Publications on reSAID Labhttps://resaid-lab.github.io/publications/Recent content in Publications on reSAID LabHugoen-USMon, 16 Nov 2026 00:00:00 +0000What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistantshttps://resaid-lab.github.io/publications/agentic-code-safety-preprint-2026/Mon, 16 Nov 2026 00:00:00 +0000https://resaid-lab.github.io/publications/agentic-code-safety-preprint-2026/ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision–Language Modelshttps://resaid-lab.github.io/publications/reshift-eccv26/Tue, 08 Sep 2026 00:00:00 +0000https://resaid-lab.github.io/publications/reshift-eccv26/Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM Reasoninghttps://resaid-lab.github.io/publications/plan-then-action-icml26/Mon, 13 Jul 2026 00:00:00 +0000https://resaid-lab.github.io/publications/plan-then-action-icml26/Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relationshttps://resaid-lab.github.io/publications/llm-bias-preprint-2026/Thu, 01 Jan 2026 00:00:00 +0000https://resaid-lab.github.io/publications/llm-bias-preprint-2026/FairSense: Long-Term Fairness Analysis of ML-Enabled Systemshttps://resaid-lab.github.io/publications/fairsense-icse25/Thu, 01 May 2025 00:00:00 +0000https://resaid-lab.github.io/publications/fairsense-icse25/Are Prompt Engineering and TODO Comments Friends or Foes? An Evaluation on GitHub Copilothttps://resaid-lab.github.io/publications/todo-copilot-icse24/Sun, 14 Apr 2024 00:00:00 +0000https://resaid-lab.github.io/publications/todo-copilot-icse24/Towards Safe ML-Based Systems in Presence of Feedback Loopshttps://resaid-lab.github.io/publications/safe-ml-fse23/Mon, 04 Dec 2023 00:00:00 +0000https://resaid-lab.github.io/publications/safe-ml-fse23/Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoMLhttps://resaid-lab.github.io/publications/fair-automl-fse23/Sun, 03 Dec 2023 00:00:00 +0000https://resaid-lab.github.io/publications/fair-automl-fse23/Fairify: Fairness Verification of Neural Networkshttps://resaid-lab.github.io/publications/fairify-icse23/Sun, 14 May 2023 00:00:00 +0000https://resaid-lab.github.io/publications/fairify-icse23/Towards Understanding Fairness and its Composition in Ensemble Machine Learninghttps://resaid-lab.github.io/publications/ensemble-fairness-icse23/Sun, 14 May 2023 00:00:00 +0000https://resaid-lab.github.io/publications/ensemble-fairness-icse23/23 Shades of Self-Admitted Technical Debt: An Empirical Study on Machine Learning Softwarehttps://resaid-lab.github.io/publications/ml-techdebt-fse22/Mon, 14 Nov 2022 00:00:00 +0000https://resaid-lab.github.io/publications/ml-techdebt-fse22/The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Largehttps://resaid-lab.github.io/publications/ds-pipeline-icse22/Sat, 21 May 2022 00:00:00 +0000https://resaid-lab.github.io/publications/ds-pipeline-icse22/Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinehttps://resaid-lab.github.io/publications/fair-preprocessing-fse21/Mon, 23 Aug 2021 00:00:00 +0000https://resaid-lab.github.io/publications/fair-preprocessing-fse21/Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairnesshttps://resaid-lab.github.io/publications/ml-fairness-fse20/Sun, 08 Nov 2020 00:00:00 +0000https://resaid-lab.github.io/publications/ml-fairness-fse20/Boa Meets Python: A Boa Dataset of Data Science Software in Python Languagehttps://resaid-lab.github.io/publications/boa-python-msr19/Sun, 26 May 2019 00:00:00 +0000https://resaid-lab.github.io/publications/boa-python-msr19/