{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T21:18:26Z","timestamp":1758057506214,"version":"3.44.0"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051875","type":"print"},{"value":"9783032051882","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-05188-2_16","type":"book-chapter","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T21:52:43Z","timestamp":1757973163000},"page":"248-263","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On the\u00a0Evaluation of\u00a0Test Suites Generated by\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Matej","family":"Cuze","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0462-2283","authenticated-orcid":false,"given":"Franz","family":"Wotawa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"issue":"2","key":"16_CR1","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1109\/TSE.2011.121","volume":"38","author":"A Arcuri","year":"2012","unstructured":"Arcuri, A., Iqbal, M.Z., Briand, L.: Random testing: theoretical results and practical implications. IEEE Trans. Software Eng. 38(2), 258\u2013277 (2012). https:\/\/doi.org\/10.1109\/TSE.2011.121","journal-title":"IEEE Trans. Software Eng."},{"key":"16_CR2","unstructured":"Bhandari, P.: A survey on prompting techniques in LLMs (2024). https:\/\/arxiv.org\/abs\/2312.03740"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Dakhel, A.M., Nikanjam, A., Majdinasab, V., Khomh, F., Desmarais, M.C.: Effective test generation using pre-trained large language models and mutation testing (2023). https:\/\/arxiv.org\/abs\/2308.16557","DOI":"10.1016\/j.infsof.2024.107468"},{"key":"16_CR4","unstructured":"Dr. Gordon Fraser, Dr. Andrea Arcuri: Github - evosuite\/evosuite: Evosuite - automated generation of junit test suites for java classes. https:\/\/github.com\/EvoSuite\/evosuite. Accessed 23 Mar 2025"},{"issue":"5","key":"16_CR5","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1109\/TSE.2010.62","volume":"37","author":"Y Jia","year":"2011","unstructured":"Jia, Y., Harman, M.: An analysis and survey of the development of mutation testing. IEEE Trans. Software Eng. 37(5), 649\u2013678 (2011). https:\/\/doi.org\/10.1109\/TSE.2010.62","journal-title":"IEEE Trans. Software Eng."},{"key":"16_CR6","unstructured":"Konrad Halas: Mutpy . pypi. https:\/\/pypi.org\/project\/MutPy\/. Accessed 05 Nov 2024"},{"key":"16_CR7","unstructured":"Ned Batchelder: Coverage.py ? coverage.py 7.6.4 documentation. https:\/\/coverage.readthedocs.io\/en\/latest\/index.html. Accessed 05 Nov 2024"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Nie, C., Leung, H.: A survey of combinatorial testing. ACM Comput. Surv. 43(2), 11:1\u201311:29 (2011)","DOI":"10.1145\/1883612.1883618"},{"key":"16_CR9","unstructured":"Peeperkorn, M., Kouwenhoven, T., Brown, D., Jordanous, A.: Is temperature the creativity parameter of large language models? (2024). https:\/\/arxiv.org\/abs\/2405.00492"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Renze, M., Guven, E.: The effect of sampling temperature on problem solving in large language models (2024). https:\/\/arxiv.org\/abs\/2402.05201","DOI":"10.18653\/v1\/2024.findings-emnlp.432"},{"key":"16_CR11","unstructured":"Utting, M., Legeard, B.: Practical Model-Based Testing: A Tools Approach. Morgan Kaufmann (2006)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Testeval: benchmarking large language models for test case generation (2025). https:\/\/arxiv.org\/abs\/2406.04531","DOI":"10.18653\/v1\/2025.findings-naacl.197"},{"key":"16_CR13","unstructured":"Yang, L., et al.: On the evaluation of large language models in unit test generation (2024). https:\/\/arxiv.org\/abs\/2406.18181"},{"key":"16_CR14","unstructured":"Zhang, Q., Shang, Y., Fang, C., Gu, S., Zhou, J., Chen, Z.: Testbench: evaluating class-level test case generation capability of large language models (2024). https:\/\/arxiv.org\/abs\/2409.17561"},{"key":"16_CR15","unstructured":"Zhao, W.X., et al.: A survey of large language models (2024). https:\/\/arxiv.org\/abs\/2303.18223"}],"container-title":["Lecture Notes in Computer Science","Testing Software and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05188-2_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T21:52:46Z","timestamp":1757973166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05188-2_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032051875","9783032051882"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05188-2_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors of this paper have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICTSS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Testing Software and Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"37","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pts2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.researchr.org\/home\/ictss-2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}