & Xiang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-4566-4_11
How Were You Created? Explaining Synthetic Face Images Generated by Diffusion Models
Atote, B. S., & Sanchez, V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92089-9_17 · Cited by 1
Face Restoration of Ancient Indian Statues using Image Inpainting
N, A. D. R., Babu, B., Danish, R., Reddy, P. K. K., Nitin, G. V. S., & Rohith, P. S. (2025) · 2025 Fourth International Conference on Smart Technologies, Communication and Robotics (STCR) · doi:10.1109/stcr62650.2025.11020280
“Yang et al. [8] developed an extensive study about diffusion models that addresses both generation from scratch and the structural preservation of images and their removal of noise.”
Integrando avaliações contrafactuais aos frameworks tradicionais de recomendação interativa
Andrade, Y., Silva, N., & da Rocha, L. C. D. (2023) · Revista Eletrônica de Iniciação Científica em Computação · doi:10.5753/reic.2023.3418
Contrastive Steering Vectors for Autoencoder Explainability
Mora, J. G. G., Ponce-Espinosa, H., & Martínez-Villaseñor, L. (2025) · Electronics · doi:10.3390/electronics14183586
Teaching Software Engineering for Artificial Intelligence: An Experience Report
Palomba, F., Voria, G., Parziale, A., Pentangelo, V., Porta, A. D., Martino, V. D., Recupito, G., & Giordano, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04207-1_15 · Cited by 1
Nasab, K. F., Imamalipour, A., & Morshedy, A. H. (2025) · Research Square · doi:10.21203/rs.3.rs-7504889/v1
Enhanced Architecture of Structure Semantics for Syntax‐Aware Code Generation
Zhou, C., Li, Z., Huang, H., Yi, X., Liu, F., & Hao, Z. (2025) · Software Practice and Experience · doi:10.1002/spe.70025
A Survey of Learning-based Method Name Prediction
Qian, H., Liu, W., Xu, T., Yin, J., Feng, X., Sun, W., Ding, Z., Chen, Y., Miao, Y., Li, J., et al. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3771999
A Review of Artificial Intelligence Applications in Aircraft Mission Planning System
Wang, R., & Yang, C. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-981-95-3025-0_21
Dimitriu, C., Carcea, D., Carcea, R., Iaţu, A., & Iftene, A. (2025) · International Conference on Innovations in Intelligent Systems and Applications (INISTA) · doi:10.1109/inista68122.2025.11249671
“In the realm of software engineering, early automation tools were used for mining formal specifications and detecting duplicate bug reports [3], [10].”
TIPDF-DWSF: a task-oriented two-stage optimization framework for diffusion model LoRA fine-tuning
Zhang, B., Lu, T., & Qin, D. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02063-2
A First Look at Fairness of Machine Learning Based Code Reviewer Recommendation
Mohajer, M. M. (2024) · York University Digital Library (York University)
Modeling Source Code For Developers
Jesse, K. (2023) · eScholarship (California Digital Library) · Cited by 3
Abbasi, M. S., Munir, B., Jayaram, V., & Rivas, P. (2025) · IEEE Access · doi:10.1109/access.2025.3609282
“To address the issue of overfitting, the following measures may be employed to prevent it during model training () [65] and to detect it in trained models: early stopping [66], data augmentation [67], and regularization techniques [68].”
High-throughput thickness analysis of 2D materials enabled by intelligent image segmentation
Ng, J. C., Muhamad, F., Yeoh, P. S. Q., Han, Z., Qiu, Z., Lai, K. W., & Zhao, X. (2026) · Nanoscale · doi:10.1039/d5nr03320a · Cited by 2
Testing Perspectives of Fog-Based IoMT Applications with Federated Learning
Baboo, A., Dash, S., Padhy, S. K., & Samuel, P. (2026) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-96265-3_14
Jian, C., Gao, X., & Ren, J. (2025) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec66174.2025.11332063
“…and Watson et al. specifically investigated the application of deep learning in software analyzing the practical implementation of deep learning models (such as recurrent neural networks and convolutional neural networks) in tasks like code representation learning and test case generation[8, 9].”
Wang, Y. (2026) · International Conference on Mechanical, Engineering, and Interaction Design (ICMEID) · doi:10.1117/12.3088766
Typestate-Based Fault Localization of API Usage Violations in a Deep Learning Program
Batole, F., Manke, R., Dyer, R., Nguyen, T. N., & Rajan, H. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3656464
“D EEP Learning (DL) programs are increasingly popular [1], typically developed using APIs from libraries such as TensorFlow, Keras, and PyTorch, which offer predefined operations for designing and configuring neural networks.”
