{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:06:42Z","timestamp":1784300802457,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,5]]},"DOI":"10.1145\/3803437.3807734","type":"proceedings-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:27:39Z","timestamp":1784298459000},"page":"1456-1459","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SERSEM: Selective Entropy-Weighted Scoring for Membership Inference in Code Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1709-9102","authenticated-orcid":false,"given":"K\u0131van\u00e7 Kuzey","family":"Dikici","sequence":"first","affiliation":[{"name":"Computer Engineering, Bilkent University, Ankara, Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6238-0963","authenticated-orcid":false,"given":"Serdar","family":"Kara","sequence":"additional","affiliation":[{"name":"Computer Engineering, Bilkent University, Ankara, Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1311-5747","authenticated-orcid":false,"given":"Semih","family":"\u00c7a\u011flar","sequence":"additional","affiliation":[{"name":"Computer Engineering, Bilkent University, Ankara, Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5550-7816","authenticated-orcid":false,"given":"Eray","family":"T\u00fcz\u00fcn","sequence":"additional","affiliation":[{"name":"Computer Engineering, Bilkent University, Ankara, Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9096-8768","authenticated-orcid":false,"given":"Sinem","family":"Sav","sequence":"additional","affiliation":[{"name":"Computer Engineering, Bilkent University, Ankara, Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639133"},{"key":"e_1_3_2_1_2_1","volume-title":"Tree-sitter: An Incremental Parsing System for Programming Tools. https:\/\/tree-sitter.github.io\/tree-sitter\/ Accessed","author":"Max Brunsfeld","year":"2024","unstructured":"Max Brunsfeld et al. 2024. Tree-sitter: An Incremental Parsing System for Programming Tools. https:\/\/tree-sitter.github.io\/tree-sitter\/ Accessed: 2026."},{"key":"e_1_3_2_1_3_1","volume-title":"The Eleventh International Conference on Learning Representations. arXiv preprint arXiv:2202","author":"Carlini Nicholas","year":"2022","unstructured":"Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang. 2022. Quantifying memorization across neural language models, In The Eleventh International Conference on Learning Representations. arXiv preprint arXiv:2202.07646."},{"key":"e_1_3_2_1_4_1","unstructured":"Ian Cordasco et al. 2024. Flake8: Your Tool for Style Guide Enforcement. https:\/\/flake8.pycqa.org\/ Accessed: 2026."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-07884-1_10"},{"key":"e_1_3_2_1_6_1","volume-title":"The Poisoned Chalice of LLM Evaluation Report. In Companion Proceedings of the 34th ACM Symposium on the Foundations of Software Engineering (FSE '26)","author":"Katzy Jonathan","year":"2026","unstructured":"Jonathan Katzy, Ali Al-Kaswan, Razvan Mihai Popescu, and Zhou Yang. 2026. The Poisoned Chalice of LLM Evaluation Report. In Companion Proceedings of the 34th ACM Symposium on the Foundations of Software Engineering (FSE '26). ACM."},{"key":"e_1_3_2_1_7_1","volume-title":"Arie van Deursen, and Maliheh Izadi.","author":"Katzy Jonathan","year":"2025","unstructured":"Jonathan Katzy, Razvan Mihai Popescu, Arie van Deursen, and Maliheh Izadi. 2025. The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models. arXiv:2501.09653 https:\/\/arxiv.org\/abs\/2501.09653"},{"key":"e_1_3_2_1_8_1","unstructured":"Ryan Kelly et al. 2024. PyEnchant: Spellchecking for Python. https:\/\/pyenchant.github.io\/pyenchant\/ Accessed: 2026."},{"key":"e_1_3_2_1_9_1","volume-title":"Jia Li, Chenghao Mou, Carlos Mu\u00f1oz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, et al.","author":"Kocetkov Denis","year":"2022","unstructured":"Denis Kocetkov, Raymond Li, Loubna Ben Allal, Jia Li, Chenghao Mou, Carlos Mu\u00f1oz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, et al. 2022. The stack: 3 tb of permissively licensed source code. arXiv preprint arXiv:2211.15533 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.01306"},{"key":"e_1_3_2_1_11_1","volume-title":"Gabriel Cassano, Joel Lamy-Poirier, Nouamane Tazi, Nikolay Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, et al.","author":"Lozhkov Anton","year":"2024","unstructured":"Anton Lozhkov, Raymond Li, Loubna Ben Allal, Gabriel Cassano, Joel Lamy-Poirier, Nouamane Tazi, Nikolay Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, et al. 2024. StarCoder 2 and The Stack v2: The Next Generation. arXiv preprint arXiv:2402.19173 (2024). https:\/\/huggingface.co\/bigcode\/starcoder2-3b"},{"key":"e_1_3_2_1_12_1","volume-title":"Detecting pretraining data from large language models. arXiv preprint arXiv:2310.16789","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, and Luke Zettlemoyer. 2023. Detecting pretraining data from large language models. arXiv preprint arXiv:2310.16789 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_2_1_14_1","volume-title":"Data Contamination Calibration for Black-box LLMs. In Findings of the Association for Computational Linguistics: ACL 2024","author":"Ye Wentao","year":"2024","unstructured":"Wentao Ye, Jiaqi Hu, Liyao Li, Haobo Wang, Gang Chen, and Junbo Zhao. 2024. Data Contamination Calibration for Black-box LLMs. In Findings of the Association for Computational Linguistics: ACL 2024, Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, Bangkok, Thailand. https:\/\/aclanthology.org\/2024.findings-acl.644\/"},{"key":"e_1_3_2_1_15_1","volume-title":"Adaptive pre-training data detection for large language models via surprising tokens. arXiv preprint arXiv:2407.21248","author":"Zhang Anqi","year":"2024","unstructured":"Anqi Zhang and Chaofeng Wu. 2024. Adaptive pre-training data detection for large language models via surprising tokens. arXiv preprint arXiv:2407.21248 (2024)."}],"event":{"name":"FSE Companion '26: 34th ACM International Conference on the Foundations of Software Engineering","location":"Concordia University Montreal QC Canada","acronym":"FSE Companion '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803437.3807734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:33:41Z","timestamp":1784298821000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803437.3807734"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":15,"alternative-id":["10.1145\/3803437.3807734","10.1145\/3803437"],"URL":"https:\/\/doi.org\/10.1145\/3803437.3807734","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}