{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T21:04:48Z","timestamp":1778706288976,"version":"3.51.4"},"reference-count":65,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","award":["UIDB\/04111\/2020"],"award-info":[{"award-number":["UIDB\/04111\/2020"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","award":["UIDB\/00066\/2020"],"award-info":[{"award-number":["UIDB\/00066\/2020"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","award":["UIDB\/00408\/2020"],"award-info":[{"award-number":["UIDB\/00408\/2020"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","award":["UID\/00408\/2025"],"award-info":[{"award-number":["UID\/00408\/2025"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","award":["CEECINST\/00002\/2021\/CP2788\/CT0001"],"award-info":[{"award-number":["CEECINST\/00002\/2021\/CP2788\/CT0001"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","award":["COFAC\/ILIND\/COPELABS\/1\/2024"],"award-info":[{"award-number":["COFAC\/ILIND\/COPELABS\/1\/2024"]}]},{"name":"Instituto Lus\u00f3fono de Investiga\u00e7\u00e3o e Desenvolvimento","award":["UIDB\/04111\/2020"],"award-info":[{"award-number":["UIDB\/04111\/2020"]}]},{"name":"Instituto Lus\u00f3fono de Investiga\u00e7\u00e3o e Desenvolvimento","award":["UIDB\/00066\/2020"],"award-info":[{"award-number":["UIDB\/00066\/2020"]}]},{"name":"Instituto Lus\u00f3fono de Investiga\u00e7\u00e3o e Desenvolvimento","award":["UIDB\/00408\/2020"],"award-info":[{"award-number":["UIDB\/00408\/2020"]}]},{"name":"Instituto Lus\u00f3fono de Investiga\u00e7\u00e3o e Desenvolvimento","award":["UID\/00408\/2025"],"award-info":[{"award-number":["UID\/00408\/2025"]}]},{"name":"Instituto Lus\u00f3fono de Investiga\u00e7\u00e3o e Desenvolvimento","award":["CEECINST\/00002\/2021\/CP2788\/CT0001"],"award-info":[{"award-number":["CEECINST\/00002\/2021\/CP2788\/CT0001"]}]},{"name":"Instituto Lus\u00f3fono de Investiga\u00e7\u00e3o e Desenvolvimento","award":["COFAC\/ILIND\/COPELABS\/1\/2024"],"award-info":[{"award-number":["COFAC\/ILIND\/COPELABS\/1\/2024"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Large language models (LLMs) have advanced rapidly as tools for automating code generation in scientific research, yet their ability to interpret and use unfamiliar Python APIs for complex computational experiments remains poorly characterized. This study systematically benchmarks a selection of state-of-the-art LLMs in generating functional Python code for two increasingly challenging scenarios: conversational data analysis with the ParShift library, and synthetic data generation and clustering using pyclugen and scikit-learn. Both experiments use structured, zero-shot prompts specifying detailed requirements but omitting in-context examples. Model outputs are evaluated quantitatively for functional correctness and prompt compliance over multiple runs, and qualitatively by analyzing the errors produced when code execution fails. Results show that only a small subset of models consistently generate correct, executable code. GPT-4.1 achieved a 100% success rate across all runs in both experimental tasks, whereas most other models succeeded in fewer than half of the runs, with only Grok-3 and Mistral-Large approaching comparable performance. In addition to benchmarking LLM performance, this approach helps identify shortcomings in third-party libraries, such as unclear documentation or obscure implementation bugs. Overall, these findings highlight current limitations of LLMs for end-to-end scientific automation and emphasize the need for careful prompt design, comprehensive library documentation, and continued advances in language model capabilities.<\/jats:p>","DOI":"10.3390\/fi17090412","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T12:15:17Z","timestamp":1757420117000},"page":"412","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8487-5837","authenticated-orcid":false,"given":"Nuno","family":"Fachada","sequence":"first","affiliation":[{"name":"Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"},{"name":"Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1356-9349","authenticated-orcid":false,"given":"Daniel","family":"Fernandes","sequence":"additional","affiliation":[{"name":"Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1594-6785","authenticated-orcid":false,"given":"Carlos M.","family":"Fernandes","sequence":"additional","affiliation":[{"name":"Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"},{"name":"Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8839-7222","authenticated-orcid":false,"given":"Bruno