Coding-Fuse: Efficient Fusion of Code Pre-Trained Models for Classification Tasks
Zhao, Y., Gong, L., Huang, Z., Jin, Y., & Wei, M. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00157
“In order to conduct a thorough evaluation, for the performance evaluation, we evaluate the F1-Score [41], [42] and AUC-PR [43]–[45] values of the models on the test dataset in the two scenarios.”
When AllClose Fails: Round-Off Error Estimation for Deep Learning Programs
Zhan, Q., Hu, X., Lin, Y., Xu, T., Xia, X., & Li, S. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00016 · Cited by 2
“Deep learning (DL) has become a cornerstone of modern computing, powering various applications, including computer vision [1], natural language processing [2], and code generation [3].”
Self-citationLuu-Minh, T., Quach-Thi-Hoai, P., Le-Anh, T., Nguyen-Van, B., & Le‐Trung, Q. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365030
“This paper proposes a system to predict CI build failures using deep learning, specifically Long Short-Term Memory (LSTM) [1] networks, optimized with Genetic Algorithms (GA).”
Sowmyadevi, S., & Mehrotra, S. (2026) · Research Square · doi:10.21203/rs.3.rs-8652186/v1
A multi-dimensional coupling model for detecting science-technology interactions within AI
Ba, Z., Zhu, L., Zhang, Y., Meng, K., & Liu, Z. (2026) · Scientometrics · doi:10.1007/s11192-026-05565-6
KG-Code: A Knowledge Graph Guided Pre-Training Approach for Code Representation
Zhang, H., & Kishi, T. (2025) · Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec66846.2025.00095
“Recent years, deep learning has been widely used in various important fields of software engineering and achieved remarkable success, such as software testing, code generation and code document generation, etc. [1].”
Unleashing the Potential of Coverage Representation in Deep Learning-Based Fault Localization
Wang, J., Lei, Y., Xie, H., & Liu, C. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3674478
“S OFTWARE engineering, as a crucial field within modern science and technology, plays a pivotal role in driving software development and interacting with users [1], [2].”
Artificial Intelligence as a Developer’s Assistant: Reducing Overtime in Software Development
Mutlu, Ö. T., & Nazlı, M. (2026) · Özgür Yayınları eBooks · doi:10.58830/ozgur.pub1255.c5108
CIPIHunter: Detecting Configuration-Induced Prediction Instability in Deep Learning Frameworks
Anonymous, Meng, S., Kim, M., Chen, X., Fang, C., Chen, Z., & Zhai, J. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3834345
Gottumukkala, D. P., Reddy, P. V. G. D. P., & Rao, S. K. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-3-032-20318-2_27
Analysis of Complex System Architecture Design in Software Engineering Assisted by ER Algorithm
Dong, Y. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14186-6_28
Чичкарьов, Є. А., & Семенов, О. В. (2026) · Telecommunication and information technologies · doi:10.31673/2412-4338.2026.019011
Implementation of a distributed bio-inspired neural architecture on FPGA
Elouaret, T. (2023) · theses.fr (ABES) · doi:10.70675/ee96a099zc0bfz4925zadb7z65cce41becda
The Reskilling Imperative: Redefining Software Engineering Skills in the Age of AI-Generated Code
Goyal, N. K., Kumar, A., Agarwal, Y., & Choudhary, P. K. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8450-4.ch011
Patil, T., Krishnan, A., & Malhotra, S. P. (2024) · International Journal of Artificial Intelligence Data Science and Machine Learning · doi:10.63282/3050-9262.ijaidsml-v5i3p121
Srinivasan, K., Natraj, R. S., Rodrigues, S., Pattarassalame, D., & Sinha, D. K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-19179-3_4 · Cited by 1
Dai, P., Ma, X., Huang, X., Wang, T., Zhao, Y., & Zhao, C. (2026) · Software Quality Journal · doi:10.1007/s11219-026-09755-6
Contreras, A., Guerra, E., & de Lara, J. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-19050-5_7
Trust and Hallucinations: A Study of 39 Experts on AI-Assisted Requirements Reverse Engineering
Alzahrani, A. A. H. (2026) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2026.0170413
Şirin, T. B., & Ay, M. (2026) · Journal of the Brazilian Society of Mechanical Sciences and Engineering · doi:10.1007/s40430-026-06338-1
“Hin - ton’s contributions, particularly in the development of the backpropagation algorithm and deep learning architectures, revolutionized the field by enabling the training of multi-layered networks, making machine learning practical and scalable [74].”
Effective Python-frontend fuzzing for deep learning libraries with runtime coverage feedback
Chen, X., Cui, N., Chen, L., Shi, G., You, R., Xu, Q., & Yin, R. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108195
A review of thermal infrared-to-visible image translation algorithms
Liu, X., Wang, Q., Xie, Y., Liu, W., & Zhou, Y. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae7822
ИНТЕЛЛЕКТУАЛЬНОЕ ОБЕСПЕЧЕНИЕ ИНФОРМАЦИОННОЙ БЕЗОПАСНОСТИ КОДА С ПОМОЩЬЮ ЯЗЫКОВЫХ МОДЕЛЕЙ
Р., Г. Э., & Д., Р. А. (n.d.) · CyberLeninK (CyberLeninka)
Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs during Code Adaptation
Zhang, T., Mao, X., Wang, S., Zhao, Y., Lu, Y., Tang, Z., Xu, W., Sun, L., Xie, C., Yang, K., et al. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3797148
DexGraspDiffuser: Target-Coupled Grasp and Action Diffusion for Dexterous Grasping
Zhu, J., Yang, H., Yang, Z., & Guo, Y. (2026) · Biomimetics · doi:10.3390/biomimetics11070465
“For grasp target generation, this enables the model to produce diverse candidate grasps conditioned on object point clouds, rather than predicting a single deterministic hand configuration [17].”
A Framework for Software Code and Model Smell Detection through Self-Supervised Learning
Alazba, A. (2024) · Research Publication Repository of King Fahd University of Petroleum and Minerals (King Fahd University of Petroleum and Minerals)
Iqbal, F., Khan, M. A., Weerakoon, O., Oyedeji, S., & Porras, J. (2026) · IEEE/ACM International Workshop on Green and Sustainable Software (GREENS) · doi:10.1145/3786148.3788622
Fusing semantics and graph neural networks: A multi-dimensional survey and technological evolution
Zhang, Y. L., & Liu, N. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115584
An Empirical Study on Deep Learning-based Line-Level Software Defect Prediction
Zhang, E., Jiang, Y., Zhang, T., & Tong, H. (2026) · International Conference on Mining Software Repositories (MSR) · doi:10.1145/3793302.3793359
“With advances in deep learning, numerous LLDP approaches have been proposed in recent years [35].”
Abdin, A. M. A. A., Alayedi, M., & Jaradat, A. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08776-z
“Deep learning models are well suited for capturing nonlinear relationships and extracting high-level features from software data such as code metrics and version histories [23].”
Modeling Like Peeling an Onion: Layerwise Analysis-Driven Automatic Behavioral Model Generation
Huang, Y., Hu, M., Chen, X., Jin, Z. G., & Xiao, S. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3744916.3787806
Tong, W., Liu, X., & Zhou, J. (2026) · International Conference on Software Engineering and Computer Applications · doi:10.1145/3829641.3829680
“111 Yanming Yang, 2022 [10] Deep learning applications, methodologies, datasets, and open challenges in software engineering.”
InfluentialLess is more: Mitigating class imbalance in deep learning-based fault localization through raw data
Wang, J., Lei, Y., Xie, H., Liu, C., & Li, X. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108338
Raghavan, P. (2026) · World Journal of Advanced Research and Reviews · doi:10.30574/wjarr.2026.32.1.2563
Вениаминович, Г. П., & Bessmertny, I. (2026) · Scientific and technical journal of information technologies mechanics and optics · doi:10.17586/2226-1494-2026-26-5-1018-1025
Multispectral image stitching based on diffusion model
Chen, G., Liu, G., Liu, F., Zhang, S., & Guan, C. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117752
Finding the Pivots to Repair Broken Source-Test Evolution Using LLMsPreprint
Chen, X., Chen, S., Cao, J., Peng, Y., Chong, C. Y., & Cheung, S.-C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.03197
Are We Just Applying LLMs? What SE Research Studies, Underexplores, and Could Do Next in the LLM EraPreprint
Saghi, Z., Sabouri, S., & Chattopadhyay, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.04206
Zhang, C. (2026) · Computers and artificial intelligence. · doi:10.70267/cai.v3n6.120132
Metadata
- Authors
- Yang, Y., Xia, X., Lo, D., & Grundy, J.
- Affiliations
- Zhejiang University (CN)
- Huawei Technologies (China) (CN)
- Singapore Management University (SG)
- Monash University (AU)
- Venue
- ACM Computing Surveys
- Published
- 2022-01-31
- Volume
- 54
- Issue
- 10s
- Pages
- 1-73
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4206238894
- Cited by
- 223
- References
- 13
- Citations by year
- 2026: 41 · 2025: 63 · 2024: 66 · 2023: 36 · 2022: 12
- FWCI
- 26.90
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- ARC Laureate Fellowship (FL190100035)
- National Research Foundation
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- deep learning, software engineering, deep neural network, software engineering tools, research trends, data preprocessing, data representation, datasets, optimization algorithms, evaluation metrics, research roadmap
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.