D.","family":"Ferreira-Saraiva","sequence":"additional","affiliation":[{"name":"Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"},{"name":"CICANT, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9409-7736","authenticated-orcid":false,"given":"Jo\u00e3o P.","family":"Matos-Carvalho","sequence":"additional","affiliation":[{"name":"Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal"},{"name":"LASIGE and Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, University of Lisbon, Campo Grande, 1749-016 Lisboa, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"key":"ref_1","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H.P.D.O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., and Brockman, G. (2021). Evaluating large language models trained on code. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Jain, N., Vaidyanath, S., Iyer, A., Natarajan, N., Parthasarathy, S., Rajamani, S., and Sharma, R. (2022, January 21\u201329). Jigsaw: Large language models meet program synthesis. Proceedings of the ICSE \u201922: 44th International Conference on Software Engineering, Pittsburgh, PA, USA.","DOI":"10.1145\/3510003.3510203"},{"key":"ref_3","first-page":"78","article-title":"On the effectiveness of large language models in domain-specific code generation","volume":"34","author":"Gu","year":"2024","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Fernandes, D., Matos-Carvalho, J.P., Fernandes, C.M., and Fachada, N. (2025). DeepSeek-V3, GPT-4, Phi-4, and LLaMA-3.3 generate correct code for LoRaWAN-related engineering tasks. Electronics, 14.","DOI":"10.3390\/electronics14071428"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"O\u2019Donoghue, O., Shtedritski, A., Ginger, J., Abboud, R., Ghareeb, A.E., Booth, J., and Rodriques, S.G. (2023). BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology. arXiv.","DOI":"10.18653\/v1\/2023.emnlp-main.162"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hong, S., Lin, Y., Liu, B., Liu, B., Wu, B., Zhang, C., Wei, C., Li, D., Chen, J., and Zhang, J. (2024). Data Interpreter: An LLM Agent for Data Science. arXiv.","DOI":"10.18653\/v1\/2025.findings-acl.1016"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1038\/s41562-025-02137-1","article-title":"The next generation of experimental research with LLMs","volume":"9","author":"Charness","year":"2025","journal-title":"Nat. Hum. Behav."},{"key":"ref_8","unstructured":"Amatriain, X. (2024). Prompt design and engineering: Introduction and advanced methods. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Spiess, C., Gros, D., Pai, K.S., Pradel, M., Rabin, M.R.I., Alipour, A., Jha, S., Devanbu, P., and Ahmed, T. (May, January 26). Calibration and correctness of language models for code. Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE), Ottawa, ON, Canada.","DOI":"10.1109\/ICSE55347.2025.00040"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101554","DOI":"10.1016\/j.softx.2023.101554","article-title":"ParShift: A Python package to study order and differentiation in group conversations","volume":"24","author":"Fachada","year":"2023","journal-title":"SoftwareX"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"110836","DOI":"10.1016\/j.knosys.2023.110836","article-title":"Generating multidimensional clusters with support lines","volume":"277","author":"Fachada","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"ref_12","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E.H., Le, Q.V., and Zhou, D. (December, January 28). Chain-of-thought prompting elicits reasoning in large language models. Proceedings of the NIPS \u201922: 36th International Conference on Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_13","unstructured":"Xiong, G., Xie, E., Shariatmadari, A.H., Guo, S., Bekiranov, S., and Zhang, A. (2024). Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models. arXiv."},{"key":"ref_14","unstructured":"Pu, Y., Lin, T., and Chen, H. (2025). PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Jin, Y., Zhao, Q., Wang, Y., Chen, H., Zhu, K., Xiao, Y., and Wang, J. (2024). AgentReview: Exploring Peer Review Dynamics with LLM Agents. arXiv.","DOI":"10.18653\/v1\/2024.emnlp-main.70"},{"key":"ref_16","unstructured":"Agarwal, S., Sahu, G., Puri, A., Laradji, I.H., Dvijotham, K.D., Stanley, J., Charlin, L., and Pal, C. (2025). LitLLM: A Toolkit for Scientific Literature Review. arXiv."},{"key":"ref_17","unstructured":"Luo, Z., Yang, Z., Xu, Z., Yang, W., and Du, X. (2025). LLM4SR: A Survey on Large Language Models for Scientific Research. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liang, J., Huang, W., Xia, F., Xu, P., Hausman, K., Ichter, B., Florence, P., and Zeng, A. (June, January 29). Code as Policies: Language Model Programs for Embodied Control. Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK.","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100488","DOI":"10.1016\/j.dibe.2024.100488","article-title":"Large language model-based code generation for the control of construction assembly robots: A hierarchical generation approach","volume":"19","author":"Luo","year":"2024","journal-title":"Dev. Built Environ."},{"key":"ref_20","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023). ReAct: Synergizing Reasoning and Acting in Language Models. arXiv."},{"key":"ref_21","unstructured":"Yang, H., Yue, S., and He, Y. (2023). Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions. arXiv."},{"key":"ref_22","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020, January 6\u201312). Language models are few-shot learners. Proceedings of the NeurIPS 2020: 34th Conference on Neural Information Processing Systems, Online."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Vemprala, S., Bonatti, R., Bucker, A., and Kapoor, A. (2023). ChatGPT for robotics: Design principles and model abilities. arXiv.","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"ref_24","unstructured":"Fachada, N., Fernandes, D., Fernandes, C.M., Ferreira-Saraiva, B., and Matos-Carvalho, J. (2025). Supplementary material for \u201cGPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries\u201d. Zenodo."},{"key":"ref_25","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_26","unstructured":"Rosenberg, A., and Hirschberg, J. (2007, January 28\u201330). V-measure: A conditional entropy-based external cluster evaluation measure. Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), Prague, Czech Republic."},{"key":"ref_27","unstructured":"Anthropic Team (2025). Claude 3.7 Sonnet System Card, Anthropic PBC. Technical Report."},{"key":"ref_28","unstructured":"Zhu, Q., Guo, D., Shao, Z., Yang, D., Wang, P., Xu, R., Wu, Y., Li, Y., Gao, H., and Ma, S. (2024). Deepseek-coder-v2: Breaking the barrier of closed-source models in code intelligence. arXiv."},{"key":"ref_29","unstructured":"Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., and Bi, X. (2025). DeepSeek-R1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv."},{"key":"ref_30","unstructured":"DeepSeek-AI, Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., and Zhang, C. (2024). DeepSeek-V3 Technical Report. arXiv."},{"key":"ref_31","unstructured":"Zhao, H., Hui, J., Howland, J., Nguyen, N., Zuo, S., Hu, A., Choquette-Choo, C.A., Shen, J., Kelley, J., and Bansal, K. (2024). Codegemma: Open code models based on gemma. arXiv."},{"key":"ref_32","unstructured":"Kamath, A., Ferret, J., Pathak, S., Vieillard, N., Merhej, R., Perrin, S., Matejovicova, T., Ram\u00e9, A., Rivi\u00e8re, M., and Rouillard, L. (2025). Gemma 3 technical report. arXiv."},{"key":"ref_33","unstructured":"Hurst, A., Lerer, A., Goucher, A.P., Perelman, A., Ramesh, A., Clark, A., Ostrow, A., Welihinda, A., Hayes, A., and Radford, A. (2024). GPT-4o system card. arXiv."},{"key":"ref_34","unstructured":"OpenAI (2025, July 09). Introducing GPT-4.1 Model Family. Available online: https:\/\/openai.com\/index\/gpt-4-1\/."},{"key":"ref_35","unstructured":"xAI (2025, July 09). Grok 3 Beta\u2014The Age of Reasoning Agents. Available online: https:\/\/x.ai\/news\/grok-3."},{"key":"ref_36","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., and Vaughan, A. (2024). The Llama 3 Herd of Models. arXiv."},{"key":"ref_37","unstructured":"Roziere, B., Gehring, J., Gloeckle, F., Sootla, S., Gat, I., Tan, X.E., Adi, Y., Liu, J., Sauvestre, R., and Remez, T. (2023). Code llama: Open foundation models for code. arXiv."},{"key":"ref_38","unstructured":"Mistral AI Team (2025, July 09). Codestral. Available online: https:\/\/mistral.ai\/news\/codestral."},{"key":"ref_39","unstructured":"Mistral AI Team (2025, July 09). Large Enough. Available online: https:\/\/mistral.ai\/news\/mistral-large-2407."},{"key":"ref_40","unstructured":"Team OLMo, Walsh, P., Soldaini, L., Groeneveld, D., Lo, K., Arora, S., Bhagia, A., Gu, Y., Huang, S., and Jordan, M. (2024). 2 OLMo 2 Furious. arXiv."},{"key":"ref_41","unstructured":"Abdin, M., Aneja, J., Behl, H., Bubeck, S., Eldan, R., Gunasekar, S., Harrison, M., Hewett, R.J., Javaheripi, M., and Kauffmann, P. (2024). Phi-4 technical report. arXiv."},{"key":"ref_42","unstructured":"Hui, B., Yang, J., Cui, Z., Yang, J., Liu, D., Zhang, L., Liu, T., Zhang, J., Yu, B., and Lu, K. (2025). Qwen2.5-Coder Technical Report. arXiv."},{"key":"ref_43","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., and Lv, C. (2025). Qwen3 technical report. arXiv."},{"key":"ref_44","first-page":"e70002","article-title":"Reproducibility in machine-learning-based research: Overview, barriers, and drivers","volume":"46","author":"Semmelrock","year":"2025","journal-title":"AI Mag."},{"key":"ref_45","unstructured":"Zhou, H., Savova, G., and Wang, L. (2025). Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models. arXiv."},{"key":"ref_46","unstructured":"Al-Onaizan, Y., Bansal, M., and Chen, Y.N. (2024). The effect of sampling temperature on problem solving in large language models. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, FL, USA, 12\u201316 November 2024, Association for Computational Linguistics."},{"key":"ref_47","unstructured":"DeepSeek, Inc. (2025, June 25). Reasoning Model (Deepseek-Reasoner)|DeepSeek API Docs. Available online: https:\/\/api-docs.deepseek.com\/guides\/reasoning_model."},{"key":"ref_48","unstructured":"Mistral AI. (2025, June 12). Sampling Guide|Mistral AI Documentation. Available online: https:\/\/docs.mistral.ai\/guides\/sampling\/."},{"key":"ref_49","unstructured":"Morgan, J., and Chiang, M. (2025, February 10). Ollama: Get Up and Running with Large Language Models. GitHub. Available online: https:\/\/github.com\/ollama\/ollama."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"87","DOI":"10.2307\/2340521","article-title":"On the Interpretation of \u03c72 from Contingency Tables, and the Calculation of P","volume":"85","author":"Fisher","year":"1922","journal-title":"J. R. Stat. Soc."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: A practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc. Ser. B (Methodol.)"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.simpat.2016.12.013","article-title":"Model-independent comparison of simulation output","volume":"72","author":"Fachada","year":"2017","journal-title":"Simul. Model. Pract. Theory"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1214\/aoms\/1177730491","article-title":"On a test of whether one of two random variables is stochastically larger than the other","volume":"18","author":"Mann","year":"1947","journal-title":"Ann. Math. Stat."},{"key":"ref_54","unstructured":"Lacchia, M. (2025, August 24). Radon. Available online: https:\/\/github.com\/rubik\/radon."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1109\/TSE.1976.233837","article-title":"A complexity measure","volume":"SE-2","author":"McCabe","year":"1976","journal-title":"IEEE Trans. Softw. Eng."},{"key":"ref_56","unstructured":"Lehtosalo, J., van Rossum, G., Levkivskyi, I., and Sullivan, M.J. (2025, August 24). mypy\u2014Optional Static Typing for Python. Available online: https:\/\/www.mypy-lang.org\/."},{"key":"ref_57","unstructured":"Astral Team (2025, August 24). Ruff. Available online: https:\/\/docs.astral.sh\/ruff\/."},{"key":"ref_58","unstructured":"Ziad\u00e9, T., Sottile, A., and Cordasco, I. (2025, August 24). Flake8: Your Tool for Style Guide Enforcement. Available online: https:\/\/flake8.pycqa.org\/."},{"key":"ref_59","unstructured":"McKinney, W. (2011, January 18). pandas: A foundational Python library for data analysis and statistics. Proceedings of the PyHPC \u201911: Python for High Performance and Scientific Computing, Seattle, WA, USA."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"ref_62","unstructured":"Seabold, S., and Perktold, J. (July, January 28). Statsmodels: Econometric and Statistical Modeling with Python. Proceedings of the 9th Python in Science Conference, Austin, TX, USA."},{"key":"ref_63","unstructured":"R Core Team (2025). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"405","DOI":"10.32614\/RJ-2016-055","article-title":"micompr: An R Package for Multivariate Independent Comparison of Observations","volume":"8","author":"Fachada","year":"2016","journal-title":"R J."},{"key":"ref_65","unstructured":"Jurafsky, D., Chai, J., Schluter, N., and Tetreault, J. (2020). Climbing towards NLU: On meaning, form, and understanding in the age of data. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, 5\u201310 July 2020, Association for Computational Linguistics."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/9\/412\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:42:17Z","timestamp":1760035337000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/9\/412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":65,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["fi17090412"],"URL":"https:\/\/doi.org\/10.3390\/fi17090412","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,8]]}}}